Identifying El Niño–Southern Oscillation influences on rainfall with classification models: implications for water resource management of Sri Lanka

Abstract

Seasonal to annual forecasts of precipitation patterns are very important for water infrastructure management. In particular, such forecasts can be used to inform decisions about the operation of multipurpose reservoir systems in the face of changing climate conditions. Success in making useful forecasts is often achieved by considering climate teleconnections such as the El Niño–Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD) as related to sea surface temperature variations. We present a statistical analysis to explore the utility of using rainfall relationships in Sri Lanka with ENSO and IOD to predict rainfall to the Mahaweli and Kelani River basins of the country. Forecasting of rainfall as the classes flood, drought, and normal is helpful for water resource management decision-making. Results of these models give better accuracy than a prediction of absolute values. Quadratic discrimination analysis (QDA) and classification tree models are used to identify the patterns of rainfall classes with respect to ENSO and IOD indices. Ensemble modeling tool Random Forest is also used to predict the rainfall classes as drought and not drought with higher skill. These models can be used to forecast the areal rainfall using predicted climate indices. Results from these models are not very accurate; however, the patterns recognized provide useful input to water resource managers as they plan for adaptation of agriculture and energy sectors in response to climate variability.