A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data

Accurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yiel...

Full description

Saved in:
Bibliographic Details
Main Authors: Dailiang Peng, Enhui Cheng, Xuxiang Feng, Jinkang Hu, Zihang Lou, Hongchi Zhang, Bin Zhao, Yulong Lv, Hao Peng, Bing Zhang
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/19/3613
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850284502587277312
author Dailiang Peng
Enhui Cheng
Xuxiang Feng
Jinkang Hu
Zihang Lou
Hongchi Zhang
Bin Zhao
Yulong Lv
Hao Peng
Bing Zhang
author_facet Dailiang Peng
Enhui Cheng
Xuxiang Feng
Jinkang Hu
Zihang Lou
Hongchi Zhang
Bin Zhao
Yulong Lv
Hao Peng
Bing Zhang
author_sort Dailiang Peng
collection DOAJ
description Accurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yield prediction in China’s main wheat-producing areas. We tested a combination of short-term WF data from the China Meteorological Administration to predict in-season yield at different forecast lengths. The results showed that explicitly incorporating WF data can improve the accuracy in crop yield predictions [Root Mean Square Error (RMSE) = 0.517 t/ha] compared to using only remote sensing data (RMSE = 0.624 t/ha). After comparing a series of WF data with different time series lengths, we found that adding 25 days of WF data can achieve the highest yield prediction accuracy. Specifically, the highest accuracy (RMSE = 0.496 t/ha) is achieved when predictions are made on Day of The Year (DOY) 215 (40 days before harvest). Our study established a deep-learning model which can be used for early yield prediction at the county level, and we have proved that weather forecast data can also be applied in data-driven deep-learning yield prediction tasks.
format Article
id doaj-art-d6413b4bc336432fa6d59fa9156250a3
institution OA Journals
issn 2072-4292
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d6413b4bc336432fa6d59fa9156250a32025-08-20T01:47:33ZengMDPI AGRemote Sensing2072-42922024-09-011619361310.3390/rs16193613A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing DataDailiang Peng0Enhui Cheng1Xuxiang Feng2Jinkang Hu3Zihang Lou4Hongchi Zhang5Bin Zhao6Yulong Lv7Hao Peng8Bing Zhang9Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaZhejiang Key Laboratory of Agricultural Remote Sensing and Information Technology, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaSchool of Information Science and Engineering, Shandong Agricultural University, Tai’an 271002, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCollege of Resource and Environment, University of Chinese Academy of Sciences, Beijing 100049, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAccurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yield prediction in China’s main wheat-producing areas. We tested a combination of short-term WF data from the China Meteorological Administration to predict in-season yield at different forecast lengths. The results showed that explicitly incorporating WF data can improve the accuracy in crop yield predictions [Root Mean Square Error (RMSE) = 0.517 t/ha] compared to using only remote sensing data (RMSE = 0.624 t/ha). After comparing a series of WF data with different time series lengths, we found that adding 25 days of WF data can achieve the highest yield prediction accuracy. Specifically, the highest accuracy (RMSE = 0.496 t/ha) is achieved when predictions are made on Day of The Year (DOY) 215 (40 days before harvest). Our study established a deep-learning model which can be used for early yield prediction at the county level, and we have proved that weather forecast data can also be applied in data-driven deep-learning yield prediction tasks.https://www.mdpi.com/2072-4292/16/19/3613weather forecast datawheat yield predictiondeep-learningtime series
spellingShingle Dailiang Peng
Enhui Cheng
Xuxiang Feng
Jinkang Hu
Zihang Lou
Hongchi Zhang
Bin Zhao
Yulong Lv
Hao Peng
Bing Zhang
A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
Remote Sensing
weather forecast data
wheat yield prediction
deep-learning
time series
title A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
title_full A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
title_fullStr A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
title_full_unstemmed A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
title_short A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data
title_sort deep learning network for wheat yield prediction combining weather forecasts and remote sensing data
topic weather forecast data
wheat yield prediction
deep-learning
time series
url https://www.mdpi.com/2072-4292/16/19/3613
work_keys_str_mv AT dailiangpeng adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT enhuicheng adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT xuxiangfeng adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT jinkanghu adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT zihanglou adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT hongchizhang adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT binzhao adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT yulonglv adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT haopeng adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT bingzhang adeeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT dailiangpeng deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT enhuicheng deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT xuxiangfeng deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT jinkanghu deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT zihanglou deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT hongchizhang deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT binzhao deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT yulonglv deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT haopeng deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata
AT bingzhang deeplearningnetworkforwheatyieldpredictioncombiningweatherforecastsandremotesensingdata