Development of Short-term Evapotranspiration Forecasting Model using Time Series Method to Support The Precision Agriculture Management in Tropics

Open field tropical horticulture production is highly affected by the uncontrollable environment. Consequently, farmer manages their farming activity so as to adapt the environment, such as an appropriate planting schedule, plant maintenance, and daily irrigation. Nowadays, climate change intensifies unpredictable weather and unstable climate distribution. The precision farming approach was introduced by the utilization of on-site environmental monitoring system to support the decision-making process for the daily operations. Evapotranspiration (ET) is the sum of evaporation and transpiration from the soil surface and plant tissue that can be used to assess the water loss behavior in open- field cultivation. In order to support the daily farm management, it is necessary to have a short-term evapotranspiration forecasting to predict n-hour step ahead. The objective of this study was to develop a short-term evapotranspiration forecasting model using time series method. The model is based on Seasonal Autoregressive Integrated Moving Average (SARIMA). The environmental data of air temperature, relative humidity, and solar radiation, observed at Rejeki Tani Yogyakarta on January to August 2014, were used for the datasheet. The ET was estimated using the FAO56 Penmann-Monteith. A suitable parameter of non- seasonal autoregressive order (p), the degree of differencing (d), moving average order (q), and their seasonal parameter (P, D, Q)m were investigated to predict 12-hour ahead of ET. As the result, the suitable parameter was SARIMA (1,2,1)(0,2,1)24. From the 8 days model verification, maximum MSE and RMSE were 0.069 and 0.091 respectively. From the model validation with the different monsoon, the coefficient of determination (R2) was 0.955.