Machine Learning-Based Prediction of Stem Water Potential in Olive Orchards Using PlanetScope Imagery and Meteorological Data

1. Introduction

Efficient irrigation management in Mediterranean woody crops, such as olive groves, represents one of the most important agronomic challenges under scenarios of increasing water scarcity and climate variability [1,2,3]. In the case of olive orchards, a dominant crop in southern Europe and particularly relevant to Mediterranean agriculture, the implementation of regulated deficit irrigation strategies requires detailed knowledge of tree physiological status to optimize water use without compromising yield [4,5]. In this context, accurate assessment of crop water status is essential to optimize water use, maintain productivity, and avoid irreversible physiological impacts. Traditionally, Stem Water Potential (SWP), measured using a Scholander pressure chamber, has become the reference physiological indicator for characterizing the water status of perennial trees and shrubs due to its strong theoretical basis and empirical consistency throughout the growing season [6].

In this context, SWP has established itself as a key tool for optimizing regulated deficit irrigation strategies. Multiple studies have demonstrated that the systematic use of SWP enables: the precise adjustment of irrigation thresholds, avoids periods of severe water stress, and improves both productivity and water efficiency [7,8]. In olive orchards, SWP values within specific ranges allow physiological activity to be maintained without significantly reducing yield, thereby providing an objective basis for regulated deficit irrigation scheduling [9,10,11]. In other Mediterranean fruit trees, such as almond and pistachio, the application of SWP-based strategies exhibited improvements in water use efficiency and production stability even under conditions of high evaporative demand [12]. On the other hand, studies in vineyards showed that combining SWP with multi-source data, including growth, leaf temperature, soil moisture, and meteorology, allows for highly accurate modeling of water stress [13]. These results highlight the importance of SWP as a crucial component of water management in woody crops and justify the need to develop methodologies that facilitate its continuous estimation using less invasive and more scalable data sources. However, despite its reliability, SWP measurement with Scholander pressure chambers is a manual, slow, and highly labor-intensive process, which limits its operational applicability in large-scale farming systems.

In recent years, new technologies have emerged focused on continuously monitoring the water status of crops using sensors installed directly on trees [14]. Among these approaches, xylem tension–based sensors stand out, as they allow continuous monitoring of stem water potential through micro-transducers inserted into the vascular tissue [15,16]. In addition, dendrometers are widely used to measure micrometric variations in trunk or branch diameter, providing indirect estimates of plant water status based on the daily contraction-expansion dynamics of the tissue [13,17,18]. Although both technologies represent a significant advance toward automated monitoring of water stress, they exhibit important limitations. Xylem tension–based sensors are intrusive and require direct implantation into plant tissue, while dendrometers require frequent calibration, phenological adjustments, and a detailed understanding of crop biomechanics. These limitations are aggravated by acquisition costs, the need for periodic maintenance, long-term stability issues, and the requirement for recurrent field visits, all of which hinder their large-scale operational adoption. In addition, many of these sensors show strong crop specificity, preventing their direct transfer between species and requiring the development of distinct configurations, calibration curves, and interpretative models for each case. Taken together, these constraints reinforce the need to advance toward non-invasive methodologies capable of providing robust estimates of crop water status without relying on specialized instrumentation installed on the tree.

In response to these limitations, remote sensing emerges as a particularly promising alternative for assessing crop water status at spatial and temporal scales unattainable with in situ sensing alone. Satellite and aerial observations provide spectral indices that are sensitive to vegetation vigor, canopy structure, and plant water content [19]. In particular, spectral indices calculated from visible and near-infrared bands have been widely used as indirect indicators of plant physiological status, as they capture changes in leaf pigment concentration, biomass, and canopy density, which are closely related to water stress dynamics [20,21,22]. The integration of these spectral indicators with ground-based physiological measurements provides a robust framework for estimating stem water potential and supporting irrigation management at the orchard scale without the need for invasive instrumentation. However, spectral indices exhibit significant limitations due to spatial resolution, environmental variability, and crop structure, making it necessary to complement them with meteorological and physiological information to improve water stress estimation. Meteorological drivers such as air temperature, vapor pressure deficit, and reference evapotranspiration play a key role in regulating plant–atmosphere water exchanges and modulating crop water stress responses [23,24]. When combined with spectral indexes, these variables provide complementary information that enhances the robustness and temporal stability of water status estimates [25,26]. Furthermore, the inclusion of physiological reference measurements, such as stem water potential, enables the calibration and validation of remote sensing–based approaches able to provide reliable and operationally scalable assessments of crop water status [27].

