Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning

Renhai Zhong, Yue Zhu, Xuhui Wang, Haifeng Li, Bin Wang, Fengqi You, Luis F. Rodríguez, Jingfeng Huang, Kuan Chong Ting, Yibin Ying, Tao Lin

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)951-959
Number of pages9
JournalFundamental Research
Issue number6
StatePublished - Nov 2023


  • Attribution analysis
  • Crop yield estimation
  • Deep Learning
  • Extreme yield loss
  • Long short-term memory
  • Multi-task learning

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Detect and attribute the extreme maize yield losses based on spatio-temporal deep learning'. Together they form a unique fingerprint.

Cite this