Data-driven recursive input–output multivariate statistical forecasting model: case of DO concentration prediction in Advancetown Lake, Australia
MetadataShow full item record
A regression model integrating data pre-processing and transformation, input selection techniques and a data-driven statistical model, facilitated accurate seven day ahead time series forecasting of selected water quality parameters. A core feature of the modelling approach is a novel recursive input-output algorithm. The herein described model development procedure was applied to the case of a seven day ahead dissolved oxygen (DO) concentration forecast for the upper hypolimnion of Advancetown Lake, Queensland, Australia. The DO was predicted with an R2 > 0.8 and a NRMSE of 14.9% on a validation data set by using 10 inputs related to water temperature or pH. A key feature of the model is that it can handle nonlinear correlations, which was essential for this forecasting problem as most of the input time series necessitated nonlinear transformations of the original data. The pre-processing of the data revealed some relevant inputs that had only six days lag, and as a consequence, those predictors were in-turn forecasted one day ahead using the same procedure. In this way, the targeted prediction horizon (i.e. seven days) was preserved. The implemented approach can be applied to a wide range of time-series forecasting problems in the complex hydro-environment research area. The reliable DO forecasting tool can be used by reservoir operators to achieve more proactive and reliable water treatment management.
Journal of Hydroinformatics
Copyright IWA Publishing 2015. The definitive peer-reviewed and edited version of this article is published in Journal of Hydroinformatics, Volume 17 (5), 817-833, DOI: 10.2166/hydro.2015.131, and is available at www.iwapublishing.com
Water Resources Engineering