Modeling Reference Crop Evapotranspiration Using Support Vector Machine (SVM) and Extreme Learning Machine (ELM) in Region IV-A, Philippines

The need for accurate estimates of reference crop evapotranspiration (ETo) is important in irrigation planning and design, scheduling, reservoir management among other applications. ETo can be accurately determined using the internationally accepted FAO Penman–Monteith (FAO-56 PM) equation. However, this requires numerous observed data, including solar radiation, air temperature, relative humidity, wind speed, which most cases are unavailable, particularly developing countries such as Philippines. This study developed models based on Support Vector Machines (SVMs) Extreme Learning (ELMs) estimation daily different input combinations meteorological data Region IV-A, performance machine learning was compared with established alternative empirical ETo. results show that SVM ELM models, at least Tmax, Tmin, Rs inputs, provide best estimates. accuracy also found to superior given same requirements. In general, showed similar modeling performance, although former lower run time than latter.