Application of deep learning for earth observation.

This work discusses how high resolution satellite images are classified into various classes like cloud, vegetation, water and miscellaneous, using feed forward neural network. Open source python libraries like GDAL and keras were used in this work. This work is generic and can be used for satellite images of any resolution, but with MX band sen…

This project focuses on land use and land cover classification using Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The classification task aims to predict the category of land based on satellite or aerial images.

Executable Research Compendium para a geração de mapas de Uso e Cobertura da Terra utilizando Cubos de dados de imagens de Satélite

This Repository Houses the Code for our Capstone Thesis Titled : "A New Framework with Convoluted Oscillatory Neural Network (CONN) for Efficient Object-Based Land Use and Land Cover Classification on Remote Sensing Images"

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

Pixel-based land cover classification in central Hanoi using Sentinel-2 imagery. Implements and compares SVM, Random Forest, and 1D CNN models to support urban planning and remote sensing applications.

A reproducible, scalable and data-driven workflow for Sentinel-2 land cover classification — outperforming traditional desktop tools like QGIS SCP.

Land use land cover (lulc) classification of aerial imagery using machine learning techniques including U-Net architecture Convolutional Neural Networks (CNNs).

Interactive Shiny Dashboard for monitoring multi-year Land Use / Land Cover (LULC) changes in Istanbul using spatial and statistical visualizations.

This project revisits and rebuilds a previous Land Use and Land Cover (LULC) classification task on the EuroSAT dataset, using Vision Transformers (ViT) and modern PyTorch best practices.

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.

By employing Remote Sensing techniques, a spatio-temporal assessment of urban expansion in Lahore District between 2000 and 2025 was done in ArcGIS Pro using both unsupervised and supervised image classification. Post-classification change detection was applied to calculate the area and percentage of land covers that converted to built-up.

Jupyter Notebook Python Script for Analyzing LULC Changes

LULC Classification and Flood Vulnerability Analysis of Malappuram District (2018–2024) using Sentinel-2 and CART Machine Learning

Land Use and Land Cover Classification in Google Earth Engine

A complete Google Earth Engine (GEE) interactive application for multi-temporal Land Use / Land Cover (LULC) mapping, change detection, trend analysis, pixel inspection, and exporting results using machine learning classifiers.

This repository is intended to provide a set of QGIS tools to facilitate land use/land cover construction.