Simultaneously, recent advances in data analysis techniques have encouraged the development of modeling approaches capable of integrating heterogeneous information sources and capturing complex, non-linear relationships among physiological, atmospheric, and spectral variables [28,29]. These advances encompass a broad range of methodologies, including statistical learning [30] , machine learning [31], deep learning [32], and data fusion frameworks [33], which enable the joint exploitation of multivariate and multiscale datasets. In several studies, these approaches have been applied to water stress assessment within precision agriculture and IoT-based platforms, combining sensor networks and automated irrigation systems that dynamically adjust irrigation amounts according to model outputs [34,35]. Such methodologies have demonstrated a clear improvement in SWP estimation compared to traditional linear models, allowing the simultaneous incorporation of spectral indices, meteorological variables, and canopy-derived descriptors without relying on restrictive assumptions [36]. Moreover, advanced data analysis techniques exhibit a strong ability to exploit large, multitemporal, and heterogeneous databases, uncovering latent patterns, interactions, and temporal dependencies that are difficult to capture using classical approaches. Their flexibility facilitates adaptation to varying environmental conditions, phenological stages, and crop configurations, enhancing model robustness as well as spatial and temporal transferability. Combined, these advances reinforce the potential of data-driven approaches as operational tools for water management in real-world precision agriculture scenarios.

Despite the advances described, a gap still exists between the scientific knowledge generated on water stress in woody crops and its operational application at the farm scale. Many previous studies have relied on short-term experimental campaigns, limited study areas, or the use of technologies that, although they improve water status monitoring, continue to require frequent field visits for sensor installation, calibration, maintenance, or validation of physiological measurements. This dependence on intensive fieldwork restricts the scalability of the proposed methodologies and hampers their adoption in large-scale production systems. Moreover, a significant portion of the literature addresses the problem through the isolated use of spectral indices or environmental variables, without systematic integration with reference physiological measurements that would ensure model robustness and transferability. In the specific case of olive orchards, studies combining multi-year time series, high spatial resolution satellite data, meteorological information, and direct stem water potential measurements to develop reliable and operational predictive models remain scarce. This methodological fragmentation, together with the persistent need for field visits and the limited availability of large, well-calibrated datasets, highlights the lack of truly scalable tools capable of continuously and accurately estimating crop water status, thereby reinforcing the need for integrative approaches that overcome the limitations of previous studies.

In this context, the objective of the present study is to predict SWP in Mediterranean olive orchards by integrating high-resolution PlanetScope satellite data and agroclimatic station records with reference physiological measurements obtained using a Scholander pressure chamber, which provide a low-bias assessment of plant water stress. To this end, a Gradient Tree Boosting approach, implemented through the XGBoost algorithm [37], was employed to model the complex and non-linear relationships among meteorological, spectral, and canopy-related variables. As a result of the data acquisition campaign, a total of 1,856 SWP measurements collected between 2021 and 2025 were compiled, together with their corresponding meteorological variables, PlanetScope spectral band reflectance values, and vegetation indices relevant to soil–plant water status estimation. These data were consolidated into a dataset comprising 183 features. The resulting dataset was curated and analyzed to characterize its temporal distribution and stratification across different levels of water stress.

2. Materials and Methods

2.1. Study Area and Sampling Design

The study was carried out at the El Valenciano experimental farm, part of the Rural Innovation Hub [38], located in the province of Seville, within the Autonomous Community of Andalusia, southern Spain (37.4° N, 5.5° W, WGS-84). The area is characterized by a Mediterranean climate, with hot, dry summers and mild, wet winters, which makes it particularly suitable for evaluating crop water stress under semi-arid conditions. The Rural Innovation Hub offers a reference agricultural environment dedicated to testing and validating technologies for smart agriculture and sustainable water management. The experimental farm exhibits marked heterogeneity in management practices, water availability, and soil characteristics, making it an ideal setting for the evaluation of remote sensing–based and advanced data-driven models for water stress prediction in Mediterranean olive orchards.

The study area consists of seventy-five sampling zones distributed across rainfed conditions, conventional irrigation, and regulated deficit irrigation regimes (Figure 1a). These zones include several commercial olive varieties, including Arbequina, Arbosana, Sikitita, Lecciana, Sultana, and Martina, which are representative of modern and intensive planting systems. The coexistence of different plant materials under contrasting management conditions enables the capture of a wide range of physiological and spectral variability, which is essential for ensuring the robustness and generalizability of the proposed model. Between 2021 and 2023, several sampling zones were incorporated into the CENTARIA project [39], where distinct irrigation strategies were implemented and systematic measurements of leaf water potential were carried out using a Scholander pressure chamber. These experimental areas covered relatively large surfaces, allowing the definition of 20 × 20 m sampling plots, spaced approximately 20 m apart (Figure 1e). During the 2024 and 2025 seasons, field sampling was conducted in different sectors of the farm through intensive survey campaigns, broadening the range of water conditions captured. In these years, due to the more limited spatial extent available compared to the CENTARIA project plots, sampling areas were defined as 10 × 10 m units covering the entire analyzed area (Figure 1b,c,d).

2.2. Data Collection

2.2.1. Ground Measurements

During the period 2021–2025, 1,321 SWP measurements were obtained using a Scholander chamber [40] which constitutes the physiological reference variable used as ground truth for training and validating the estimation models developed in this study. The measurements were taken mainly during the period May–October, coinciding with conditions of maximum evaporative demand and the application of deficit irrigation, when the water response of olive trees shows greater physiological variability and an accurate estimate is most valuable.

