The full-day workshop will provide a forum for presenting original research in computer vision and pattern recognition applied to large-scale remote sensing imagery. The focus will be on recent advancements in automatic analysis of remote sensing imagery for Earth Observation and its impact on geoscience, climate change, sustainable development goals, and the general understanding of the Earth system. A non-exhaustive list of topics of interest includes the following:

– Super-resolution in the spectral and spatial domain
– Hyperspectral and multispectral image processing
– Reconstruction and segmentation of optical and LiDAR 3D point clouds
– Feature extraction and learning from spatiotemporal data
– Analysis  of UAV / aerial and satellite images and videos
– Deep learning tailored for large-scale Earth Observation
– Domain adaptation, concept drift, and the detection of out-of-distribution data
– Data-centric machine learning
– Evaluating models using unlabeled data
– Self-, weakly, and unsupervised approaches for learning with spatial data
– Foundation models and representation learning in the context of EO
– Human-in-the-loop and active learning
– Multi-resolution, multi-temporal, multi-sensor, multi-modal processing
– Fusion of machine learning and physical models
– Explainable and interpretable machine learning in Earth Observation applications
– Uncertainty quantification of machine-learning based prediction from EO data
– Applications for climate change, sustainable development goals, and geoscience
– Public benchmark datasets: training data standards, testing & evaluation metrics, as well as open-source research and development.