Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data
It is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/14/3550 |
_version_ | 1797587611375632384 |
---|---|
author | Tianbao Huang Guanglong Ou Yong Wu Xiaoli Zhang Zihao Liu Hui Xu Xiongwei Xu Zhenghui Wang Can Xu |
author_facet | Tianbao Huang Guanglong Ou Yong Wu Xiaoli Zhang Zihao Liu Hui Xu Xiongwei Xu Zhenghui Wang Can Xu |
author_sort | Tianbao Huang |
collection | DOAJ |
description | It is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random forest (RRF), and Bayesian regularization neural network (BRNN) machine learning algorithms were constructed to estimate the AGB of four forest types based on environmental factors and the variables selected by the Boruta algorithm in Yunnan Province and using integrated Landsat 8 OLI and Sentinel 2A images. The results showed that (1) DEM was the most important variable for estimating the AGB of coniferous forests, evergreen broadleaved forests, deciduous broadleaved forests, and mixed forests; while the vegetation index was the most important variable for estimating deciduous broadleaved forests, the climatic factors had a higher variable importance for estimating coniferous and mixed forests, and texture features and vegetation index had a higher variable importance for estimating evergreen broadleaved forests. (2) In terms of specific model performance for the four forest types, RRF was the best model both in estimating the AGB of coniferous forests and mixed forests; the R<sup>2</sup> and RMSE for coniferous forests were 0.63 and 43.23 Mg ha<sup>−1</sup>, respectively, and the R<sup>2</sup> and RMSE for mixed forests were 0.56 and 47.79 Mg ha<sup>−1</sup>, respectively. BRNN performed the best in estimating the AGB of evergreen broadleaved forests; the R<sup>2</sup> was 0.53 and the RMSE was 68.16 Mg ha<sup>−1</sup>. QRF was the best in estimating the AGB of deciduous broadleaved forests, with R<sup>2</sup> of 0.43 and RMSE of 45.09 Mg ha<sup>−1</sup>. (3) RRF was the best model for the four forest types according to the mean values, with R<sup>2</sup> and RMSE of 0.503 and 52.335 Mg ha<sup>−1</sup>, respectively. In conclusion, different variables and suitable models should be considered when estimating the AGB of different forest types. This study could provide a reference for the estimation of forest AGB based on remote sensing in complex terrain areas with a high degree of forest heterogeneity. |
first_indexed | 2024-03-11T00:41:22Z |
format | Article |
id | doaj.art-c8a30021c0b448e985c1a656ea88e92b |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T00:41:22Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-c8a30021c0b448e985c1a656ea88e92b2023-11-18T21:12:22ZengMDPI AGRemote Sensing2072-42922023-07-011514355010.3390/rs15143550Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source DataTianbao Huang0Guanglong Ou1Yong Wu2Xiaoli Zhang3Zihao Liu4Hui Xu5Xiongwei Xu6Zhenghui Wang7Can Xu8Kunming General Survey of Natural Resources Center, China Geological Survey, Kunming 650111, ChinaKey Laboratory of Southwest Mountain Forest Resources Conservation and Utilization, Southwest Forestry University, Ministry of Education, Kunming 650233, ChinaKey Laboratory of Southwest Mountain Forest Resources Conservation and Utilization, Southwest Forestry University, Ministry of Education, Kunming 650233, ChinaKey Laboratory of Southwest Mountain Forest Resources Conservation and Utilization, Southwest Forestry University, Ministry of Education, Kunming 650233, ChinaKey Laboratory of Southwest Mountain Forest Resources Conservation and Utilization, Southwest Forestry University, Ministry of Education, Kunming 650233, ChinaKey Laboratory of Southwest Mountain Forest Resources Conservation and Utilization, Southwest Forestry University, Ministry of Education, Kunming 650233, ChinaKunming General Survey of Natural Resources Center, China Geological Survey, Kunming 650111, ChinaKunming General Survey of Natural Resources Center, China Geological Survey, Kunming 650111, ChinaKunming General Survey of Natural Resources Center, China Geological Survey, Kunming 650111, ChinaIt is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random forest (RRF), and Bayesian regularization neural network (BRNN) machine learning algorithms were constructed to estimate the AGB of four forest types based on environmental factors and the variables selected by the Boruta algorithm in Yunnan Province and using integrated Landsat 8 OLI and Sentinel 2A images. The results showed that (1) DEM was the most important variable for estimating the AGB of coniferous forests, evergreen broadleaved forests, deciduous broadleaved forests, and mixed forests; while the vegetation index was the most important variable for estimating deciduous broadleaved forests, the climatic factors had a higher variable importance for estimating coniferous and mixed forests, and texture features and vegetation index had a higher variable importance for estimating evergreen broadleaved forests. (2) In terms of specific model performance for the four forest types, RRF was the best model both in estimating the AGB of coniferous forests and mixed forests; the R<sup>2</sup> and RMSE for coniferous forests were 0.63 and 43.23 Mg ha<sup>−1</sup>, respectively, and the R<sup>2</sup> and RMSE for mixed forests were 0.56 and 47.79 Mg ha<sup>−1</sup>, respectively. BRNN performed the best in estimating the AGB of evergreen broadleaved forests; the R<sup>2</sup> was 0.53 and the RMSE was 68.16 Mg ha<sup>−1</sup>. QRF was the best in estimating the AGB of deciduous broadleaved forests, with R<sup>2</sup> of 0.43 and RMSE of 45.09 Mg ha<sup>−1</sup>. (3) RRF was the best model for the four forest types according to the mean values, with R<sup>2</sup> and RMSE of 0.503 and 52.335 Mg ha<sup>−1</sup>, respectively. In conclusion, different variables and suitable models should be considered when estimating the AGB of different forest types. This study could provide a reference for the estimation of forest AGB based on remote sensing in complex terrain areas with a high degree of forest heterogeneity.https://www.mdpi.com/2072-4292/15/14/3550environmental factorsforest AGB estimationforest heterogeneityforest typesmachine learning algorithmsYunnan Province of China |
spellingShingle | Tianbao Huang Guanglong Ou Yong Wu Xiaoli Zhang Zihao Liu Hui Xu Xiongwei Xu Zhenghui Wang Can Xu Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data Remote Sensing environmental factors forest AGB estimation forest heterogeneity forest types machine learning algorithms Yunnan Province of China |
title | Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data |
title_full | Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data |
title_fullStr | Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data |
title_full_unstemmed | Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data |
title_short | Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data |
title_sort | estimating the aboveground biomass of various forest types with high heterogeneity at the provincial scale based on multi source data |
topic | environmental factors forest AGB estimation forest heterogeneity forest types machine learning algorithms Yunnan Province of China |
url | https://www.mdpi.com/2072-4292/15/14/3550 |
work_keys_str_mv | AT tianbaohuang estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT guanglongou estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT yongwu estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT xiaolizhang estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT zihaoliu estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT huixu estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT xiongweixu estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT zhenghuiwang estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata AT canxu estimatingtheabovegroundbiomassofvariousforesttypeswithhighheterogeneityattheprovincialscalebasedonmultisourcedata |