Classifying El Ni & x00F1;o-Southern Oscillation Combining Network Science and Machine Learning

Author(s)

De Castro Santos, Matheus A. ^[1] ; Vega-Oliveros, Didier A. ^{[2, 3]} ; Zhao, Liang ^[3] ; Berton, Lilian ^[1]

Affiliation

^[1] Univ Fed Sao Paulo, Inst Sci & Technol, BR-12247014 Sao Jose Dos Campos - Brazil

^[2] Indiana Univ, Sch Informat Comp & Engn, Bloomington, IN 47408 - USA

^[3] Univ Sao Paulo, Fac Philosophy Sci & Letters Ribeirao Preto FFCLR, BR-14040901 Ribeirao Preto - Brazil

• Document type: Journal article
• Source: IEEE ACCESS; v. 8, p. 55711-55723, 2020.
• Web of Science Citations: 0

Abstract

Machine learning and complex network theory have emerged as crucial tools to extract meaningful information from big data, especially those related to complex systems. In this work, we aim to combine them to analyze El Ni \& x00F1;o Southern Oscillation (ENSO) phases. This non-linear phenomenon consists of anomalous (de)increase of temperature at the tropical Pacific Ocean, which has irregular occurrence and causes climatic variability worldwide. We construct temporal Climate Networks from the Surface Air Temperature time-series and calculate network metrics to characterize the warm and cold ENSO episodes. The metrics are used as topological features for classification. We employ ten classifiers and achieved 80 \& x0025; AUC ROC when predicting the intensity of Strong/ Weak El Ni \& x00F1;o and Strong/Weak La Ni \& x00F1;a for the next season. The complex network represents the relationship among different regions of the planet and machine learning creates models to classify the different classes of ENSO. This work opens new paths of research by integrating network science and machine learning to analyze complex data like global climate systems. (AU)

• FAPESP's process: 18/01722-3 - Semi-supervised learning via complex networks: network construction, selection and propagation of labels and applications
• Grantee: Lilian Berton
• Support Opportunities: Regular Research Grants
• FAPESP's process: 18/24260-5 - Spatiotemporal Data Analytics based on Complex Networks
• Grantee: Didier Augusto Vega Oliveros
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor
• FAPESP's process: 16/23698-1 - Dynamical Processes in Complex Network based on Machine Learning
• Grantee: Didier Augusto Vega Oliveros
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 15/50122-0 - Dynamic phenomena in complex networks: basics and applications
• Grantee: Elbert Einstein Nehrer Macau
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 18/04029-7 - Analysis of the relationships between the El Niño phenomenon and climatological variables using complex networks
• Grantee: Matheus Augusto de Castro Santos
• Support Opportunities: Scholarships in Brazil - Scientific Initiation