Rainfall Prediction Model Improvement by Fuzzy Set Theory

摘要

This paper presents the improvement of the fuzzy inference model primarily developed for predicting rainfall with data from United States Department of Agriculture (USDA) Soil Climate Analysis Network (SCAN) Station at the Alabama Agricultural and Mechanical University (AAMU) Campus for the year 2004. The primary model was developed with Fuzzy variables selected based on the degree of association of different factors with various combinations causing rainfall. An increase in wind speed (WS) and a decrease in temperature (TP) when compared between the ith and (i-1)th day were found to have a positive relation with rainfall. Results of the model showed better performance after introducing the threshold values of 1) relative humidity (RH) of the ith day;2) humidity increase (HI) when compared between the ith and (i-1)th day;and 3) product (P) of increase in wind speed (WS) and decrease in temperature (TP) when compared between the ith and (i-1)th day. In case of the improved model, errors between actual and calculated amount of rainfall (RF) were 1.20%, 2.19%, and 9.60% when using USDA-SCAN data from AAMU campus for years 2003, 2004 and 2005, respectively. The improved model was tested at William A. Thomas Agricultural Research Station (WTARS) and Bragg farm in Alabama to check the applicability of the model. The errors between the actual and calculated amount of rainfall (RF) were 3.20%, 5.90%, and 1.66% using USDA-SCAN data from WATARS for years 2003, 2004, and 2005, respectively. Similarly, errors were 10.37%, 11.69%, and 25.52% when using SCAN data from Bragg farm for years 2004, 2005, and 2006, respectively. The primary model yielded the value of error equals 12.35% using USDA- SCAN data from AAMU campus for 2004. The present model performance was proven to be better than the primary model.