The measurement procedure followed standardized protocols to ensure the reliability of the values obtained. In each sampling zone, fully expanded leaves were selected from the inner, shaded part of the canopy in order to minimize the influence of direct radiation and rapid variations in stomatal opening. Prior to extraction, the leaves were placed in aluminum bags for 10–15 minutes, allowing water equilibrium between the petiole and xylem, an essential step for obtaining an accurate reading of water potential. After stabilization, the leaves were cut and immediately processed in the Scholander chamber, recording the SWP value in absolute megapascals (MPa). SWP measurements were taken in accordance with the agronomic requirements derived from deficit irrigation management, which meant that the sampling dates did not necessarily coincide with the satellite acquisition times. This time lag, far from being a limitation, reflects the actual conditions of crop management, where irrigation decisions are scheduled based on the physiological state of the plant and not on the availability of orbital images. Methodologically, this lack of synchrony, represented by a time lag, generates an additional physiological variable, which has been explicitly considered in the model design and allows for the evaluation of its ability to predict water status even when spectral information and field measurements are not obtained simultaneously.

2.2.2. PlanetScope Data Acquisition and Vegetation Indices Estimation

High-resolution multispectral imagery from the PlanetScope nanosatellites constellation, a commercial system operated by Planet Labs Inc., was used to monitor vegetation conditions at the plot scale. Although the sensors acquire imagery with a native spatial resolution that typically ranges between 3.7 m and 4.1 m depending on orbital altitude, the data are resampled and distributed to users at a standardized spatial resolution of 3 m. Surface reflectance products from Dove Classic and the Dove-R sensors, launched from 2016-2018, include four spectral bands: blue (455–515 nm), green (500–590 nm), red (590–670 nm), and near-infrared (780–860 nm). The most recent SuperDove sensors acquire an eight-band configuration that incorporates the coastal blue (430–450 nm), yellow (590–610 nm), red-edge (705–745 nm), and a second near-infrared band (860–880 nm) into the previous four bands. The near-daily revisit frequency enables continuous monitoring of crop dynamics during periods of peak water demand, reducing data gaps caused by cloud cover [41]. After a project proposal was approved, 16-bit orthorectified surface reflectance imagery was accessed through the Planet Education and Research Program [42]. These multispectral datasets are atmospherically corrected to minimize the effects of local atmospheric variability, ensuring radiometric consistency, and supporting reliable multitemporal analyses [43].

The use of spectral indices is one of the most widely used tools in remote sensing to characterize the physiological state of vegetation [44,45]. These indices are obtained through mathematical combinations of reflectances in different regions of the electromagnetic spectrum. The 8-band enhanced spectral configuration improves sensitivity to vegetation structure, chlorophyll content, and canopy stress. Based on these spectral bands, several vegetation indices, which are widely used to assess vegetation vigor, were computed (Table 1). The vegetation indices provide relevant information for predicting and interpreting the hydrological response of the plant in response to exogenous characteristics [46].

PlanetScope spectral bands used for index calculation. Four-band PlanetScope products include B (Blue: B02), G (Green: B04), R (Red: B06), and NIR (Near-Infrared: B08). Eight-band (SuperDove) products additionally provide CB (Coastal Blue: B01), G1 (Green I: B03), Y (Yellow: B05), and RE (Red Edge: B07).

The derived indices were grouped into structural vegetation indices (NDVI, EVI2, SAVI, OSAVI, MSAVI), chlorophyll-related indices (GNDVI, CI green), red-edge-based indices (NDRE, CI red_edge), visible-based indices (VARI), photosynthetic efficiency indices (PRI), and senescence-related indices (PSRI, SIPI). Within the structural group, soil-adjusted indices such as SAVI, OSAVI, and MSAVI were included to explicitly minimize soil background effects, particularly in woody crops with wide spacing or partial coverage, such as olive orchards. Indices were computed conditionally based on band availability, allowing consistent processing of both 4-band and 8-band PlanetScope imagery. Red-edge-based indices (NDRE and CI red_edge) were only derived when SuperDove 8-band data were available (84 of the 89 dates analyzed). Indices whose original formulations rely on narrow or sensor-specific spectral bands, such as the PRI, PSRI, and SIPI indices, were computed using adapted or approximate formulations to ensure compatibility with PlanetScope imagery. PRI was derived using different band combinations for Dove and SuperDove sensors due to differences in spectral availability. With SuperDove data, a closer approximation to the original PRI formulation was estimated through the use of narrow green bands, while Dove imagery required an alternative visible-band approximation.

For the study, both mean and maximum values were extracted for each original spectral band of the PlanetScope imagery as well as for all derived vegetation indices within each sampling zone. Mean values were used to characterize the overall vegetation condition by integrating intra-plot spatial heterogeneity related to management practices, soil properties, and water availability. In contrast, maximum values were considered representative of the potential vegetation response, reducing the influence of soil background and mixed pixels. The combined analysis of mean and maximum statistics enabled a robust assessment of spatial variability within sampling zones and improved the detection of localized stress patterns and temporal changes in vegetation conditions.

