Advanced machine learning for regional potato yield prediction: analysis of essential drivers

Abstract Localized yield prediction is critical for farmers and policymakers, supporting sustainability, food security, and climate change adaptation. This research evaluates machine learning models, including Random Forest and Gradient Boosting, for predicting crop yields. These models can be adapt...

Full description

Saved in:
Bibliographic Details
Main Authors: Dania Tamayo-Vera, Morteza Mesbah, Yinsuo Zhang, Xiuquan Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:npj Sustainable Agriculture
Online Access:https://doi.org/10.1038/s44264-025-00052-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850251566686142464
author Dania Tamayo-Vera
Morteza Mesbah
Yinsuo Zhang
Xiuquan Wang
author_facet Dania Tamayo-Vera
Morteza Mesbah
Yinsuo Zhang
Xiuquan Wang
author_sort Dania Tamayo-Vera
collection DOAJ
description Abstract Localized yield prediction is critical for farmers and policymakers, supporting sustainability, food security, and climate change adaptation. This research evaluates machine learning models, including Random Forest and Gradient Boosting, for predicting crop yields. These models can be adapted for in-season yield forecasting, providing predictions as early as one month before harvest. The study applied models to postal code-level yield data from 1982 to 2016, incorporating daily climate data, agroclimatic indices, soil parameters, and earth observation NDVI data for Prince Edward Island (PEI), Canada. SHapley Additive exPlanations (SHAP) values identified temperature variables and NDVI as significant predictors. The study highlighted rainfall and soil water retention’s importance for irrigation strategies. Random Forest achieved an RMSE of 0.011 (t/ac), 0.6 (t/ac) less than the best linear regression model. This precision translates to $81,600 CAD per farm annually in PEI, supporting economic and environmental benefits through improved planning and land management.
format Article
id doaj-art-368dd7ee3f0b438aa5283d89bbdfb54b
institution OA Journals
issn 2731-9202
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series npj Sustainable Agriculture
spelling doaj-art-368dd7ee3f0b438aa5283d89bbdfb54b2025-08-20T01:57:52ZengNature Portfolionpj Sustainable Agriculture2731-92022025-03-013111310.1038/s44264-025-00052-6Advanced machine learning for regional potato yield prediction: analysis of essential driversDania Tamayo-Vera0Morteza Mesbah1Yinsuo Zhang2Xiuquan Wang3School of Mathematical and Computational Sciences, University of Prince Edward IslandCharlottetown Research and Development Centre, Agriculture and Agri-Food CanadaAgroClimate, Geomatics and Earth Observations and Agri-Env Resilience Center, Science and Technology Branch, Agriculture and Agri-Food CanadaCanadian Centre for Climate Change and Adaptation, University of Prince Edward IslandAbstract Localized yield prediction is critical for farmers and policymakers, supporting sustainability, food security, and climate change adaptation. This research evaluates machine learning models, including Random Forest and Gradient Boosting, for predicting crop yields. These models can be adapted for in-season yield forecasting, providing predictions as early as one month before harvest. The study applied models to postal code-level yield data from 1982 to 2016, incorporating daily climate data, agroclimatic indices, soil parameters, and earth observation NDVI data for Prince Edward Island (PEI), Canada. SHapley Additive exPlanations (SHAP) values identified temperature variables and NDVI as significant predictors. The study highlighted rainfall and soil water retention’s importance for irrigation strategies. Random Forest achieved an RMSE of 0.011 (t/ac), 0.6 (t/ac) less than the best linear regression model. This precision translates to $81,600 CAD per farm annually in PEI, supporting economic and environmental benefits through improved planning and land management.https://doi.org/10.1038/s44264-025-00052-6
spellingShingle Dania Tamayo-Vera
Morteza Mesbah
Yinsuo Zhang
Xiuquan Wang
Advanced machine learning for regional potato yield prediction: analysis of essential drivers
npj Sustainable Agriculture
title Advanced machine learning for regional potato yield prediction: analysis of essential drivers
title_full Advanced machine learning for regional potato yield prediction: analysis of essential drivers
title_fullStr Advanced machine learning for regional potato yield prediction: analysis of essential drivers
title_full_unstemmed Advanced machine learning for regional potato yield prediction: analysis of essential drivers
title_short Advanced machine learning for regional potato yield prediction: analysis of essential drivers
title_sort advanced machine learning for regional potato yield prediction analysis of essential drivers
url https://doi.org/10.1038/s44264-025-00052-6
work_keys_str_mv AT daniatamayovera advancedmachinelearningforregionalpotatoyieldpredictionanalysisofessentialdrivers
AT mortezamesbah advancedmachinelearningforregionalpotatoyieldpredictionanalysisofessentialdrivers
AT yinsuozhang advancedmachinelearningforregionalpotatoyieldpredictionanalysisofessentialdrivers
AT xiuquanwang advancedmachinelearningforregionalpotatoyieldpredictionanalysisofessentialdrivers