Crown Profile Modeling and Prediction Based on Ensemble Learning
Improving prediction accuracy is a prominent modeling issue in relation to forest simulations, and ensemble learning is a new effective method for improving the precision of crown profile model simulations in order to overcome the disadvantages of statistical modeling. Background: Ensemble learning...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/3/410 |
| _version_ | 1797471559010484224 |
|---|---|
| author | Yuling Chen Chen Dong Baoguo Wu |
| author_facet | Yuling Chen Chen Dong Baoguo Wu |
| author_sort | Yuling Chen |
| collection | DOAJ |
| description | Improving prediction accuracy is a prominent modeling issue in relation to forest simulations, and ensemble learning is a new effective method for improving the precision of crown profile model simulations in order to overcome the disadvantages of statistical modeling. Background: Ensemble learning (a machine learning paradigm in which multiple learners are trained to achieve better performance) has strong nonlinear problem learning ability and flexibility in terms of analyzing longitudinal data, and it remains rarely explored so far in the field of crown profile modeling forest science. In this study, we explored the application of ensemble learning to the modeling and prediction of crown profiles. Methods: We evaluated the performance of ensemble learning procedures and marginal model in modeling crown profile using the crown profile database from China fir plantations in Fujian, in southern China. Results: The ensemble learning approach for the crown profile model appeared to have better performance and higher efficiency (R<sup>2</sup> > 0.9). The crown equation model 18 showed an intermediate performance in its estimation, whereas GBDT (MAE = 0.3250, MSE = 0.2450) appeared to have the best performance and higher efficiency. Conclusions: The ensemble learning method can combine the advantages of multiple learners and has higher model accuracy, robustness and overall induction ability, and is thus an effective technique for crown profile modeling and prediction. |
| first_indexed | 2024-03-09T19:49:53Z |
| format | Article |
| id | doaj.art-14ceed378d574c7598e10423261edba1 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-09T19:49:53Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-14ceed378d574c7598e10423261edba12023-11-24T01:12:45ZengMDPI AGForests1999-49072022-03-0113341010.3390/f13030410Crown Profile Modeling and Prediction Based on Ensemble LearningYuling Chen0Chen Dong1Baoguo Wu2School of Environmental and Resources Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Sciences, Zhejiang A&F University, Hangzhou 311300, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaImproving prediction accuracy is a prominent modeling issue in relation to forest simulations, and ensemble learning is a new effective method for improving the precision of crown profile model simulations in order to overcome the disadvantages of statistical modeling. Background: Ensemble learning (a machine learning paradigm in which multiple learners are trained to achieve better performance) has strong nonlinear problem learning ability and flexibility in terms of analyzing longitudinal data, and it remains rarely explored so far in the field of crown profile modeling forest science. In this study, we explored the application of ensemble learning to the modeling and prediction of crown profiles. Methods: We evaluated the performance of ensemble learning procedures and marginal model in modeling crown profile using the crown profile database from China fir plantations in Fujian, in southern China. Results: The ensemble learning approach for the crown profile model appeared to have better performance and higher efficiency (R<sup>2</sup> > 0.9). The crown equation model 18 showed an intermediate performance in its estimation, whereas GBDT (MAE = 0.3250, MSE = 0.2450) appeared to have the best performance and higher efficiency. Conclusions: The ensemble learning method can combine the advantages of multiple learners and has higher model accuracy, robustness and overall induction ability, and is thus an effective technique for crown profile modeling and prediction.https://www.mdpi.com/1999-4907/13/3/410crown profile modelensemble learningmarginal model |
| spellingShingle | Yuling Chen Chen Dong Baoguo Wu Crown Profile Modeling and Prediction Based on Ensemble Learning Forests crown profile model ensemble learning marginal model |
| title | Crown Profile Modeling and Prediction Based on Ensemble Learning |
| title_full | Crown Profile Modeling and Prediction Based on Ensemble Learning |
| title_fullStr | Crown Profile Modeling and Prediction Based on Ensemble Learning |
| title_full_unstemmed | Crown Profile Modeling and Prediction Based on Ensemble Learning |
| title_short | Crown Profile Modeling and Prediction Based on Ensemble Learning |
| title_sort | crown profile modeling and prediction based on ensemble learning |
| topic | crown profile model ensemble learning marginal model |
| url | https://www.mdpi.com/1999-4907/13/3/410 |
| work_keys_str_mv | AT yulingchen crownprofilemodelingandpredictionbasedonensemblelearning AT chendong crownprofilemodelingandpredictionbasedonensemblelearning AT baoguowu crownprofilemodelingandpredictionbasedonensemblelearning |