Satellite Image Time Series

Satellite image time series (SITS) analysis focuses on extracting meaningful information from sequences of satellite images to monitor dynamic processes on Earth's surface. Current research emphasizes developing robust deep learning models, including convolutional neural networks (CNNs), vision transformers (ViTs), and hybrid architectures, to address challenges like cloud cover, irregular data sampling, and cross-regional variations in temporal patterns. These advancements are crucial for improving accuracy in applications such as land cover mapping, precision agriculture, and environmental monitoring, enabling more effective resource management and informed decision-making. The field is also actively exploring self-supervised learning and techniques to leverage multi-modal data for enhanced performance and reduced reliance on labeled datasets.