A Risk-Driven Maritime Patrol Route Optimization Framework for IUU Fishing Surveillance Using Multi-Source AIS and SAR Data Fusion

1. Introduction

Illegal, unreported and unregulated (IUU) fishing is one of the most serious threats to marine ecosystems and fisheries economies throughout the Western Pacific region [10]. The expansive exclusive economic zones (EEZ) in the Western Pacific create tremendous challenges for maritime law enforcement agencies due to limited patrol resources.

Over the past decade, the detection and monitoring of IUU fishing has changed dramatically as a result of advances in satellite technology, machine-learning algorithms, and open-data programs. Early detection methods relied on the Automatic Identification System (AIS), a mandatory transponder system for vessels greater than 300 gross tonnage required by SOLAS regulations. Pioneering research conducted by de Souza et al. [8] used AIS data in conjunction with machine learning techniques to identify suspicious patterns of fishing behaviour, and Kroodsma et al. [19] used neural network classifiers applied to billions of AIS position reports to create a map of global patterns of fishing effort at unprecedented resolution. Unfortunately, vessels participating in IUU fishing may simply turn off their transponders, rendering them invisible to monitoring systems, ultimately limiting the use of AIS for monitoring IUU fishing. Ford et al. [11] used spatial-statistical modelling to quantify the extent of this vulnerability by identifying AIS transmission gaps as reliable indicators of illicit behaviour due to the intentional turning off of a vessel’s transponder. More recently, Rodríguez et al. [33] have confirmed that 87.1% of all “silent anomalies” (i.e., vessels that experience prolonged AIS transmission blackouts exceeding 24 hours) are located within 100 km of the coastline, providing a reliable indicator of IUU fishing activity within that area.

The advent of Synthetic Aperture Radar (SAR) as a complementary surveillance technology is beginning to address this gap in monitoring capability. SAR instruments, particularly Sentinel-1 C-band instruments, can detect vessel backscatter signatures independent of whether the vessel has an active transponder; therefore, it is possible to identify “dark vessels” (i.e., vessels that are not operating under AIS surveillance) [12,31]. Kurekin et al. [20] have provided operational evidence of this by showing that 75% of SAR-detected vessels operating in the waters off Ghana had no corresponding AIS signal; thus, they were able to quantify the extent of IUU fishing by dark vessels within Ghana. The creation of large-scale labelled SAR datasets, such as xView3-SAR [28] has now opened up new avenues for the application of deep learning approaches to the classification of dark vessels [3]. The pioneering work of Paolo et al. [27] has also provided the first comprehensive mapping of industrial fishing activities around the globe, using Sentinel-1 imagery, and has demonstrated that approximately 25% of industrial fishing vessels worldwide are currently not broadcasting their location via AIS.

Typical methods of maritime law enforcement include two types of patrol strategies. The first type is a systematic lawnmower-style scanning approach that ensures full coverage of the patrol area; however, it overlooks the risk heterogeneity associated with IUU fishing activities and wastes patrol assets on low-risk waters. The second type is hotspot-based monitoring, which effectively directs patrols to areas with a concentrated fishing effort; however, it does not account for new or emerging IUU fishing activities in regions with no historical record of high fishing intensity. Neither method leverages the increasing availability of satellite-based data for maritime surveillance to support adaptive patrol planning.

Advances in maritime domain awareness have led to the development of numerous new, rich, and open-access datasets based on real satellite observations. Global Fishing Watch (GFW) provides monthly datasets estimating global fishing activities derived from AIS data, which are publicly available in the Zenodo online archive [14]. Additionally, Paolo et al. [27] published the first comprehensive map of industrial maritime activities using real Synthetic Aperture Radar (SAR) imagery from the ESA’s Sentinel-1 system, and established effective methods for detecting non-compliant “dark” vessels that disable AIS transponders to evade detection. GFW also provides an application programming interface (API) that records encounter events, defined as close-proximity meetings between vessels. These encounters indicate potential locations for illegal transshipment activities, a common practice associated with IUU fishing operations [24]. The fusion of multiple datasets (e.g., AIS, SAR, and other sensor modalities) to generate a more accurate maritime situational overview has become an important tool for maritime stakeholders [7,26,32,35]. Fusing heterogeneous real-world datasets into a unified composite risk assessment framework provides an opportunity to better evaluate the risk levels of patrol routes, while also presenting a methodological challenge to design patrol routes that maximize the efficiency of risk-based patrol missions.

This research addresses a multi-vessel patrol route optimization problem and introduces an optimal control strategy for patrol vessel movements based on a composite IUU fishing risk assessment model constructed exclusively using real-world data. The major contributions of this paper are:

1.

The first study to integrate real Sentinel-1 SAR dark vessel detections (Paolo et al. [27], Nature) into the optimization of the operational IUU patrol route for the Western Pacific. Unlike prior work that uses simulated dark vessel distributions, our risk model is built entirely on verified satellite observations, revealing that SAR-informed task sets are fundamentally harder to cover than AIS-only targets, a finding with direct implications for maritime enforcement resource allocation.

2.

An Adaptive Priority-Boosted ACO (APB-ACO) algorithm featuring two-phase deadline-sensitive route construction with adaptive strategy selection. The algorithm builds a deadline-constrained prefix that ensures that high-priority tasks are covered within 72 hours, followed by a distance-optimal suffix, and automatically selects between single-phase and two-phase strategies based on composite fitness. This guaranties that APB-ACO is never worse than standard PB-ACO, achieving 7% shorter routes (21,658±9 km) with 46 times lower standard deviation than PB-ACO ($\sigma =9$ km vs. 414 km).

3.

Although it may seem counterintuitive that removing SAR data results in an improved composite score, it is scientifically significant that the AIS-only task landscape is easier for the remaining geographic area, which explains the increased Composite Score (CS) from 0.483 to 0.684. This counterintuitive outcome is important because it illustrates how the integration of SAR increases the difficulty of patrol targets and serves as a methodological contribution to the development and validation of multi-source fusion systems.

4.

The open-source implementation of GFW and SAR datasets includes modeling of fuel consumption, avoidance of restricted zones, and sensitivity analysis of composite score weights. The extended comparison of six algorithms (PB-ACO, APB-ACO, GA, PSO, DQN, NSGA-II) demonstrate the unique contributions that metaheuristic, evolutionary, and reinforcement learning methods have to the development of effective patrol strategies to combat IUU poaching on the high seas.

The remainder of this paper is organized as follows. Section 2 reviews related work on IUU detection, maritime patrol optimization, ant colony optimization variants, and multi-source data fusion. Section 3 describes the proposed methodology. Section 4 presents the experimental setup and real data sources. Section 5 reports and discusses the results. Section 6 concludes the paper and outlines future research directions.

2. Related Work

2.1. IUU Fishing Detection and Surveillance Technologies

The past years have seen developments in methods for IUU fishing detection through the evolution of three successive generations of techniques: anomaly detection based on AIS data; detection of dark vessels using SAR satellite imagery; and data fusion from multiple remote sensing platforms (including optical and SAR) and investigation of such datasets for fishing vessel identification.

The first-generation techniques used the ubiquitous availability of AIS data to identify global patterns of fishing vessel behavior. For example, through data mining and machine learning of AIS data, De Souza et al. [8] were able to identify anomalous fishing patterns (suspicious behaviour). Kroodsma et al. [19] further demonstrated that it is possible to demonstrate global patterns of fishing effort (the geographic extent of fishing activity) using a resolution that was unprecedented prior to their research. They found that >55% of all fishing activity occurred within the waters of only five nations. Marzuki et al. [22] were also able to identify different types of fishing gear used based on the analysis of the AIS trajectories of the fishing vessels and their ability to classify the activities of fishing. Miller et al. [24] identified global trends in transshipment behaviours, and established the encounter event (which occurs when one vessel meets another) as one of the most reliable indicators to identify potential IUU operation.

