AUTOFLOW© - A novel application for Water Resource Management and Climate Change Response using smart technology
MetadataShow full item record
Urban areas are increasingly at risk from climate change, with negative impacts predicted for human health, the economy and ecosystems. These risks require responses from cities to improve their resilience. Several analysis platforms have been developed worldwide to help effectively control and response to these impacts from different angles, including water resources management, energy production and consumption management, air pollution control, or other natural resources management. To contribute to this goal, Griffith University in Australia has developed Autoflow©, a smart application for water demand analysis and carbon emission monitoring and prediction. Various advanced mathematical models have been embedded into this system, from machine learning and pattern recognition techniques for water end use analysis, to Dynamic Harmonic Regression, Kalman Filter and Fixed interval smooth algorithms for water demand forecasting. Once being deployed, Autoflow© will be an effective environmental management tool that can: (i) provide water utilities and water consumers with detailed real-time information on how, when, where water has been consumed (e.g. shower event at 11:23:35 AM or clothes washer at 4:00:15 PM on Monday 11/12/2014),(ii) perform water demand forecasting at end-use level (e.g. expected 1.5 mega litres of shower consumption from 6pm – 7m in suburb A tomorrow), (iii) real-time monitor and predict carbon emission level from water consumption (e.g. Property A: Carbon emission from 6am-6pm tomorrow is 12.4kg), and (iv) suggest options for reducing water consumption and carbon emission.
Proceedings of the 8th International Congress on Environmental Modelling and Software: Supporting Sustainable Futures
© The Author(s) 2016. The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the author(s).
Pattern Recognition and Data Mining