“Time series networks are one way to extract patterns from data of very big volume or great variety. Artificial Intelligence is generating data in new forms of complexity, leading to the new era of big data”, says Kurths. “Advanced interdisciplinary data analysis techniques can help to capture the hidden structures in the midst of otherwise chaotic data points, including approaches from machine learning, data mining, statistics, language and text processing. In consequence, we transform the chaotic data sets into something comprehensible, which allows us making better and faster decisions.” The combination of network and time series analysis complements existing approaches and allows a more reliable understanding of causal interactions in the climate system, the detection of tipping points and early warning signals in a changing world, or the prediction of El Niño events.
The Potsdam Institute aims at increasing the use of artificial intelligence to analyze big data in order to better understand how climate impacts hit people on the ground, and how the latter react to such shocks. This could help to better protect the public from such risks in the future.
Article: Yong Zou, Reik V. Donner, Norbert Marwan, Jonathan F. Donges, Jürgen Kurths (2019): Complex network approaches to nonlinear time series analysis. Physics Reports 787 [DOI: /10.1016/j.physrep.2018.10.005]
Weblink to the paper: https://doi.org/10.1016/j.physrep.2018.10.005
