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

Abstract

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 computational 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.

Evaluation of Historical CMIP6 Model Simulations of Seasonal Mean Temperature over Pakistan during 1970–2014

“…The nearest neighbor interpolation allowed better classification of similar close points by weighted average using data triangulation [43]. The land surfaces, particularly hilly terrains, were better interpolated due to sub-regionalization of grid points by the nearest cell center of an input grid [44]. The multi-model ensemble (MM-Ensemble) was created by simple averaging of regridded models for each season, i.e., summer and winter seasons; MM-Ensemble was preferred and believed to contain information from all models [45].…”

Evaluation and projection of mean surface temperature using CMIP6 models over East Africa

“…The standardized datasets were then re-gridded to a common grid of lowest model resolution by utilizing the nearest neighbor interpolation technique. The aforementioned technique interpolation follows the better classification of diverse geography by triangulating nearest points and sub-regionalization of grid points by the nearest cell center of input grids (Mallika et al, 2015;Vermeulen et al, 2017).…”

Future Changes in Seasonal Temperature Over Pakistan in CMIP6

“…Since all models had varying horizontal resolutions, they were regridded to a common grid of 1.4°×1.4° using the nearest neighbor interpolation technique (Vermeulen et al, 2017). This approach gives a good representation of hilly terrain (Mallika et al, 2015).…”