Fernworthy Reservoir, Dartmoor Forest, West Devon District

AISB2013 Symposium: Machine Learning in Water Systems


Part of:
AISB Annual Convention 2013
University of Exeter, UK
April 2nd-5th 2013

The convention is organised by the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB).

Themes of the symposium

The symposium seeks to bring together computer scientists, hydrologists, water engineers, and environmental scientists, to explore the key issues governing the successful application of machine learning (e.g. data-driven models and optimisation techniques) to water systems.

Papers are invited that explore issues of model and/or optimisation strategy design, selection and application, particularly those that investigate one or more of the following issues within the context of water systems:

  • Water system knowledge requirements for model development
  • Choice of machine learning and/or data-driven modelling technique:
    ANN, SVM, SOM, BBN, RBF, GP, ANFIS, Model/Decision Tree, CA etc
  • Choice of learning/optimisation process:
    GA/EA, PSO, ACO, gradient-descent-based, backpropagation etc
  • Machine learning innovations as applied to water systems
  • Novel combinations of techniques to solve real-world water-related problems
  • Hybrid modelling techniques to improve computational performance and model accuracy
  • Model design and meta-heuristics
  • Metrics and measures to quantify and evaluate model performance
  • Operational setting and requirements' effect on model development
  • Move from "black box" to "grey box" models

Papers that compare models and/or methods are particularly encouraged.

Important Dates and Submissions

The symposium welcomes both extended abstracts (4 pages), and full papers (8 pages).
Please use the templates from last year’s convention, accessible from http://events.cs.bham.ac.uk/turing12/submission.php.

Submissions are welcomed by 11:59pm GMT, 14th January 2013 to the MALWAS2013 easychair link.
For further information please contact MALWAS2013@gmail.com.

The best papers will be considered for publication in Journal of Hydroinformatics.

  • Extended abstract  and full paper submission deadline: 14 January 2013
  • Notification of acceptance/rejection decisions: 11 February 2013
  • Final versions of accepted papers (Camera ready copy): 4 March 2013

There will be a separate proceedings for each symposium, produced before the convention. Each delegate will receive a memory stick containing the proceedings of all the symposia.

Programme Committee

Detailed Symposium Description

The emergence of water, alongside energy and food, as one of the three major, interlinked, global environmental security issues provides abundant challenges and opportunities for the application of Machine Learning to such problems as optimisation of water distribution and drainage networks’ design and operation, modelling and prediction of fluvial, pluvial, urban and coastal flooding, sediment transport and water quality issues. Advances in GIS, remote sensing and weather forecasting techniques mean that environmental data is becoming increasingly abundant at the same time as demands for solutions and tools to work on these problems become more urgent.

Numerical models have been applied widely to improve the understanding and operational management of natural and manmade water systems. Traditionally, so-called “physically-based” models have been applied for such purposes. However, such models are often computationally demanding, and frequently require significant data to constrain model structures and parameters.  Data-Driven Models (DDMs) based on Machine Learning techniques - which seek to provide a mapping between the inputs and outputs of a given system, with little prior process knowledge – have emerged as an attractive option for prediction and classification in water systems. The principal benefit of such DDMs is their fast execution time, which allows many more model evaluations for a fixed computational budget. Such models have been applied widely to address a variety of problems within water systems modelling, including: system simulation (e.g. rainfall-runoff modelling/rating curve prediction) when trained on measured data, and also when employed as metamodels and trained to emulate models with a stronger physical (or process) basis; to improve the speed of the optimisation procedure by acting as a surrogate model to the full fitness evaluation; to correct systematic errors in physically-based models during real-time forecasting; to provide uncertainty bound predictions during model forecasting when trained on uncertainty bounds derived from offline calibration; and in classification (for example of predicted severity of a hazard or exceedances of regulatory limits).

Despite their potential benefit, successful application of machine learning techniques is not straightforward. A variety of machine learning techniques, optimisation methods and evaluation procedures have been applied in the research literature. It is not always clear which methods will perform best in different settings, and how choices made will influence performance. As an example, different machine learning techniques might perform best depending on how their performance is evaluated within a given operational setting. Furthermore, although such methods are technically “black-box” models, system understanding may be required to choose the best input variables, and tailor the approach to the operational setting in question. With a view towards sharing the interdisciplinary knowledge required to make appropriate methodological decisions, papers are invited that explore issues of model design and application,