Machine Learning in the Climatic Database: Support Vector Machine’s Algorithm to Map Environmental Events in Months of the Year

• Gilvandro de Medeiros UFRN
• Orivaldo de Santana Junior UFRN
• John Luiz UFRN

DOI: https://doi.org/10.5753/epoca.2018.13454

Resumo

With the dissemination of Artificial Intelligence (AI), it becomes common the application of machine learning algorithms (ML) to model and solve problems. In this context, we intend to validate the performance of the ML Vector Support Machine (SVM) algorithm using a public climatic database for the city of Natal. The methodology for this consisted of using the data of said base to train and test the algorithm, placing the information referring to the month of the year in function of the other variables of a given climatic event. Once validated, it is considered promising to deepen the study and application of computational intelligence for meteorological and environmental purposes.

Referências

Duda, R. O., Hart, P. E. and Stork, D. G. (2000) “Pattern Classification”, ed. 2, New York: Wiley-Interscience.

GOVERNO FEDERAL; Sistema de Monitoramento Agrometeorologico. (2018) “Estatísticas”, www.agritempo.gov.br, August.

Negnevitsky, M. (2011) “Artificial Intelligence: A Guide to Intelligent Systems”, ed. 3, Canada: Pearson Education.

Géron, A. (2017) “Hands-On Machine Learning with Scikit-Learn and TensorFlow”, ed. 1, USA.

Parmar, Aakash & Mistree, Kinjal & Sompura, Mithila. (2017). Machine Learning Techniques For Rainfall Prediction: A Review.