Crop Yield Analysis and Predictions Using Traditional and Machine Learning Models

Agriculture plays a vital role in national economies and global food security, yet increasing population demands and climate variability continue to challenge sustainable crop production. Accurate crop yield prediction can significantly support farmers and policymakers by enabling better planning, resource allocation, and risk management. This study presents a machine-learning-based framework for predicting crop yield using key agronomic and environmental attributes, including rainfall, crop type, climatic conditions, cultivated area, fertilizer and pesticide usage, production statistics, and historical yield records. Multiple predictive models were evaluated, including ARIMA, Decision Tree, Random Forest, Gradient Boosting, and XGBoost regressors, to identify the most effective approach for yield forecasting. Experimental results demonstrate that machine learning models—particularly tree-based methods—achieve strong predictive performance, with the Decision Tree model obtaining the highest accuracy of 99.62% and the lowest error values across MAE, RMSE, and R² metrics. The evaluation confirms that ML models reduce prediction errors and offer interpretable feature contributions, providing actionable insights for stakeholders. Overall, the findings validate the effectiveness of machine-learning approaches in agricultural forecasting and highlight their potential to enhance climate adaptation, optimize resource utilization, and support data-driven strategies for improved food security and sustainable agricultural development.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-18
DOI
https://doi.org/10.20944/preprints202611.1918.v1
Primary Topic
Smart Agriculture and AI
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Crop Yield Analysis and Predictions Using Traditional and Machine Learning Models

Bilal Ishfaq, Ghulam Paracha
Preprints.org
Smart Agriculture and AI
preprint

Crop Yield Analysis and Predictions Using Traditional and Machine Learning Models

Bilal Ishfaq, Ghulam Paracha
preprint en

Abstract

Agriculture plays a vital role in national economies and global food security, yet increasing population demands and climate variability continue to challenge sustainable crop production. Accurate crop yield prediction can significantly support farmers and policymakers by enabling better planning, resource allocation, and risk management. This study presents a machine-learning-based framework for predicting crop yield using key agronomic and environmental attributes, including rainfall, crop type, climatic conditions, cultivated area, fertilizer and pesticide usage, production statistics, and historical yield records. Multiple predictive models were evaluated, including ARIMA, Decision Tree, Random Forest, Gradient Boosting, and XGBoost regressors, to identify the most effective approach for yield forecasting. Experimental results demonstrate that machine learning models—particularly tree-based methods—achieve strong predictive performance, with the Decision Tree model obtaining the highest accuracy of 99.62% and the lowest error values across MAE, RMSE, and R² metrics. The evaluation confirms that ML models reduce prediction errors and offer interpretable feature contributions, providing actionable insights for stakeholders. Overall, the findings validate the effectiveness of machine-learning approaches in agricultural forecasting and highlight their potential to enhance climate adaptation, optimize resource utilization, and support data-driven strategies for improved food security and sustainable agricultural development.

Preprints.org
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon