Ensemble machine learning-based recommendation system for effective prediction of suitable agricultural crop cultivation

Aug 5, 2026

Upload by Patrick

Agriculture underpins food security and industrial inputs, yet rising population pressure and shrinking farmland can cause production shortfalls. Selecting suitable crops for specific regions requires reliable forecasting from historical environmental and cultivation data, but public data are limited. This study uses Bangladesh as a case, gathers and preprocesses institution-sourced data, and proposes an ensemble machine learning approach (KRR) to predict major crops. Evaluation with MAE, MSE, RMSE, and R2 plus Diebold–Mariano testing and a recommender module supports robust crop selection for the next season.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Agriculture challenges and need for crop forecasting

Proposed ensemble approach and evaluation

TYPE Original Research PUBLISHED 10 August 2023 DOI 10.3389/fpls.2023.1234555 OPEN ACCESS EDITED BY Muhammad Fazal Ijaz, Sejong University, Republic of Korea REVIEWED BY Sambit Bakshi, National Institute of Technology Rourkela, India Mohammed Chachan Younis, University of Mosul, Iraq Yassine Maleh, Universite´ Sultan Moulay Slimane, Morocco *CORRESPONDENCE Seifedine Kardy seifedine. kadry@noroff. no Yunyoung Nam [ynam@sch.ac.kr](ynam@sch.ac.kr)[ ](ynam@sch.ac.kr)Md Palash Uddin [palash_cse@hstu.ac.bd](palash_cse@hstu.ac.bd) RECEIVED 04 June 2023 ACCEPTED 17 July 2023 PUBLISHED 10 August 2023 CITATION Hasan M, Marjan MA, Uddin MP, Afjal MI, Kardy S, Ma S and Nam Y (2023) Ensemble machine learning-based recommendation system for effective prediction of suitable agricultural crop cultivation. Front. Plant Sci. 14:1234555 . doi: 10.3389/fpls.2023.1234555 COPYRIGHT © 2023 Hasan, Marjan, Uddin, Afjal, Kardy, Ma and Nam. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Ensemble machine learningbased recommendation system for effective prediction of suitable agricultural crop cultivation Mahmudul Hasan 1, Md Abu Marjan 1, Md Palash Uddin 1,2*, Masud Ibn Afjal 1, Seifedine Kardy 3,4,5*, Shaoqi Ma 6 and Yunyoung Nam 6* 1 Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh, 2School of Information Technology, Deakin University, Geelong, VIC, Australia, 3 Department of Applied Data Science, Noroff University College, Kristiansand, Norway, 4Artiﬁcial Intelligence Research Center (AIRC), Ajman University, Ajman, United Arab Emirates, 5 Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon, 6 Department of ICT Convergence, Soonchunhyang University, Asan, Republic of Korea Agriculture is the most critical sector for food supply on the earth, and it is also responsible for supplying raw materials for other industrial productions. Currently, the growth in agricultural production is not sufﬁcient to keep up with the growing population, which may result in a food shortfall for the world’s inhabitants. As a result, increasing food production is crucial for developing nations with limited land and resources. It is essential to select a suitable crop fora speciﬁc region to increase its production rate. Effective crop production forecasting in that area based on historical data, including environmental and cultivation areas, and crop production amount, is required. However, the data for such forecasting are not publicly available. As such, in this paper, we take a case study of a developing country, Bangladesh, whose economy relies on agriculture. We ﬁrst gather and preprocess the data from the relevant research institutions of Bangladesh and then propose an ensemble machine learning approach, called K-nearest Neighbor Random Forest Ridge Regression (KRR), to effectively predict the production of the major crops (three different kinds of rice, potato, and wheat) . KRR is designed after investigating ﬁve existing traditional machine learning (Support Vector Regression, Naïve Bayes, and Ridge Regression) and ensemble learning (Random Forest and CatBoost) algorithms. We consider four classical evaluation metrics, i.e., mean absolute error, mean square error (MSE), root MSE, and R2, to evaluate the performance of the proposed KRR over the other machine learning models. It shows 0 . 009 MSE, 99% R2 for Aus; 0 . 92 MSE, 90% R2 for Aman; 0 . 246 MSE, 99% R2 for Boro; 0 .062 MSE, 99% R2 for wh

FAQs

What problem does the ensemble recommendation system address?

It targets accurate prediction of suitable agricultural crops for specific land areas to improve crop planning and production forecasting when data availability is limited.

What model does the paper propose for crop production prediction?

The proposed ensemble method is K-nearest Neighbor Random Forest Ridge Regression (KRR), built after comparing traditional and ensemble machine learning baselines.

How is the proposed approach evaluated?

Performance is measured using MAE, MSE, RMSE, and R2, and robustness is checked with the Diebold–Mariano test against benchmark ML models. A recommender system then suggests suitable crops for the next season.

Aug 5, 2026

Upload by Patrick