Published Paper Details:

The Gross Domestic Product (GDP) of a developing country like India significantly depends on agriculture and the associated industry namely agribusiness industry. These sectors are highly vulnerable with respect to extreme weather events (EWE). It is reported in various literatures that the frequency of EWEs has been increased in recent years over the globe which affects different sectors of agriculture and living beings. Therefore, it demands an accurate prediction prior to a season which would be helpful in this direction. Deep Learning (DL) and Machine Learning (ML) approaches have been popular in the field of prediction. However, it is also proved the performance of ML and DL models varies according to the data sets. In this project work, several ML and DL models such as Linear regression, Decision tree regression, Random Forest regressor, and Neural Network will be used for comparison of the performance in accurate prediction. For this purpose, temperature data of India at a monthly scale spanning over 1901-2015 considered for the analysis. Towards end of the project, the best model will be chosen and will be used for prediction of temperature at monthly scale. Further, significant effort will be given for the development of new strategy which can predict the extreme events.