Journal Article10.1016/j.jhydrol.2023.129458
Multi-parameter approaches for improved ensemble prediction accuracy in hydrology and water quality modeling
12
TL;DR: In this paper , a variety of ensemble methods, including simple averaging, median filtering, weighted averaging, Bayesian model averaging, and their variants, were tested in watershed modeling implemented to predict daily water discharge and total phosphorus (TP) loads of a study watershed.
read more
Abstract: Ensemble approaches can be a quick way to improve hydrological prediction accuracy by considering multiple plausible modeling representations of a system. Previous studies showed that the use of multiple types of models could increase prediction accuracy, but model selection subjectivity and parameter equifinality issues remain unsolved. This study proposes to consider multiple parameter sets identified in the model calibration process and information on their performance for improved accuracy of ensemble hydrological prediction. In this study, we investigate whether multi-parameter ensemble (MP) compared to multi-model ensemble (MM) approaches can improve the accuracy of hydrology and water quality prediction. A variety of ensemble methods, including simple averaging, median filtering, weighted averaging, Bayesian model averaging (BMA), and their variants, were tested in watershed modeling implemented to predict daily water discharge and total phosphorus (TP) loads of a study watershed. The parameter spaces of two watershed loading models, Soil and Water Assessment Tool (SWAT) and Hydrological Simulation Program-FORTRAN (HSPF), were sampled using a multi-objective heuristic optimization algorithm, namely A Multi-Algorithm Genetically Adaptive Multiobjective (AMALGAM). The modeling experiment showed that the MP approach more effectively improved modeling accuracy statistics compared to the MM of both models as well as single-model and single-parameter approaches. The ensemble approaches did not always improve modeling accuracy, and their efficiency depended on ways to determine weights for ensemble members. The BMA method outperformed the other weighting schemes tested in this study, and its performance was responsive to the number and diversity (or variance) of ensemble member candidates and the computational cost to create the candidates. The findings demonstrate how the information of parameter sets sampled in model calibration and their performance statistics could help improve hydrological prediction accuracy.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
LSTM time series NDVI prediction method incorporating climate elements: A case study of Yellow River Basin, China
Yan Guo,Lifeng Zhang,Yi He,Shengpeng Cao,Hongzhe Li,Ling Ran,Yujie Ding,Filonchyk Mikalai +7 more
TL;DR: This study develops a multilayer multivariate LSTM model incorporating climate elements to predict NDVI time series in the Yellow River Basin, China, achieving improved accuracy and reliability compared to existing models, with implications for assessing the region's hydrological and ecological environment.
17
Quantifying the contribution of external loadings and internal hydrodynamic processes to the water quality of Lake Okeechobee
TL;DR: In this paper , the authors investigated how the water quality of Lake Okeechobee is controlled by external and internal factors using statistical and numerical modeling approaches, and found that wind (speed) is the major driving force for the internal hydrodynamic processes; its impact on algal biomass was greater than those of the external loadings.
13
Convergence of mechanistic modeling and artificial intelligence in hydrologic science and engineering
TL;DR: This work calls for reimagining the original definition of AI in hydrology to incorporate not only today’s main focus on learning, but on decision analytics and action rules, and on development of autonomous machines in a continuous cycle of learning and refinement in the context of strong ethical, legal, social and economic constrains.
6
Application of the Improved K-Nearest Neighbor-Based Multi-Model Ensemble Method for Runoff Prediction
Tao Xie,Lu Chen,Bin Yi,Siming Li,Zhiyuan Leng,Xiaoxue Gan,Ziyi Mei +6 more
TL;DR: This study introduces the Improved K-Nearest Neighbor Multi-Model Ensemble (IKNN-MME) method for runoff prediction, which dynamically adjusts model weights based on historical data similarity, outperforming other ensemble methods and benchmark models in four US basins.
6
Leveraging Bayesian deep learning and ensemble methods for uncertainty quantification in image classification: A ranking-based approach
Abdullah A. Abdullah,Masoud M. Hassan,Yaseen T. Mustafa +2 more
TL;DR: This study proposes a novel approach that leverages the power of Bayesian ensembles for enhanced uncertainty quantification and exploits the disparity between predicted positive and negative classes and employes it as a ranking metric for model selection.
References
River flow forecasting through conceptual models part I — A discussion of principles☆
J.E. Nash,J.V. Sutcliffe +1 more
TL;DR: In this article, the principles governing the application of the conceptual model technique to river flow forecasting are discussed and the necessity for a systematic approach to the development and testing of the model is explained and some preliminary ideas suggested.
23.3K
Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations
Daniel N. Moriasi,Jeffrey G. Arnold,M. W. Van Liew,Ronald L. Bingner,R. D. Harmel,Tamie L. Veith +5 more
TL;DR: In this paper, the authors present guidelines for watershed model evaluation based on the review results and project-specific considerations, including single-event simulation, quality and quantity of measured data, model calibration procedure, evaluation time step, and project scope and magnitude.
12.2K
Large Area Hydrologic Modeling and Assessment Part i: Model Development
TL;DR: A conceptual, continuous time model called SWAT (Soil and Water Assessment Tool) was developed to assist water resource managers in assessing the impact of management on water supplies and nonpoint source pollution in watersheds and large river basins as discussed by the authors.
7.8K
Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling
TL;DR: A diagnostically interesting decomposition of NSE is presented, which facilitates analysis of the relative importance of its different components in the context of hydrological modelling, and it is shown how model calibration problems can arise due to interactions among these components.
5.3K
The future of distributed models: model calibration and uncertainty prediction.
Keith Beven,Andrew Binley +1 more
TL;DR: The GLUE procedure works with multiple sets of parameter values and allows that, within the limitations of a given model structure and errors in boundary conditions and field observations, different sets of values may be equally likely as simulators of a catchment.
4.7K