Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions

This study investigated how genotype, environment, and management (G×E×M) interactions influence yield and highlight the importance of accurate, early yield predictions for effective farm management and enhancing food security. We developed a yield prediction model capable of determining field-level...

Full description

Saved in:
Bibliographic Details
Main Authors: Saiara Samira Sajid, Zahra Khalilzadeh, Lizhi Wang, Guiping Hu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1537990/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849420723538362368
author Saiara Samira Sajid
Zahra Khalilzadeh
Lizhi Wang
Guiping Hu
author_facet Saiara Samira Sajid
Zahra Khalilzadeh
Lizhi Wang
Guiping Hu
author_sort Saiara Samira Sajid
collection DOAJ
description This study investigated how genotype, environment, and management (G×E×M) interactions influence yield and highlight the importance of accurate, early yield predictions for effective farm management and enhancing food security. We developed a yield prediction model capable of determining field-level outputs based on comprehensive data inputs, including genotype, spatial, temporal, environmental, and management factors. Among tested models—LASSO, Random Forest, XGBoost, single-modal CNN-DNN, and multimodal CNN-DNN—the multimodal CNN-DNN ensembled with XGBoost demonstrated superior performance. Applied to the G2F dataset covering 21 states from 2014 to 2021 across various treatments (i.e., standard, drought, irrigation, disease trials), the model excelled particularly in stable historical yield settings (RMSE 2.36 Mg/ha for standard treatment) with an overall RMSE of 2.45 Mg/ha. Additionally, we introduced an empirical tool for identifying high-yield hybrids suitable for standard and challenging conditions. Exploratory analysis confirmed that crop yields vary greatly by hybrid and location interaction and that late planting generally yields less than standard timing. Customized management strategies based on specific local and hybrid conditions are crucial for optimal yield outcomes.
format Article
id doaj-art-6da1bb3a139143598d93bf65f48d70e4
institution Kabale University
issn 1664-462X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-6da1bb3a139143598d93bf65f48d70e42025-08-20T03:31:40ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-07-011610.3389/fpls.2025.15379901537990Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactionsSaiara Samira Sajid0Zahra Khalilzadeh1Lizhi Wang2Guiping Hu3Iowa State University, Industrial Manufacturing & Systems Engineering, Ames, IA, United StatesIowa State University, Industrial Manufacturing & Systems Engineering, Ames, IA, United StatesOklahoma State University, Industrial Engineering & Management, Stillwater, OK, United StatesOklahoma State University, Industrial Engineering & Management, Stillwater, OK, United StatesThis study investigated how genotype, environment, and management (G×E×M) interactions influence yield and highlight the importance of accurate, early yield predictions for effective farm management and enhancing food security. We developed a yield prediction model capable of determining field-level outputs based on comprehensive data inputs, including genotype, spatial, temporal, environmental, and management factors. Among tested models—LASSO, Random Forest, XGBoost, single-modal CNN-DNN, and multimodal CNN-DNN—the multimodal CNN-DNN ensembled with XGBoost demonstrated superior performance. Applied to the G2F dataset covering 21 states from 2014 to 2021 across various treatments (i.e., standard, drought, irrigation, disease trials), the model excelled particularly in stable historical yield settings (RMSE 2.36 Mg/ha for standard treatment) with an overall RMSE of 2.45 Mg/ha. Additionally, we introduced an empirical tool for identifying high-yield hybrids suitable for standard and challenging conditions. Exploratory analysis confirmed that crop yields vary greatly by hybrid and location interaction and that late planting generally yields less than standard timing. Customized management strategies based on specific local and hybrid conditions are crucial for optimal yield outcomes.https://www.frontiersin.org/articles/10.3389/fpls.2025.1537990/fullgenotypeplanting datehigh-yield hybrid classificationprecision farmingmultimodal CNN-DNN
spellingShingle Saiara Samira Sajid
Zahra Khalilzadeh
Lizhi Wang
Guiping Hu
Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
Frontiers in Plant Science
genotype
planting date
high-yield hybrid classification
precision farming
multimodal CNN-DNN
title Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
title_full Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
title_fullStr Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
title_full_unstemmed Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
title_short Analyses of crop yield dynamics and the development of a multimodal neural network prediction model with G×E×M interactions
title_sort analyses of crop yield dynamics and the development of a multimodal neural network prediction model with g e m interactions
topic genotype
planting date
high-yield hybrid classification
precision farming
multimodal CNN-DNN
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1537990/full
work_keys_str_mv AT saiarasamirasajid analysesofcropyielddynamicsandthedevelopmentofamultimodalneuralnetworkpredictionmodelwithgeminteractions
AT zahrakhalilzadeh analysesofcropyielddynamicsandthedevelopmentofamultimodalneuralnetworkpredictionmodelwithgeminteractions
AT lizhiwang analysesofcropyielddynamicsandthedevelopmentofamultimodalneuralnetworkpredictionmodelwithgeminteractions
AT guipinghu analysesofcropyielddynamicsandthedevelopmentofamultimodalneuralnetworkpredictionmodelwithgeminteractions