This page contains code for the article "Remote sensing-based biomass estimation of dry deciduous tropical forest using machine learning and ensemble analysis" published in Journal of Environmental Management (https://doi.org/10.1016/j.jenvman.2022.114639).
Machine learning and ensemble analysis estimate for predicting above-ground biomass (AGB)
The code contains following:
- Feature selection algorithm (Boruta and VIF)
- Modelling techniques (GAMM, kNN, SVM, ANN and RF)
- Spatial autocorrelation
- Sensitivity analysis
- Data analysis (includes analysing figures from manuscript and supplementary materials)
Code 1-4 are coded in 'R', whereas 5 is coded in 'python'. Most of the spatial analysis/mapping that are not included above were done using either ArcGIS or ERDAS Imagine.
Coded by:
Chandrakant Singh
Stockholm Resilience Centre, Stockholm University
Contact: chandrakant.singh@su.se