In Indonesia, paddy production depends heavily on the amount of rainfall. Thus, there needs to be a risk analysis for paddy production by utilizing rainfall data patterns. However, since much rainfall data is missing then we use the ENSO indicator which is anomaly SST 3.4. In the previous research, the results of software design include analysis of the relationship between paddy harvest area and anomaly of SST 3.4 by using Copula and estimation model design of paddy harvest area using Robust regression. This research implements the prediction model of harvested area based on ENSO indicators into a web-based software. The results of this harvested area model will be used to predict paddy production. Furthermore, the prediction of rice production is compared with the amount of rice consumption of the population to obtain the level of risk of paddy production. Thematic maps are used to present the risk level of paddy production.
|Number of pages
|International Journal of Machine Learning and Computing
|Published - 1 Jun 2019
- Decision Support System (DSS)
- Robust regression