Automated extraction of buildings from earth observation (EO) data is important for various applications, including updating of maps, risk assessment, urban planning, policy making. Combining data from different sensors such as high-resolution multispectral (HRI) and light detection and ranging (LiDAR) has shown great potential in building extraction. Deep learning (DL) is increasingly used in multimodal data fusion and urban object extraction. However, DL-based multimodal fusion networks may underperform due to insufficient learning of “joint features” from multiple sources and oversimplified approaches to fusing multimodal features. Recently, an hybrid attention-aware fusion network (HAFNet) has been proposed for building extraction from a dataset including co-located Very-High-Resolution (VHR) optical images and Light Detection And Ranging (LiDAR) joint data. The system reported good performances thanks to the adaptivity of the attention mechanism to the features of the information content of the three streams but suffered from model overparametrization, which inevitably leads to long training times and heavy computational load. In this paper the authors propose a restructuring of the scheme, which involved replacing VGG-16-like encoders with the recently proposed EfficientNet, whose advantages counteract exactly the issues found with the HAFNet scheme. The novel configuration was tested on multiple benchmark datasets, reporting great improvements in terms of processing times, and also in terms of accuracy. The new scheme, called HAFNetE (HAFNet with EfficientNet integration), appears indeed capable of achieving good results with less parameters, translating into better computational efficiency. Based on these findings, we can conclude that, given the current advancements in single-thread schemes, the classical multi-thread HAFNet scheme could be effectively transformed by the HAFNetE scheme by replacing VGG-16 with EfficientNet blocks on each single thread. The remarkable reduction achieved in computational requirements moves the system one step closer to on-board implementation in a possible, future “urban mapping” satellite constellation.

The ongoing expansion in volume, velocity and variety of geospatial data has stimulated the development of artificial intelligence applications and associated online cartographic visualizations. In this context, the cartographic communication through peer-reviewed media evolved to incorporate Findability, Accessibility, Interoperability and Re-usability (FAIR) principles. In this paper, we review the functionalities proposed by current international peer-reviewed media for accessing, exploring and re-using geospatial data, and situate them on a diagram conceived for peer-reviewed cartography in the artificial intelligence era. We then present an overview of the cartographic infrastructure and workflow currently available in the Terra Digitalis journal for the online publication of massive spatiotemporal data. This free and opensource based solution allows a smooth integration, from data submission to final peer reviewed publication, of dynamic, interactive 2D and 3D maps. As a proof of concept, we present two maps derived from massive spatiotemporal data, related, respectively, to a climate numerical model (raster data) and a bike sharing system’s origin-destination dataset (vector data). We argue that the combination of technologies used in the journal provides an efficient and low-cost solution, unmatched by other publication media, to boost the accessibility and FAIR principles for geospatial big data.