The limitations associated with the use of AIS alone were established by Ford et al. [11], who developed a spatial statistical approach to identify gaps in AIS transmission related to IUU activity. They identified that gaps in AIS data created through intentional disablement of vessel transponders can be identified through the use of a spatial clustering approach; therefore, the presence of clustering in AIS gap data indicates that the vessels involved deliberately attempt to evade detection. Rodríguez et al. [33] conducted a detailed analysis of so-called “silent anomalies” within the AIS trajectories of fishing vessels and determined that the majority long-duration AIS blackouts (>24 hours) occurred in coastal communities and serve as a highly reliable proxy for IUU activities. Welch et al. [39] also demonstrated an association between economic indicators and satellite observations to identify hotspots of IUU fishing. The authors of this study identified that areas of high-value gross fish production combined with ineffective governance had the highest concentration of dark fishing vessels.

The second generation of IUU detection systems incorporated the use of SAR satellite imagery to identify dark vessels that are not equipped with AIS transponders. For example, Park et al. [29] developed a method for matching SAR data (which is used to identify dark vessels) to provide information on the movement and location of vessels that use radar technology as a means of detecting their illegal activity. Additionally, Kurekin et al. [20] demonstrated the ability of SAR to monitor the illegal fishing activities of unregistered fishing vessels operating in Ghana’s territorial waters. They identified that 75% of the vessels identified using SAR technology did not have any corresponding AIS data, therefore quantifying the extent of dark vessel activity from IUU fishing. Galdelli et al. [12] proposed an approach in which the AIS and SAR data could be integrated and synchronized, using point-to-point and point-to-line associations to identify vessels operating without an AIS signal in the vicinity of an AIS gap. The xView3-SAR benchmark dataset, developed by Paolo et al. [28] (which was released at the NeurIPS 2022 conference), contained approximately 1,000 labelled (annotated) images from the European Space Agency’s (ESA) Sentinel-1 satellite and will provide the foundation for deep learning-based dark vessel detection. The study by Bai et al. [3] further advanced the understanding of the classification capabilities of SAR data through detailed development of a dedicated deep-learning pipeline for the classification of various fishing activities.

A landmark contribution came from Paolo et al. [27], who published a global mapping of industrial maritime activity using Sentinel-1 SAR imagery, providing the first systematic dataset of dark vessel detections at global scale. Their study found that approximately 25% of industrial fishing vessels were not broadcast on AIS, underscoring the critical limitation of AIS-only monitoring systems. This dataset forms the primary SAR input for the risk assessment model proposed in the present work.

2.2. Maritime Patrol and Route Optimization

Maritime patrol route optimization can be formulated as a variant of the Vehicle Routing Problem (VRP) with time windows and priority constraints. The problem combines spatial coverage requirements with temporal urgency constraints, making it substantially more complex than standard TSP or VRP formulations. Chen et al. [5] addressed multi-USV cooperative path planning using hierarchical task allocation with improved ACO, demonstrating the feasibility of coordinated multi-vessel patrol operations. Liu et al. [21] proposed multi-AUV path planning with communication constraints using improved ACO variants, highlighting the importance of inter-vehicle distance limits in maritime operations.

Recent years have seen growing interest in applying swarm intelligence and optimization methods to maritime patrol specifically. Pu et al. [30] developed a hybrid partition-based patrolling scheme for maritime area patrol with multiple cooperative unmanned surface vehicles, directly mirroring the multi-vessel patrol structure with targets of different importance levels considered in this paper. Hou et al. [16] addressed long-term multi-UAV maritime patrol scheduling as a multi-objective 0–1 integer programming problem, providing structural parallels to the multi-patrol-vessel scheduling formulation. Afrianta et al. [2] conducted a systematic review of ACO and PSO methods for multi-USV maritime patrol route planning (2020–2025), covering coordination frameworks including leader-follower, virtual structure, behavior-driven, and consensus-based approaches.

A key gap in the maritime patrol literature is the disconnect between detection and response: most works focus on spatial coverage optimization without integrating risk models derived from surveillance data. Adi [1] addressed this gap by applying kernel density estimation (KDE) to historical maritime violations to generate risk-probability surfaces to optimize UAV surveillance patrol paths, a methodology aligned with the threat-probability grid generation approach used in this paper. Hou et al. [17] addressed maritime resource allocation using cluster-based optimization for search and rescue operations, demonstrating the effectiveness of risk-cluster-driven resource assignment for maritime asset deployment, an analogous problem structure to patrol vessel dispatch.

Despite these advances, existing maritime patrol optimization studies typically use simulated or proxy data rather than real satellite observations for risk assessment. Furthermore, few integrate deadline constraints that reflect operational urgency—the requirement that high-priority IUU hotspots must be visited within specific time windows to maintain deterrence effectiveness. This paper addresses both limitations by integrating real multi-source satellite data into a deadline-aware patrol routing framework.

2.3. Ant Colony Optimization and Metaheuristic Variants

The Traveling Salesman Problem (TSP) is one of the applications for which Ant Colony Optimization (ACO) was developed by Dorigo and Gambardella [9]. Because of the ACO’s nature of using pheromone based learning and balancing the exploration and the exploitation of the solution space, ACO is a good fit for maritime routing. ACO’s theoretical convergence properties were first demonstrated through the work of Stützle and Dorigo [36], where they showed that a class of ACO algorithms will converge to the best solution with probability 1 given certain bounded pheromone conditions.

Since the original development of the ACO, several different ACO-based algorithms have been developed to address specific optimisation problems. An example of a specific application of ACO is the Team Orienteering Problem with Time Windows (TOPTW), which is structurally similar to the patrol route planning problem we are addressing in this paper. ACO-based benchmark formulations that most closely relate to the patrol routes with time constraints that this paper attempts to solve can be found in the work of Montemanni and Gambardella [25]. Additionally, Mavrovouniotis et al. [23] provided a comprehensive survey of the ACO variants which have been developed specifically for dynamic combinatorial optimisation problems. This includes evaporation-based and population-based ACO frameworks that have been developed to adjust to the dynamic nature of a problem instance, and thus represent a direct correlation to the scenarios associated with risk assessments that will be completed, updated, and reported during the execution of a patrol mission.

Another area of research in ACO is with respect to adaptive parameter control. With respect to this topic Wu et al. [40] have proposed different ways to adjust pheromone volatilisation and heuristic information to create an optimal balance between speed of convergence and ability to search the entire solution space, thus making way to the development of an ACO algorithm with adaptive evaporation. This work represents directly the basis for the use of the adaptive evaporation schedule that was developed for the ACO format that is described later in this paper. Greater attention has also been given to the integration of machine learning and ACO. Tariq et al. [38] combined machine learning-predicted urgency scores with the ACO heuristic value for the Vehicle Routing Problem with Time Windows (VRPTW) and validated the approaches of hybrid machine learning and ACO. Urgency scores associated with each risk score were used to modulate the pheromone attraction of ants and were directly related to the priority-weighted ACO algorithm that will be explained in more detail in the next section.

The merging of ACO with clustering based problem decomposition has produced promising results. Kim et al. [18] identified the potential for ACO to be combined with DBSCAN clustering to develop an improved ACO for solving heterogeneous multi-trip VRPs with Time Windows. As is the case in this paper, they used a clustering then routing approach to develop their Clustering-based Improved Ant Colony Optimisation (CIACO) algorithm. The CIACO algorithm outperformed the benchmark solutions by significantly minimising the distance travelled when solving benchmark instances and provides the context for the DBSCAN-ACO pipeline that has been developed for the current research effort.

2.4. Multi-Source Maritime Data Fusion

Heterogeneous maritime surveillance integration has been critical to developing complete and thorough situational awareness on the sea. For example, Morando et al. [26] have created a multi-sensor data fusion product through the integration of satellite remote sensing imagery, Automatic Information Systems (AIS), and Radio Frequency (RF) data, subsequently demonstrating that combined data products generate a richer source of threat assessment than does any standalone data source. Similarly, Rodger and Guida [32] used an accompanied classification-aided method to modify Synthetic Aperture Radar (SAR) and AIS data through the use of transfer learning, allowing for the successful classification of unknown vessels based on detected vessel type and therefore allowing for effective patrol target prioritization through the association of dark-vessel detections with AIS metadata.

A further example is De Farias et al. [7], who suggested creating a hybrid framework using AIS Behaviour Modelled data along with an Expert Rule system to determine the classification of marine operations. Classifications of marine operations include “Illegal Fishing”, “Suspicious Activity”, “Anomaly”, and “Normal”, with a direct correlation to the probability of the subject vessel representing a threat. The Threat Probability Data generated allows for effective inputs to the patrol routing system.

