Abstract
Abstract. Today, many processes at the Earth's surface are constantly monitored by multiple data streams. These observations have become central to advancing our understanding of vegetation dynamics in response to climate or land use change. Another set of important applications is monitoring effects of extreme climatic events, other disturbances such as fires, or abrupt land transitions. One important methodological question is how to reliably detect anomalies in an automated and generic way within multivariate data streams, which typically vary seasonally and are interconnected across variables. Although many algorithms have been proposed for detecting anomalies in multivariate data, only a few have been investigated in the context of Earth system science applications. In this study, we systematically combine and compare feature extraction and anomaly detection algorithms for detecting anomalous events. Our aim is to identify suitable workflows for automatically detecting anomalous patterns in multivariate Earth system data streams. We rely on artificial data that mimic typical properties and anomalies in multivariate spatiotemporal Earth observations like sudden changes in basic characteristics of time series such as the sample mean, the variance, changes in the cycle amplitude, and trends. This artificial experiment is needed as there is no gold standard for the identification of anomalies in real Earth observations. Our results show that a well-chosen feature extraction step (e.g., subtracting seasonal cycles, or dimensionality reduction) is more important than the choice of a particular anomaly detection algorithm. Nevertheless, we identify three detection algorithms (k-nearest neighbors mean distance, kernel density estimation, a recurrence approach) and their combinations (ensembles) that outperform other multivariate approaches as well as univariate extreme-event detection methods. Our results therefore provide an effective workflow to automatically detect anomalies in Earth system science data.
Highlights
The Earth system can be conceptualized as a system of highly interconnected subsystems
One matter of concern is changes in hydrometeorological extremes that may translate into anomalies in vegetation dynamics, or extremes in vegetation dynamics that might result from slight changes in climatological conditions or human intervention and that can have severe consequences for vegetation and the carbon cycle (Easterling et al, 2000; Meehl and Tebaldi, 2004; Seneviratne et al, 2012; Reichstein et al, 2013)
As the number of possible combinations is considerably large, we focus here on dimensionality reduction techniques (ICA, Principal component analysis (PCA)) combined with some Exponentially weighted moving average (EWMA) to reduce the noise level afterwards
Summary
The Earth system can be conceptualized as a system of highly interconnected subsystems (e.g., atmosphere, biosphere, hydrosphere, lithosphere). Each of these subsystems can be monitored and characterized by multiple variables. One key scientific challenge is co-interpreting these multiple views of the Earth system, in particular to address the impacts of changes in the climate system, the land use system, and other transformations. Apart from natural events, one aims to detect events that are a direct consequence of human interference, e.g., detecting deforestation activities is required to assess the compliance with laws or agreements on forest conservation and climate change
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