2.2.3. Meteorological Data

The meteorological data used in this study were obtained from the SE101_IFAPA Centro Las Torres–Tomejil agroclimatic station [59], located approximately 10 km from the El Valenciano experimental farm. The station is operated and periodically calibrated by public authorities, ensuring data quality and reliability. Its use allows methodological standardization and guarantees the reproducibility of the results, without the need to deploy additional field instrumentation or to introduce technical dependencies on the participating farms [60].

From this station, the meteorological variables effectively used in the analysis were collected, including daily mean, maximum and minimum air temperature (with their corresponding time of occurrence), daily mean, maximum and minimum relative humidity (with their corresponding time of occurrence), global solar radiation, cumulative and effective precipitation, and reference evapotranspiration (ET₀) (see Table 2).

Each time series has been temporally synchronized with the field sampling schedule and the satellite acquisition dates. For each meteorological variable, three daily metrics were calculated: the maximum value, the minimum value, and the mean of all values throughout the day. This information is particularly relevant for variables with high intra-daily variability, such as temperature and relative humidity, for which extreme values may be more representative of crop stress conditions.

For the construction of the dataset, it was necessary to account for the temporal dependencies between meteorological variables from previous days and the measurement at the current time t. Accordingly, for each SWP observation, six meteorological records were included for each variable, temporally shifted by one-day intervals (lags), starting from the day of the SWP measurement (lag 0) until 5 days before. Thus, for each prediction, up to a maximum of six lagged values were considered ($M_t, M_{t-1}, \dots , M_{t-5}$).

The integration of these open-access meteorological data enhances the practical applicability of the developed model, enabling its use in farms that do not have on-site weather stations and facilitating its transferability to other agricultural environments with similar conditions.

2.2.4. Dataset Curation and Description

The dataset used in this study was constructed through the integration of spectral, meteorological, and physiological information, resulting in a dataset that combines observations from different sources for each study area. In total, 1,856 SWP values were obtained, corresponding to the 1,856 field measurements acquired using a Scholander pressure chamber. These measurements essentially constitute the target variable for the prediction task.

Figure 2 shows the overall distribution of SWP values in the dataset. The data are expressed as absolute values in MPa (since SWP is always negative) and span a range from 0.80 to 4.5 MPa, where higher SWP values indicate greater levels of crop water stress. It can be observed that the frequency of SWP values above 2 MPa progressively decreases, reflecting the tendency to minimize water stress through deficit irrigation strategies. This aspect is not trivial, as the prediction of high SWP values is particularly important due to the increased risk posed to the crop under such conditions. Consequently, when applying data-driven estimation techniques, it is essential to consider dataset stratification strategies to mitigate the imbalance of observations in the upper range of SWP values.

Figure 3 shows the distribution and frequency of SWP values as a function of the ordinal week of the year. This distribution indicates that the data were collected from early March to late October. The frequency of SWP datapoints, grouped by ordinal week, reveals the presence of sample clusters associated with the different farms. A temporal correlation between SWP and the ordinal week of the year can be observed, driven by the meteorological variables characteristic of each month of the growing season.

The variability of the data as a function of the time of year introduces two levels of difficulty in SWP estimation. During the early months of the season (March–May), milder temperatures and a less pronounced lack of precipitation make SWP easier to predict, as it remains relatively stable. It is during the second and third quarters of the year that water stress can increase sharply, depending on specific irrigation conditions, temperature, humidity, and other environmental factors.

Regarding the aggregation of PlanetScope data into the dataset—including both the original spectral bands and the derived spectral indices—it must be considered that temporal mismatches may occur between PlanetScope acquisitions and SWP measurements. This misalignment arises from differences between the timing of SWP measurements, which are conducted by technicians according to farm operations, and the satellite overpass frequency of PlanetScope. To mitigate the need to restrict the dataset to SWP measurements acquired only on days with PlanetScope data, the closest available PlanetScope observation within a ±96-hour temporal window was selected. It is reasonable to assume that, due to the continuous nature of crop dehydration processes, PlanetScope-derived index values remain valid over a short temporal window, provided they are acquired at a similar time of day. In this context, each SWP observation was assigned a one-to-one correspondence with a PlanetScope data record, with a maximum absolute temporal lag of 96 hours.

Figure 4 shows the histogram of the data as a function of the temporal difference between each SWP measurement and its corresponding PlanetScope observation. It can be observed that approximately half of the PlanetScope data were acquired on the same day as the SWP measurement. This represents an advantage of the PlanetScope constellation, which provides an almost daily acquisition frequency with a maximum temporal offset of less than four days. The remaining samples with lags greater or smaller than 24 hours are, in most cases, associated with PlanetScope data unavailability due to missing images or cloud cover over the study area.

From the aggregation of PlanetScope and meteorological variables, clear correlation relationships between variables can be derived and visualized. In Figure 5, two variables are shown that allow the identification of noisy linear and non-linear relationships with SWP.

The large volume of available data enables the development of a reliable predictive model for estimating crop water stress.

