Remote Sensing Data Analysis in R 🛰

List of resources for mineral exploration and machine learning, generally with useful code and examples.

Spectral endmembers and unmixing tools for satellite land cover mapping.

Processing of HSIs: spectral unmixing and classification.

[ICCV 2025] UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields

MLNMF: Multilayer Nonnegative Matrix Factorization

Pipeline for remotely sensed imagery. The pipeline processes satellite imagery alongside auxiliary data in multiple steps to arrive at a set of trend files related to land-cover changes.

Data and MATLAB code for the simulations of [R. Arablouei, “Spectral unmixing with perturbed endmembers,” submitted to the IEEE Transactions on Geoscience and Remote Sensing, 2017.]

This toolbox allows the implementation of the Diffusion and Volume maximization-based Image Clustering algorithm for unsupervised hyperspectral image clustering. See "README.md" for more information. Copyright: Sam L. Polk, 2023.

Decoding and analysis software for MRBLEs (Microspheres with Ratiometric Barcode Lanthanide Encoding).

Analysis of the reflectance spectra from paintings: classification and endmembers.

Plate-forme Python modulaire pour l’analyse et le démélange spectral semi-supervisé d’images hyperspectrales HySpex (jeu de données DLR HySU). Elle combine : un pipeline NMF pour extraire endmembers + abondances ; un VAE convolutionnel semi-supervisé pour la classification de patchs ; des outils de pré-traitement et visualisation (RMSE, SAD, SID

Classifying the materials of individual pixels taken by satellite using Spectral Unmixing and Pixel Classification.

compare two-point UV/Vis spectroscopy read-out with spectral unmixing

A high resolution tool for snow cover reconstruction studies

It is possible to predict the spectrum of e.g. a nucleobase in a nucleoside-nucleobase conversion.

My semester project for the course 'Machine Learning and Computational Statistics' during my studies in MSc in Data Science, AUEB.

This code generates snow properties by applying the SPIReS algorithm v2024.1.0, derived from https://github.com/edwardbair/SPIRES (Bair et al., 2021) to the MOD09GA product (Vermotte and Wolfe, 2021). The algorithm produces daily raster images of snow cover and snow surface properties.