Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China
Rubber (<i>Hevea brasiliensis Muell.</i>) plantations are among the most critical agricultural ecosystems in tropical regions, playing a vital role in regional carbon balance. Accurate large-scale biomass estimation for these plantations remains a challenging task due to the severe signa...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/13/3447 |
| _version_ | 1797590882388541440 |
|---|---|
| author | Xin Li Xincheng Wang Yuanfeng Gao Jiuhao Wu Renxi Cheng Donghao Ren Qing Bao Ting Yun Zhixiang Wu Guishui Xie Bangqian Chen |
| author_facet | Xin Li Xincheng Wang Yuanfeng Gao Jiuhao Wu Renxi Cheng Donghao Ren Qing Bao Ting Yun Zhixiang Wu Guishui Xie Bangqian Chen |
| author_sort | Xin Li |
| collection | DOAJ |
| description | Rubber (<i>Hevea brasiliensis Muell.</i>) plantations are among the most critical agricultural ecosystems in tropical regions, playing a vital role in regional carbon balance. Accurate large-scale biomass estimation for these plantations remains a challenging task due to the severe signal saturation problem. Recent advances in remote sensing big data, cloud platforms, and machine learning have facilitated the precise acquisition of key physiological variables, such as stand age (A) and canopy height (H), which are critical parameters for biomass estimation but have been underutilized in prior studies. Using Hainan Island—the second-largest rubber planting base in China—as a case study, we integrated extensive ground surveys, maps of stand age and canopy height, remote sensing indicators (RSIs), and geographical and climate indicators (ECIs) to ascertain the optimal method for estimating rubber plantation biomass. We compared different inputs and estimation approaches (direct and indirect) using the random forest algorithm and analyzed the spatiotemporal characteristics of rubber plantation biomass on Hainan Island. The results indicated that the traditional model (RSIs + ECIs) had low accuracy and significant estimation bias (R<sup>2</sup> = 0.24, RMSE = 38.36 mg/ha). The addition of either stand age or canopy height considerably enhance model accuracy (R<sup>2</sup> = 0.77, RMSE ≈ 21.12 mg/ha). Moreover, incorporating the DBH obtained through indirect inversion yielded even greater predictive accuracy (R<sup>2</sup> = 0.97, RMSE = 7.73 mg/ha), outperforming estimates derived from an allometric equation model input with the DBH (R<sup>2</sup> = 0.67, RMSE = 25.43 mg/ha). However, augmenting the model with stand age, canopy height, or their combination based on RSIs, ECIs, and DBH only marginally improved the accuracy. Consequently, it is not recommended in scenarios with limited data and computing resources. Employing the optimal model, we generated biomass maps of rubber plantations on Hainan Island for 2016 and 2020, revealing that the spatiotemporal distribution pattern of the biomass is closely associated with the establishment year of the rubber plantations. While average biomass in a few areas has undergone slight decreases, total biomass has exhibited significant growth, reaching 5.46 × 10<sup>7</sup> mg by the end of 2020, underscoring its considerable value as a carbon sink. |
| first_indexed | 2024-03-11T01:29:46Z |
| format | Article |
| id | doaj.art-dde37652b0f4465aa80e9c6eaf3e08ce |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:29:46Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-dde37652b0f4465aa80e9c6eaf3e08ce2023-11-18T17:26:26ZengMDPI AGRemote Sensing2072-42922023-07-011513344710.3390/rs15133447Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, ChinaXin Li0Xincheng Wang1Yuanfeng Gao2Jiuhao Wu3Renxi Cheng4Donghao Ren5Qing Bao6Ting Yun7Zhixiang Wu8Guishui Xie9Bangqian Chen10Co-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaCo-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037, ChinaRubber Research Institute (RRI), Chinese Academy of Tropical Agricultural Sciences (CATAS), Hainan Danzhou Agro-Ecosystem National Observation and Research Station, State Key Laboratory Incubation Base for Cultivation & Physiology of Tropical Crops, Haikou 571101, ChinaRubber Research Institute (RRI), Chinese Academy of Tropical Agricultural Sciences (CATAS), Hainan Danzhou Agro-Ecosystem National Observation and Research Station, State Key Laboratory Incubation Base for Cultivation & Physiology of Tropical Crops, Haikou 571101, ChinaRubber Research Institute (RRI), Chinese Academy of Tropical Agricultural Sciences (CATAS), Hainan Danzhou Agro-Ecosystem National Observation and Research Station, State Key Laboratory Incubation Base for Cultivation & Physiology of Tropical Crops, Haikou 571101, ChinaRubber (<i>Hevea brasiliensis Muell.