2.3. Data Driven Model

The prediction of water stress can be addressed using different Machine Learning or Deep Learning algorithms. In previous studies, approaches based on Random Forest Regression or Support Vector Regression [62] have been commonly adopted. In general, the application of these algorithms has relied on a black-box approach, in which models are primarily compared based on their performance metrics. In this section, the proposed methodology is described, which is based on Gradient Tree Boosting using the XGBoost algorithm [37].

2.4. XGBoost for the Estimation of Agronomic Variables

Decision trees are supervised models that approximate nonlinear relationships through successive partitions of the feature space. At each split, a threshold is selected on a predictor variable with the aim of reducing the dispersion of the response variable in the resulting nodes. This hierarchical construction allows interactions among predictors to be captured without imposing parametric assumptions on the data distribution. However, an individual decision tree is often unstable and sensitive to noise, leading to a high risk of overfitting in complex regression problems.

To mitigate this risk, the boosting paradigm was introduced, which consists of additively combining multiple decision trees trained in a sequential manner. Each subsequent tree is fitted using the residual errors of the model accumulated up to that point, thereby progressively improving predictive performance. This procedure can be interpreted as a functional optimization process that minimizes a loss function through the iterative incorporation of weak learners. In this way, bias and variance are balanced, yielding more robust models without the need to excessively increase tree depth (see Figure 6).

XGBoost (Extreme Gradient Boosting) implements this approach through a formulation that improves both computational efficiency and overfitting control. The objective function includes an explicit regularization term that penalizes tree complexity, preventing the generation of unnecessary splits and enhancing generalization capability. Its training algorithm relies on a second-order gradient approximation, computing not only the gradient but also Hessian information to estimate the expected gain of each split. This treatment enables the selection of partitions that optimize error reduction in a more stable and effective manner. In addition, the computational design of XGBoost incorporates parallelization, efficient threshold search strategies, and optimized handling of sparse data, enabling its application in scenarios involving large datasets and high dimensionality.

These properties are particularly well suited for the estimation of water stress in olive orchards using meteorological variables and spectral indices derived from remote sensing. In this domain, the relationships between predictors and the response variable are highly nonlinear and may involve interactions that depend on time and on the physiological state of the crop. XGBoost is able to capture such interactions without requiring the manual specification of complex transformations, and it provides feature importance measures that allow an assessment of which variables contribute most to the prediction. This capability supports a degree of model interpretability, facilitates the identification of relevant spectral or meteorological indicators, and can inform the design of monitoring or agricultural intervention strategies. Moreover, its computational efficiency enables the execution of comparative analyses, cross-validation procedures, and interactions with feature selection techniques within reasonable time frames.

3. Experiments and Results

The following section presents the results obtained from the application of XGBoost for SWP prediction using the proposed dataset. First, the results of the hyperparameter optimization study are reported. Subsequently, an ablation study is presented to analyze the individual contribution of each feature family to the final model performance. Finally, a comparison with algorithms and methods reported in previous studies is carried out to validate the robustness and relevance of the obtained results1.

3.1. Dataset Preparation for Training and Validation

For all training procedures, the dataset was split into 80% for training and 20% for validation. Due to the uneven distribution of the data across SWP values, a stratified split was adopted to ensure that both the training and validation sets contained a proportional representation of each SWP range.

For this purpose, the SWP values were divided into 10 intervals spanning from the minimum value (0.797 MPa) to the maximum value (3.75 MPa). Within each interval, samples were assigned to the training and validation sets according to the 80/20 ratio. As a result, both datasets exhibit a similar distribution across the full range of available SWP values, thereby preventing the overrepresentation of specific measurements and serving as a mechanism to control bias.

For both model training and the ablation studies, cross-validation was applied to obtain the optimal model configuration. The cross-validation (CV) technique consists of dividing the training set into equally sized subsets. For each subset (fold), the model is trained using only the data outside that fold. In this study, five folds were used for all experiments. Final performance was computed as the average performance obtained across the models trained while excluding each fold in turn. This approach yields results with reduced bias with respect to the data used for training and can be employed as a criterion for hyperparameter or model architecture selection. For comparisons among different algorithms, however, predictions on the validation dataset were used, as these data were never included in any fold during the training process.

3.2. Performance Metrics

The following metrics are described to assess the optimality of the models and the baseline approaches:

Root Mean Squared Error ($RMSE$): It is the root mean square error. This metric represents an average error in which large errors are penalized more heavily than small ones, providing a less biased representation of the effect of outliers.

$$RMSE\left(y,\widehat{y}\right)={\displaystyle \frac{1}{N}}\sum _{i=0}^N{\left(y-\widehat{y}\right)}^2$$

Mean Average Error ($MAE$): It is the mean error produced by the model with respect to the true values. This metric treats all errors equally and is therefore more sensitive to outliers in the predictions than the RMSE.

$$MAE\left(y,\widehat{y}\right)={\displaystyle \frac{1}{N}}\sum _{i=0}^N\left(y-\widehat{y}\right)$$

