Comparing different data preprocessing methods to predict soil organic carbon content on soil spectra features

Soil Heating in Fire (SheFire) Model: Annotated .Rmd scripts and an R package to build and use a SheFire model for how different soil depths heat and cool during fires

The soilspec package: data and functions for the book 'Soil Spectral Inference with R'

Soil Heating in Fire (SheFire) Model: Annotated .Rmd scripts and an R package to build and use a SheFire model for how different soil depths heat and cool during fires

This repository contains files for automated soil sampling selection using the K-Means algorithm in R. The repository is intended for researchers and practitioners interested in automated soil sampling selection using the K-Means algorithm.

This repository collects material (code, presentation, images, test data) prepared for the webinar series of the Excalibur H2020 Training

R scripts for predicting soil organic carbon using soil spectral library from visible, near-infrared and shortwave-infrared (VNIR) and middle-infrared (MIR) using LASSO and PLS regression methods and the target-oriented cross-validation strategy.

This was a final data project for my isotopes class at Purdue. It might not be perfect because it has being a while and it was one of my first projects using R.

An R implementation of the DSMART algorithm

An R implementation of KL divergence-based sample size optimization

Soil texture classification and spatial mapping using R Studio.

Tools for calculating Soil Quality Index (SQI) using scientifically validated methods

Customisable Tools to Calculate Precipitation Event Rainfall Erosivity Index

Modular ensemble modeling framework for MIR spectral data and soil covariate prediction

The fingR package is designed to support sediment source fingerprinting studies: dataset characterisation, tracer selection from analysed properties using the three-step method, modelling of source contributions using the Bayesian Mixing Model (BMM), and evaluation of model predictions using virtual mixtures, and it supports BMM and MixSIAR models.

Provides supervised variational autoencoders (VAE), i.e. deep learning models for regression with high-dimensional predictors, such as visible, near-infrared, and shortwave infrared (VIS–NIR–SWIR) soil spectroscopy data.

Soil spectral modelling, visualization and prediction · soilVAE + OSSL v1.2 · VisNIR & MIR

An open-source R Shiny app for recording and analyzing soil conditions where plants grow. Crowdsourced data for gardeners, researchers, and land managers.