Modeling and Simulation of Oil Palm Plantation Productivity Based on Land Quality and Climate Using Artificial Neural Network

Abstract

Crop growth and production on particular land and climate is strongly influenced by the interaction between plants, climate, soil, and management. Land quality and climate which greatly affect the expected production of oil palm are soil type, soil depth, altitude, soil pH, rainfall year^-1, average temperature, water deficit in mm year^-1, air humidity, and solar radiation. Oil palm production as a function of land quality and climate can be predicted using various methods, one of them is artificial neural network (ANN). This study used the algorithm backpropagation ANN method. The aim of this research was to develop a prediction model of oil palm plantation productivity based on land quality and climate and simulate the effect of climate change on oil palm productivity. The result showed that water deficit and average temperature had negative correlation to the productivity of oil palm plantations, while sun shine duration, relative humidity and annual rainfall had positive correlation with the productivity of oil palm plantations. Through the optimization procedure obtained the best ANN architecture is 12 neurons in input layer, 3 neurons in the hidden layer and 1 neuron in the output layer, the best model obtained at 30 000 iterations on training step with a value of determination coefficient (R²): 0.98 and Root Mean Square Error (RMSE): 0.49, while on the test step obtained the value of R²: 0.94 and RMSE: 1.63. The results of simulation showed that the simultaneous influence of climate changes i.e. decreasing the rainfall quantity of 100 mm year^-1, 1 °C temperature rise, and increasing water deficit 50 mm year^-1 reduced the productivity of oil palm plantations by 2 tons ha^-1 year^-1. It can be concluded that ANN can be used to predict the production of palm oil based on land quality and local climate with very good results and we can predict the effect of climate change on the yield of oil palm.