Annual mean temperature prediction of India using K-nearest neighbour technique

M. Mallika, S. Meenakshi Sundaram, M. Nirmala
2015 Applied Mathematical Sciences  
Weather can be defined as the condition of air on earth for a given time and at a given place. Weather prediction has been of great interest and a challenging task for researchers for so many years. To predict weather so many factors have to be considered like temperature, atmospheric pressure, humidity, wind pressure etc. In particular temperature prediction plays a vital role for planning in so many fields like agriculture, industry, climatic conditions and so on. Various statistical and
more » ... tational methods are applied for temperature prediction so far and literature survey shows that machine learning methods outperformed the standard traditional methods. In this paper, one of the machine learning algorithm K-Nearest Neighbour algorithm (KNN) is applied for predicting annual mean temperature of India based on the annual maximum and annual minimum temperatures of India. The proposed model predicts annual mean temperature and the findings are compared using the error measure MAPE.
doi:10.12988/ams.2015.411953 fatcat:ekvts6as4zfmhh4jgd7f56olhu