Towards a Multi-Representational Approach to Prediction, Understanding, and Discovery in Hydrology

Fuente, Luis de la; Gupta, Hoshin; Condon, Laura E.

doi:10.1002/essoar.10508656.1

Cited by 4 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies have focused on the interpretation of the internal processes and weights in the LSTM network, which is one of the main limitations of this architecture connected to its structural complexity. In [17], the authors explored a new LSTM architecture to overcome this problem, representing the internal system processes in a manner that is analogous to a hydrological reservoir (HydroLSTM). The performances of the HydroLSTM and LSTM architectures were compared using data from hydroclimatically varied catchments.…”

Section: Related Workmentioning

confidence: 99%

“…In this way, the gradient flows over time, even for long periods, and its derivative remains computable (they neither vanish nor diverge). LSTM networks have been demonstrated to be able to dynamically map the input and output of a dynamical system; their use for learning the inherent properties of a given dynamical system has been studied in [14,17,18,24,[26][27][28], obtaining promising results. They have proven to be powerful in representing long and short temporal dependencies in multiple examples with respect to other recurrent architectures, such as Gated Recurrent Unit (GRU), BIdirectional-LSTM (BI-LSTM), etc.…”

Section: Long Short-term Memory (Lstm) Networkmentioning

confidence: 99%

See 1 more Smart Citation

LSTM Network for the Oxygen Concentration Modeling of a Wastewater Treatment Plant

et al. 2023

View full text Add to dashboard Cite

The activated sludge process is a well-known method used to treat municipal and industrial wastewater. In this complex process, the oxygen concentration in the reactors plays a key role in the plant efficiency. This paper proposes the use of a Long Short-Term Memory (LSTM) network to identify an input–output model suitable for the design of an oxygen concentration controller. The model is identified from easily accessible measures collected from a real plant. This dataset covers almost a month of data collected from the plant. The performances achieved with the proposed LSTM model are compared with those obtained with a standard AutoRegressive model with eXogenous input (ARX). Both models capture the oscillation frequencies and the overall behavior (ARX Pearson correlation coefficient ρ = 0.833 , LSTM ρ = 0.921), but, while the ARX model fails to reach the correct amplitude (index of fitting FIT = 41.20%), the LSTM presents satisfactory performance (FIT = 60.56%).

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Long Short-term Memory (Lstm) Networkmentioning

confidence: 99%

LSTM Network for the Oxygen Concentration Modeling of a Wastewater Treatment Plant

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Because the LSTM cell‐states represent abstract features in some latent space, extra analyses must be performed to determine how they are informationally related to actual physical quantities (Lees et al., 2022). Interesting and creative developments have included the application of metric‐based approaches (Jiang et al., 2022) and the design of reduced complexity “ HydroLSTM ” architectures (De la Fuente, Ehsani, et al., 2023) that seek to facilitate the process of deciphering what has been learned by LSTM‐type models.…”

Section: Introduction and Scopementioning

confidence: 99%

A Mass‐Conserving‐Perceptron for Machine‐Learning‐Based Modeling of Geoscientific Systems

Wang,

Gupta

2024

Water Resources Research

View full text Add to dashboard Cite

Although decades of effort have been devoted to building Physical‐Conceptual (PC) models for predicting the time‐series evolution of geoscientific systems, recent work shows that Machine Learning (ML) based Gated Recurrent Neural Network technology can be used to develop models that are much more accurate. However, the difficulty of extracting physical understanding from ML‐based models complicates their utility for enhancing scientific knowledge regarding system structure and function. Here, we propose a physically interpretable Mass‐Conserving‐Perceptron (MCP) as a way to bridge the gap between PC‐based and ML‐based modeling approaches. The MCP exploits the inherent isomorphism between the directed graph structures underlying both PC models and GRNNs to explicitly represent the mass‐conserving nature of physical processes while enabling the functional nature of such processes to be directly learned (in an interpretable manner) from available data using off‐the‐shelf ML technology. As a proof of concept, we investigate the functional expressivity (capacity) of the MCP, explore its ability to parsimoniously represent the rainfall‐runoff (RR) dynamics of the Leaf River Basin, and demonstrate its utility for scientific hypothesis testing. To conclude, we discuss extensions of the concept to enable ML‐based physical‐conceptual representation of the coupled nature of mass‐energy‐information flows through geoscientific systems.

show abstract

“…All of the simulated and observed data were drawn from a recent multi-catchment hydrological model benchmarking study (Mai et al, 2022) involving multiple physical-conceptualbased models (PC-based;De la Fuente et al, 2021) and one machine-learning-based (MLbased) model.…”

Section: Introductionmentioning

confidence: 99%

In Defense of Metrics: Metrics Sufficiently Encode Typical Human Preferences Regarding Hydrological Model Performance

Gauch¹,

Kratzert²,

Gilon³

et al. 2023

Preprint

View full text Add to dashboard Cite

Building accurate rainfall-runoff models is an integral part of hydrological science and practice. The variety of modeling goals and applications have led to a large suite of evaluation metrics for these models. Yet, hydrologists still put considerable trust into visual judgment, although it is unclear whether such judgment agrees or disagrees with existing quantitative metrics. In this study, we tasked 622 experts to compare and judge more than 14,000 pairs of hydrographs from 13 different models. Our results show that expert opinion broadly agrees with quantitative metrics and results in a clear preference for a Machine Learning model over traditional hydrological models. The expert opinions are, however, subject to significant amounts of inconsistency. Nevertheless, where experts agree, we can predict their opinion purely from quantitative metrics, which indicates that the metrics sufficiently encode human preferences in a small set of numbers. While there remains room for improvement of quantitative metrics, we suggest that the hydrologic community should reinforce their benchmarking efforts and put more trust in these metrics.

show abstract

Towards a Multi-Representational Approach to Prediction, Understanding, and Discovery in Hydrology

Cited by 4 publications

References 32 publications

LSTM Network for the Oxygen Concentration Modeling of a Wastewater Treatment Plant

LSTM Network for the Oxygen Concentration Modeling of a Wastewater Treatment Plant

A Mass‐Conserving‐Perceptron for Machine‐Learning‐Based Modeling of Geoscientific Systems

In Defense of Metrics: Metrics Sufficiently Encode Typical Human Preferences Regarding Hydrological Model Performance

Contact Info

Product

Resources

About