Determination coefficient ($R^2$): It represents the correlation between the predicted and observed values. This metric measures how much of the variance in the data is explained by the model, within a range of [0,1], where 1 corresponds to a perfect model. It is useful for comparing models with one another, provided that the number of data points remains constant, since its denominator increases proportionally with the sample size.

$$R^2\left(y,\widehat{y}\right)={\displaystyle \frac{1-{\sum }_{\mathrm{i}=0}^{\mathrm{N}}{\left(\mathrm{y}-\widehat{\mathrm{y}}\right)}^2}{{\sum }_{\mathrm{i}=0}^{\mathrm{N}}{\left(\mathrm{y}-\overline{\mathrm{y}}\right)}^2}}$$

3.3. XGBoost Hyper Parametrization

In any application of ML/DL algorithms, the effect of hyperparameters on final performance should be systematically analyzed. Given the large number of training and validation parameters involved in algorithms such as XGBoost, it is necessary to investigate which parameter values can maximize prediction optimality. To obtain an efficient model, the search was focused on identifying the optimal values of the hyperparameters listed in Table 3. These hyperparameters are those that are commonly reported to have the greatest influence on regressor performance [63].

For hyperparameter optimization, a Tree-structured Parzen Estimator (TPE)–based search algorithm [64] was employed using all available feature types. During the optimization process, the TPE algorithm learns which parameter values lead to good performance and which do not. Based on this information, it constructs two probability distributions: one corresponding to promising configurations and another associated with poorly performing ones. New parameter values are then preferentially sampled from the distribution of promising configurations, thereby increasing the likelihood of improving the model at each iteration.

The study was conducted using 100 iterations of the TPE algorithm. The final parameter values obtained from this process are reported in Table 3.

The comparison shows that TPE-based optimization consistently improves generalization metrics with respect to the default configuration (see Table 4). Hyperparameter optimization using TPE systematically enhances performance: RMSE is reduced by approximately 7%, MAE by a similar margin, and R² increases by around 3%. These differences indicate that hyperparameter tuning provides measurable benefits over default parameter settings for SWP estimation, resulting in lower average prediction error and a higher proportion of explained variance (see Table 5). Finally, Figure 7 illustrates the predicted values in comparison with the observed values for the test set.

3.3.1. Feature Importance Analysis

XGBoost provides several metrics to quantify the importance of each feature in the model. Two of the most commonly used are Gain and Weight. Both are derived from the structure of the generated trees, but they reflect different aspects of each predictor’s contribution.

The analysis of feature importance in XGBoost using the Gain and Weight metrics provides complementary insights into the role of each predictor in SWP estimation using meteorological and spectral data. Gain quantifies the average reduction in the loss function associated with the use of a given feature in internal tree splits. It therefore identifies variables whose marginal contribution to error reduction is high, even if they are used infrequently. Weight, in contrast, measures the frequency with which a feature is used in splits across all trees in the model, providing information on its structural recurrence within the decision process.

These metrics make it possible to assess the informative capacity of each type of variable. A high Gain value for certain PlanetScope bands or indices would suggest that they contain information sensitive to physiological changes related to water stress, even if their contribution appears in specific and non-recurrent splits. Conversely, a high Weight value for meteorological predictors would indicate that these variables are systematically used by the model, reflecting their consistent relevance under different environmental conditions.

After training XGBoost with the optimal set of parameters, the importance of each feature can be examined in terms of its Gain (Figure 8) and Weight (Figure 9). The results reveal that minimum air temperatures dominate the Gain importance in the resulting estimator. This finding suggests that temperature variability contains highly discriminative information regarding the water status of olive trees. From a physiological perspective, this implies that temperature changes are strongly associated with plant or soil water behavior, possibly through their relationship with processes such as transpiration, evaporative demand, and stomatal regulation.

On the other hand, when analyzing the Weight importance of the resulting model, vegetation indices—and particularly the maximum values of the base spectral bands—are found to dominate. This indicates that the XGBoost model relies more frequently on these features across the trees to perform splits. Although the magnitude of improvement at each split may be moderate, their repeated use suggests that they provide consistent and useful information for discriminating SWP levels across different data subsets.

This recurrence implies that extreme variations (maximum values) in these bands, as well as the behavior of the PRI index, contain detectable and persistent signals related to crop water status, which are associated with plant physiological responses such as changes in reflectance linked to chlorophyll content, photosynthetic efficiency, or stomatal regulation.

In the following experiment, feature importance was analyzed in relation to model accuracy, using RMSE as the reference metric. To assess the practical relevance of the features in terms of their contribution to the final error, an ablation study was conducted considering five feature set configurations, in addition to a baseline case including all features. These feature sets were defined as follows: (i) meteorological data only, including all temporal lags; (ii) PlanetScope data only, comprising both base spectral bands and derived indices; (iii) meteorological data with temporal lags combined with PlanetScope vegetation indices; (iv) meteorological data without lags combined with all PlanetScope data; and (v) complete meteorological data combined with PlanetScope base spectral bands only.

