TY - GEN

T1 - Deep learning based 3D point cloud regression for estimating forest biomass

AU - Oehmcke, Stefan

AU - Li, Lei

AU - Revenga, Jaime C.

AU - Nord-Larsen, Thomas

AU - Trepekli, Katerina

AU - Gieseke, Fabian

AU - Igel, Christian

N1 - Publisher Copyright: © 2022 Owner/Author.

PY - 2022/11/1

Y1 - 2022/11/1

N2 - Knowledge of forest biomass stocks and their development is important for implementing effective climate change mitigation measures. Remote sensing using airborne LiDAR can be used to measure vegetation structure at large scale. We present deep learning systems for predicting wood volume, above-ground biomass (AGB), and subsequently above-ground carbon stocks directly from airborne LiDAR point clouds. Specifically, we devise different neural network architectures for point cloud regression and evaluate them on remote sensing data of areas for which AGB estimates have been obtained from field measurements in a national forest inventory. Our adaptation of Minkowski convolutional neural networks for regression gave the best results. The deep neural networks produced significantly more accurate wood volume, AGB, and carbon estimates compared to state-of-the-art approaches operating on basic statistics of the point clouds. In contrast to other methods, no digital terrain model is required. We expect this finding to have a strong impact on LiDAR-based analyses of terrestrial ecosystem dynamics.

AB - Knowledge of forest biomass stocks and their development is important for implementing effective climate change mitigation measures. Remote sensing using airborne LiDAR can be used to measure vegetation structure at large scale. We present deep learning systems for predicting wood volume, above-ground biomass (AGB), and subsequently above-ground carbon stocks directly from airborne LiDAR point clouds. Specifically, we devise different neural network architectures for point cloud regression and evaluate them on remote sensing data of areas for which AGB estimates have been obtained from field measurements in a national forest inventory. Our adaptation of Minkowski convolutional neural networks for regression gave the best results. The deep neural networks produced significantly more accurate wood volume, AGB, and carbon estimates compared to state-of-the-art approaches operating on basic statistics of the point clouds. In contrast to other methods, no digital terrain model is required. We expect this finding to have a strong impact on LiDAR-based analyses of terrestrial ecosystem dynamics.

KW - biomass

KW - climate change

KW - datasets

KW - LiDAR

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85143591559&partnerID=8YFLogxK

U2 - 10.1145/3557915.3561471

DO - 10.1145/3557915.3561471

M3 - Article in proceedings

AN - SCOPUS:85143591559

SP - 1

EP - 4

BT - 30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2022

A2 - Renz, Matthias

A2 - Sarwat, Mohamed

A2 - Nascimento, Mario A.

A2 - Shekhar, Shashi

A2 - Xie, Xing

PB - Association for Computing Machinery, Inc.

T2 - 30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2022

Y2 - 1 November 2022 through 4 November 2022

ER -