A BiLSTM-based predictive model for rice production
Juan Yun1 · Hanjun Lee2
12Department of Management Information Systems, Myongji University
Correspondence to: 1 Student, Department of Management Information Systems, Myongji University, Seoul 03674, Korea.
2 Corresponding author: Associate professor, Department of Management Information Systems, Myongji University, Seoul 03674, Korea. E-mail: hjlee1609@gmail.com
2 Corresponding author: Associate professor, Department of Management Information Systems, Myongji University, Seoul 03674, Korea. E-mail: hjlee1609@gmail.com
Received July 4, 2023; Revised July 28, 2023; Accepted August 2, 2023.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- Rice is overwhelmingly the most produced crop in domestic agriculture. Ensuring stable rice supply is a major national priority every year, and accurate prediction of rice harvests is crucial for formulating rice supply policies. However, research in this area is relatively scarce compared to other agricultural crops, and existing studies also have significant room for improvement in terms of prediction accuracy. In this study, we collected moderate resolution imaging spectroradiometer (MODIS) dataset, including vegetation indices such as normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI), along with meteorological data. We proposed a rice production forecasting model using a deep learning technique called BiLSTM, taking into account the temporal characteristics. The results of this study can serve as valuable empirical evidence for decision-making in rice supply policies.
- Keywords : BiLSTM, EVI, machine learning, NDVI, rice production
Full Text(PDF) Free
