Title: Assessment of rice yield prediction models based on big data analytics for better supply chain decision-making in Thailand

Authors: Sumanya Ngandee; Attaphongse Taparugssanagorn; Chutiporn Anutariya; John K.M. Kuwornu

Addresses: Department of Information and Communication Technologies, School of Engineering and Technology, Asian Institute of Technology, 58 Moo 9, Km. 42, Paholyothin Highway, Klong Luang, PathumThani, 12120 Thailand ' Department of Information and Communication Technologies, School of Engineering and Technology, Asian Institute of Technology, 58 Moo 9, Km. 42, Paholyothin Highway, Klong Luang, PathumThani, 12120 Thailand ' Department of Information and Communication Technologies, School of Engineering and Technology, Asian Institute of Technology, 58 Moo 9, Km. 42, Paholyothin Highway, Klong Luang, PathumThani, 12120 Thailand ' Department of Food, Agriculture and Bioresources, School of Environment, Resources and Development (SERD), Asian Institute of Technology (AIT), Klong Luang, Pathumthani 12120, Thailand; Department of Agricultural Economics, Agribusiness and Extension, University of Energy and Natural Resources, P.O. Box 214, Sunyani, Ghana

Abstract: This study examined rice yield prediction models for the main type of in-season rice cultivated in Thailand. Models were generated using the machine learning (ML) algorithms: generalised linear model (GLM), feed-forward neural network (FFNN), support vector machine (SVM), and random forest (RF). The models were evaluated using mean absolute percentage error (MAPE), root mean square error (RMSE), and R2 statistic. The results show that the FFNN, which is a deep neural network outperforms the other models. In addition, the FFNN can simultaneously account for complex nonlinear relationships in high-dimensional datasets. While the Big-O complexity and the execution runtime of the FFNN exceed the other models, its execution of predictions takes the least execution runtime. The practical implication of this study is to improve the quality of agricultural information dissemination services and the general public for the development of Thailand's agricultural sector, rice supply chains and the economy as a whole.

Keywords: precision agriculture; crop yield prediction; forecasting; big data analytics; Thailand.

DOI: 10.1504/IJVCM.2021.118289

International Journal of Value Chain Management, 2021 Vol.12 No.3, pp.221 - 240

Received: 26 May 2020
Accepted: 29 Sep 2020

Published online: 05 Oct 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article