Motivation Retrieving relevant satellite imagery from vast archives is crucial for applications like disaster response and environmental monitoring. While existing text-to-image retrieval systems have shown promise, they are mostly limited to RGB data, failing to exploit the rich information in other sensor types like Synthetic Aperture Radar (SAR) and multispectral imagery. The CLOSP architecture successfully created a unified semantic space for both optical and SAR data, but its analysis is limited to single, static images. Many critical remote sensing applications, such as change detection and trend analysis, rely on observing areas over time. The current framework has not been extended to a temporal dimension, which would be a logical and valuable next step to enable dynamic queries like "urban growth over the last decade". Additionally, ready-made embeddings like Google Satellite Embeddings provide a ready-to-use aggregated resource for global-scale analysis.
Task
Reference
Text-to-Remote-Sensing-Image Retrieval beyond RGB Sources
Motivation
Forecasting surface water dynamics is crucial for managing water resources and adapting to climate change. While the introduction of multi-modal datasets that include satellite imagery, climate data, and elevation models represents a significant step forward, we still need to effectively investigate how specific climate variables influence the model's predictions. Moreover, the investigation of which geographical areas are more prone to model failure was not fully exploited, particularly since we do not know if certain climate conditions make predictions harder. The relationship between different input channels and the type of change (e.g., positive or negative) was not investigated in depth to determine which spectral bands are more relevant.
Task