Maize and soybean yield prediction using machine learning methods: a systematic literature review

Abstract Today’s agronomy is data-rich, and machine learning (ML) provides the ability to efficiently predict crop yields, utilizing high-volume data to optimize agricultural decision-making. Numerous ML models are used, yet systemized framework guiding the crop-targeted selection of models, feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Ramandeep Kumar Sharma, Jasleen Kaur, Gary Feng, Yanbo Huang, Chandan Kumar, Yi Wang, Sandhir Sharma, Johnie Jenkins, Jagmandeep Dhillon
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Discover Agriculture
Subjects:
Online Access:https://doi.org/10.1007/s44279-025-00215-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850042334756995072
author Ramandeep Kumar Sharma
Jasleen Kaur
Gary Feng
Yanbo Huang
Chandan Kumar
Yi Wang
Sandhir Sharma
Johnie Jenkins
Jagmandeep Dhillon
author_facet Ramandeep Kumar Sharma
Jasleen Kaur
Gary Feng
Yanbo Huang
Chandan Kumar
Yi Wang
Sandhir Sharma
Johnie Jenkins
Jagmandeep Dhillon
author_sort Ramandeep Kumar Sharma
collection DOAJ
description Abstract Today’s agronomy is data-rich, and machine learning (ML) provides the ability to efficiently predict crop yields, utilizing high-volume data to optimize agricultural decision-making. Numerous ML models are used, yet systemized framework guiding the crop-targeted selection of models, features, accuracy measures, and addressing associated challenges is lacking, specifically for soybean and maize, world’s vital crops. Henceforth, this is the first crop-targeted systematic literature review (SLR) performed to retrieve/consolidate the ML techniques and key features utilized in maize and soybean yield prediction research. The study searched four databases (ProQuest, Wiley, Science Direct, and EBSCOhost), producing 1859 articles, which finally reduced to 82 articles following SLR’s inclusion/exclusion criteria. These papers were thoroughly analysed for generating common consensus and future research recommendations. Results revealed the temperature, precipitation, historical crop yield, normalized difference vegetation index (NDVI), and soil pH to be the most utilized ML features for yield prediction research. The Random Forest (RF), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Extreme Gradient Boosting (XG-Boost) were identified as the mostly used ML algorithms. Most often applied deep learning techniques include long short-term memory (LSTM) and convolutional neural networks (CNNs). In the utilized models, the most used performance assessment measures were noted as the coefficient of determination (R2), root absolute error (RAE), root mean square error (RMSE), and mean absolute error (MAE). This SLR also reported major challenges with obtaining high quantity/quality data, model complexity tackling, and incorporating the inclusion of farm management factors in yield prediction process. Altogether, this SLR offers a valuable framework for model selection, feature unification, accuracy measures comparison, model performance assessment, and addressing challenges in ML-based yield prediction research, with an emphasis on maize and soybean.
format Article
id doaj-art-dff8b8815adf4a21b45aba122807c0fd
institution DOAJ
issn 2731-9598
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Discover Agriculture
spelling doaj-art-dff8b8815adf4a21b45aba122807c0fd2025-08-20T02:55:35ZengSpringerDiscover Agriculture2731-95982025-04-013112910.1007/s44279-025-00215-6Maize and soybean yield prediction using machine learning methods: a systematic literature reviewRamandeep Kumar Sharma0Jasleen Kaur1Gary Feng2Yanbo Huang3Chandan Kumar4Yi Wang5Sandhir Sharma6Johnie Jenkins7Jagmandeep Dhillon8Rutgers, The State University of New JerseyChitkara Business School , Chitkara UniversityGenetics and Sustainable Agriculture Research Unit, USDA-ARSGenetics and Sustainable Agriculture Research Unit, USDA-ARSDepartment of Plant and Soil Sciences, Mississippi State UniversityDepartment of Plant and Agroecosystem Sciences, University of Wisconsin-MadisonChitkara Business School , Chitkara UniversityGenetics and Sustainable Agriculture Research Unit, USDA-ARSDepartment of Plant and Soil Sciences, Mississippi State UniversityAbstract Today’s agronomy is data-rich, and machine learning (ML) provides the ability to efficiently predict crop yields, utilizing high-volume data to optimize agricultural decision-making. Numerous ML models are used, yet systemized framework guiding the crop-targeted selection of models, features, accuracy measures, and addressing associated challenges is lacking, specifically for soybean and maize, world’s vital crops. Henceforth, this is the first crop-targeted systematic literature review (SLR) performed to retrieve/consolidate the ML techniques and key features utilized in maize and soybean yield prediction research. The study searched four databases (ProQuest, Wiley, Science Direct, and EBSCOhost), producing 1859 articles, which finally reduced to 82 articles following SLR’s inclusion/exclusion criteria. These papers were thoroughly analysed for generating common consensus and future research recommendations. Results revealed the temperature, precipitation, historical crop yield, normalized difference vegetation index (NDVI), and soil pH to be the most utilized ML features for yield prediction research. The Random Forest (RF), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Extreme Gradient Boosting (XG-Boost) were identified as the mostly used ML algorithms. Most often applied deep learning techniques include long short-term memory (LSTM) and convolutional neural networks (CNNs). In the utilized models, the most used performance assessment measures were noted as the coefficient of determination (R2), root absolute error (RAE), root mean square error (RMSE), and mean absolute error (MAE). This SLR also reported major challenges with obtaining high quantity/quality data, model complexity tackling, and incorporating the inclusion of farm management factors in yield prediction process. Altogether, this SLR offers a valuable framework for model selection, feature unification, accuracy measures comparison, model performance assessment, and addressing challenges in ML-based yield prediction research, with an emphasis on maize and soybean.https://doi.org/10.1007/s44279-025-00215-6Machine learning in agronomyDeep learningCrop managementPrecision agricultureArtificial intelligence
spellingShingle Ramandeep Kumar Sharma
Jasleen Kaur
Gary Feng
Yanbo Huang
Chandan Kumar
Yi Wang
Sandhir Sharma
Johnie Jenkins
Jagmandeep Dhillon
Maize and soybean yield prediction using machine learning methods: a systematic literature review
Discover Agriculture
Machine learning in agronomy
Deep learning
Crop management
Precision agriculture
Artificial intelligence
title Maize and soybean yield prediction using machine learning methods: a systematic literature review
title_full Maize and soybean yield prediction using machine learning methods: a systematic literature review
title_fullStr Maize and soybean yield prediction using machine learning methods: a systematic literature review
title_full_unstemmed Maize and soybean yield prediction using machine learning methods: a systematic literature review
title_short Maize and soybean yield prediction using machine learning methods: a systematic literature review
title_sort maize and soybean yield prediction using machine learning methods a systematic literature review
topic Machine learning in agronomy
Deep learning
Crop management
Precision agriculture
Artificial intelligence
url https://doi.org/10.1007/s44279-025-00215-6
work_keys_str_mv AT ramandeepkumarsharma maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT jasleenkaur maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT garyfeng maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT yanbohuang maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT chandankumar maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT yiwang maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT sandhirsharma maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT johniejenkins maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview
AT jagmandeepdhillon maizeandsoybeanyieldpredictionusingmachinelearningmethodsasystematicliteraturereview