RiverSnap - estimation of river hydraulic parameters using machine learning/AI models

PyTorch U-TAE model for binary water and land segmentation from Sentinel-1 and Sentinel-2 imagery using the IBM Granite flood dataset.

Deep Learning based Water Segmentation in Satellite Imagery

This project includes data preprocessing, visualization, model training, and evaluation using TensorFlow and Keras, building a deep learning model for predicting binary water mask using UNet and pretrained models such as ResNet34, ResNet50 and EfficientNetV2B0, and establishing a UI using Flask, HTML, CSS & JS to give instant predictions.

A robust solution that accurately segmenting water bodies using multispectral and optical data. This solution is vital for monitoring water resources, flood management, and environmental conservation, where precise segmentation can significantly impact decision-making.

OpenMMLab-based remote sensing segmentation pipeline for binary water extraction using SegFormer, ensemble inference, and test-time augmentation.

Open Earth remote-sensing MCP server that lets AI agents discover geospatial data and run tools for STAC, Sentinel-2, nightlights, water mapping, spectral indices, and SAR metadata.