Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality

Ensuring accurate predictions of wheat yield and nutritional content is vital for enhancing agricultural pro ductivity and food security. This study aims to improve wheat yield prediction by integrating process-based models (PBM), machine learning (ML), and remote sensing (RS) techniques. Three Dec...

Descripción completa

Detalles Bibliográficos
Autores principales: Kheir, Ahmed M.S., Govind, Ajit, Nangia, Vinay, El-Maghraby, Maher A., Elnashar, Abdelrazek, Ahmed, Mukhtar, Aboelsoud, Hesham, Mostafa, Rania, Feike, Til
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/175162
_version_ 1855533425329438720
author Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
El-Maghraby, Maher A.
Elnashar, Abdelrazek
Ahmed, Mukhtar
Aboelsoud, Hesham
Mostafa, Rania
Feike, Til
author_browse Aboelsoud, Hesham
Ahmed, Mukhtar
El-Maghraby, Maher A.
Elnashar, Abdelrazek
Feike, Til
Govind, Ajit
Kheir, Ahmed M.S.
Mostafa, Rania
Nangia, Vinay
author_facet Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
El-Maghraby, Maher A.
Elnashar, Abdelrazek
Ahmed, Mukhtar
Aboelsoud, Hesham
Mostafa, Rania
Feike, Til
author_sort Kheir, Ahmed M.S.
collection Repository of Agricultural Research Outputs (CGSpace)
description Ensuring accurate predictions of wheat yield and nutritional content is vital for enhancing agricultural pro ductivity and food security. This study aims to improve wheat yield prediction by integrating process-based models (PBM), machine learning (ML), and remote sensing (RS) techniques. Three Decision Support System for Agrotechnology Transfer (DSSAT) wheat models were calibrated and evaluated using field data from three wheat cultivars grown over three seasons in diverse environments. We developed a hybrid PBM-ML-RS approach using polynomial regression to generate iron (Fe) and zinc (Zn) content from nitrogen predictions. The DSSAT wheat models slightly overestimated wheat yield but accurately predicted nitrogen content. The hybrid PBM-ML- RS approach closely estimated Fe and Zn content with a root mean square error (RMSE) of 0.42 t/ha for yield and 0.89 % for nitrogen content. The integration of ML and RS improved the prediction accuracy for Fe and Zn, achieving RMSE values of 0.35 % and 0.28 % respectively. Spatial simulations provided detailed geographic estimations of wheat yield and nutrient content, supporting site-specific management practices. This study demonstrates the potential of combining PBM, ML, and RS for comprehensive yield and nutrition prediction. The f indings indicate a modest decrease in protein, Fe, and Zn concentrations with increasing grain yield, exhibiting high variability across different sites and cultivars. Future research should integrate additional data sources to enhance model robustness and applicability to other crops and regions, contributing to sustainable agriculture and food security.
format Journal Article
id CGSpace175162
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1751622026-01-22T02:11:30Z Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality Kheir, Ahmed M.S. Govind, Ajit Nangia, Vinay El-Maghraby, Maher A. Elnashar, Abdelrazek Ahmed, Mukhtar Aboelsoud, Hesham Mostafa, Rania Feike, Til uncertainty zinc iron wheat dssat protein random forest regressor nutrient concentration Ensuring accurate predictions of wheat yield and nutritional content is vital for enhancing agricultural pro ductivity and food security. This study aims to improve wheat yield prediction by integrating process-based models (PBM), machine learning (ML), and remote sensing (RS) techniques. Three Decision Support System for Agrotechnology Transfer (DSSAT) wheat models were calibrated and evaluated using field data from three wheat cultivars grown over three seasons in diverse environments. We developed a hybrid PBM-ML-RS approach using polynomial regression to generate iron (Fe) and zinc (Zn) content from nitrogen predictions. The DSSAT wheat models slightly overestimated wheat yield but accurately predicted nitrogen content. The hybrid PBM-ML- RS approach closely estimated Fe and Zn content with a root mean square error (RMSE) of 0.42 t/ha for yield and 0.89 % for nitrogen content. The integration of ML and RS improved the prediction accuracy for Fe and Zn, achieving RMSE values of 0.35 % and 0.28 % respectively. Spatial simulations provided detailed geographic estimations of wheat yield and nutrient content, supporting site-specific management practices. This study demonstrates the potential of combining PBM, ML, and RS for comprehensive yield and nutrition prediction. The f indings indicate a modest decrease in protein, Fe, and Zn concentrations with increasing grain yield, exhibiting high variability across different sites and cultivars. Future research should integrate additional data sources to enhance model robustness and applicability to other crops and regions, contributing to sustainable agriculture and food security. 2025-03-23 2025-06-18T16:27:31Z 2025-06-18T16:27:31Z Journal Article https://hdl.handle.net/10568/175162 en Open Access application/pdf Elsevier Ahmed M. S. Kheir, Ajit Govind, Vinay Nangia, Maher A. El-Maghraby, Abdelrazek Elnashar, Mukhtar Ahmed, Hesham Aboelsoud, Rania Mostafa, Til Feike. (23/3/2025). Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality. Computers and Electronics in Agriculture, 234.
spellingShingle uncertainty
zinc
iron
wheat
dssat
protein
random forest regressor
nutrient concentration
Kheir, Ahmed M.S.
Govind, Ajit
Nangia, Vinay
El-Maghraby, Maher A.
Elnashar, Abdelrazek
Ahmed, Mukhtar
Aboelsoud, Hesham
Mostafa, Rania
Feike, Til
Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title_full Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title_fullStr Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title_full_unstemmed Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title_short Hybridization of process-based models, remote sensing, and machine learning for enhanced spatial predictions of wheat yield and quality
title_sort hybridization of process based models remote sensing and machine learning for enhanced spatial predictions of wheat yield and quality
topic uncertainty
zinc
iron
wheat
dssat
protein
random forest regressor
nutrient concentration
url https://hdl.handle.net/10568/175162
work_keys_str_mv AT kheirahmedms hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT govindajit hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT nangiavinay hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT elmaghrabymahera hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT elnasharabdelrazek hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT ahmedmukhtar hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT aboelsoudhesham hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT mostafarania hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality
AT feiketil hybridizationofprocessbasedmodelsremotesensingandmachinelearningforenhancedspatialpredictionsofwheatyieldandquality