Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning
Providing accurate crop yield estimations at large spatial scales and understanding yield losses under extreme climate stress is an urgent challenge for sustaining global food security. While the data-driven deep learning approach has shown great capacity in predicting yield patterns, its capacity t...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2023-11-01
|
| Series: | Fundamental Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667325822002126 |
| _version_ | 1797454287182233600 |
|---|---|
| author | Renhai Zhong Yue Zhu Xuhui Wang Haifeng Li Bin Wang Fengqi You Luis F. Rodríguez Jingfeng Huang K.C. Ting Yibin Ying Tao Lin |
| author_facet | Renhai Zhong Yue Zhu Xuhui Wang Haifeng Li Bin Wang Fengqi You Luis F. Rodríguez Jingfeng Huang K.C. Ting Yibin Ying Tao Lin |
| author_sort | Renhai Zhong |
| collection | DOAJ |
| description | Providing accurate crop yield estimations at large spatial scales and understanding yield losses under extreme climate stress is an urgent challenge for sustaining global food security. While the data-driven deep learning approach has shown great capacity in predicting yield patterns, its capacity to detect and attribute the impacts of climatic extremes on yields remains unknown. In this study, we developed a deep neural network based multi-task learning framework to estimate variations of maize yield at the county level over the US Corn Belt from 2006 to 2018, with a special focus on the extreme yield loss in 2012. We found that our deep learning model hindcasted the yield variations with good accuracy for 2006-2018 (R2 = 0.81) and well reproduced the extreme yield anomalies in 2012 (R2 = 0.79). Further attribution analysis indicated that extreme heat stress was the major cause for yield loss, contributing to 72.5% of the yield loss, followed by anomalies of vapor pressure deficit (17.6%) and precipitation (10.8%). Our deep learning model was also able to estimate the accumulated impact of climatic factors on maize yield and identify that the silking phase was the most critical stage shaping the yield response to extreme climate stress in 2012. Our results provide a new framework of spatio-temporal deep learning to assess and attribute the crop yield response to climate variations in the data rich era. |
| first_indexed | 2024-03-09T15:35:07Z |
| format | Article |
| id | doaj.art-78c26525eaf24a07ab60f647fb7ca3b8 |
| institution | Directory Open Access Journal |
| issn | 2667-3258 |
| language | English |
| last_indexed | 2024-03-09T15:35:07Z |
| publishDate | 2023-11-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Fundamental Research |
| spelling | doaj.art-78c26525eaf24a07ab60f647fb7ca3b82023-11-26T05:14:28ZengKeAi Communications Co. Ltd.Fundamental Research2667-32582023-11-0136951959Detect and attribute the extreme maize yield losses based on spatio-temporal deep learningRenhai Zhong0Yue Zhu1Xuhui Wang2Haifeng Li3Bin Wang4Fengqi You5Luis F. Rodríguez6Jingfeng Huang7K.C. Ting8Yibin Ying9Tao Lin10College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, Zhejiang 310058, China; International Campus, Zhejiang University, Haining, Zhejiang 314400, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, Zhejiang 310058, ChinaSino-French Institute for Earth System Science, College of Urban and Environmental Sciences, Peking University, Beijing 100871, ChinaSchool of Geosciences and Info-Physics, Central South University, South Lushan Road, Changsha 410000, ChinaNSW Department of Primary Industries, Wagga Wagga Agricultural Institute, Pine Gully Road Wagga Wagga, NSW 2650, AustraliaRobert Frederick Smith School of Chemical and Biomolecular Engineering, Cornell University, Ithaca, NY 14853, USADepartment of Agricultural and Biological Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USAInstitute of Applied Remote Sensing and Information Technology, Zhejiang University, Hangzhou, Zhejiang 310058, ChinaInternational Campus, Zhejiang University, Haining, Zhejiang 314400, China; Department of Agricultural and Biological Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USACollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, Zhejiang 310058, China; Key Laboratory of On Site Processing Equipment for Agricultural Products, Ministry of Agriculture and Rural Affairs, Hangzhou, Zhejiang 310058, China; Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province, Hangzhou, Zhejiang 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, Zhejiang 310058, China; Key Laboratory of On Site Processing Equipment for Agricultural Products, Ministry of Agriculture and Rural Affairs, Hangzhou, Zhejiang 310058, China; Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province, Hangzhou, Zhejiang 310058, China; Corresponding author.Providing accurate crop yield estimations at large spatial scales and understanding yield losses under extreme climate stress is an urgent challenge for sustaining global food security. While the data-driven deep learning approach has shown great capacity in predicting yield patterns, its capacity to detect and attribute the impacts of climatic extremes on yields remains unknown. In this study, we developed a deep neural network based multi-task learning framework to estimate variations of maize yield at the county level over the US Corn Belt from 2006 to 2018, with a special focus on the extreme yield loss in 2012. We found that our deep learning model hindcasted the yield variations with good accuracy for 2006-2018 (R2 = 0.81) and well reproduced the extreme yield anomalies in 2012 (R2 = 0.79). Further attribution analysis indicated that extreme heat stress was the major cause for yield loss, contributing to 72.5% of the yield loss, followed by anomalies of vapor pressure deficit (17.6%) and precipitation (10.8%). Our deep learning model was also able to estimate the accumulated impact of climatic factors on maize yield and identify that the silking phase was the most critical stage shaping the yield response to extreme climate stress in 2012. Our results provide a new framework of spatio-temporal deep learning to assess and attribute the crop yield response to climate variations in the data rich era.http://www.sciencedirect.com/science/article/pii/S2667325822002126Crop yield estimationDeep LearningLong short-term memoryMulti-task learningExtreme yield lossAttribution analysis |
| spellingShingle | Renhai Zhong Yue Zhu Xuhui Wang Haifeng Li Bin Wang Fengqi You Luis F. Rodríguez Jingfeng Huang K.C. Ting Yibin Ying Tao Lin Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning Fundamental Research Crop yield estimation Deep Learning Long short-term memory Multi-task learning Extreme yield loss Attribution analysis |
| title | Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning |
| title_full | Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning |
| title_fullStr | Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning |
| title_full_unstemmed | Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning |
| title_short | Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning |
| title_sort | detect and attribute the extreme maize yield losses based on spatio temporal deep learning |
| topic | Crop yield estimation Deep Learning Long short-term memory Multi-task learning Extreme yield loss Attribution analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2667325822002126 |
| work_keys_str_mv | AT renhaizhong detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT yuezhu detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT xuhuiwang detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT haifengli detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT binwang detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT fengqiyou detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT luisfrodriguez detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT jingfenghuang detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT kcting detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT yibinying detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning AT taolin detectandattributetheextrememaizeyieldlossesbasedonspatiotemporaldeeplearning |