A Prediction of Precipitation Data Based on Support Vector Machine and Particle Swarm Optimization (PSO-SVM) Algorithms

• Published in: Algorithms Vol. 10; no. 2; p. 57
• Main Authors: Du, Jinglin, Liu, Yayun, Yu, Yanan, Yan, Weilan
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2017
• Subjects: Accuracy; Algorithms; Atmospheric models; Computer simulation; Dependent variables; Impact prediction; Machine learning; Particle swarm optimization; Precipitation; precipitation prediction; Rain; Rainfall; support vector machine; Support vector machines; Task complexity; Weather; Wind speed
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a10020057

Precipitation is a very important topic in weather forecasts. Weather forecasts, especially precipitation prediction, poses complex tasks because they depend on various parameters to predict the dependent variables like temperature, humidity, wind speed and direction, which are changing from time to time and weather calculation varies with the geographical location along with its atmospheric variables. To improve the prediction accuracy of precipitation, this context proposes a prediction model for rainfall forecast based on Support Vector Machine with Particle Swarm Optimization (PSO-SVM) to replace the linear threshold used in traditional precipitation. Parameter selection has a critical impact on the predictive accuracy of SVM, and PSO is proposed to find the optimal parameters for SVM. The PSO-SVM algorithm was used for the training of a model by using the historical data for precipitation prediction, which can be useful information and used by people of all walks of life in making wise and intelligent decisions. The simulations demonstrate that prediction models indicate that the performance of the proposed algorithm has much better accuracy than the direct prediction model based on a set of experimental data if other things are equal. On the other hand, simulation results demonstrate the effectiveness and advantages of the SVM-PSO model used in machine learning and further promises the scope for improvement as more and more relevant attributes can be used in predicting the dependent variables.