Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery
The accurate estimation of aboveground biomass (AGB) in rubber plantations is essential for predicting rubber production and assessing carbon storage. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) can obtain high spatiotemporal resolution imagery of rubber plantations, offering si...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/1/32 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588647096909824 |
|---|---|
| author | Hongjian Tan Weili Kou Weiheng Xu Leiguang Wang Huan Wang Ning Lu |
| author_facet | Hongjian Tan Weili Kou Weiheng Xu Leiguang Wang Huan Wang Ning Lu |
| author_sort | Hongjian Tan |
| collection | DOAJ |
| description | The accurate estimation of aboveground biomass (AGB) in rubber plantations is essential for predicting rubber production and assessing carbon storage. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) can obtain high spatiotemporal resolution imagery of rubber plantations, offering significant advantages in capturing fine structural details and heterogeneity. However, most previous studies primarily focused on developing biomass estimation models for rubber using machine learning (ML) algorithms in conjunction with feature selection methods based on UAV-acquired multispectral imagery. The reliance on feature selection methods limits the model’s generalizability, robustness, and predictive accuracy. In contrast, deep learning (DL) exhibits considerable promise in extracting features from high-resolution UAV-based multispectral imagery without the need for manual selection. Nonetheless, it remains unclear whether DL can surpass traditional ML methods in improving the AGB estimation accuracy in rubber plantations. To address this, our study evaluated the performance of three ML algorithms (random forest regression, RFR; XGBoost regression, XGBR; categorical boosting regression, CatBoost) combined with feature selection techniques and a deep convolutional neural network (DCNN) using multispectral imagery obtained from UAV for the AGB estimation of rubber plantations. The results indicate that the RFR combined with a principal component analysis (PCA) for feature selection yielded the best performance (<i>R</i><sup>2</sup> = 0.81, <i>RMSE</i> = 11.63 t/ha, <i>MAE</i> = 9.27 t/ha) between the three ML algorithms. Meanwhile, the DCNN model derived from the G, R, and NIR spectral bands achieved the highest estimation accuracy (<i>R</i><sup>2</sup> = 0.89, <i>RMSE</i> = 6.44 t/ha, <i>MAE</i> = 5.72 t/ha), where it outperformed the other ML methods. Our study highlights the great potential of combining UAV-based multispectral imagery with DL techniques to improve AGB estimation in rubber plantations, offering a new perspective for estimating the physiological and biochemical growth parameters of forests. |
| format | Article |
| id | doaj-art-b88522b97b2e4c5c96909817ca4c10aa |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-b88522b97b2e4c5c96909817ca4c10aa2025-01-24T13:29:42ZengMDPI AGDrones2504-446X2025-01-01913210.3390/drones9010032Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral ImageryHongjian Tan0Weili Kou1Weiheng Xu2Leiguang Wang3Huan Wang4Ning Lu5College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650223, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650223, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650223, ChinaCollege of Landscape Architecture and Horticulture, Southwest Forestry University, Kunming 650223, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650223, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650223, ChinaThe accurate estimation of aboveground biomass (AGB) in rubber plantations is essential for predicting rubber production and assessing carbon storage. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) can obtain high spatiotemporal resolution imagery of rubber plantations, offering significant advantages in capturing fine structural details and heterogeneity. However, most previous studies primarily focused on developing biomass estimation models for rubber using machine learning (ML) algorithms in conjunction with feature selection methods based on UAV-acquired multispectral imagery. The reliance on feature selection methods limits the model’s generalizability, robustness, and predictive accuracy. In contrast, deep learning (DL) exhibits considerable promise in extracting features from high-resolution UAV-based multispectral imagery without the need for manual selection. Nonetheless, it remains unclear whether DL can surpass traditional ML methods in improving the AGB estimation accuracy in rubber plantations. To address this, our study evaluated the performance of three ML algorithms (random forest regression, RFR; XGBoost regression, XGBR; categorical boosting regression, CatBoost) combined with feature selection techniques and a deep convolutional neural network (DCNN) using multispectral imagery obtained from UAV for the AGB estimation of rubber plantations. The results indicate that the RFR combined with a principal component analysis (PCA) for feature selection yielded the best performance (<i>R</i><sup>2</sup> = 0.81, <i>RMSE</i> = 11.63 t/ha, <i>MAE</i> = 9.27 t/ha) between the three ML algorithms. Meanwhile, the DCNN model derived from the G, R, and NIR spectral bands achieved the highest estimation accuracy (<i>R</i><sup>2</sup> = 0.89, <i>RMSE</i> = 6.44 t/ha, <i>MAE</i> = 5.72 t/ha), where it outperformed the other ML methods. Our study highlights the great potential of combining UAV-based multispectral imagery with DL techniques to improve AGB estimation in rubber plantations, offering a new perspective for estimating the physiological and biochemical growth parameters of forests.https://www.mdpi.com/2504-446X/9/1/32aboveground biomassmultispectral imagesfeature selectionmachine learningdeep convolutional neural network |
| spellingShingle | Hongjian Tan Weili Kou Weiheng Xu Leiguang Wang Huan Wang Ning Lu Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery Drones aboveground biomass multispectral images feature selection machine learning deep convolutional neural network |
| title | Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery |
| title_full | Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery |
| title_fullStr | Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery |
| title_full_unstemmed | Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery |
| title_short | Improved Estimation of Aboveground Biomass in Rubber Plantations Using Deep Learning on UAV Multispectral Imagery |
| title_sort | improved estimation of aboveground biomass in rubber plantations using deep learning on uav multispectral imagery |
| topic | aboveground biomass multispectral images feature selection machine learning deep convolutional neural network |
| url | https://www.mdpi.com/2504-446X/9/1/32 |
| work_keys_str_mv | AT hongjiantan improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery AT weilikou improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery AT weihengxu improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery AT leiguangwang improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery AT huanwang improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery AT ninglu improvedestimationofabovegroundbiomassinrubberplantationsusingdeeplearningonuavmultispectralimagery |