MATHEMATICAL MODELING FOR RAINFALLPREDICTION THROUGH RULE BASE FUZZY INFERENCE SYSTEM USING MATLAB: A CASE STUDY IN RAIPUR DISTRICT (CHHATTISGARH STATE)

Abstract

In human life, Weather forecasting is a very important and required field because in our country maximum people depend upon agriculture. The agricultural economy is largely based upon irrigation and rainfall. For analyzing the productivity of crops rainfall prediction is required and necessary for all farmers. In the present work, we use a rule-based fuzzy inference system (FIS) is employed to forecast day-wise concentrations in the ruler area of the Raipur district. This forecasting model was developed by using the 2 year period July 2016 and July 2017 and the evaluation of the model was achieved through a series of well-established evaluation parameters and methodologies. The evaluation reveals that the FIS models give the best forecasting values of approximately 87 to 88 percent. This will be more accurate as compared to the previous models. For a generation model, we take five parameters: Average temperature, wind direction, pressure, entire cloud cover, and corresponding humidity are the input variable for our model, each parameter consist of three membership functions. The data is used two years metrological data of the rural area of Raipur district (Chhattisgarh state). Our model is based on thirty-two If-Then rules and fuzzy reasoning. The output variable has three membership functions (Light, Medium, and Heavy Rainfall) which are assigned as (0 - 100) percentages for rainfall prediction given in day-wise. The result is in high concurrence, with the actual data.