Machine Learning-Based Prediction of Crop Yield Using Decision Tree Approach in Agricultural Systems

View at publisher Summarise with VIRAT
Authors: Amit Mittal, Anant Deogaonkar, Chandan Vichoray
Cited by: 0
References: 18

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

Proper crop yield forecast is essential to the contemporary agricultural control and resource planning. In this work, an analytical model of soil and climatic condition prediction is given that predicts the crop yield using a Decision Tree (DT) regression model. The data on which this analysis was done was based on the secondary agricultural record that included variables like soil PH, nitrogen in soil, rain, temperature, and humidity. MATLAB has been mostly applied in the development of models, simulation, and visualization. The workflow includes splitting the data into the training and testing parts, training a DT model, and testing its predictive performance with such statistical measures as Mean Absolute Error (MAE), root mean square error (RMSE), and the coefficient of determination ($R^{2}$). The model developed obtained an MAE of 41.719, RMSE 53.286 and R2 0.383 which is a decent predictive result. The findings show that the soil pH, nitrogen, and humidity play a significant role in predicting crop yield. The findings have been validated using various plots and graphical output such as the graph of the model structure, feature importance and the graph of comparative yield prediction. The general work emphasises the potential viability of machine learning in an agricultural setting especially in yield forecasting and agronomic decision support.

Fields of Study & Subjects

Smart Agriculture and AI Artificial Intelligence in Healthcare Data Mining and Machine Learning Applications

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1176–1181
Publication date
21 January 2026
Language
EN