FOREST BIOPHYSICAL PARAMETER ESTIMATION VIA MACHINE LEARNING AND NEURAL NETWORK APPROACHES

被引：1

作者：

Aksoy, Samet ^{[1
]}

Al Shwayyat, Shouq Zuhter Hasan ^{[2
]}

Topgul, Sule Nur ^{[1
]}

Sertel, Elif ^{[1
]}

Unsalan, Cem ^{[2
]}

Salo, Jari ^{[3
]}

Holmstrom, Anton ^{[4
]}

Wallerman, Jorgen ^{[5
]}

Nilsson, Mats ^{[5
]}

Fransson, Johan E. S. ^{[6
]}

机构：

[1] Istanbul Tech Univ, Istanbul, Turkiye

[2] Marmara Univ, Istanbul, Turkiye

[3] Univ Helsinki, Helsinki, Finland

[4] Katam Technol, Lund, Sweden

[5] Swedish Univ Agr Sci, Uppsala, Sweden

[6] Linnaeus Univ, Vaxjo, Sweden

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

基金：

芬兰科学院; 瑞典研究理事会;

关键词：

Forest; map; global; machine learning; Artificial Intelligence;

D O I：

10.1109/IGARSS52108.2023.10282899

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

This paper presents the first results of the ongoing development of new forest mapping methods for the Swedish national forest mapping case using Airborne Laser Scanning (ALS) data, utilizing the recent findings in machine learning (ML) and Artificial Intelligence (AI) techniques. We used Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) as ML models. In addition, Neural networks (NN) based approaches were utilized in this study. ALS derived features were used to estimate the stem volume (V), above-ground biomass (AGB), basal area (B), tree height (H), stem diameter (D), and forest stand age (A). XGBoost ML algorithm outperformed RF 1 % to 3 % in the R-2 metric. NN model performed similar to ML model, however it is superior in the estimation of V, AGB, and B parameters.

引用

页码：2661 / 2664

页数：4

共 50 条

[1] Parameter estimation via weak measurement with machine learning
Liu, Wenhuan
Huang, Jingzheng
Li, Yanjia
Li, Hongjing
Fang, Chen
Yu, Yang
Zeng, Guihua
JOURNAL OF PHYSICS B-ATOMIC MOLECULAR AND OPTICAL PHYSICS, 2019, 52 (04)
[2] Machine learning approaches for underwater sensor network parameter prediction
Uyan, Osman Gokhan
Akbas, Ayhan
Gungor, Vehbi Cagri
AD HOC NETWORKS, 2023, 144
[3] Active Learning Methods for Biophysical Parameter Estimation
Pasolli, Edoardo
Melgani, Farid
Alajlan, Naif
Bazi, Yakoub
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2012, 50 (10): : 4071 - 4084
[4] Biophysical Parameter Estimation With a Semisupervised Support Vector Machine
Camps-Valls, Gustavo
Munoz-Mari, Jordi
Gomez-Chova, Luis
Richter, Katja
Calpe-Maravilla, Javier
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2009, 6 (02) : 248 - 252
[5] Machine learning for parameter estimation
Kutz, J. Nathan
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2023, 120 (12)
[6] Inversion of a lidar waveform model for forest biophysical parameter estimation
Koetz, B
Morsdorf, F
Sun, G
Ranson, KJ
Itten, K
Allgöwer, B
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) : 49 - 53
[7] Network Parameter Setting for Reinforcement Learning Approaches Using Neural Networks
Yamada, Kazuaki
JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2011, 15 (07) : 822 - 830
[8] Network parameter setting for reinforcement learning approaches using neural networks
Yamada, Kazuaki
Ohkura, Kazuhiro
Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, 2012, 78 (792): : 2950 - 2961
[9] Machine learning approaches for biomolecular, biophysical, and biomaterials research
Rickert, Carolin A.
Lieleg, Oliver
BIOPHYSICS REVIEWS, 2022, 3 (02):
[10] Combining Multisource Data and Machine Learning Approaches for Multiscale Estimation of Forest Biomass
Hong, Yifeng
Xu, Jiaming
Wu, Chunyan
Pang, Yong
Zhang, Shougong
Chen, Dongsheng
Yang, Bo
FORESTS, 2023, 14 (11):

← 1 2 3 4 5 →