AboutTopCourses
← heapsort-ai

Geospatial AI

6 items

RESEARCHarXiv CS.AI·1d ago

Land cover and flood type govern the detection limits of satellite-based flood mapping across diverse global flood events

This research assesses the operational reliability of satellite-based flood mapping using geospatial foundation models, specifically Prithvi-EO-2.0, across 19 diverse global flood events. Detection accuracy was found to be jointly dependent on land cover and flood type, with higher agreement in croplands and riverine events, and significantly lower detection in tree cover and built-up areas.

Flood mappingGeospatial AISatellite imagingNatural hazards
40
RESEARCHarXiv CS.LG·29d ago

Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa

This paper evaluates whether geospatial foundation model embeddings improve cross-country maize yield predictions in Sub-Saharan Africa. It finds that while within-country predictions are moderate, all feature sets, including foundation model embeddings, perform poorly under cross-country testing, indicating a significant generalisability gap.

Geospatial AISub-Saharan AfricaMachine Learningfoundation models
27
RESEARCHarXiv CS.LG·4/28/2026

Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition

This paper introduces a satellite-reanalysis PM2.5 fusion system for air quality monitoring in Africa, employing LightGBM and conformal prediction. The system addresses challenges in geographic generalization and uncertainty quantification crucial for the continent's green industrial transition.

Geospatial AIenvironmental AIMachine LearningAir Quality
27