Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions

9Citations
Citations of this article
35Readers
Mendeley users who have this article in their library.

Abstract

Machine learning (ML) models, and Long Short-Term Memory (LSTM) networks in particular, have demonstrated remarkable performance in streamflow prediction and are increasingly being used by the hydrological research community. However, most of these applications do not include uncertainty quantification (UQ). ML models are data driven and can suffer from large extrapolation errors when applied to changing climate/environmental conditions. UQ is required to quantify the influence of data noises on model predictions and avoid overconfident projections in extrapolation. In this work, we integrate a novel UQ method, called PI3NN, with LSTM networks for streamflow prediction. PI3NN calculates Prediction Intervals by training 3 Neural Networks. It can precisely quantify the predictive uncertainty caused by the data noise and identify out-of-distribution (OOD) data in a non-stationary condition to avoid overconfident predictions. We apply the PI3NN-LSTM method in the snow-dominant East River Watershed in the western US and in the rain-driven Walker Branch Watershed in the southeastern US. Results indicate that for the prediction data which have similar features as the training data, PI3NN precisely quantifies the predictive uncertainty with the desired confidence level; and for the OOD data where the LSTM network fails to make accurate predictions, PI3NN produces a reasonably large uncertainty indicating that the results are not trustworthy and should avoid overconfidence. PI3NN is computationally efficient, robust in performance, and generalizable to various network structures and data with no distributional assumptions. It can be broadly applied in ML-based hydrological simulations for credible prediction.

References Powered by Scopus

Long Short-Term Memory

76938Citations
N/AReaders
Get full text

Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks

1019Citations
N/AReaders
Get full text

A Shuffled Complex Evolution Metropolis algorithm for optimization and uncertainty assessment of hydrologic model parameters

1006Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Data reformation – A novel data processing technique enhancing machine learning applicability for predicting streamflow extremes

11Citations
N/AReaders
Get full text

Forecasting influent wastewater quality by chaos coupled machine learning optimized with Bayesian algorithm

5Citations
N/AReaders
Get full text

Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock images

4Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Liu, S., Lu, D., Painter, S. L., Griffiths, N. A., & Pierce, E. M. (2023). Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions. Frontiers in Water, 5. https://doi.org/10.3389/frwa.2023.1150126

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 10

63%

Researcher 4

25%

Professor / Associate Prof. 1

6%

Lecturer / Post doc 1

6%

Readers' Discipline

Tooltip

Engineering 9

56%

Environmental Science 4

25%

Computer Science 2

13%

Decision Sciences 1

6%

Article Metrics

Tooltip
Mentions
News Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free