</i>) plantations are among the most critical agricultural ecosystems in tropical regions, playing a vital role in regional carbon balance. Accurate large-scale biomass estimation for these plantations remains a challenging task due to the severe signal saturation problem. Recent advances in remote sensing big data, cloud platforms, and machine learning have facilitated the precise acquisition of key physiological variables, such as stand age (A) and canopy height (H), which are critical parameters for biomass estimation but have been underutilized in prior studies. Using Hainan Island—the second-largest rubber planting base in China—as a case study, we integrated extensive ground surveys, maps of stand age and canopy height, remote sensing indicators (RSIs), and geographical and climate indicators (ECIs) to ascertain the optimal method for estimating rubber plantation biomass. We compared different inputs and estimation approaches (direct and indirect) using the random forest algorithm and analyzed the spatiotemporal characteristics of rubber plantation biomass on Hainan Island. The results indicated that the traditional model (RSIs + ECIs) had low accuracy and significant estimation bias (R<sup>2</sup> = 0.24, RMSE = 38.36 mg/ha). The addition of either stand age or canopy height considerably enhance model accuracy (R<sup>2</sup> = 0.77, RMSE ≈ 21.12 mg/ha). Moreover, incorporating the DBH obtained through indirect inversion yielded even greater predictive accuracy (R<sup>2</sup> = 0.97, RMSE = 7.73 mg/ha), outperforming estimates derived from an allometric equation model input with the DBH (R<sup>2</sup> = 0.67, RMSE = 25.43 mg/ha). However, augmenting the model with stand age, canopy height, or their combination based on RSIs, ECIs, and DBH only marginally improved the accuracy. Consequently, it is not recommended in scenarios with limited data and computing resources. Employing the optimal model, we generated biomass maps of rubber plantations on Hainan Island for 2016 and 2020, revealing that the spatiotemporal distribution pattern of the biomass is closely associated with the establishment year of the rubber plantations. While average biomass in a few areas has undergone slight decreases, total biomass has exhibited significant growth, reaching 5.46 × 10<sup>7</sup> mg by the end of 2020, underscoring its considerable value as a carbon sink.https://www.mdpi.com/2072-4292/15/13/3447biomassrubber plantationsDBHmodel comparison |
| spellingShingle | Xin Li Xincheng Wang Yuanfeng Gao Jiuhao Wu Renxi Cheng Donghao Ren Qing Bao Ting Yun Zhixiang Wu Guishui Xie Bangqian Chen Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China Remote Sensing biomass rubber plantations DBH model comparison |
| title | Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China |
| title_full | Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China |
| title_fullStr | Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China |
| title_full_unstemmed | Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China |
| title_short | Comparison of Different Important Predictors and Models for Estimating Large-Scale Biomass of Rubber Plantations in Hainan Island, China |
| title_sort | comparison of different important predictors and models for estimating large scale biomass of rubber plantations in hainan island china |
| topic | biomass rubber plantations DBH model comparison |
| url | https://www.mdpi.com/2072-4292/15/13/3447 |
| work_keys_str_mv | AT xinli comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT xinchengwang comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT yuanfenggao comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT jiuhaowu comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT renxicheng comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT donghaoren comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT qingbao comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT tingyun comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT zhixiangwu comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT guishuixie comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina AT bangqianchen comparisonofdifferentimportantpredictorsandmodelsforestimatinglargescalebiomassofrubberplantationsinhainanislandchina |