Song et al. [35], meanwhile, have developed a method of combining AIS with remote sensing images to improve the identification and positioning of maritime targets. This new methodology supports a future system that will utilize data from satellite detection capabilities through to finalised patrol locations.

Despite these advancements in data fusion methodologies, there remains a significant gap between the capabilities offered by multi-source detection systems and the ability to translate the outputs of these systems into effective and actionable patrol route planning. Current fusion frameworks are largely focused on increasing detection accuracy or classification performance, rather than the direct operational utilization of this output in the form of actionable patrol routing decisions. The present paper seeks to fill this gap by creating an input path that allows for the direct input of risk scores generated via the fusion of AIS, SAR, and Encounter Data into a Patrol Route Optimisation System or pipeline.

2.5. Research Gap and Contributions

The Vehicle Routing Problem with Time Windows and priority constraints (VRPTW-P) provides the theoretical foundation for the patrol routing problem addressed in this paper. Tanash and As’ad [37] formulated a MILP model for priority-based heterogeneous VRPTW with pickup and delivery, establishing a close structural analogue to multi-patrol-vessel routing with risk-priority-weighted targets and different vessel capabilities. Ruiz-y-Ruiz et al. [34] addressed the inventory routing problem with priorities and a fixed heterogeneous fleet, while Corona-Gutiérrez et al. [6] introduced priority indexes into a cumulative capacitated VRP framework using NSGA-II, with a bi-objective formulation (latency and tardiness minimization) paralleling the coverage-distance trade-off in patrol optimization. Ghannadpour and Zarrabi [13] formulated a heterogeneous multi-objective VRP with customer priority satisfaction, providing a multi-objective benchmark for heterogeneous fleet problems. Chen et al. [4] developed an IGA-ACO hybrid for VRPTW achieving competitive results on Solomon benchmarks, providing algorithmic context for hybrid genetic-ACO strategies.

While significant progress has been made in both IUU detection and patrol optimization independently, our review identifies three critical gaps that this paper addresses. First, no prior patrol optimization study has incorporated real Sentinel-1 SAR dark vessel detections from Paolo et al. [27]—the most comprehensive global dataset of non-cooperative vessel activity—into operational route planning. Second, existing ACO-based patrol algorithms lack explicit deadline awareness for high-priority targets, relying instead on distance-greedy heuristics that may schedule critical tasks beyond operational time windows. Third, the literature lacks empirical evidence on how multi-source data fusion affects the difficulty of the resulting optimization problem—a question directly addressed by the ablation experiments in this paper, which reveal that SAR-informed task sets are fundamentally harder to cover than AIS-only targets.

3. Methodology

The proposed framework consists of five sequential modules: (1) multi-source IUU risk assessment modeling, (2) risk-driven patrol task generation, (3) multi-vessel task allocation, (4) APB-ACO-based route planning, and (5) formation coordination under communication constraints. The flow of the algorithm framework is shown in Figure 1.

3.1. Multi-Source IUU Risk Assessment Model

The area being researched can be divided into an equal grid ($0.5^{\circ }\times 0.5^{\circ }$), with 1,600 cells total. For each of the 1,600 grid cells, three risk indicators are developed from actual observational data:

AIS Fishing Effort (F): The monthly aggregated fishing effort data from GFW Zenodo (247,846 records in total for 2022, averaged per record) is normalized to $[0,1]$ using the min-max method in all cells. The more fishing effort (hours fished) in a cell, the greater the potential for IUU violations. The majority of fishing effort in the study area is from the fishing fleets of Taiwan (TWN), Japan (JPN) and China (CHN).

Dark Vessel Density from Synthetic Aperture Radar (SAR)(D): The density of vessels detected by satellite using SAR that do not have AIS data match within each cell of the grid [27]. There were 389 vessels (as detected by SAR) in total within the study area; 131 of those vessels (33.7%) were detected without the corresponding AIS data (dark vessels). The dark vessel detection points were subjected to a kernel density estimate (KDE) analysis to produce a continuous density surface normalized to $[0,1]$. High dark vessel density values in a cell suggest a possible intention to avoid AIS and therefore may indicate IUU activity.

Vessel Encounters (E): The total number of vessel encounters per grid cell retrieved via the GFW Events API (186 deduplicated events in 2022). The total number of vessel encounters also includes 84 identified as possible risk vessel encounters and 29 associated with carrier vessels typically involved in transshipping at sea. All encounters with All vessel are normalized to $[0,1]$. Frequent encounters with vessels within remote waters serve as a known indicator of illegal transshipment activity on the water.

The composite risk score R for each cell is calculated as a weighted sum:

$$R=w_1·F+w_2·D+w_3·E$$

(1)

where $w_1+w_2+w_3=1$. The default weights are set as $w_1=0.4$ (fishing effort), $w_2=0.4$ (dark vessel), and $w_3=0.2$ (encounter density). The weight rationale is as follows:

$w_1=0.4$ (Fisheries Effort): The AIS-derived data representing fishing effort serves as a reliable indicator of the spatial distribution of risk associated with IUU (illegal, unreported, and unregulated) fishing activity within the study area. It has been recorded 247,846 times across the entire region, demonstrating comprehensive spatial coverage and strong methodological validity [19]. However, the fishing effort captured by AIS includes both legal and illegal activities. Therefore, the two components of this indicator are assigned equal weight.

$w_2=0.4$ (SAR Dark Vessel): The use of SAR derived images of fishing vessels that were detected as a dark vessel (no AIS signals) to determine IUU activity by examining locations of AIS-evading vessels, especially through the unmatched 33.7% rate of detections recorded in our study area (131 of 389 real SAR detections) is a good direct indicator of vessels operating in the absence of an AIS signal. This confirms that dark vessels are travelling through the study area as a result of AIS avoidance, so dark vessels warrant the same weighting as fishing effort. Lastly, as we mentioned in the ablation analysis, if the dark vessel data is eliminated from analysis, it clearly demonstrates that it includes vessels that could serve as operationally significant hotspots for vessels that are in IUU activities but cannot be monitored with the use of AIS (the composite changes from 0.483 to 0.684 due to the ease of an AIS only task set and confirming that the SAR information is able to indicate dark vessel hotspots that cannot be monitored through AIS).

$w_3=0.2$ (Encounter Density): The GFW Events API provides information from 186 non-duplicated records of encounter events; these will be less frequent than the other indicator species (e.g., the DFO [Department of Fisheries and Oceans] and SAR-derived Indicators) and will also contain a greater degree of uncertainty (notice that an encounter event is a risk indicator - it may not have been a IUU activity). Therefore, the low weighting associated with these indicator records reflects both the relatively low quantity of records compared to the other two indicators (the AIS and SAR data) and the indirect manner in which risk of transshipping occurs. If the occurrence of encounter activity within regions is increased, then we predict this weight will increase.

The sensitivity of the results to weight changes is discussed in Section 5.9 through the use of ablation techniques. The determination of optimal weight for regional applications will be an area for future research.

3.2. Risk-Driven Task Generation

A patrol location may consist of a grid cell that has a risk score higher than the threshold of $R\ge 0.3$. To further identify patrol locations, DBSCAN cluster analysis (where $\mathrm{eps}=0.5^{\circ }$ and $\min \_\mathrm{samples}=2$) will be used in order to combine similar high-risk grid cells into one much larger patrol location. This will reduce the total number of individual targets (patrol locations) without losing the spatial distribution of risk. An $\mathrm{eps}$ value of $0.5^{\circ }$ is ∼55 km at the equator, which is between the minimum operating radius of a maritime patrol vessel. Setting the $\min \_\mathrm{samples}=2$ criterion ensures that true clusters of risk exist while eliminating isolated single-cell anomalies ($0.3<R<0.4$). Each of these combined patrol locations’ tasks will be assigned a priority score based on the maximum risk found in that cluster of grid cells and a revisit frequency that is inversely proportional to the level of risk (high risk = 12 hours; medium risk = 24 hours; low risk = 72 hours).

