Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province
Accurate and timely estimation of cotton yield over large areas is essential for precision agriculture, facilitating the operation of commodity markets and guiding agronomic management practices. Remote sensing (RS) and crop models are effective means to predict cotton yield in the field. The satell...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.1048479/full |
| _version_ | 1797950647107059712 |
|---|---|
| author | Ping Lang Ping Lang Lifu Zhang Lifu Zhang Changping Huang Changping Huang Jiahua Chen Jiahua Chen Xiaoyan Kang Ze Zhang Qingxi Tong |
| author_facet | Ping Lang Ping Lang Lifu Zhang Lifu Zhang Changping Huang Changping Huang Jiahua Chen Jiahua Chen Xiaoyan Kang Ze Zhang Qingxi Tong |
| author_sort | Ping Lang |
| collection | DOAJ |
| description | Accurate and timely estimation of cotton yield over large areas is essential for precision agriculture, facilitating the operation of commodity markets and guiding agronomic management practices. Remote sensing (RS) and crop models are effective means to predict cotton yield in the field. The satellite vegetation indices (VIs) can describe crop yield variations over large areas but can’t take the exact environmental impact into consideration. Climate variables (CVs), the result of the influence of spatial heterogeneity in large regions, can provide environmental information for better estimation of cotton yield. In this study, the most important VIs and CVs for estimating county-level cotton yield across Xinjiang Province were screened out. We found that the VIs of canopy structure and chlorophyll contents, and the CVs of moisture, were the most significant factors for cotton growth. For yield estimation, we utilized four approaches: least absolute shrinkage and selection operator regression (LASSO), support vector regression (SVR), random forest regression (RFR) and long short-term memory (LSTM). Due to its ability to capture temporal features over the long term, LSTM performed best, with an R2 of 0.76, root mean square error (RMSE) of 150 kg/ha and relative RMSE (rRMSE) of 8.67%; moreover, an additional 10% of the variance could be explained by adding CVs to the VIs. For the within-season yield estimation using LSTM, predictions made 2 months before harvest were the most accurate (R2 = 0.65, RMSE = 220 kg/ha, rRMSE = 15.97%). Our study demonstrated the feasibility of yield estimation and early prediction at the county level over large cotton cultivation areas by integrating satellite and environmental data. |
| first_indexed | 2024-04-10T22:18:27Z |
| format | Article |
| id | doaj.art-47cfef36a8cd48a2ac6a330b3d2c50a6 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-10T22:18:27Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-47cfef36a8cd48a2ac6a330b3d2c50a62023-01-18T05:44:34ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-01-011310.3389/fpls.2022.10484791048479Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang ProvincePing Lang0Ping Lang1Lifu Zhang2Lifu Zhang3Changping Huang4Changping Huang5Jiahua Chen6Jiahua Chen7Xiaoyan Kang8Ze Zhang9Qingxi Tong10State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaXinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, College of Agriculture, Shihezi University, Shihezi, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAccurate and timely estimation of cotton yield over large areas is essential for precision agriculture, facilitating the operation of commodity markets and guiding agronomic management practices. Remote sensing (RS) and crop models are effective means to predict cotton yield in the field. The satellite vegetation indices (VIs) can describe crop yield variations over large areas but can’t take the exact environmental impact into consideration. Climate variables (CVs), the result of the influence of spatial heterogeneity in large regions, can provide environmental information for better estimation of cotton yield. In this study, the most important VIs and CVs for estimating county-level cotton yield across Xinjiang Province were screened out. We found that the VIs of canopy structure and chlorophyll contents, and the CVs of moisture, were the most significant factors for cotton growth. For yield estimation, we utilized four approaches: least absolute shrinkage and selection operator regression (LASSO), support vector regression (SVR), random forest regression (RFR) and long short-term memory (LSTM). Due to its ability to capture temporal features over the long term, LSTM performed best, with an R2 of 0.76, root mean square error (RMSE) of 150 kg/ha and relative RMSE (rRMSE) of 8.67%; moreover, an additional 10% of the variance could be explained by adding CVs to the VIs. For the within-season yield estimation using LSTM, predictions made 2 months before harvest were the most accurate (R2 = 0.65, RMSE = 220 kg/ha, rRMSE = 15.97%). Our study demonstrated the feasibility of yield estimation and early prediction at the county level over large cotton cultivation areas by integrating satellite and environmental data.https://www.frontiersin.org/articles/10.3389/fpls.2022.1048479/fullremote sensingclimate variablesGEEdeep learningyield estimationcotton |
| spellingShingle | Ping Lang Ping Lang Lifu Zhang Lifu Zhang Changping Huang Changping Huang Jiahua Chen Jiahua Chen Xiaoyan Kang Ze Zhang Qingxi Tong Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province Frontiers in Plant Science remote sensing climate variables GEE deep learning yield estimation cotton |
| title | Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province |
| title_full | Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province |
| title_fullStr | Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province |
| title_full_unstemmed | Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province |
| title_short | Integrating environmental and satellite data to estimate county-level cotton yield in Xinjiang Province |
| title_sort | integrating environmental and satellite data to estimate county level cotton yield in xinjiang province |
| topic | remote sensing climate variables GEE deep learning yield estimation cotton |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.1048479/full |
| work_keys_str_mv | AT pinglang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT pinglang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT lifuzhang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT lifuzhang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT changpinghuang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT changpinghuang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT jiahuachen integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT jiahuachen integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT xiaoyankang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT zezhang integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince AT qingxitong integratingenvironmentalandsatellitedatatoestimatecountylevelcottonyieldinxinjiangprovince |