Date of Publication :22nd February 2018
Abstract: Changing Climatic conditions are leading to alternate weather patterns. Accurately predicting weather patterns is important as they have wide social and economic impact. This paper proposes and analyzes a predictive model which analyse a wide range of data points with the aim of predicting likelihood and pattern of location-specific rainfall at a high degree of confidence. We extract knowledge from historical weather data collected from NOAA(National Oceanic Atmospheric Administration)[10]. From the collected weather data comprising of 15 attributes, only 5 attributes are most relevant to rainfall prediction. Data preprocessing and data transformation on raw weather data set is performed, so that it shall be possible to work on Bayesian and K-NN the data mining, prediction model used for rainfall prediction. The model is trained using training dataset and tested on test data for accuracy. We have used comparative approach of Bayesian and K-NN models and found Bayesian approach to be more accurate.
Reference :
-
- B.B Meshram, Valmik B Nikam, “Modelling Rainfall Prediction using Data Mining Method, A Bayesian Approach”, Fifth International Conference on Computational Intelligence, Modelling and Simulation,2013.
- Siddhart S Bhatkande, Roopa.G Hubballi, “Weather Prediction Based on Decision Tree Algorithm Using Data Mining Techniques”, International Journal of Advanced Research in Computer and Communication Engineering Vol.5, Issue 5, May 2016.
- M Ramzan Talib, Toseef Ullah, M Umer Sarwar, M Kashif Hanif and Nafees Ayub, “Application of Data Mining Techniques in Weather Data Analysis”, IJCSNS International Journal of Computer Science and Network Security, June2017.
- Jyothis Joseph, Ratheesh T K, “Rainfall Prediction using Data Mining Techniques”, International Journal of Computer Applications (0975 – 8887)Volume 83 – No 8, December 2013.