Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology

Abstract Key to model development is the selection of an appropriate representational system, including both the representation of what is observed (the data), and the formal mathematical structure used to construct the input‐state‐output mapping. These choices are critical, because they completely...

Full description

Saved in:
Bibliographic Details
Main Authors: Luis A. De la Fuente, Hoshin V. Gupta, Laura E. Condon
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2021WR031548
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433299648249856
author Luis A. De la Fuente
Hoshin V. Gupta
Laura E. Condon
author_facet Luis A. De la Fuente
Hoshin V. Gupta
Laura E. Condon
author_sort Luis A. De la Fuente
collection DOAJ
description Abstract Key to model development is the selection of an appropriate representational system, including both the representation of what is observed (the data), and the formal mathematical structure used to construct the input‐state‐output mapping. These choices are critical, because they completely determine the questions we can ask, the nature of the analyses and inferences we can perform, and the answers we can obtain. Accordingly, a representation that is suitable for one kind of investigation might be limited in its ability to support some other kind. Arguably, how different representational approaches affect what we can learn from data is poorly understood. This paper explores three representational strategies as vehicles for understanding how catchment scale hydrological processes vary across hydro‐geo‐climatologically diverse Chile. Specifically, we test a lumped water‐balance model (GR4J), a data‐based dynamical systems model (LSTM), and a data‐based regression tree model (Random Forest). Insights were obtained regarding system memory encoded in data, spatial transferability by use of surrogate attributes, and informational deficiencies of the data set that limit our ability to learn an adequate input‐output relationship. As expected, each approach exhibits specific strengths, with LSTM providing the best characterization of dynamics, GR4J being the most robust under informationally deficient conditions, and Random Forest regression‐tree method being most supportive of interpretation. Overall, the contrasting nature of the three approaches suggests the value of adopting a multi‐representational framework to more fully extract information from the data and, by doing so, find information that better facilities the goals of robust prediction and improved understanding, ultimately supporting enhanced scientific discovery.
format Article
id doaj-art-d83124f36e654d27bb83d5a5a05ce30f
institution Kabale University
issn 0043-1397
1944-7973
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-d83124f36e654d27bb83d5a5a05ce30f2025-08-20T03:27:06ZengWileyWater Resources Research0043-13971944-79732023-01-01591n/an/a10.1029/2021WR031548Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in HydrologyLuis A. De la Fuente0Hoshin V. Gupta1Laura E. Condon2Department of Hydrology and Atmospheric Sciences The University of Arizona Tucson AZ USADepartment of Hydrology and Atmospheric Sciences The University of Arizona Tucson AZ USADepartment of Hydrology and Atmospheric Sciences The University of Arizona Tucson AZ USAAbstract Key to model development is the selection of an appropriate representational system, including both the representation of what is observed (the data), and the formal mathematical structure used to construct the input‐state‐output mapping. These choices are critical, because they completely determine the questions we can ask, the nature of the analyses and inferences we can perform, and the answers we can obtain. Accordingly, a representation that is suitable for one kind of investigation might be limited in its ability to support some other kind. Arguably, how different representational approaches affect what we can learn from data is poorly understood. This paper explores three representational strategies as vehicles for understanding how catchment scale hydrological processes vary across hydro‐geo‐climatologically diverse Chile. Specifically, we test a lumped water‐balance model (GR4J), a data‐based dynamical systems model (LSTM), and a data‐based regression tree model (Random Forest). Insights were obtained regarding system memory encoded in data, spatial transferability by use of surrogate attributes, and informational deficiencies of the data set that limit our ability to learn an adequate input‐output relationship. As expected, each approach exhibits specific strengths, with LSTM providing the best characterization of dynamics, GR4J being the most robust under informationally deficient conditions, and Random Forest regression‐tree method being most supportive of interpretation. Overall, the contrasting nature of the three approaches suggests the value of adopting a multi‐representational framework to more fully extract information from the data and, by doing so, find information that better facilities the goals of robust prediction and improved understanding, ultimately supporting enhanced scientific discovery.https://doi.org/10.1029/2021WR031548representationmachine learningLSTMRandom ForestGR4Jconceptual model
spellingShingle Luis A. De la Fuente
Hoshin V. Gupta
Laura E. Condon
Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
Water Resources Research
representation
machine learning
LSTM
Random Forest
GR4J
conceptual model
title Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
title_full Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
title_fullStr Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
title_full_unstemmed Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
title_short Toward a Multi‐Representational Approach to Prediction and Understanding, in Support of Discovery in Hydrology
title_sort toward a multi representational approach to prediction and understanding in support of discovery in hydrology
topic representation
machine learning
LSTM
Random Forest
GR4J
conceptual model
url https://doi.org/10.1029/2021WR031548
work_keys_str_mv AT luisadelafuente towardamultirepresentationalapproachtopredictionandunderstandinginsupportofdiscoveryinhydrology
AT hoshinvgupta towardamultirepresentationalapproachtopredictionandunderstandinginsupportofdiscoveryinhydrology
AT lauraecondon towardamultirepresentationalapproachtopredictionandunderstandinginsupportofdiscoveryinhydrology