3.3. Multi-Vessel Task Allocation

The division of patrol duties between K vessels (K=3 for this investigation) will be achieved using a two-phase process. The way priority-weighted clustering of k-means is computed during Phase 1 is by using a task’s priority score to weight the position of the task so that high-risk areas will have more attention directed at them. During Phase 2, tasks will be reallocated from vessels that have been overloaded with tasks to vessels that have been underloaded with tasks. This will be done by reallocating tasks so that the distance traveled from the previous position to the new position is minimal (i.e., the closest task that can be assigned).

3.4. Adaptive Priority-Boosted ACO with Two-Phase Deadline-Aware Route Construction

Each vessel’s patrol route is optimized using our Adaptive Priority-Boosted ACO (APB-ACO) algorithm, featuring a two-phase deadline-aware construction mechanism with adaptive strategy selection. This design addresses a fundamental challenge in IUU patrol routing: patrol routes span 200–500 hours of total travel, far exceeding the 72-hour deadline within which high-priority tasks must be covered. Standard distance-minimizing ACO algorithms may schedule high-priority tasks late in the route, violating operational deadlines.

3.4.1. Standard ACO Formulation

In standard Ant Colony Optimization, artificial ants construct solutions iteratively by probabilistic transitions between nodes. The transition probability from node i to node j for a single ant is:

$$P_{\mathrm{std}}(i\to j)={\displaystyle \frac{{\left[\tau (i,j)\right]}^{\alpha }·{\left[\eta (i,j)\right]}^{\beta }}{{\sum }_{k\in {\mathcal{N}}_i}{\left[\tau (i,k)\right]}^{\alpha }·{\left[\eta (i,k)\right]}^{\beta }}}$$

(2)

where $\tau (i,j)$ is the intensity of the pheromone on the edge $(i,j)$, $\eta (i,j)=1/d(i,j)$ is the inverse distance heuristic ($d(i,j)$ = the Haversine distance), and $\alpha$, $\beta$ are exponents controlling the relative influence of the pheromone versus distance. Standard ACO is effective for distance-minimization problems such as the Traveling Salesman Problem, but tends to converge on routes that minimize total distance—potentially bypassing isolated high-priority nodes or scheduling them beyond the coverage deadline.

3.4.2. Two-Phase Deadline-Aware Route Construction

The APB-ACO system solves the problem of meeting deadlines by creating routes in two steps, separating how to reach your deadlines from how to find a good place to work from.

In Phase One, Deadline-Constrained Prefix, you will be creating a part of your route out of a limited number of possible stops. The list of stops is made up of the highest priority tasks, and the three closest bridge nodes (KNN) for each of the high-priority tasks.

Phase One focuses on creating a close-knit group of high-priority (HP) tasks and the bridge nodes that connect each of them. This approach ensures that Task One has a close item; thus, timeframes can be met with minimal detours (or unnecessary distance) to get there. Route construction for Phase 01 utilizes an ACO algorithm based on how much each node is boosted in priority during route construction.

The bridge nodes play a significant role in route construction because they keep your Route Prefix concentrated on the vicinity of the HP nodes, which would help avoid long, inefficient detours between geographically distant HP nodes. For route construction in Phase 1, a modified transition attractiveness formula is applied:

$$\gamma (i,j)=1+\lambda ·P{\left(j\right)}^{\alpha }·exp\left(-\overline{d}\left(j\right)/D_{\mathrm{scale}}\right)$$

(3)

In the above equation, $\overline{d}\left(j\right)$ is the mean distance from the task node j to all the previous tasks. $D_{\mathrm{scale}}$ refers to the global mean distance in pairs, $\lambda =2.0$ (a boost intensity), and $\alpha =1.5$ (priority exponent). The exponential decay gives the strongest boosts to the nodes with higher priorities embedded in clusters that are very dense.

In Phase Two, to create a distance-optimal suffix, the remaining nodes (those that were not visited in Phase 1), will be optimized the same as a normal PB-ACO optimization will start from the previous node in Phase 1 and will minimize distance for the remaining part of the route. The pheromone matrix will also be shared between the two phases, allowing Phase 1 knowledge to be transferred to Phase 2. The sole focus for phase 2 will be on minimizing distance in the last segment of the Route.

3.4.3. Adaptive Strategy Selection

The mechanism for adaptive choice selection is a key contribution of the APB-ACO methodology, which ensures that APB-ACO will never perform worse than the PB-ACO methodology. The algorithm utilizes a parallel construction, creating two separate routes, and selecting the route with the optimal combination of delivery cost (distance(R)) and urgency penalty (the sum of the maximum arrival lateness times the priority) as identified in Equation (4) above.

Single-phase priority boosted ACOs will perform better than other methods when a substantial portion of high-priority task coverage will be achieved through standard routing within 72 hours (Strategy 1). Two-phase construction methods will provide a better outcome when time-to-completion constraints exclude coverage of high-priority tasks within the 72-hour deadline.

The composite fitness function identifies which hybrid strategy to utilize based on the distance from the depot to the task to be completed (distance(R)) plus a weighted penalty for lateness incurred for visiting a high-priority task after its deadline. The urgency penalty term heavily penalizes late or non-deliveries of high-priority tasks, hence directing the selection process towards hybrid strategies that support the coverage of all high-priority tasks within the 72-hour deadline. When a standard routing mechanism will provide coverage of high-priority tasks within the 72-hour deadline, a single-phase route will be selected because it represents the shortest distance. When a high-priority task will not be completed within the 72-hour deadline, a two-phase route will be created to guarantee timely delivery. Therefore, the APB-ACO methodology is viable across a wide variety of different task distributions.

3.4.4. Pheromone Update with Elite Strategy

To create the most effective routes, APB-ACO utilizes an advanced pheromone update strategy in which both the iteration-best route and the global-best route are strongly reinforced. The formula used for this calculation is as follows:

$$\tau (i,j)\leftarrow (1-\rho )·\tau (i,j)+\Delta {\tau }_{\mathrm{iter}}(i,j)+\Delta {\tau }_{\mathrm{global}}(i,j)$$

(4)

where $\Delta {\tau }_{\mathrm{iter}}=Q/L_{\mathrm{iter}}$ for edges that are part of the iteration-best route and $\Delta {\tau }_{\mathrm{global}}=Q/L_{\mathrm{global}}$ for edges that are part of the global-best route, with $Q=1$ and $L=$ total route length. The evaporation rate ($\rho$) determines how quickly the pheromones on each edge will break down over time. The use of an elite strategy to update the routes means that the best worldwide routes will receive faster pheromone accumulation than the average world route, which will promote even faster convergence to a better solution.

3.4.5. Adaptive Evaporation Schedule

APB-ACO employs a time-decaying evaporation rate:

$$\rho \left(t\right)=max\left({\rho }_{min},{\rho }_{\mathrm{init}}·{\left(1-t/T\right)}^{2dt}\right)$$

(5)

where ${\rho }_{\mathrm{init}}=0.15$, ${\rho }_{min}=0.05$, and T is the total number of iterations. High early evaporation encourages exploration by rapidly degrading suboptimal pheromone trails, while reduced later evaporation preserves high-quality routes discovered during convergence. The square-root decay provides a smooth transition between exploration and exploitation phases.

3.4.6. 2-Opt Local Search Refinement

To further refine each ant’s discovered route, a local search using 2-opt is performed upon completion of all ants’ routes. For each pair of nonadjacent edges $(i,i+1)$ and $(j,j+1)$, the distance improvement is calculated based on the changes made by reversing the section between $i+1$ and j. If reversing this portion of the route between these two edges results in a shorter consolidated route than the original route, the reversal is performed. The process repeats until no further improvements can be obtained or a maximum of 50 iterations is reached. Importantly, since 2-opt was conducted separately to refine each phase independently, the refinement of Phase 1 was performed before constructing Phase 2, while the refinement of Phase 2 was executed after its completion.

3.4.7. Convergence Analysis and Complexity

Theorem 1 establishes the Convergence of APB-ACO with ${\rho }_{\min }>0$. As $T\to \infty$, APB-ACO will converge to the optimal solution with probability one.

