Study of Developing Models of Crop Failure Risk Information

Abstract

Climate is one factor that can influence plant growth. The risk of crop failure due to climate variability can be in the form of reduced water sources, which impact water needs in the land and the emergence of pests and diseases in plants. The risk of planting failure can impact product quality, which has the potential to decrease, higher plant handling costs, and various things that cause losses to farming businesses. The availability of climate forecast information, such as rainfall and other parameters, encourages writers to apply it to information that is easier for users to understand. One of the machine learning algorithms, Decision Tree, is used as a model in determining the risk of planting failure based on each attribute/parameter, including monthly rain, ENSO and IOD phenomena, drought, groundwater availability, and Oldeman climate type. This study aims to make a model prediction of crop failure risk potential, and the calculation is based on climate prediction data. The results of this study show differences in climatic conditions for each commodity when there is an increased potential risk of planting failure. Monthly rainfall is the most dominant factor influencing rice, maize, and soybean planting failure. Validation of the decision tree model shows that this model is quite good in determining the potential risk of crop failure in all commodities studied, with the proportion of correct proportion of more than 65%. However, the Heidke Skill Score (HSS) shows that this model is good for Paddy and Soybean; Maize shows an HSS of less than zero.