sentinel-2-data

An end-to-end GeoAI platform for agricultural monitoring using satellite foundation model embeddings, AlphaEarth, Galileo representations, NDVI-based vegetation analysis, and machine learning based crop classification.

Multimodal Accessibility and Place Profiling Engine for arbitrary Regions

Classical and quantum machine-learning framework for detecting and mapping natural hydrogen prospectivity in Kazakhstan using Sentinel-2 satellite imagery.

Data analysis and object detection to assess Hurricane Maria's impact using NDVI analysis and YOLO modeling for disaster relief planning.

We are using Sentinel-2 satellite imagery and a specialized U-Net deep learning model to detect changes in landscapes before and after flood events. Using the OMBRIA dataset, the model reliably identifies flooded areas to support disaster management and response efforts.

Automated Sentinel-2 / Earth Engine pipeline for wildfire burn severity (dNBR/RBR), post-fire erosion modeling (RUSLE), and emergency forest recovery (Spain RDL 15/2022).

Hybrid ML + GIS pipeline for wildfire vegetation risk: U-Net segmentation on Sentinel-2 with Dynamic World labels, fused with line-distance and slope to produce a tunable risk raster. Validated across three external California AOIs.

I wondered who counts the Amazon's lost trees, so I tried it myself: a U-Net on Sentinel-2 images maps 8,705 ha cleared in Rondônia (2021 to 2026), checked by hand on 300 random points

Download selected surface-reflectance bands Sentinel-2A Level-2A (12 bands, no B10) and Landsat 8/9 Collection 2 Level-2 (7 SR bands), through Earth Search.

An analysis of seasonal NDVI changes using the imagery from Sentinel-2 mission. Includes plots and stats for insights into vegetation health.

Given a desired extent, resolution, and desired analyses, downloads Sentinel 2 imagery from planetary-computer, downloads DEM tiles from Copernicus, and then analyzes them through NDVI, NDWI, MNDVI, MNDWI, and SAVI.

GRASS addon to download Sentinel-2 scenes by S2 scene ID using EODAG.

Piattaforma self-hosted per l'analisi comparativa di immagini satellitari. Confronta riprese nel tempo (Sentinel-2, Esri World Imagery o caricamento manuale), rileva automaticamente i cambiamenti con filtri anti-rumore, enhancement e soglie regolabili, e offre zoom, annotazioni, libreria ed export completo di report.

GEE-based wildfire susceptibility model (2019-2024) combining LULC, NDVI, NBR, fuel moisture, LST and terrain with Random Forest to produce probability based predictive susceptibility map.

Extension to read from Earth Observation data archives