Prediction and anomaly detection of rainfall using evolving neural network to support planting calender in soreang (Bandung)

As an agricultural country and located around the equator line, Indonesia geographical position between two continents and oceans is very sensitive to regional and global atmospheric circulations as sunspot, cosmic rays, Indian Ocean Dipole(IOD) and Southern Oscillation Index(SOI). The disruption of one circulation can affect climate and weather. The extreme anomaly climate is very influential in the agriculture field because in many regions rainfall is the main source of water to meet the needs of agriculture, so that agricultural activities always depend on the rainfall. As a consequence, agricultural activities in this area, especially rice plants should always pay attention and adjust the pattern of rainfall. Because of that, to determine the best beginning of growing season based on prediction and anomaly detection of rainfall used local, regional and global variables that influences rainfall is very important. So, losses due to precipitation anomalies in planting time or growing season until harvest can be minimized because farmers can adjust the planting starting time with the change of the rainfall and the attention to anomalies of rainfall. Artificial Neural Network (ANN) is widely used for predictions because of its accuracy and data error tolerance but have some limited. Therefore this study proposes ENN which used ANN and Genetic Algorithm(GA) to optimize and find the best weights and biases. From three scenarios, one hidden layer in ANN architecture was sufficient and ENN had good performance in different dataset. The rainfall prediction result used all data (January-December) from 1999–2013 had the accuracy of 84.6%, 66.02% for dry season (April-September) and 79.7% for wet season (October-March). Based on the prediction and anomaly detection in this research, in Soreang region the first week of January, April and October 2014 were confirmed for the starting time of planting in 2014.