Proof overview: The convergence of APB-ACO follows the classical ACO convergence theory established by Stützle and Dorigo in 1994, with the additional factor of the adaptability of the algorithm. There are three sufficient conditions to satisfy:

label=

The addition of the evaporation floor, ${\rho }_{\min }>0$, guarantees that all pheromones at every iteration will all have ${\tau }_{\min }\ge 0$. The elite update also has the finite deposit limit of ${\tau }_{\max }$.

lbbel=

The transition probability $\gamma (i,j)>0$. Since all node pairs will have a positive transition probability from node i to node j, any unvisited node j will also have a positive selection probability from node i.

lcbel=

The best-solution reinforcement principle ensures that as pheromones are deposited on the global best solution, pheromones will continually increase (in expectation) on the optimum solution as compared with the suboptimal solutions.

Thus, under Conditions 1–3, every feasible route will have a non-zero probability of being constructed at each iteration. By the Borel-Cantelli lemma, if enough iterations happen, the chance of constructing the globally optimal route with probability one will happen. The adaptive parameters for $\gamma$ and $\rho \left(t\right)$ are in compliance with Conditions 1–3, as $\gamma \ge 1$, only acts to scale the probabilities, and does not set them to zero, and $\rho \left(t\right)\ge {\rho }_{\min }>0$ ensures that the pheromones remain within limits.

The convergence of the selection of the adaptive strategies will be preserved in APB-ACO because the minimum-fitness solution from two different converging strategies will always be selected. □

The complexity of the APB-ACO algorithm will be $O(T·m·N^2·K)$ per vessel, where T is the number of iterations, m is the number of ants, N the number of task points assigned, $K\le 50$ is the maximum number of 2-opt iterations, and the selection of the adaptive strategy will double the constant. However, this does not change the asymptotic complexity of APB-ACO. The default parameters are $T=200$, $m=20$, $N\approx 30$–43, and $K=50$. Thus, each vessel’s algorithm should run about 56 seconds on one CPU core with these parameters. The space complexity for APB-ACO is the same as that of standard ACO, which is $O\left(N^2\right)$ for pheromone and distance matrices.

3.4.8. Why APB-ACO Outperforms Standard ACO for IUU Patrol

Standard artificial bee colony (ABC) routing algorithms have been shown through experimentation to converge towards distance-optimal routes and provide task clustering around spatially dense areas. For illegal, unreported, and unregulated (IUU) fishing patrol areas identified by synthetic aperture radar (SAR), the most important targets (i.e., hotspots) are geographically isolated from the majority of the fishing effort (e.g., 14.28$\circ$N, 145.44$\circ$E near the Mariana Islands), while sea turtle and coral reef protection areas are located between 3–8 $\circ$ N. If an ABC routing algorithm is implemented without deadline awareness and uses distance heuristics $\eta {(i,j)}^{\beta }$, it will exponentially penalize transitions to distant, high-priority tasks or result in their scheduling beyond the 72-hour coverage window. These challenges are addressed by the two-phase structure of the adaptive priority-based ant colony optimization routing algorithm (APB-ACO). Specifically, APB-ACO constructs the prefix of the routing path before building the end nodes, ensuring that high-priority task locations are visited before the operational coverage deadline, regardless of the geographical distance between low-density high-priority tasks and high-density tasks. The adaptive path selection strategy of APB-ACO is also designed to avoid distance-based penalties when meeting task completion deadlines. These findings are confirmed by the results presented in Section 5.5, which demonstrate that APB-ACO generated a total route distance of only 21,658±9 km with 100% coverage of high-priority task locations, compared to 23,294±414 km generated by PB-ACO. The reduction in standard deviation is substantial (i.e., 46 times lower for APB-ACO: $\sigma =9$ km vs. $\sigma =414$ km), highlighting the reliability and repeatability of solutions obtained via the two-phase construction process and routing optimization across multiple random seeds.

3.4.9. Algorithm Pseudocode

Algorithm 1 presents the complete APB-ACO procedure with adaptive strategy selection.

Algorithm 1:APB-ACO with Adaptive Strategy Selection

Require: Distance matrix $\mathbf{D}$, priority scores $\mathbf{P}$, deadline $T_d=72$ h Ensure: Route $R^{*}$, total distance $d^{*}$ 1: Identify HP tasks: $\mathrm{HP}\leftarrow \{j:P\left(j\right)\ge {\theta }_{\mathrm{high}}\}$ 2: Build Phase-1 candidate set: ${\mathcal{C}}_1\leftarrow \mathrm{HP}\cup \mathrm{KNN}(\mathrm{HP},K=3)$ 3: Strategy 1: Single-phase 4: $R_{\mathrm{sp}}\leftarrow \mathrm{PB}-\mathrm{ACO}(\mathrm{all}\mathrm{nodes},\gamma -\mathrm{boosted})$ 5: Apply 2-opt to $R_{\mathrm{sp}}$ 6: $f_{\mathrm{sp}}\leftarrow \mathrm{distance}\left(R_{\mathrm{sp}}\right)+\mu ·\sum \mathrm{bad}\mathrm{hbox}\left(R_{\mathrm{sp}}\right)$ 7: Strategy 2: Two-phase 8: $R_1\leftarrow \mathrm{PB}-\mathrm{ACO}({\mathcal{C}}_1,\gamma -\mathrm{boosted})$ Phase 1: HP prefix 9: Apply 2-opt to $R_1$ 10: $R_2\leftarrow \mathrm{PB}-\mathrm{ACO}(\mathrm{remaining}\mathrm{nodes},\mathrm{start}=\mathrm{last}\left(R_1\right))$ Phase 2 11: Apply 2-opt to $R_2$ 12: $R_{\mathrm{tp}}\leftarrow R_1\oplus R_2$ 13: $f_{\mathrm{tp}}\leftarrow \mathrm{distance}\left(R_{\mathrm{tp}}\right)+\mu ·\sum \mathrm{bad}\mathrm{hbox}\left(R_{\mathrm{tp}}\right)$ 14: Adaptive selection 15: if$f_{\mathrm{tp}}\le f_{\mathrm{sp}}$then 16:    $R^{*}\leftarrow R_{\mathrm{tp}}$ 17: else 18:    $R^{*}\leftarrow R_{\mathrm{sp}}$ 19: end ifreturn$R^{*}$, $\mathrm{distance}\left(R^{*}\right)$

3.4.10. APB-ACO Parameter Configuration

Table 1 summarizes the APB-ACO parameter configuration.

3.5. Formation Coordination

After individual route planning, a coordination module enforces fleet-level constraints. Ship positions are interpolated at 10-minute intervals to construct a time series. The communication constraint requires that no pair of vessels exceeds a maximum separation distance (500 km). When violations are detected, intermediate waypoints are inserted to pull distant ships closer together. The coordination module also tracks cooperative patrol coverage, where high-priority tasks require the simultaneous presence of at least two vessels within a 50 km radius.

3.6. Evaluation Metrics

The following metrics are used for performance evaluation:

Coverage Rate (72 h): Percentage of high-risk task points visited within a 72-hour simulation window.

Average Revisit Interval: Mean time between consecutive visits to high-risk points (hours).

Total Distance: Sum of Haversine distances traveled by all vessels (km).

Distance Balance: Coefficient of variation ($\mathrm{CV}=\sigma /\mu$) of distances across vessels. Lower values indicate more equitable workload distribution.

Composite Score:

$$S=0.35\times {\displaystyle \frac{\mathrm{Coverage}}{100}}+0.25\times (1-\mathrm{CV})+0.25\times \mathrm{EfficiencyNorm}+0.15\times (1-\mathrm{CommPenalty})$$

(6)

Each component is normalized to $[0,1]$ to avoid arbitrary scaling factors. $\mathrm{Coverage}/100$ converts percentage to ratio; $(1-\mathrm{CV})$ maps balance to $[0,1]$; efficiency is capped at 1 via $\mathrm{EfficiencyNorm}=min(\mathrm{bad}\mathrm{hbox}/({\mathrm{Distance}}_m/1000)/5,1)$; the communication penalty is the ratio of violations to total time steps. The composite score $S\in [0,1]$, with higher values indicating a better overall performance.

The composite scoring system (0.35,0.25,0.25,0.15) was developed using a subjectively determined weight that represented an operational priority for high-risk area coverage above all other considerations. The formulation of a bounded composite score [0,1] precludes any given component from dominating the overall composite score due to arbitrary differences in their relative scales and may provide a more formal and interpretable performance measure than previously considered ad hoc scaling methods. Future researchers should continue exploring the use of multi-objective composite formulations that illustrate the full Pareto frontier of coverage vs. efficiency trade-offs by eliminating the need to convert to a scalar value.

4. Experimental Setup

4.1. Study Area and Real Data Sources

The Western Pacific Ocean (0–20$\circ$ North Latitude, 140–160$\circ$ East Longitude) includes portions of the Philippine Sea, the Federated States of Micronesia (FSM) Exclusive Economic Zone (EEZ), Palau, Guam, the Northern Mariana Islands, and Papua New Guinea, and it also includes parts of the International High Seas where distant water fishing fleets operate. This specific area was chosen due to the many different IUU related activities that are known to occur there, based on all three real data sources used for this research.

Three sources of data were used to conduct this research, and all of the three sources come from actual satellite observations and vessel observations. GFW Fishing Efforts (Actual AIS Data): 247,846 actual vessel fishing hours from Global Fishing Watch monthly datasets (January to December 2022), retrieved from Zenodo DOI 10.5281/zenodo.14982712. The data for the area included (0–20$\circ$ North Latitude, 140–160$\circ$ East Longitude) and represented Actual Vessel Hours Generated from AIS position reports through the GFW neural network algorithm for detecting fishing vessels. These records included 20 or more flag states with Taiwan, Japan and China being the primary flag states contributing to this area.

SAR Dark Vessel Data (Actual Sentinel-1 Data): 389 actual SAR vessels from Paolo et al.. “Satellite-Mapping Reveals Extensive Industrial Activity at Sea” (Nature, 625:85–91). These SAR vessels were identified using Sentinel-1 C band SAR images that were processed using computer vision to detect the vessels on the images using backscatter energy signatures of the vessels on the SAR images. Out of the 389 vessels detected within the study area, 131 (33.7%) of them were unable to be matched to AIS broadcasts and are therefore classified as Dark Vessels, meaning that the vessels were likely operating without A. 258 matched detections of the SR-AIS co-registration system.

Encounter Events (Actual GFW Events API): 186 deduplicated validated vessel encounters sourced from the GFW Events API [15] for the 2022 calendar year within the study area. GFW defines “encounters” as interactions between two vessels that travel within a close distance (within 500 meters) for at least 2 hours at a slow speed (<2 knots). Of the 186 identified encounters, 84 (45.2%) were classified as potential high-risk encounters based on vessel type and flag state, and 29 (15.6%) involved carrier vessels, indicating potential at-sea transshipment activities.

Table 2. Summary of Real Data Sources Used in This Study.

Data Source	Records / Detections	Coverage Period	Key Metric
GFW AIS Fishing Effort (Zenodo, 2022)	247,846 records	Jan–Dec 2022	Vessel-hours/$0.{01}^{\circ }$ cell; top flags: TWN, JPN, CHN
Sentinel-1 SAR Dark Vessels (Paolo et al. [27])	389 detections (131 = 33.7% dark)	2022	Unmatched rate: 33.7%; KDE density field normalized to $[0,1]$
GFW Events API (Encounter Events)	186 deduplicated (84 risk-flagged, 29 carrier)	Jan–Dec 2022	Risk encounter rate: 45.2%; carrier involvement: 15.6%

Table 2. Summary of Real Data Sources Used in This Study.

Data Source	Records / Detections	Coverage Period	Key Metric
GFW AIS Fishing Effort (Zenodo, 2022)	247,846 records	Jan–Dec 2022	Vessel-hours/$0.{01}^{\circ }$ cell; top flags: TWN, JPN, CHN
Sentinel-1 SAR Dark Vessels (Paolo et al. [27])	389 detections (131 = 33.7% dark)	2022	Unmatched rate: 33.7%; KDE density field normalized to $[0,1]$
GFW Events API (Encounter Events)	186 deduplicated (84 risk-flagged, 29 carrier)	Jan–Dec 2022	Risk encounter rate: 45.2%; carrier involvement: 15.6%

4.2. Vessel Configuration

To evaluate the stability of each algorithm and facilitate cross-algorithm comparisons, each algorithm was run 30 times with different random seed values (seeds 1–30). DQN and NSGA-II had far higher computational requirements than APB-ACO (over 120 seconds per run); thus, each of these algorithms was run only 10 times. The mean values for the route-level metrics from all repetitions (runs) of each algorithm are reported. Pairwise comparisons of statistical significance (relative to the APB-ACO algorithm) were tested using the Wilcoxon rank-sum (Mann-Whitney U) test. The Wilcoxon rank-sum test is a nonparametric test suitable for small sample sizes and/or non-normal distributions. $*p<0.05$; $**p<0.01$; $***p<0.001$.

4.3. DQN Route Planning Details

To provide a complete characterization of the DQN-based route planner included in the six-algorithm comparison, this section details the state representation, action space, reward function, network architecture, hyperparameters, and training procedure.

4.3.1. State Space

The state is a $4N$-dimensional vector concatenating four components of length N (number of task nodes):

Current node one-hot encoding:N dimensions. A one-hot vector with a 1 at the index of the current node and 0 elsewhere.

Visited mask:N dimensions. A binary vector where 1 indicates the node has been visited.

Priority scores:N dimensions. Normalized priority scores $P\left(j\right)\in [0,1]$ for each task node j.

Normalized distances:N dimensions. Haversine distances from the current node to all other nodes, normalized by the maximum pairwise distance to $[0,1]$.

4.3.2. Action Space

The action space consists of a limited set of N unique options, represented by the index values of each node of the task within the environment. The Q-values for the previously visited task nodes are set to $-\infty$ and are masked from the observations of the agent, preventing the agent from revisiting these nodes during the selection process $argmax$.

4.3.3. Reward Function

The reward at each step balances distance minimization and early high-priority visits:

$$R(s,a)=-d(\mathrm{current},\mathrm{next})+P\left(\mathrm{next}\right)\times (1-\mathrm{step}/N)\times 10$$

(7)

4.3.4. Network Architecture

The Q-network is a 3-layer MLP: Input ($4N\to 256$, ReLU), Hidden ($256\to 128$, ReLU), Output ($128\to N$, Linear). The output produces N Q-values. Both online ($\theta$) and target (${\theta }^{\prime }$) networks share this architecture; the target is updated every 10 episodes.

4.3.5. Hyperparameters

Learning rate: 0.001 (Adam); discount $\gamma =0.99$; $\epsilon$: $1.0\to 0.01$ (linear); replay buffer: 5,000; batch size: 64; target update: every 10 episodes; training episodes: 500.

4.3.6. DQN Route Planner Algorithm

Algorithm 2 presents the DQN-based route planner.

Algorithm 2:DQN-based Route Planner

Require: Distance matrix $\mathbf{D}$, priority scores $\mathbf{P}$, episodes E Ensure: Optimal route ${\pi }^{*}$ 1: Initialize Q-network $\theta$ and target ${\theta }^{\prime }\leftarrow \theta$ 2: Initialize replay buffer $\mathcal{B}$ (capacity 5,000) 3: for episode $e=1$ to E do 4:    Select start; visited $\leftarrow \left\{s_0\right\}$ 5:    for step $t=1$ to $N-1$ do 6:      State $s=\left[\mathrm{bad}\mathrm{hbox}\right(\mathrm{curr})\parallel \mathrm{visited}\parallel \mathbf{P}\parallel \mathrm{dist}]$ 7:      $\epsilon$-greedy: random or $argmaxQ(s,a;\theta )$ 8:      Execute, store $(s,a,r,s^{\prime })$ in $\mathcal{B}$ 9:      Mini-batch SGD on Bellman loss 10:    end for 11:    Decay $\epsilon$; update ${\theta }^{\prime }$ every 10 episodes 12: end for 13: Greedy inference: ${\pi }^{*}$ with $\epsilon =0$

4.4. Baseline Methods

Lawnmower Scanning (Baseline 1): A systematic boustrophedon pattern that covers the entire study area uniformly, without risk-based prioritization.

Fishing Effort Hotspot (Baseline 2): Patrol routes directed to the top AIS fishing effort hotspots, using only GFW fishing effort data (no SAR dark vessel or encounter data).

4.5. Operational Constraints

Fuel Consumption Model. Patrol vessel fuel consumption is estimated using the Admiralty formula: $F=k·v^3·t_{\mathrm{transit}}+f_{\mathrm{idle}}·t_{\mathrm{station}}$, where $k={10}^{-4}$, v is speed in knots, $f_{\mathrm{idle}}=0.05$ tons/hour. At 15 knots, transit consumption $\approx 0.34$ tons/hour.

