Machine Learning Approaches for Predicting Maize Biomass Yield - Leveraging Feature Engineering and Comprehensive Data Integration

Aug 5, 2026

Upload by Skyler

Efficient prediction of corn biomass yield underpins sustainable crop production and renewable energy planning. This study applies advanced machine learning models—Gradient Boosting Machines, Random Forests, Support Vector Machines, and Artificial Neural Networks—fed with integrated environmental, soil, and crop-management data from key U.S. regions. A feature-engineering framework creates a Soil Fertility Index and Growing Degree Days and adds interaction terms to model nonlinear relationships. Sensitivity analysis using SHAP identifies SFI, GDDs, and cumulative rainfall as the strongest drivers. An ensemble combining GBMs, RFs, and ANNs achieves RMSE 0.80 t/ha and R2 0.89.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Keywords

1. Introduction

Renewable energy and sustainable agriculture context

Limitations of traditional prediction models

Benefits of machine learning for yield prediction

Article Machine Learning Approaches for Predicting Maize Biomass Yield: Leveraging Feature Engineering and Comprehensive Data Integration Maryam Abbasi 1, Paulo Váz 2, José Silva 2 and Pedro Martins 2, * Academic Editor: Bin Ji Received: 18 October 2024 Revised: 21 December 2024 Accepted: 23 December 2024 Published: 2 January 2025 Citation: Abbasi, M.; Váz, P.; Silva, J.; Martins, P. Machine Learning Approaches for Predicting Maize Biomass Yield: Leveraging Feature Engineering and Comprehensive Data Integration. Sustainability 2025, 17, 256 . [https://doi.org/10.3390/su17010256](https://doi.org/10.3390/su17010256) [Copyright:](Copyright:) © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . 1 Applied Research Institute, Polytechnic of Coimbra, 3000 Coimbra, Portugal; [maryam.abbasi@ipc.pt](maryam.abbasi@ipc.pt) 2 Research Center in Digital Services, Polytechnic of Viseu, 3500 Viseu, Portugal; [paulovaz@estgv.ipv.pt](paulovaz@estgv.ipv.pt) (P.V.); [jsilva@estgv.ipv.pt](jsilva@estgv.ipv.pt) (J.S.) * [Correspondence: pedromom@estgv.ipv.pt](Correspondence: pedromom@estgv.ipv.pt) Abstract: The efficient prediction of corn biomass yield is critical for optimizing crop production and addressing global challenges in sustainable agriculture and renewable energy. This study employs advanced machine learning techniques, including Gradient Boosting Machines (GBMs), Random Forests (RFs), Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs), integrated with comprehensive environmental, soil, and crop management data from key agricultural regions in the United States. A novel framework combines feature engineering, such as the creation of a Soil Fertility Index (SFI) and Growing Degree Days (GDDs), and the incorporation of interaction terms to address complex non-linear relationships between input variables and biomass yield. We conduct extensive sensitivity analysis and employ SHAP (SHapley Additive exPlanations) values to enhance model interpretability, identifying SFI, GDDs, and cumulative rainfall as the most influential features driving yield outcomes. Our findings highlight significant synergies among these variables, emphasizing their critical role in rural environmental governance and precision agriculture. Furthermore, an ensemble approach combining GBMs, RFs, and ANNs outperformed individual models, achieving an RMSE of 0.80 t/ha and R2 of 0.89 . These results underscore the potential of hybrid modeling for real-world applications in sustainable farming practices. Addressing the concerns of passive farmer participation, we propose targeted incentives, education, and institutional support mechanisms to enhance stakeholder collaboration in rural environmental governance. While the models assume rational decision-making, the inclusion of cultural and political factors warrants further investigation to improve the robustness of the framework. Additionally, a map of the study region and improved visualizations of feature importance enhance the clarity and relevance of our findings. This research contributes to the growing body of knowledge on predictive modeling in agriculture, combining theoretical rigor with practical insights to support policymakers and stakeholders in optimizing resource use and addressing environmental challenges. By improving the interpretability and applicability of machine learning models, this study provides actionable strategies for enhancing crop yield predictions and advancing rural environmental governance. Keywords: biomass yield prediction; machine learning; gradient boosting machines; random forest; support vector machines; soil fertility index; feature engineering; sensitivity analysis; sust

FAQs

Which machine learning models are used to predict maize biomass yield?

The study uses Gradient Boosting Machines, Random Forests, Support Vector Machines, and Artificial Neural Networks.

What feature-engineering methods improve the models?

It introduces a Soil Fertility Index and Growing Degree Days, and it incorporates interaction terms to capture nonlinear relationships.

How do the authors assess feature importance and interpret the results?

They perform extensive sensitivity analysis and use SHAP values to identify the most influential features driving yield outcomes.

Aug 5, 2026

Upload by Skyler