Welcome to our research group's homepage!

If you have ever wondered how innovations in Computer Science and Information Technology can help combat some of the grave water sustainability challenges our society faces today, then you have come to the right place!!

 

We conduct interdisciplinary, computational research in the field of Hydroinformatics to develop innovative and effective solutions for sustainable planning and management of water-based systems. Hydroinformatics is a relatively new area of research that combines simulation and decision-making models with information and communication technologies to help solve challenging water management problems in hydraulics, hydrology and environmental engineering. Water-based systems, by nature, are extremely complex, dynamic, uncertain, ill-defined, non-linear, and constitute multidimensional interactions between natural, man-made, and human/social systems. By using a wide variety of digital technologies for data gathering, data analyses, and data modeling, the field of Hydroinformatics provides a unique opportunity to address these challenges in management of water-based systems.

 

In our group, we create innovations in a wide variety of Hydroinformatics approaches, including computational modeling of complex water-based systems, multi-objective optimization, interactive optimization, noisy optimization, evolutionary computing, multi-agent models, Markov decision processes, neural networks, human-computer interaction, data assimilation, high performance computing, etc. These innovations help us solve a variety of problems, such as:

  1. How can communities collaborate via web-based technologies to plan and design conservation practices or green stormwater practices on their landscape?
  2. How can high performance computing and optimization algorithms be used to design short term and long term watershed adaptation alternatives, for communities combatting flooding, droughts, and/or water quality impacts due to changing climate and anthropogenic drivers?
  3. How can observations from different types of sensors (e.g., in-situ instruments, satellites, and unmanned aerial systems (UASs), etc.) be used to improve data assimilation in water quality models?
  4. What types of data-driven, machine learning models are useful for simulating complex water systems when we don't know the exact mechanistic process in the system?