Machine Learning Approaches for Wheat Yield Prediction Using Multiple Features: A Case Study on Indian State-Level Data

View at publisher Summarise with VIRAT
Authors: Barinderjit Kaur, Vikas Wasson, Simrandeep Singh
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Accurate forecasting of wheat yields is essential for food security, agricultural planning, and sustainable resource management. Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) enable modeling of complex interactions among climatic, soil, and environmental factors. This study utilizes a state-level Indian dataset spanning the period 1997-2022 to evaluate the performance of five supervised machine learning models for wheat yield prediction. Model performance was evaluated using the coefficient of determination R2value, adjusted R2value and the Root Mean Square Error (RMSE). The evaluated models include Linear Regression, Ridge Regression, Lasso Regression, Decision Tree, and Random Forest. Experimental results indicate that the Random Forest model (R2= 0.817, RMSE = 0.35) and Ridge Regression model (R2= 0.828, RMSE = 0.34) exhibit superior generalisation performance. The feature importance analysis identifies fertilizer application as the most influential factor, followed closely by rainfall and the cultivated area, consistent with established agronomic principles. The findings demonstrate the effectiveness of ensemble and regularized learning approaches as decision-support tools for precision agriculture across diverse agro-climatic regions of India.

Fields of Study & Subjects

Smart Agriculture and AI Climate change impacts on agriculture Artificial Intelligence in Healthcare

Publication details

Journal / source
International Conference on Signal Processing and Electronics Design (ICSPED)
Pages
109–114
Publication date
23 January 2026
Language
EN