Restricted Zone Avoidance. Two restricted zones: (a) circular military exclusion zone around Guam ($13.{45}^{\circ }$N, $144.{78}^{\circ }$E; radius 50 km), and (b) rectangular shipping lane along the North Caroline Ridge (9–${11}^{\circ }$N, 148–${149}^{\circ }$E).

5. Results and Discussion

5.1. Risk Assessment and Task Generation

Utilizing a composite risk model created a 1,600 cell risk grid derived from both GFW and SAR to measure the risk associated with illegal, unreported and unregulated (IUU) fishing and distance water fishing grounds has shown that high risk cells ($\ge 0.3$) within the total risk grid are located in the southwestern region (3 – 8$\circ$ N, 140 – 148$\circ$ E), and that the areas of overlap between all three datasets (real time data from GFW, Sentinel I SAR and Dark Vessel Detection (D) by GFW) indicate a strong association between the two datasets, validating the nearness of dark vessel inactivity to the suspected IUU fishing grounds. This finding was confirmed by the 33.7% unmatched dark vessel rate (i.e., 131 dark vessel detections out of 389) from real time Sentinel I SAR data for the same temporal interval, providing further confidence in the size and implication of risk of IUU fishing to the area. Figure 2 illustrates the IUU risk scores as processed by the composite risk model.

DBSCAN clustering on real-data risk scores yielded 100 patrol task points, of which 2 were classified as high-risk (priority score $\ge 0.8$, revisit frequency = 12 h), 1 as medium-risk (revisit frequency = 24 h), and 97 as low-risk (revisit frequency = 72 h). The two high-risk clusters spatially correspond to the areas of highest dark vessel density from real SAR data. One high-risk task is located at approximately $14.{28}^{\circ }$N, $145.{44}^{\circ }$E, near the Mariana Islands, where vessel transshipment activity and AIS non-compliance rates are particularly elevated.

5.2. Baseline Comparison

Table 3 presents the performance comparison between the proposed risk-driven approach and baselines.

The risk-driven PB-ACO approach achieves a composite score of 0.483, substantially outperforming lawnmower (0.225) and fishing-effort-only (0.000) baselines. The proposed method achieves 50% high-risk coverage rate within 72 hours while neither baseline achieves any high-risk coverage. The fuel efficiency metric demonstrates the stark advantage: 7.01 tons per coverage point, 62 times more efficient than lawnmower scanning.

Figure 3. Patrol route comparison across three strategies. The risk-driven approach concentrates effort around SAR dark vessel hotspots, while lawnmower and fishing-effort strategies distribute effort uniformly.

Figure 3. Patrol route comparison across three strategies. The risk-driven approach concentrates effort around SAR dark vessel hotspots, while lawnmower and fishing-effort strategies distribute effort uniformly.

5.3. Ablation Study

To quantify the contribution of each real data source, we performed ablation experiments using four different weight configurations (Table 3).

Table 4. Ablation Study: Contribution of Real Data Sources.

Configuration	${\mathit{w}}_1$	${\mathit{w}}_2$	${\mathit{w}}_3$	Composite	Coverage (%)	Dist (km)
Full Model (AIS+SAR+Enc.)	0.4	0.4	0.2	0.483	50.0	28,618
w/o Dark Vessel (AIS+Enc only)	0.6	0.0	0.4	0.684	100.0	30,142
w/o Encounter (AIS+SAR only)	0.5	0.5	0.0	0.478	50.0	30,336
Fishing Effort Only	1.0	0.0	0.0	0.684	100.0	30,142

Table 4. Ablation Study: Contribution of Real Data Sources.

Configuration	${\mathit{w}}_1$	${\mathit{w}}_2$	${\mathit{w}}_3$	Composite	Coverage (%)	Dist (km)
Full Model (AIS+SAR+Enc.)	0.4	0.4	0.2	0.483	50.0	28,618
w/o Dark Vessel (AIS+Enc only)	0.6	0.0	0.4	0.684	100.0	30,142
w/o Encounter (AIS+SAR only)	0.5	0.5	0.0	0.478	50.0	30,336
Fishing Effort Only	1.0	0.0	0.0	0.684	100.0	30,142

The results of these experiments are somewhat counter-intuitive. By removing the SAR dark vessel component ($w_2=0$) from our model, the composite score improved from 0.483 to 0.684, and the coverage increased from 50% to 100%. The reason is that tasks derived from AIS data tend to cluster in areas accessible to fishing vessels, whereas the full model represents genuine SAR-identified dark vessel hotspots, which are located in geographically isolated regions and are difficult to patrol within the given time window (72 hours). Therefore, this finding further supports the integration of SAR data alongside AIS-derived data: the proposed system targets genuine and challenging areas where AIS monitoring would otherwise be ineffective.

Figure 4. Ablation study results showing the impact of removing individual data sources.

Figure 4. Ablation study results showing the impact of removing individual data sources.

5.4. ACO Parameter Sensitivity Analysis

The sensitivity of the ACO algorithm to three key parameters was analyzed: number of ants ($n_{\mathrm{ants}}$), evaporation rate ($\rho$), and heuristic weight ($\beta$). Table 5 presents $n_{\mathrm{ants}}$ sensitivity results.

Figure 5. ACO parameter sensitivity analysis. Safe operating ranges: $\rho \in [0.05,0.3]$, $\beta \in [0.5,3.0]$.

Figure 5. ACO parameter sensitivity analysis. Safe operating ranges: $\rho \in [0.05,0.3]$, $\beta \in [0.5,3.0]$.

Coverage varies with $n_{\mathrm{ants}}$: 100% at $n_{\mathrm{ants}}=5,30,50$ (composite 0.73–0.74); 50% at $n_{\mathrm{ants}}=10,20$. Higher $n_{\mathrm{ants}}$ (≥30) provide more consistent coverage. The safe operating range for evaporation is $\rho \in [0.05,0.3]$; $\beta =5.0$ causes distance-greedy routing that bypasses isolated HP targets.

5.5. Multi-Algorithm Comparison

Table 6 compares six optimization algorithms on the same real-data instance. DQN and NSGA-II details are in Section 4.3 and below.

APB-ACO achieves the shortest mean distance (21,658 km) with $\sigma =9$ km—46 times lower standard deviation than PB-ACO ($\sigma =9$ km vs. 414 km). Five of six algorithms achieve 100% HP coverage; only NSGA-II fails (0%). APB-ACO is 7.0% shorter than PB-ACO ($p<0.001$).

Figure 6. Multi-algorithm comparison. APB-ACO achieves shortest distance (21,658±9 km) with highest stability; Wilcoxon tests confirm significance ($p<0.001$) vs. all algorithms.

Figure 6. Multi-algorithm comparison. APB-ACO achieves shortest distance (21,658±9 km) with highest stability; Wilcoxon tests confirm significance ($p<0.001$) vs. all algorithms.

Table 7. Wilcoxon Rank-Sum Test p-Values (APB-ACO as Reference).

Metric	PB-ACO	GA	PSO	DQN	NSGA-II
Total Distance	<0.001 ***	<0.001 ***	<0.001 ***	<0.001 ***	<0.001 ***
Priority Position	<0.001 ***	0.055 n.s.	<0.001 ***	0.017 *	0.012 *

* $p<0.05$, ** $p<0.01$, *** $p<0.001$. Two-sided Wilcoxon rank-sum.

Table 7. Wilcoxon Rank-Sum Test p-Values (APB-ACO as Reference).

Metric	PB-ACO	GA	PSO	DQN	NSGA-II
Total Distance	<0.001 ***	<0.001 ***	<0.001 ***	<0.001 ***	<0.001 ***
Priority Position	<0.001 ***	0.055 n.s.	<0.001 ***	0.017 *	0.012 *

* $p<0.05$, ** $p<0.01$, *** $p<0.001$. Two-sided Wilcoxon rank-sum.

