Application of deep learning for earth observation.

Visualize classified time series data with interactive Sankey plots in Google Earth Engine

A Colab notebook for land cover mapping and monitoring using Earth Engine

Tool for Quantitative Analysis and Visualization of Land Use and Land Cover Change.

This repository contains the official implementation of the paper "LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mapping".

A repository containing data for the paper" Urbanization-led land cover change impacts terrestrial carbon storage capacity: A high-resolution remote sensing-based nation-wide assessment in Pakistan (1990–2020)"

This repository will guide you how to use deep learning algorithms for land use land cover classification using satellite dataset!

This project uses a U-Net CNN to classify land use for the entire City ot Toronto at high-resolution in an automated pipeline.

Moirai - Land Data System

Repository for Amazon biome classification codes.

LULC samples for the Restore+ project dataset.

Repositório usado durante o treinamento do mapbiomas-chile

This repository provides the data processing pipelines and Python scripts required to reproduce the quantitative modeling of capitalist land enclosure in PIK2, Indonesia, by applying information geometry, Markov chains, and percolation theory to Sentinel-2 land use data.

A Google Earth Engine Land use (crops) classification workflow using Random Forest, one year of ground data, Sentinel-2, and Landsats; to produce multiyear annual 30-m crop maps

Deep learning pipeline (UNet) for built-up area extraction from Sentinel-2 imagery — applied to Chennai for urban heat island and climate risk analysis

Tool to enrich land-use/land-cover data with historical data, OpenStreetMap and protected areas

Analytics based on Dynamic World LULC derived from Sentinel - 2 images

Methodology description of the Mapbiomas' industrial and artisanal mining detection target

This repository contains an academic field-based GIS project on Dulahajara Mouza, including land use data collection, digitization in ArcGIS, and a socio-economic survey to understand how land use patterns relate to local livelihoods and development.

Trained EfficientNet models, achieving up to 98% validation accuracy in land cover classification.