Prediction of Crop Yields Based on Fuzzy Rule-Based System (FRBS) Using the Takagi Sugeno-Kang Approach

Abstract

Predicting the effects of climate change on crop yields requires a model and its parameters, how crops respond to weather. Predictions from different models often disagree with the climatic variables and its impact. A common approach is to use statistical models trained on historical yields and some simplified measurements of weather, such as growing season average temperature and precipitation. Climate change is really concern to the entire world. Its direct impact on the crop growth and yield is very important to understand. In the present study Fuzzy logic crop yield model was developed by considering different climate change variables. Temperature, Rainfall, evaporation, humidity parameters are considered for the crop yield model. Model is being developed by considering the 15-year crop yield data and same period for the climatic variables. Triangular membership function is being adopted in the fuzzy model. In this study a fuzzy rule-based system (FRBS) using the Takagi Sugeno-Kang approach has been used for the developing the crop yield model. Model is validated by coefficient of correlation, and found that, there is more than 0.9 coefficient of correlation between observed and evaluated yield.