Weather analysis to predict rice cultivation time using multiple linear regression to escalate farmer's exchange rate
Luminto, Harlili · 2017
Agriculture is one of primary sectors of the national economy and is receiving more attention from government annually in order to increase productions and boost national economy. Agriculture, especially rice cultivation, has been challenged with various issues for the past decades such as extreme weather (global warming) which could result in crop failure. From the weather aspect, this paper aims to build weather analysis program to predict rice cultivation time in hope to escalate Farmer's Exchange Rate (FER). Farmer's Exchange Rate is an proxy indicator to determine how prosperous farmers from certain regions are. Weather analysis is conducted by retrieving weather data from National Weather Forecast and Farmer's Exchange Rate data from National Statistics Authority for the past 1 year and using the obtained data to build a regression model using Multiple Linear Regreesion (MLR) to determine the correlation between weather and FER. The variables are “Average Temperature”, “Average Humidity”, “Rainfall”, and “Solar Radiation”. The resulted model is then projected using line chart. Based on evaluation the proposed analysis from 2 different regions tested gives overall Root Mean Square Error (RMSE) between 0.39-1.34.