Forecasting Rainfed Agricultural Production in Arid and Semi-Arid Lands Using Learning Machine Methods: A Case Study

Abstract

With the rising demand for food products and the direct impact of climate change on food production in many parts of the world, recent years have seen growing interest in the subject of food security and the role of rainfed farming in this area. Machine learning methods can be used to predict crop yield based on a combination of remote sensing data and data collected by ground weather stations. This paper argues that forecasting drylands farming yield can be reliable for management purpose under uncertain conditions using machine learning methods and remote sensing data and determines which indicators are most important in predicting the yield of chickpea. In this study, the yield of rainfed chickpea farms in 11 top chickpea producing counties in Kermanshah province, Iran, was predicted using three machine learning methods, namely support vector regression (SVR), random forest (RF), and K-nearest neighbors (KNN). To improve prediction accuracy, for each county, remote sensing data were overlaid by the satellite images of rainfed farms with a suitable slope and altitude for rainfed farming. An integrated database was created by combining weather data, remote sensing data, and chickpea yield statistics. The methods were evaluated using the leave-one-out cross-validation (LOOCV) technique and compared in terms of multiple measures. Given the sensitivity of rainfed chickpea yield to the time of data, the predictions were made in two scenarios: (1) using the averages of the data of all growing months, and (2) using the data of a combination of months. The results showed that RF provides more accurate yield predictions than other methods. The predictions of this method were 7–8% different from the statistics reported by the Statistical Center and the Ministry of Agriculture of Iran. It was found that for pre-harvest prediction of rainfed chickpea yield, using the data of the March–April period (the averages of two months) offers the best result in terms of the correlation coefficient for the relationship between the yield and the predictor indices.