Publications

Understanding Changes in Environmental Time Series with Time-frequency Causality Analysis
Maha Shadaydeh and Yanira Guanche Garcia and Miguel Mahecha and Joachim Denzler.
European Geosciences Union General Assembly (EGU): Abstract + Poster Presentation. 2020.
[bibtex] [pdf] [web] [abstract]

Abstract: Understanding causal effect relationships between the different variables in dynamical systems is an important and challenging problem in different areas of research such as attribution of climate change, brain neural connectivity analysis, psychology, among many others. These relationships are guided by the process generating them. Hence, detecting changes or new patterns in the causal effect relationships can be used not only for the detection but also for the diagnosis and attribution of changes in the underlying process.Time series of environmental time series most often contain multiple periodical components, e.g. daily and seasonal cycles, induced by the meteorological forcing variables. This can significantly mask the underlying endogenous causality structure when using time-domain analysis and therefore results in several spurious links. Filtering these periodic components as preprocessing step might degrade causal inference. This motivates the use of time-frequency processing techniques such as Wavelet or short-time Fourier transform where the causality structure can be examined at each frequency component and on multiple time scales.In this study, we use a parametric time-frequency representation of vector autoregressive Granger causality for causal inference. We first show that causal inference using time-frequency domain analysis outperforms time-domain analysis when dealing with time series that contain periodic components, trends, or noise. The proposed approach allows for the estimation of the causal effect interaction between each pair of variables in the system on multiple time scales and hence for excluding links that result from periodic components.Second, we investigate whether anomalous events can be identified based on the observed changes in causal relationships. We consider two representative examples in environmental systems: land-atmosphere ecosystem and marine climate. Through these two examples, we show that an anomalous event can indeed be identified as the event where the causal intensities differ according to a distance measure from the average causal intensities. Two different methods are used for testing the statistical significance of the causal-effect intensity at each frequency component.Once the anomalous event is detected, the driver of the event can be identified based on the analysis of changes in the obtained causal effect relationships during the time duration of the event and consequently provide an explanation of the detected anomalous event. Current research efforts are directed towards the extension of this work by using nonlinear state-space models, both statistical and deep learning-based ones.

Attribution of Multivariate Extreme Events
Yanira Guanche and Maha Shadaydeh and Miguel Mahecha and Joachim Denzler.
International Workshop on Climate Informatics (CI). 2019.
[bibtex] [pdf] [abstract]

Time-Frequency Causal Inference Uncovers Anomalous Events in Environmental Systems
Maha Shadaydeh and Joachim Denzler and Yanira Guanche Garcia and Miguel Mahecha.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 499-512. 2019.
[bibtex] [pdf] [abstract]

Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
Björn Barz and Erik Rodner and Yanira Guanche Garcia and Joachim Denzler.
IEEE Transactions on Pattern Analysis and Machine Intelligence. 41 (5): pages 1088-1101. 2019. (Pre-print published in 2018.)
[bibtex] [pdf] [web] [code] [abstract]

Analyzing the Time Variant Causality in Ecological Time Series: A Time-Frequency Approach
Maha Shadaydeh and Yanira Guanche Garcia and Miguel Mahecha and Markus Reichstein and Joachim Denzler.
International Conference on Ecological Informatics (ICEI). Pages 151-152. 2018.
[bibtex] [abstract]

Abstract: Attribution in ecosystems aims to identify the cause-effect relationships between the variables involved. The availability of high temporal resolution data along with the powerful computing platforms further enhance the capacity of data-driven methods in capturing the complex relationships between the variables of the underlying system. Time series of ecological variables most often contain different periodical components that can significantly mask the underling causality structure in time domain. This motivates the use of time-frequency processing techniques such as wavelet analysis or short time Fourier transform. In this study we present a time-frequency approach for causality analysis where the coupling between the variables is assumed to follow a locally time-invariant multivariate autoregressive (MVAR) model. We propose a sliding time window approach to examine the change of interactions, i.e. direction and strength of causality, between the different variables over seasons. The cause-effect relationships are extracted using the frequency domain representation of the MVAR Granger causality (MVAR-GC) [1,2] based on the generalized partial directed coherence (gPDC) [3]. We have first applied the proposed method to synthetic data to evaluate its sensitivity to different issues such as the selection of the model order, the sampling frequency, the absence of cause as well as the presence of non-linear coupling. The method is then applied to half-hourly meteorological observations and land flux eddy covariance data to investigate the causal-effect relationships between global radiation (Rg), air temperature (Tair), and the CO2 land fluxes: gross primary productivity (GPP), net ecosystem exchange (NEE) and ecosystem respiration (Reco). The results show that time-frequency analysis based on MVAR-GC has promising potential in identifying the time variant causality structure within these variables along with the main time delay between different cause- effect pairs. Further research work is currently going for the investigation of the selection criteria of the model order, the sampling frequency, and the size of the time window at different time scales of causality analysis. This study is carried out within the framework of the project BACI which in part aims at developing an attribution scheme for changes in ecosystem functioning and studying the impacts of these changes on biodiversity patterns.

Extreme anomaly event detection in biosphere using linear regression and a spatiotemporal MRF model
Yanira Guanche Garcia and Maha Shadaydeh and Miguel Mahecha and Joachim Denzler.
Natural Hazards. pages 1-19. 2018.
[bibtex] [pdf] [web] [abstract]

Abstract: Detecting abnormal events within time series is crucial for analyzing and understanding the dynamics of the system in many research areas. In this paper, we propose a methodology to detect these anomalies in multivariate environmental data. Five biosphere variables from a preliminary version of the Earth System Data Cube have been used in this study: Gross Primary Productivity, Latent Energy, Net Ecosystem Exchange, Sensible Heat and Terrestrial Ecosystem Respiration. To tackle the spatiotemporal dependencies of the biosphere variables, the proposed methodology after preprocessing the data is divided into two steps: a feature extraction step applied to each time series in the grid independently, followed by a spatiotemporal event detection step applied to the obtained novelty scores over the entire study area. The first step is based on the assumption that the time series of each variable can be represented by an autoregressive moving average (ARMA) process, and the anomalies are those time instances that are not well represented by the estimated ARMA model. The Mahalanobis distance of the ARMA models multivariate residuals is used as a novelty score. In the second step, the obtained novelty scores of the entire study are treated as time series of images. Markov random fields (MRFs) provide an effective and theoretically well-established methodology for integrating spatiotemporal dependency into the classification of image time series. In this study, the classification of the novelty score images into three classes, intense anomaly, possible anomaly, and normal, is performed using unsupervised K-means clustering followed by multi-temporal MRF segmentation applied recursively on the images of each consecutive \(L \ge \) 1 time steps. The proposed methodology was applied to an area covering Europe and Africa. Experimental results and validation based on known historic events show that the method is able to detect historic events and also provides a useful tool to define sensitive regions.

Classification of Spatiotemporal Marine Climate Patterns using Wavelet Coherence and Markov Random Field
Maha Shadaydeh and Yanira Guanche Garcia and Joachim Denzler.
American Geophysical Union Fall Meeting (AGU): Abstract + Oral Presentation. 2018.
[bibtex] [web] [abstract]

Abstract: Sea condition characterization and classification is a widely studied topic but rather challenging one due to the spatial and temporal variability in marine climate. The aim of this study is to develop a data-driven method for the classification of marine climate patterns. The proposed method consists of two main steps: i) Feature extraction applied to the time series of each point of the grid independently. ii) Spatiotemporal classification applied on the obtained features over the entire study area. The causal intensity between coupled marine variables can be efficiently visualized at different time-scales using wavelet coherence. To this end, we extract a set of features from the statistically significant wavelet coherence of each pair of the used marine variables: significant wave height (hs), mean wave period (Tm), and wave direction (m). The obtained features, in addition to the sea level pressure (SLP), over the entire study area are then treated as multi-channel images. For the spatiotemporal classification of these images, we first apply the unsupervised K-means clustering method on the images of each three consecutive time instances. The K clusters represent K different marine climate patterns. Markov Random Fields (MRFs) provide an effective methodology for integrating spatiotemporal dependency between adjacent points into the image classification process. In this study, we use a MRF model for defining the spatiotemporal extent of the detected marine climate patterns, with the statistics of the detected K clusters used for the initial training. Experimental results show that the proposed method allows for a practical classification of marine climate into representative patterns that can be used for an accurate characterization of sea conditions, the analysis of extreme events and its impacts along the coast. A case study in the North Sea will be presented using the coasDat dataset [1]. [1] Weisse, R., H. v. Storch, U. Callies, A. Chrastansky, F. Feser, I. Grabemann, H. Guenther, A. Pluess, Th. Stoye, J. Tellkamp, J. Winterfeldt and K. Woth, (2008): Regional meteo-marine reanalyses and climate change projections: Results for Northern Europe and potentials for coastal and offshore applications. Bull. Amer. Meteor. Soc., 90, 849-860.

BACI: Towards a Biosphere Atmosphere Change Index - Detection of Extreme Events in the Biosphere
Yanira Guanche Garcia and Maha Shadaydeh and Miguel Mahecha and Markus Reichstein and Joachim Denzler.
BigSkyEarth Conference: AstroGeoInformatics. 2018.
[bibtex] [pdf] [web]

Causality analysis of ecological time series: a time-frequency approach
Maha Shadaydeh and Yanira Guanche Garcia and Miguel Mahecha and Markus Reichstein and Joachim Denzler.
International Workshop on Climate Informatics (CI). 2018.
[bibtex] [pdf]

Multivariate anomaly detection for Earth observations: a comparison of algorithms and feature extraction techniques
Milan Flach and Fabian Gans and Alexander Brenning and Joachim Denzler and Markus Reichstein and Erik Rodner and Sebastian Bathiany and Paul Bodesheim and Yanira Guanche and Sebasitan Sippel and Miguel D. Mahecha.
Earth System Dynamics. 8 (3): pages 677-696. 2017.
[bibtex] [pdf] [web] [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.

Biosphere Anomalies Detection by Regression Models
Yanira Guanche and Maha Shadaydeh and Miguel Mahecha and Joachim Denzler.
Conference on Advances in Extreme Value Analysis and Application to Natural Hazards (EVAN). 2017.
[bibtex] [pdf]

Maximally Divergent Intervals for Extreme Weather Event Detection
Björn Barz and Yanira Guanche and Erik Rodner and Joachim Denzler.
MTS/IEEE OCEANS Conference Aberdeen. Pages 1-9. 2017.
[bibtex] [pdf] [abstract]

Modelling ocean parameters through Graphical Models
Felix Schneider and Yanira Guanche and Joachim Denzler.
MTS/IEEE OCEANS Conference Aberdeen. Pages 1-6. 2017.
[bibtex] [pdf]

Using Statistical Process Control for detecting anomalies in multivariate spatiotemporal Earth Observations
Milan Flach and Miguel Mahecha and Fabian Gans and Erik Rodner and Paul Bodesheim and Yanira Guanche-Garcia and Alexander Brenning and Joachim Denzler and Markus Reichstein.
European Geosciences Union General Assembly (EGU): Abstract + Oral Presentation. 2016.
[bibtex] [pdf] [web] [abstract]

Abstract: The number of available Earth observations (EOs) is currently substantially increasing. Detecting anomalous pat-terns in these multivariate time series is an important step in identifying changes in the underlying dynamicalsystem. Likewise, data quality issues might result in anomalous multivariate data constellations and have to beidentified before corrupting subsequent analyses. In industrial application a common strategy is to monitor pro-duction chains with several sensors coupled to some statistical process control (SPC) algorithm. The basic ideais to raise an alarm when these sensor data depict some anomalous pattern according to the SPC, i.e. the produc-tion chain is considered out of control. In fact, the industrial applications are conceptually similar to the on-linemonitoring of EOs. However, algorithms used in the context of SPC or process monitoring are rarely consideredfor supervising multivariate spatio-temporal Earth observations. The objective of this study is to exploit the poten-tial and transferability of SPC concepts to Earth system applications. We compare a range of different algorithmstypically applied by SPC systems and evaluate their capability to detect e.g. known extreme events in land sur-face processes. Specifically two main issues are addressed: (1) identifying the most suitable combination of datapre-processing and detection algorithm for a specific type of event and (2) analyzing the limits of the individual ap-proaches with respect to the magnitude, spatio-temporal size of the event as well as the datas signal to noise ratio.Extensive artificial data sets that represent the typical properties of Earth observations are used in this study. Ourresults show that the majority of the algorithms used can be considered for the detection of multivariate spatiotem-poral events and directly transferred to real Earth observation data as currently assembled in different projectsat the European scale, e.g. http://baci-h2020.eu/index.php/ and http://earthsystemdatacube.net/. Known anomaliessuch as the Russian heatwave are detected as well as anomalies which are not detectable with univariate methods.

Detecting Multivariate Biosphere Extremes
Yanira Guanche Garcia and Erik Rodner and Milan Flach and Sebastian Sippel and Miguel Mahecha and Joachim Denzler.
International Workshop on Climate Informatics (CI). Pages 9-12. 2016.
[bibtex] [web] [abstract]

Hot spots of multivariate extreme anomalies in Earth observations
Milan Flach and Sebastian Sippel and Paul Bodesheim and Alexander Brenning and Joachim Denzler and Fabian Gans and Yanira Guanche and Markus Reichstein and Erik Rodner and Miguel D. Mahecha.
American Geophysical Union Fall Meeting (AGU): Abstract + Oral Presentation. 2016.
[bibtex] [web] [abstract]

Maximally Divergent Intervals for Anomaly Detection
Erik Rodner and Björn Barz and Yanira Guanche and Milan Flach and Miguel Mahecha and Paul Bodesheim and Markus Reichstein and Joachim Denzler.
Workshop on Anomaly Detection (ICML-WS). 2016. Best Paper Award
[bibtex] [pdf] [web] [code] [abstract]

Closure of discussion: Point-in-time and extreme-value probability simulation technique for engineering design
Roberto Minguez and Yanira Guanche and Fernando J. Mendez.
Structural Safety. pages 5-7. 2014.
[bibtex] [abstract]

A methodology for deriving extreme nearshore sea conditions for structural design and flood risk analysis
Ben Gouldby and Fernando J. Mendez and Yanira Guanche and Ana Rueda and Roberto Minguez.
Coastal Engineering. pages 15-26. 2014.
[bibtex] [abstract]

A method for finding the optimal predictor indices for local wave climate conditions
Paula Camus and Fernando J. Mendez and Inigo J. Losada and Melisa Menendez and Antonio Espejo and Jorge Perez and Ana Rueda and Yanira Guanche.
Ocean Dynamics. pages 1025-1038. 2014.
[bibtex] [abstract]

Autoregressive logistic regression applied to atmospheric circulation patterns
Yanira Guanche and Roberto Minguez and Fernando J. Mendez.
Climate Dynamics. 42 (1): pages 537-552. 2013.
[bibtex] [abstract]

A simplified method to downscale wave dynamics on vertical breakwaters
Yanira Guanche and Paula Camus and Raul Guanche and Fernando J. Mendez and Raul Medina.
Coastal Engineering. 71: pages 68-77. 2013.
[bibtex] [abstract]

