arXiv ·
MBZUAI researchers introduce TerraFM, a scalable self-supervised learning model for Earth observation that uses Sentinel-1 and Sentinel-2 imagery. The model unifies radar and optical inputs through modality-specific patch embeddings and adaptive cross-attention fusion. TerraFM achieves strong generalization on classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
arXiv ·
The paper proposes a method for causal inference using satellite image time series to determine the impact of interventions on climate change, focusing on quantifying deforestation due to human causes. The method uses computer vision and deep learning to detect forest tree coverage levels over time and Bayesian structural causal models to estimate counterfactuals. The framework is applied to analyze deforestation levels before and after the hyperinflation event in Brazil in the Amazon rainforest region.
arXiv ·
This paper introduces a novel approach for monitoring and analyzing the evolution of complex geographic objects in satellite image time-series. The method uses a spatiotemporal graph and constraint satisfaction problems (CSP) to model and analyze object changes. Experiments on real-world satellite images from Saudi Arabian cities demonstrate the effectiveness of the proposed approach.
arXiv ·
This paper introduces a novel two-step method for predicting urban expansion using time-series satellite imagery. The approach combines semantic image segmentation with a CNN-LSTM model to learn temporal features. Experiments on satellite images from Riyadh, Jeddah, and Dammam in Saudi Arabia demonstrate improved performance compared to existing methods based on Mean Square Error, Root Mean Square Error, Peak Signal to Noise Ratio, Structural Similarity Index, and overall classification accuracy.
KAUST ·
KAUST's Hydrology, Agriculture and Land Observation Lab (HALO) uses remote sensing tools like drones to map and monitor agricultural sites, including one of the world's largest olive farms in Al Jouf. They also collaborate with the Ministry of Environment, Water and Agriculture of Saudi Arabia and the Center for Desert Agriculture. HALO's mangrove project focuses on carbon sequestration by Avicennia marina mangroves in the Red Sea as part of the KAUST Circular Carbon Initiative. Why it matters: This research contributes to understanding and promoting the conservation of mangrove ecosystems for carbon neutrality in line with Saudi Arabia's sustainability goals.
MBZUAI ·
MBZUAI, in partnership with IBM Research, is developing GeoChat+, a vision-language model (VLM) for multi-modal, temporal remote sensing image analysis. GeoChat+ builds on the previous GeoChat model, enhancing capabilities with multi-modal images from various Earth observation systems like Sentinel-1, Sentinel-2, Landsat, and high-resolution imagery. GeoChat+ will integrate data from multiple satellites at different times to detect environmental changes and analyze the impact on soil quality, air quality, and erosion. Why it matters: This advancement promises to revolutionize geographic data analysis, providing detailed reports for high-risk regions and aiding reforestation efforts.
KAUST ·
KAUST's Hydrology and Land Observation (Halo) lab, led by Matthew McCabe, is using drones and satellites to monitor agricultural water usage in Saudi Arabia. They employ thermal cameras, sensors, and imagery from CubeSats to map crop types, health, and water stress. The team uses machine learning and AI to analyze the images, aiming to promote sustainable water management. Why it matters: This research addresses critical water scarcity issues in the region by providing data-driven insights for more efficient agricultural practices.
MBZUAI ·
Researchers at MBZUAI, IBM Research, and other institutions have developed EarthDial, a new vision-language model (VLM) specifically designed to process geospatial data from remote sensing technologies. EarthDial handles data in multiple modalities and resolutions, processing images captured at different times to observe environmental changes. The model outperformed others on over 40 tasks including image classification, object detection, and change detection. Why it matters: This unified model bridges the gap between generic VLMs and domain-specific models, enabling complex geospatial data analysis for applications like disaster assessment and climate monitoring in the region.