Improving forest above-ground biomass estimation by integrating individual machine learning models
The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies hav...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Multidisciplinary Digital Publishing Institute
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/113524/1/113524.pdf |
| _version_ | 1825940335517237248 |
|---|---|
| author | Luo, Mi Ahmad Anees, Shoaib Huang, Qiuyan Qin, Xin Qin, Zhihao Fan, Jianlong Han, Guangping Zhang, Liguo Mohd Shafri, Helmi Zulhaidi |
| author_facet | Luo, Mi Ahmad Anees, Shoaib Huang, Qiuyan Qin, Xin Qin, Zhihao Fan, Jianlong Han, Guangping Zhang, Liguo Mohd Shafri, Helmi Zulhaidi |
| author_sort | Luo, Mi |
| collection | UPM |
| description | The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies have demonstrated that a single machine learning model can produce highly accurate estimations of forest AGB in many situations, efforts are still required to explore the possible improvement in forest AGB estimation for a specific scenario under study. This study aims to investigate the performance of novel ensemble machine learning methods for forest AGB estimation and analyzes whether these methods are affected by forest types, independent variables, and spatial autocorrelation. Four well-known machine learning models (CatBoost, LightGBM, random forest (RF), and XGBoost) were compared for forest AGB estimation in the study using eight scenarios devised on the basis of two study regions, two variable types, and two validation strategies. Subsequently, a hybrid model combining the strengths of these individual models was proposed for forest AGB estimation. The findings indicated that no individual model outperforms the others in all scenarios. The RF model demonstrates superior performance in scenarios 5, 6, and 7, while the CatBoost model shows the best performance in the remaining scenarios. Moreover, the proposed hybrid model consistently has the best performance in all scenarios in spite of some uncertainties. The ensemble strategy developed in this study for the hybrid model substantially improves estimation accuracy and exhibits greater stability, effectively addressing the challenge of model selection encountered in the forest AGB forecasting process. |
| first_indexed | 2024-12-09T02:26:31Z |
| format | Article |
| id | upm.eprints-113524 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-12-09T02:26:31Z |
| publishDate | 2024 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | upm.eprints-1135242024-11-26T03:19:29Z http://psasir.upm.edu.my/id/eprint/113524/ Improving forest above-ground biomass estimation by integrating individual machine learning models Luo, Mi Ahmad Anees, Shoaib Huang, Qiuyan Qin, Xin Qin, Zhihao Fan, Jianlong Han, Guangping Zhang, Liguo Mohd Shafri, Helmi Zulhaidi The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies have demonstrated that a single machine learning model can produce highly accurate estimations of forest AGB in many situations, efforts are still required to explore the possible improvement in forest AGB estimation for a specific scenario under study. This study aims to investigate the performance of novel ensemble machine learning methods for forest AGB estimation and analyzes whether these methods are affected by forest types, independent variables, and spatial autocorrelation. Four well-known machine learning models (CatBoost, LightGBM, random forest (RF), and XGBoost) were compared for forest AGB estimation in the study using eight scenarios devised on the basis of two study regions, two variable types, and two validation strategies. Subsequently, a hybrid model combining the strengths of these individual models was proposed for forest AGB estimation. The findings indicated that no individual model outperforms the others in all scenarios. The RF model demonstrates superior performance in scenarios 5, 6, and 7, while the CatBoost model shows the best performance in the remaining scenarios. Moreover, the proposed hybrid model consistently has the best performance in all scenarios in spite of some uncertainties. The ensemble strategy developed in this study for the hybrid model substantially improves estimation accuracy and exhibits greater stability, effectively addressing the challenge of model selection encountered in the forest AGB forecasting process. Multidisciplinary Digital Publishing Institute 2024 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/113524/1/113524.pdf Luo, Mi and Ahmad Anees, Shoaib and Huang, Qiuyan and Qin, Xin and Qin, Zhihao and Fan, Jianlong and Han, Guangping and Zhang, Liguo and Mohd Shafri, Helmi Zulhaidi (2024) Improving forest above-ground biomass estimation by integrating individual machine learning models. Forests, 15 (6). art. no. 975. pp. 1-23. ISSN 1999-4907; eISSN: 1999-4907 https://www.mdpi.com/1999-4907/15/6/975 10.3390/f15060975 |
| spellingShingle | Luo, Mi Ahmad Anees, Shoaib Huang, Qiuyan Qin, Xin Qin, Zhihao Fan, Jianlong Han, Guangping Zhang, Liguo Mohd Shafri, Helmi Zulhaidi Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title | Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title_full | Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title_fullStr | Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title_full_unstemmed | Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title_short | Improving forest above-ground biomass estimation by integrating individual machine learning models |
| title_sort | improving forest above ground biomass estimation by integrating individual machine learning models |
| url | http://psasir.upm.edu.my/id/eprint/113524/1/113524.pdf |
| work_keys_str_mv | AT luomi improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT ahmadaneesshoaib improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT huangqiuyan improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT qinxin improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT qinzhihao improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT fanjianlong improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT hanguangping improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT zhangliguo improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels AT mohdshafrihelmizulhaidi improvingforestabovegroundbiomassestimationbyintegratingindividualmachinelearningmodels |