• K V S Krishna Praneeth
• Ishan Jha
• Siddhartha Gupta
• Merin Meleet

Weather forecasting plays an integral role in our daily lives and influences a wide array of activities. This paper presents a survey on the various statistical approaches to weather prediction. The need for this methodology is governed by the instability and high cost associated with the physical model. A comparative study is performed and the aptness of each model is discussed. Various environmental parameters such as temperature, rainfall, humidity are evaluated with the help of these models. Among the existing machine learning techniques, prominent techniques such as Linear and Functional Regression, Artificial Neural Networks and Support Vector Machines are analysed. The results show that the models compare well against the numerical models and the efficacy of the Support Vector Machines and Neural Networks exceeds that of Regression models.

Functional Regression, Linear Regression, Neural Networks, Numerical Weather prediction, Statistical Learning Theory, Support Vector Machines, Weather Forecasting

"Comparative Study of Machine Learning Models in Weather Forecasting", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.519-523, May-2019, Available :http://www.jetir.org/papers/JETIR1905F78.pdf

"Comparative Study of Machine Learning Models in Weather Forecasting", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp519-523, May-2019, Available at : http://www.jetir.org/papers/JETIR1905F78.pdf