5.6. Discussion of Algorithm Performance

Using a minimum route distance of 21,658 ± 9 km, APB-ACO outperforms PB-ACO by 7.0%, which yields a distance of 23,294 ± 414 km (Wilcoxon $p<0.001$). Furthermore, the standard deviation ($\sigma =9$ km) is 46 times lower than that of PB-ACO ($\sigma =414$ km). This improvement stems from restricting phase 1 of APB-ACO to high-priority (HP) nodes and nearest neighbors, which introduces very little stochastic variability. With independent 2-opt refinement applied in both phases, the variability of solutions generated by APB-ACO is virtually eliminated.

While the composite scores are approximately equal (PB-ACO: 0.709; APB-ACO: 0.706), the clear advantages of a considerably shorter total distance ($-7.0\%$) and significantly improved stability ($46\times$ lower variance) demonstrate the operational superiority of APB-ACO. Moreover, the adaptive selection mechanism guarantees that the performance of APB-ACO is not worse than that of PB-ACO. The computational time of 56.3 s to generate an adaptive solution based on positional data is acceptable for the offline generation of patrol routes.

5.7. Scalability Analysis: Impact of High-Priority Task Ratio

To assess the robustness and effectiveness, we evaluated scenarios with the number of high-priority (HP) tasks ranging from 2 to 20 (representing 2–20% of 100 HP assignments), with 10 independent runs for each configuration (Table 7). (Table 8).

Figure 7. Scalability analysis (2–20% HP ratio). APB-ACO maintains 85–100% coverage while PB-ACO degrades to 44%.

Figure 7. Scalability analysis (2–20% HP ratio). APB-ACO maintains 85–100% coverage while PB-ACO degrades to 44%.

The proposed APB-ACO method consistently generates the shortest routes while achieving the highest HP task completion rates. Specifically, APB-ACO reduces route distance by 7.8–9.8% and improves HP task completion to 85–100%, compared to only 44–92% for competing methods. The performance gap between APB-ACO and other algorithms widens as the number of HP tasks increases: a 41-percentage-point improvement at HP=20, versus a 25-percentage-point improvement at HP=2. Therefore, the two-phase construction strategy of APB-ACO becomes increasingly critical as the number of deadline-critical HP assignments grows.

5.8. Convergence Analysis

APB-ACO achieves 21,921 km from the first iteration, converging to 21,646 km at iteration 200—only 1.3% improvement. PB-ACO starts at 40,832 km and requires ∼75 iterations for 43% improvement. Even at $T=1$, APB-ACO outperforms PB-ACO’s fully converged solution (21,921 < 23,110 km), demonstrating the power of structural decomposition over pure metaheuristic search.

Figure 8. Convergence curves. APB-ACO achieves near-optimal distance from iteration 1 (21,921 km); PB-ACO requires ∼75 iterations to approach 23,110 km.

Figure 8. Convergence curves. APB-ACO achieves near-optimal distance from iteration 1 (21,921 km); PB-ACO requires ∼75 iterations to approach 23,110 km.

5.9. Composite Score Weight Sensitivity

Composite score ranges from 0.433 to 0.521 (±9.3% from default). The ranking (risk-driven > lawnmower > fishing-effort-only) is preserved across all configurations.

Table 9. Composite Score Weight Sensitivity Analysis.

Configuration	${\mathit{w}}_{\mathbf{cov}}$	${\mathit{w}}_{\mathbf{bal}}$	${\mathit{w}}_{\mathbf{eff}}$	${\mathit{w}}_{\mathbf{comm}}$	Composite	Rank (vs. Default)
Coverage-Focused	0.50	0.20	0.20	0.10	0.496	+2.7%
Balance-Focused	0.25	0.35	0.25	0.15	0.521	Best
Efficiency-Focused	0.25	0.20	0.40	0.15	0.441	−8.7%
Default	0.35	0.25	0.25	0.15	0.483	Baseline
Equal Weights	0.25	0.25	0.25	0.25	0.433	−10.4%

Table 9. Composite Score Weight Sensitivity Analysis.

Configuration	${\mathit{w}}_{\mathbf{cov}}$	${\mathit{w}}_{\mathbf{bal}}$	${\mathit{w}}_{\mathbf{eff}}$	${\mathit{w}}_{\mathbf{comm}}$	Composite	Rank (vs. Default)
Coverage-Focused	0.50	0.20	0.20	0.10	0.496	+2.7%
Balance-Focused	0.25	0.35	0.25	0.15	0.521	Best
Efficiency-Focused	0.25	0.20	0.40	0.15	0.441	−8.7%
Default	0.35	0.25	0.25	0.15	0.483	Baseline
Equal Weights	0.25	0.25	0.25	0.25	0.433	−10.4%

5.10. Discussion

The results of this study identify key scientific and operational findings. First, the dark vessel rate derived from real Sentinel-1 SAR data is 33.7%, considerably above the 17–25% estimated from synthetic studies, which supports the high level of AIS non-compliance in the Western Pacific and the necessity of SAR monitoring [20,27].

Second, the high spatial collinearity between GFW Events API encounter data and SAR dark vessel hotspots limited their independent contribution during the ablation process. This is expected because the hotspots of encounter near the Mariana Islands overlap with the hotspots of dark vessels, where ships engaged in transshipping frequently disable their AIS transponders [24].

Third, the violation of the 500 km communication distance requirement (over 1,100 violations within 72 h) demonstrates that fleet cohesion across a $2,220\mathrm{km}\times 2,220\mathrm{km}$ region using only three vessels remains a critical operational challenge.

Fourth, findings suggest a three-tier enforcement strategy: (1) persistent surveillance of SAR-identified dark vessel corridors near the Mariana Islands; (2) risk-driven rotating patrols of AIS fishing effort hotspots; (3) periodic lawnmower sweeps of low-risk areas for deterrence.

Fifth, achieving violation-free communication would require 6–8 vessels or satellite relay (Iridium/Starlink). The framework can accommodate this by adjusting the $\mathrm{bad}\mathrm{hbox}$ parameter.

6. Conclusions

This paper presented a comprehensive framework for IUU risk-driven fleet patrol route optimization integrating three real multi-source maritime surveillance datasets. Unlike previous works relying on simulated data, this study demonstrates the framework on real Sentinel-1 SAR detections [27], real GFW Events API encounters [15], and real GFW Zenodo AIS fishing effort [14]. Statistical validation through 30 repeated runs and Wilcoxon tests provides rigorous evidence. The key findings are:

1.

The multi-source risk model ($w_1=0.4$, $w_2=0.4$, $w_3=0.2$) achieves 50% high-risk coverage and composite score 0.483, outperforming lawnmower (+0.258) and fishing-effort-only (+0.483) baselines.

2.

The ablation study reveals that removing SAR data counterintuitively increases the composite score (0.483 → 0.684) because AIS-only tasks are geographically easier, confirming SAR introduces genuinely harder patrol targets invisible to AIS monitoring.

3.

APB-ACO achieves the shortest route distance (21,658 ± 9 km), 7.0% shorter than PB-ACO (23,294 ± 414 km), with the highest stability (46 times lower standard deviation than PB-ACO, $\sigma =9$ km vs. 414 km). All differences are statistically significant ($p<0.001$). The adaptive strategy selection guarantees APB-ACO is never worse than PB-ACO.

4.

APB-ACO introduces two-phase deadline-aware construction, adaptive evaporation, and 2-opt refinement per phase, with formal convergence proof (probability 1 as $T\to \infty$). Parameter sensitivity reveals safe ranges: $\rho \in [0.05,0.3]$, $\beta \in [0.5,3.0]$.

5.

Fuel consumption analysis shows 19.3% fuel savings vs. lawnmower (350.4 vs. 434.3 tons) and 62 times higher fuel efficiency per coverage point.

Scalability experiments confirm APB-ACO’s advantage grows with HP task count (85–100% coverage vs. PB-ACO’s 44% at 20% HP ratio). Convergence analysis shows near-optimal solutions from iteration 1.

Future work will address: (a) dynamic near-real-time risk models; (b) multi-objective Pareto frontier exposure; (c) weather and sea state constraints; (d) hybrid ACO-PSO algorithms; (e) field validation with patrol agencies; (f) restricted zone avoidance as hard constraints; (g) adaptive fleet pre-positioning based on seasonal SAR patterns; and (h) temporal risk dynamics through deep learning forecasters (LSTM/Transformer) for 12–48 h risk prediction.