The need for operational reasoning in data-driven rating curve prediction of suspended sediment

The use of data-driven modelling techniques to deliver improved suspended sediment rating curves has received considerable interest in recent years. Studies indicate an increased level of performance over traditional approaches when such techniques are adopted. However, closer scrutiny reveals that,...

Full description

Bibliographic Details
Main Authors: Mount, Nick J., Abrahart, R.J., Dawson, C.W., Ab Ghani, N.
Format: Article
Published: Wiley 2012
Subjects:
Online Access:https://eprints.nottingham.ac.uk/28055/
_version_ 1848793496716050432
author Mount, Nick J.
Abrahart, R.J.
Dawson, C.W.
Ab Ghani, N.
author_facet Mount, Nick J.
Abrahart, R.J.
Dawson, C.W.
Ab Ghani, N.
author_sort Mount, Nick J.
building Nottingham Research Data Repository
collection Online Access
description The use of data-driven modelling techniques to deliver improved suspended sediment rating curves has received considerable interest in recent years. Studies indicate an increased level of performance over traditional approaches when such techniques are adopted. However, closer scrutiny reveals that, unlike their traditional counterparts, data-driven solutions commonly include lagged sediment data as model inputs and this seriously limits their operational application. In this paper we argue the need for a greater degree of operational reasoning underpinning data-driven rating curve solutions and demonstrate how incorrect conclusions about the performance of a data-driven modelling technique can be reached when the model solution is based upon operationally-invalid input combinations. We exemplify the problem through the re-analysis and augmentation of a recent and typical published study which uses gene expression programming to model the rating curve. We compare and contrast the previously-published, solutions, whose inputs negate their operational application, with a range of newly developed and directly comparable traditional and data-driven solutions which do have operational value. Results clearly demonstrate that the performance benefits of the published gene expression programming solutions are dependent on the inclusion of operationally-limiting, lagged data inputs. Indeed, when operationally inapplicable input combinations are discounted from the models, and the analysis is repeated, gene expression programming fails to perform as well as many simpler, more standard multiple linear regression, piecewise linear regression and neural network counterparts. The potential for overstatement of the benefits of the data-driven paradigm in rating curve studies is thus highlighted.
first_indexed 2025-11-14T19:01:14Z
format Article
id nottingham-28055
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:01:14Z
publishDate 2012
publisher Wiley
recordtype eprints
repository_type Digital Repository
spelling nottingham-280552020-05-04T16:32:28Z https://eprints.nottingham.ac.uk/28055/ The need for operational reasoning in data-driven rating curve prediction of suspended sediment Mount, Nick J. Abrahart, R.J. Dawson, C.W. Ab Ghani, N. The use of data-driven modelling techniques to deliver improved suspended sediment rating curves has received considerable interest in recent years. Studies indicate an increased level of performance over traditional approaches when such techniques are adopted. However, closer scrutiny reveals that, unlike their traditional counterparts, data-driven solutions commonly include lagged sediment data as model inputs and this seriously limits their operational application. In this paper we argue the need for a greater degree of operational reasoning underpinning data-driven rating curve solutions and demonstrate how incorrect conclusions about the performance of a data-driven modelling technique can be reached when the model solution is based upon operationally-invalid input combinations. We exemplify the problem through the re-analysis and augmentation of a recent and typical published study which uses gene expression programming to model the rating curve. We compare and contrast the previously-published, solutions, whose inputs negate their operational application, with a range of newly developed and directly comparable traditional and data-driven solutions which do have operational value. Results clearly demonstrate that the performance benefits of the published gene expression programming solutions are dependent on the inclusion of operationally-limiting, lagged data inputs. Indeed, when operationally inapplicable input combinations are discounted from the models, and the analysis is repeated, gene expression programming fails to perform as well as many simpler, more standard multiple linear regression, piecewise linear regression and neural network counterparts. The potential for overstatement of the benefits of the data-driven paradigm in rating curve studies is thus highlighted. Wiley 2012-02-21 Article PeerReviewed Mount, Nick J., Abrahart, R.J., Dawson, C.W. and Ab Ghani, N. (2012) The need for operational reasoning in data-driven rating curve prediction of suspended sediment. Hydrological Processes, 26 (26). pp. 3982-4000. ISSN 1099-1085 suspended sediment; data-driven; rating curve; modelling; operational validity http://onlinelibrary.wiley.com/doi/10.1002/hyp.8439/abstract doi:10.1002/hyp.8439 doi:10.1002/hyp.8439
spellingShingle suspended sediment; data-driven; rating curve; modelling; operational validity
Mount, Nick J.
Abrahart, R.J.
Dawson, C.W.
Ab Ghani, N.
The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title_full The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title_fullStr The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title_full_unstemmed The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title_short The need for operational reasoning in data-driven rating curve prediction of suspended sediment
title_sort need for operational reasoning in data-driven rating curve prediction of suspended sediment
topic suspended sediment; data-driven; rating curve; modelling; operational validity
url https://eprints.nottingham.ac.uk/28055/
https://eprints.nottingham.ac.uk/28055/
https://eprints.nottingham.ac.uk/28055/