Figure 10 shows the RMSE obtained when training XGBoost on the training dataset and evaluating it on the test dataset. The results of the ablation study (see Figure 10 and Table 6) indicate that the progressive removal of feature groups leads to a systematic increase in error, reflected in both RMSE and MAE, together with a decrease in the coefficient of determination (R²). The model including all variables achieves the best overall performance (RMSE = 0.282), suggesting that the joint combination of meteorological predictors, temporal lags, and spectral variables captures complementary information that is relevant for SWP estimation.

The exclusion of specific feature groups produces differentiated effects. The feature set composed of meteorological variables with temporal lags and base spectral bands maintains performance close to the full model (RMSE = 0.295), indicating that base bands provide relevant information and that vegetation indices are not critical when meteorological data are exploited with temporal memory. Similarly, removing meteorological lags results in a moderate performance penalty (RMSE = 0.298), highlighting that the inclusion of temporal dependencies, while beneficial, is not the primary determining factor of predictive capability.

The feature set combining meteorological variables with lags and PlanetScope vegetation indices leads to a more pronounced degradation in performance (RMSE = 0.318). This increase suggests that raw spectral bands contain more direct or stable information for inferring water stress than derived indices, at least under the experimental conditions considered. Finally, the model excluding meteorological data exhibits the largest loss in performance (RMSE = 0.377), revealing that atmospheric variables constitute the dominant component in SWP prediction, whereas spectral features alone are insufficient to adequately characterize water stress variability.

These empirical results are consistent with the interpretation derived from the previous Gain and Weight analyses: meteorological variables—particularly temperature and variables related to evaporative demand—produce substantial reductions in the loss function (high Gain), while base bands and indices such as PRI appear recurrently across the trees (high Weight), providing complementary but insufficient information on their own. Overall, the ablation study empirically confirms the practical relevance of both feature groups and indicates that the integration of atmospheric predictors with satellite base spectral bands constitutes an efficient combination for estimating SWP using XGBoost models.

3.3.2. Comparison with Other Algorithms

Multiple linear regression (MLR) constitutes the simplest baseline model in the comparison. It is based on the assumption that the target variable can be expressed as a linear combination of the predictors, with coefficients estimated by least squares. Its low performance (RMSE = 0.49; R² = 0.58) indicates that the relationship between meteorological and spectral predictors and SWP is strongly nonlinear and non-additive, rendering this model insufficient to represent the physiological dynamics of the crop.

Random Forest (RF) employs an ensemble of decision trees trained using bagging, that is, bootstrap subsets of the data and random subsets of features at each split. This strategy reduces estimator variance by averaging multiple uncorrelated predictors. Although it substantially improves upon linear regression (RMSE = 0.38; R² = 0.78), its ability to capture complex interactions appears limited when compared to boosting-based methods, in agreement with previous studies [62].

Gaussian Processes (GP) with an RBF kernel constitute a nonparametric probabilistic approach capable of modeling nonlinear relationships through covariance functions. Each prediction is accompanied by an uncertainty estimate, which is valuable in agronomic applications. However, their performance (RMSE = 0.34; R² = 0.75) reveals difficulties in generalizing under high-dimensional settings and potential collinearity among satellite and meteorological predictors, in addition to the high computational cost involved.

Support Vector Regression (SVR) extends SVM to the regression setting by constructing a prediction function that minimizes an error margin defined by the epsilon-insensitive loss. With appropriate kernels, it can capture nonlinear relationships. The results (RMSE = 0.30; R² = 0.81) indicate that the method models the problem reasonably well, although it underperforms relative to XGBoost, possibly due to limitations in handling nonlinear interactions among multiple heterogeneous features.

The implemented dense neural network employs several hidden layers with 128, 256, and 64 neurons, respectively, providing an architecture capable of approximating complex functions. However, the achieved performance (RMSE = 0.37; R² = 0.72) indicates that, even after optimization, the model fails to stably capture the relationship between predictors and SWP, likely due to the limited size of the dataset.

Finally, XGBoost combines multiple trees trained sequentially to correct residual errors through an objective function that includes regularization terms, facilitating overfitting control and training efficiency. Its second-order gradient formulation and ability to handle heterogeneous data explain its superior performance (RMSE = 0.27; R² = 0.84; MAE = 0.21). This result supports the conclusion that interactions among meteorological variables, temporal variability, and spectral information can be effectively modeled using regularized boosting. Compared with linear methods or dense neural networks, XGBoost offers clear advantages in terms of stability, relative interpretability, and predictive performance, consolidating its suitability for estimating olive water stress from remote sensing and meteorological data. Table 7 summarizes the different algorithms considered in the comparison.

4. Discussion

The results of this study reinforce that estimating water status in woody crops cannot rely solely on spectral information and requires explicit integration of atmospheric variables such as evapotranspiration. In this regard, our findings are consistent with those reported by [65], who demonstrated that meteorological predictors such as air temperature and reference evapotranspiration (ETo) explain a larger fraction of the daily variability of stem water potential than spectral indices considered in isolation.

