Skip to content

Applying point cloud deep learning to estimate tree aboveground biomass.

License

Notifications You must be signed in to change notification settings

harryseely/Biomass-DL

Repository files navigation

Point Cloud Deep Learning for Tree Biomass Regression

Overview

This repository contains code used to train the Deep Neural Network (DNN) and Random Forest (RF) models from the study "Modelling Tree Biomass Using Direct and Additive Methods with Point Cloud Deep Learning in a Temperate Mixed Forest" by Seely et al. 2023. This repository should be used as a reference for information relating to the specific model architectures, training regimes, or any other technical details of the analysis.

Please note that this repository is not set up as a python package. This code is provided to serve as a useful reference for further research and applications of point cloud deep learning for tree biomass regression.

Trained Models

Trained models are provided in the "trained_models" folder for both direct and additive AGB estimation.

Visual Abstract

“Visual_abstract_for_point_cloud_deep_learning”

Citation

Seely, H., Coops, N.C., White, J.C., Montwé, D., Winiwarter, L., Ragab, A., 2023. Modelling tree biomass using direct and additive methods with point cloud deep learning in a temperate mixed forest. Science of Remote Sensing 100110. https://doi.org/10.1016/j.srs.2023.100110

Referenced Repositories

The following GitHub repos were essential in the development of the code used in this study:

About

Applying point cloud deep learning to estimate tree aboveground biomass.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages