Prof. Dr. Emmanuel Müller

Erik Scharwächter

PhD student
Knowledge Discovery and Data Mining (HPI)

Research associate
GFZ Potsdam


Contact Information

Email: erik.scharwaechter(at)hpi.de
Tel: +49 331 5509 1383
Office: E 1-02.3

Research Interests

  • Methods: Event, change and anomaly detection, Time series analysis, Network analysis
  • Data: Earth observation data, Human mobility and communication data, Social networks
  • Applications: Disaster response, Natural hazards, Big data for development

Event impacts on time series

Due to the ubiquitous collection of data over time, important events like natural disasters, financial crises, or mass displacements of people often leave traces in environmental, economic, or other time series. Anomalies, extreme values, and significant changes in these time series can indicate the occurrence of such events. Hence, a lot of research focuses on detecting unusual patterns in time series to improve our understanding of the underlying systems and enable early warning systems. However, there is little agreement on how to precisely quantify the effect of discrete events on continuous time series in an interpretable way. In this project, we aim at filling this gap by exploring novel methods to correlate time series with event series.

As part of this project, we participated in the Data for Climate Action Challenge held by UN Global Pulse in 2017 with our submission "How natural disasters resonate across the globe: a study on social media activity." We used Twitter data kindly provided by Crimson Hexagon and natural disaster data from EMDAT to analyze how disasters in different regions of the world trigger social media reactions in other parts of the world. More details coming soon.

Monitoring correlations in massive time series collections

The observation of urban, societal and environmental variables like air pollution level, mobile phone activity, or tropical vegetation cover through various sensors allows to detect interesting, unusual events in near real-time. In this project, novel approaches to capture and analyze complex dynamics within massive collections of time series of such sensor readings are explored to reveal anomalous events and interesting patterns. A special focus is put on dynamics in the correlation structure of time series as well as the different spatial scales of events—ranging from small events with localized impacts to massive events that lead to global anomalies. The project combines methods from anomaly detection, clustering and correlation tracking. [COREQ]

Evolution of dynamic networks

Complex networks like social networks are ever-changing. New links are formed, existing ties are broken, individuals change their attitudes. In this project, we aim at microscopic descriptions of the processes that govern network evolution by mining frequently occurring graph evolution rules. These rules formally characterize the evolution of a dynamic network, help domain experts analyze the underlying processes, and allow to build data-driven models for friendship and opinion dynamics. In collaboration with COPAN@Potsdam Institute for Climate Impact Research. [EvoMine]

Short CV

External reviewer at KDD [2017-2018], CIKM [2016-2017], SDM [2018], ICDE [2018], IJCAI [2018], ExploreDB [2017].

[since 2016] PhD student at Hasso Plattner Institute and Research Associate at GFZ Potsdam
[2015-2016] Guest at Potsdam Institute for Climate Impact Research
[2014] Exchange student at Indian Institute of Technology Guwahati
[2013] Research assistant at Qatar Computing Research Institute, Doha
[2008-2016] BSc/MSc in Computer Science at RWTH Aachen University


Open master theses

Teaching assistant

  • Big Data Analytics, Lab (SS 2016, SS 2017)
  • Big Data Analytics, Lecture (WS 2015, WS 2016)
  • Smart Representations for Big Data Analytics, Seminar (SS 2017)


  • Erik Scharwächter, Fabian Geier, Lukas Faber, Emmanuel Müller. Low Redundancy Estimation of Correlation Matrices for Time Series using Triangular Bounds. In: Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018. (in press) (website)
  • Erik Scharwächter, Emmanuel Müller, Jonathan Donges, Marwan Hassani, Thomas Seidl. Detecting Change Processes in Dynamic Networks by Frequent Graph Evolution Rule Mining. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), 2016. (pdf) (slides) (website)
  • Erik Scharwächter, Stephan Vogel. Solving substitution ciphers for OCR with a semi-
    supervised Hidden Markov Model.
    In: Proceedings of the 13th IEEE International Conference on
    Document Analysis and Recognition (ICDAR)
    , 2015. (pdf) (slides)
  • Matthias Huck, Erik Scharwächter, Hermann Ney. Source-Side Discontinuous Phrases for
    Machine Translation: A Comparative Study on Phrase Extraction and Search.
    In: The Prague
    Bulletin of Mathematical Linguistics
    , No. 99, 2013, pp. 17–38. (pdf)

Click here for a list of my publications on DBLP.