Institute of Information Theory and Automation

You are here

Mini-Symposium MTR 2022


The department of Decision-Making Theory organizes a Mini-Symposium dedicated to three exceptional speakers: Manuel Herrera, Bruno Melo Brentan, and Ariele Zanfei. The Mini-Symposium is organized in a hybrid form. It is possible to participate either in person or connect virtually using the Zoom application.

The symposium will be held at UTIA, in Lecture hall No. 3 accessible from the lobby, on Thursday, March 17, 2022, starting at 14:00 CET.

14:00 - 15:00: Network modelling for infrastructure systems operation and management (Zoom Link)

Dr. Manuel Herrera (Senior Research Associate at the Institute for Manufacturing, University of Cambridge, United Kingdom) 

ABSTRACT - Infrastructure systems are fundamental for society's well-being, and economy, providing services as important as transport, water, energy, and internet, among others. Infrastructure systems management is a challenging task as it encompasses the analysis and synthesis of many individual assets interacting with one another for which it is true that “the whole is greater than the sum of its parts”. Consequently, infrastructure systems are complex systems and modelling them as a network plays a pivotal role for optimal infrastructure operation and management. This talk, then, revolves around the topic of network modelling and the number of different choices for network representation together with their corresponding implications on mining patterns both in network structure and dynamics. To this end, the traditional spatial network representation and analysis of an infrastructure system will be expanded to other views, such as those coming from multilayer networks and how this representation is able to find multiple aspects in a system for further analysis and a better informed decision-making support. Additional network views are found in the bipartite network representation of infrastructure systems and its 1-mode projections, allowing to particularly focus on network link analysis rather than node analysis; or to focus on both. The hypergraph network representation closes the talk; presenting multiscale solutions for complex network analysis as an emergent paradigm for infrastructure systems management. Examples on road, water and internet networks will illustrate each of the concepts introduced in the talk.

15:10 - 15:30 coffee break

15:30 - 16:30: Smarter management of water distribution systems: from complex network theory to optimal operation of control devices (Zoom link)

Prof. Bruno Melo Brentan (Assistant Professor at the Hydraulic Engineering and Water Resources Department of the Federal University of Minas Gerais, Brazil): 

ABSTRACT - Water distribution systems are dynamic and often require quick decisions from operators. In order to improve the effectiveness of those decisions, many computational and mathematical tools have been applied to model water systems. In this talk, we will do an overview regarding some applications of complex network theory, optimization tools, and decision-making theory tools for optimal management of water systems

16:30 - 17:00 coffee break

17:00 - 18:00 Potential of data for managing water distribution systems: water demand forecasting with graph neural networks (Zoom link)

Ing. Ariele Zanfei (PhD candidate at the Faculty of Science and Technology of the Free University of Bozen-Bolzano, Italy):

ABSTRACT - Sustainable management is the keyword for the future. The constant increase of water demands due to socio-economic factors and climate change are putting under an increasing strain on our distribution systems. In this condition, water management needs proper care to undertake a transition towards a smart and sustainable paradigm. The new era of Big data and artificial intelligence allows innovative ways to make water management more efficient. For instance, it is possible to develop reliable data-driven methods to predict water demands, to detect anomalies in the water systems, to find optimal locations for sensors, and much more. This talk is aimed at exploring the potential of using demand data for developing methodologies aimed at supporting the management of water networks, especially for forecasting purposes.

19:00 symposium dinner

2022-03-03 13:57