Multiple resolution river flow time series modelling using machine learning methods
Date
2014
Authors
Shahriar, M.S.
Kamruzzaman, M.
Beecham, S.C.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, 2014, vol.02-December-2014, pp.1-5
Statement of Responsibility
Conference Name
Workshop on Machine Learning for Sensory Data Analysis (2 Dec 2014 : Australia)
Abstract
We develop multiple resolution river flow time series model using machine learning methods at three locations in South Australia. In multiple resolution river flow models, we identify the best method from a set of widely used machine learning methods. We also identify optimized lag values of river flow and rainfall as input time series in predicting river flow multiple days ahead. The best models are ranked based on mean absolute error. Experimental results demonstrate thatM5P method provides the lowest error over artificial neural network, linear regression and support vector regression in modelling river flow for multiple days ahead prediction for all three locations. Although M5P gives better accuracy over other methods for these locations as also found in the recent research in hydrological time series modelling, it may not be the best method for other geographical locations. Detailed evaluation of statistical and machine learning methods maybe needed in predicting river flow for any location of interest.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2014 Association for Computing Machinery