Abstract: A coastal structure is usually designed with the final objective to guarantee its functionality and stability throughout its life cycle. Regarding stability, the three main failure modes are sliding, overturning and failure of the foundations. To accomplish the design objectives, a design sea state is usually used when calculating the loads and scour around the structure. This design sea state corresponds to a certain sea state with specific return period values of a significant wave height. However, the combination of different simultaneous sea state parameters can produce other critical situations compromising the stability of the structure which then require the calculation of long time series of wave forces corresponding to long-term historical wave situations. Moreover, a design force associated to a certain return period can be defined from the time series of the stability parameters. The most accurate techniques which can be used to estimate structure stability are based on numerical and physical models, but these are very time consuming and the calculation of long time series is therefore unfeasible. Here, we propose a hybrid methodology to transform wave conditions into wave forces acting upon vertical structures and scour around it. The methodology consists of a selection of a subset of sea states representative of wave climate at the structure location, using a maximum dissimilarity algorithm, The wave forces acting upon the structure and scour around it, for the wave situations selected, are then estimated as is the reconstruction of the calculated parameters corresponding to historical sea states using an interpolation technique based on radial basis function. The validation of the results, through a direct comparison between reconstructed series and analytically (semi-empirical formulations) calculated ones, confirms the ability of the developed methodology to reconstruct time series of stability parameters on vertical breakwaters. This methodology allows its application to numerical and physical models.

Climate-based Monte Carlo simulation of trivariate sea states
Yanira Guanche and Roberto Minguez and Fernando J. Mendez.
Coastal Engineering. 80: pages 107-121. 2013.
[bibtex] [abstract]

Point-in-time and extreme-value probability simulation technique for engineering design
Roberto Minguez and Yanira Guanche and Fernando J. Mendez.
Structural Safety. 41: pages 29-36. 2013.
[bibtex] [abstract]

Numerical simulation of three-dimensional breaking waves on a gravel slope using a two-phase flow NavierStokes model
Pablo Higuera and Manuel Jesus and Javier L. Lara and Inigo J. Losada and Yanira Guanche and Gabriel Barajas.
Journal of Computational and Applied Mathematics. 246: pages 144-152. 2013.
[bibtex] [abstract]

A multivariate approach to estimate design loads for offshore wind turbines
Yanira Guanche and Raul Guanche and Paula Camus and Fernando J. Mendez and Raul Medina.
Wind Energy. 16 (7): pages 1091-1106. 2012.
[bibtex] [abstract]

Abstract: The design of offshore wind farms is a complex process that requires a detailed study of the oceanographic, meteorological and geotechnical conditions at the site. The structure and all structural members shall be designed in a way that they can be resistant against different kinks of loads: permanent, variable, environmental, accidental and deformations. This paper is focused on those called environmental loads. The main environmental conditions that may contribute to structural damage, operational disturbances or other failures are wind, waves, currents and sea ice. Thus, the combination of the different parameters may produce many different critical situations for the integrity of the structure, requiring the calculation of long time series corresponding to long-term historical data situations. The most accurate techniques available at the moment to estimate loads acting upon a structure are numerical and physical models; however, they are very time consuming, and the calculation of long time series of data is unfeasible. Therefore, a new hybrid methodology to select waveswindcurrent representative conditions that allow the interpolation of long time series of forces on a wind turbine is proposed. The methodology consists of a selection of a subset of representative cases of wavewindcurrent climate at the structure's location by using a maximum dissimilarity algorithm, then estimating loads acting upon the structure for the seawind states selected and the reconstruction of loads corresponding to historical data using an interpolation technique based on radial basis function. To validate the proposed methodology and because of there is no availability of long time records of loads on wind turbines, the well-known IEC 614003 has been applied to estimate the loads for the complete reanalysis time series of waves, winds and currents. The validation of the results confirms the ability of the methodology developed to reconstruct time series of forces on the structure on the basis of the previously selected cases. This methodology permits application of numerical and physical models to offshore wind farm design, considerably reducing the number of tests or simulations. Copyright 2012 John Wiley & Sons, Ltd.