-
Meta SAM 3 Meets Earth Observation: A look into using Segment Anything for object detection and tracking from animated Satellite time series
The world of geospatial AI just got a powerful new tool. Meta’s latest Segment Anything Model 3 (SAM 3), a foundation model for detection, segmentation, and tracking in images and video, is opening up…
-
Satellite Embeddings in Geospatial Workflows: Navigating the Challenges and the Excitement
Using a blender (throwing diverse data into a model) has long been a popular playground among my generation of graduate students working with satellite imagery and machine learning. But as many of us have…
-
Exploring earthquake building damage with Satellite Embedding
The complexity of urban areas, with their diverse building types and structures, makes damage classification particularly challenging. Satellite images provide a broad overview of the affected areas, but their accuracy often requires validation through…
-
How Well Do Crop-Type Models Transfer with Embeddings? Exploring Generalization with AlphaEarth Embeddings
Remote sensing has enabled the production of up-to-date crop type maps to support food security, management, and research. However, crop types maps remain largely limited to regions where ground truth labels are available to…
Esmaeel Adrah -- Blog & Portfolio 