Modeling vegetation greenness and its climate sensitivity with deep‐learning technology
Abstract Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ece3.7564 |
| _version_ | 1818609665231028224 |
|---|---|
| author | Zhiting Chen Hongyan Liu Chongyang Xu Xiuchen Wu Boyi Liang Jing Cao Deliang Chen |
| author_facet | Zhiting Chen Hongyan Liu Chongyang Xu Xiuchen Wu Boyi Liang Jing Cao Deliang Chen |
| author_sort | Zhiting Chen |
| collection | DOAJ |
| description | Abstract Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–vegetation models based on long short‐term memory (LSTM) network, which is a powerful deep‐learning algorithm for long‐time series modeling, to achieve accurate vegetation monitoring and investigate the complex relationship between climate and vegetation. We selected the normalized difference vegetation index (NDVI) that represents vegetation greenness as model outputs. The climate data (monthly temperature and precipitation) were used as inputs. We trained the networks with data from 1982 to 2003, and the data from 2004 to 2015 were used to validate the models. Error analysis and sensitivity analysis were performed to assess the model errors and investigate the sensitivity of global vegetation to climate change. Results show that models based on deep learning are very effective in simulating and predicting the vegetation greenness dynamics. For models training, the root mean square error (RMSE) is <0.01. Model validation also assure the accuracy of our models. Furthermore, sensitivity analysis of models revealed a spatial pattern of global vegetation to climate, which provides us a new way to investigate the climate sensitivity of vegetation. Our study suggests that it is a good way to integrate deep‐learning method to monitor the vegetation change under global change. In the future, we can explore more complex climatic and ecological systems with deep learning and coupling with certain physical process to better understand the nature. |
| first_indexed | 2024-12-16T15:02:09Z |
| format | Article |
| id | doaj.art-49c49564c6a74f04927b768011907e57 |
| institution | Directory Open Access Journal |
| issn | 2045-7758 |
| language | English |
| last_indexed | 2024-12-16T15:02:09Z |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecology and Evolution |
| spelling | doaj.art-49c49564c6a74f04927b768011907e572022-12-21T22:27:15ZengWileyEcology and Evolution2045-77582021-06-0111127335734510.1002/ece3.7564Modeling vegetation greenness and its climate sensitivity with deep‐learning technologyZhiting Chen0Hongyan Liu1Chongyang Xu2Xiuchen Wu3Boyi Liang4Jing Cao5Deliang Chen6College of Urban and Environmental Sciences and MOE Laboratory for Earth Surface Processes Peking University Beijing ChinaCollege of Urban and Environmental Sciences and MOE Laboratory for Earth Surface Processes Peking University Beijing ChinaCollege of Urban and Environmental Sciences and MOE Laboratory for Earth Surface Processes Peking University Beijing ChinaFaculty of Geographical Sciences Beijing Normal University Beijing ChinaCollege of Urban and Environmental Sciences and MOE Laboratory for Earth Surface Processes Peking University Beijing ChinaCollege of Urban and Environmental Sciences and MOE Laboratory for Earth Surface Processes Peking University Beijing ChinaAugust Röhss Chair Department of Earth Sciences University of Gothenburg Gothenburg SwedenAbstract Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–vegetation models based on long short‐term memory (LSTM) network, which is a powerful deep‐learning algorithm for long‐time series modeling, to achieve accurate vegetation monitoring and investigate the complex relationship between climate and vegetation. We selected the normalized difference vegetation index (NDVI) that represents vegetation greenness as model outputs. The climate data (monthly temperature and precipitation) were used as inputs. We trained the networks with data from 1982 to 2003, and the data from 2004 to 2015 were used to validate the models. Error analysis and sensitivity analysis were performed to assess the model errors and investigate the sensitivity of global vegetation to climate change. Results show that models based on deep learning are very effective in simulating and predicting the vegetation greenness dynamics. For models training, the root mean square error (RMSE) is <0.01. Model validation also assure the accuracy of our models. Furthermore, sensitivity analysis of models revealed a spatial pattern of global vegetation to climate, which provides us a new way to investigate the climate sensitivity of vegetation. Our study suggests that it is a good way to integrate deep‐learning method to monitor the vegetation change under global change. In the future, we can explore more complex climatic and ecological systems with deep learning and coupling with certain physical process to better understand the nature.https://doi.org/10.1002/ece3.7564climate changeclimate sensitivitydeep learninglong short‐term memory networkvegetation greennessvegetation–climate relationship |
| spellingShingle | Zhiting Chen Hongyan Liu Chongyang Xu Xiuchen Wu Boyi Liang Jing Cao Deliang Chen Modeling vegetation greenness and its climate sensitivity with deep‐learning technology Ecology and Evolution climate change climate sensitivity deep learning long short‐term memory network vegetation greenness vegetation–climate relationship |
| title | Modeling vegetation greenness and its climate sensitivity with deep‐learning technology |
| title_full | Modeling vegetation greenness and its climate sensitivity with deep‐learning technology |
| title_fullStr | Modeling vegetation greenness and its climate sensitivity with deep‐learning technology |
| title_full_unstemmed | Modeling vegetation greenness and its climate sensitivity with deep‐learning technology |
| title_short | Modeling vegetation greenness and its climate sensitivity with deep‐learning technology |
| title_sort | modeling vegetation greenness and its climate sensitivity with deep learning technology |
| topic | climate change climate sensitivity deep learning long short‐term memory network vegetation greenness vegetation–climate relationship |
| url | https://doi.org/10.1002/ece3.7564 |
| work_keys_str_mv | AT zhitingchen modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT hongyanliu modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT chongyangxu modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT xiuchenwu modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT boyiliang modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT jingcao modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology AT deliangchen modelingvegetationgreennessanditsclimatesensitivitywithdeeplearningtechnology |