The direct comparison with the study by [66], is particularly relevant, given the high degree of methodological similarity and the comparable agronomic context. In that work, conducted in Mediterranean olive orchards and based on high spatial resolution PlanetScope imagery, it was shown that machine learning models achieve their best performance when combining base spectral bands and vegetation indices (VIs), with multimodal approaches clearly outperforming purely spectral ones. However, [66], also reported a significant loss of predictive capability when transferring the models to independent seasons, highlighting the sensitivity of optical indices to interannual variability in atmospheric and phenological conditions.

With regards to the final accuracy of the model, it has been observed that the combination of a higher amount of data with a proper definition of the algorithms surpasses previous works (Garofalo et al., 2024). In this previous work, only 192 samples of SWP were used for training and validation. In this paper, the dataset comprises almost 10 times the previous amount. The combination of the plenitude of datapoints, the data preparation and the XGBoost algorithm shows a RMSE a 30% lower in this proposal. Moreover, beyond the merit figures, a cross-validation approach has been conducted to present the accuracy scores without data bias.

Within this framework, the results presented here confirm that specific PlanetScope-derived indices play a relevant role in water stress prediction [19]. In particular, indices associated with canopy vigor and structure, such as PRI, VARI, PSRI, and EVI2, show a consistent contribution, especially under conditions of high spatial heterogeneity within the crop. These indices capture changes in leaf density and photosynthetic activity that reflect integrated responses to water stress, rather than the short-term daily dynamics of stem water potential. Likewise, indices more sensitive to water content and chlorophyll concentration, such as combinations based on green and near-infrared (NIR) bands, exhibit a higher relative importance during phenological stages of maximum vegetative activity, in agreement with the findings of [66].

Nevertheless, both in our study and in the reference work, the reflectance values of PlanetScope base bands—particularly the NIR and red bands—provide complementary and highly valuable information when directly integrated into the models, avoiding the information loss inherent to the formulation of normalized indices. This observation is consistent with recent studies in olive [10] , almond [16], and pistachio orchards [12], where raw spectral bands combined with non-linear learning algorithms improve model stability against changes in canopy structure and illumination conditions.

From an atmospheric perspective, our results confirm that air temperature, solar radiation, and ETo are the most influential predictors, in line not only with [65] but also with studies conducted in vineyards, stone fruit orchards, and citrus crops [67]. The dominance of these variables highlights that stem water potential largely represents a direct response to instantaneous evaporative demand, while spectral information acts as a modulating factor that incorporates effects related to canopy structure, vigor, and accumulated physiological status.

A key aspect emerging from the comparison with the analyzed studies is that the exclusive use of meteorological variables may introduce biases when the agrometeorological station is not fully representative of the crop’s microclimatic conditions. In this context, the integration of PlanetScope-derived indices enables the capture of the spatial response of the canopy to atmospheric forcing, thereby reducing the uncertainty associated with the spatial separation between meteorological sensors and the agricultural plot. This synergy explains the superior performance of multimodal models compared to those based on a single source of information.

Overall, the evidence suggests that the combination of multiple PlanetScope spectral indices, base band reflectance values, and key meteorological variables constitutes a rich and complementary source of information for the accurate estimation of crop water status. Compared to approaches based exclusively on vegetation indices, the proposed integration allows the simultaneous capture of atmospheric demand, canopy structure, and internal plant physiological processes. These results further support the role of multimodal models as advanced tools for water stress monitoring and decision-making in precision irrigation systems, particularly in Mediterranean woody crops characterized by high spatial and temporal heterogeneity.

5. Conclusions and Future Works

The results confirm that reliable estimation of water status in woody crops cannot rely solely on spectral information, but requires explicit integration of atmospheric variables characterizing evaporative demand. In particular, air temperature, solar radiation, and reference evapotranspiration emerge as the most influential predictors of stem water potential, while spectral information acts as a modulating factor that incorporates effects associated with canopy structure, vegetative vigor, and the accumulated physiological status of the crop.

The combination of PlanetScope-derived spectral indices and base band reflectance values, especially in the near-infrared region, consistently improves model performance compared with approaches based exclusively on normalized indices. The results highlight that indices related to vigor, senescence, and photosynthetic efficiency provide relevant complementary information, particularly in scenarios characterized by high spatial heterogeneity within the crop.

As a main direction for future research, future work will focus on extending the proposed methodology to Sentinel-2 imagery, as this open-access and globally available data source would substantially enhance the operational applicability of the approach. However, this transition entails additional challenges associated with both the coarser spatial resolution (10 × 10 m) and the revisit frequency (approximately 5 days). Future studies should assess the impact of spatial aggregation on the ability to detect within-field variability, as well as develop temporal integration strategies to reconstruct daily water status dynamics from less frequent satellite observations.

Additionally, it will be necessary to analyze the consistency and transferability of spectral indices and bands between PlanetScope and Sentinel-2, taking into account differences in spectral configuration and radiometric response. Validation of the approach under multi-site and multi-year conditions will contribute to the development of more robust and generalizable models, capable of supporting water stress monitoring and irrigation decision-making at broader spatial scales through the use of freely available satellite data.