A novel ensemble-based conceptual-data-driven approach for improved streamflow simulations

Abstract A novel framework, an ensemble-based conceptual-data-driven approach (CDDA), is developed that integrates a hydrological model (HM) with a data-driven model (DDM) to simulate an ensemble of HM residuals. Thus, a CDDA delivers an ensemble of ‘residual-corrected’ streamflow simulations. This framework is beneficial because it respects hydrological processes via the HM and it profits from the DDM’s ability to simulate the complex relationship between residuals and input variables. The CDDA enables exploring different DDMs to identify the most suitable model. Eight DDMs are explored: Multiple Linear Regression (MLR), k Nearest Neighbours Regression (kNN), Second-Order Volterra Series Model, Artificial Neural Networks (ANN), and two variants of eXtreme Gradient Boosting (XGB) and Random Forests (RF). The proposed CDDA, tested on three Swiss catchments, was able to improve the mean continuous ranked probability score by 16-29% over the standalone HM. Based on these results, XGB and RF are recommended for simulating the HM residuals.

• Publication year

  2021

• Venue

  Environmental Modelling & Software

• Publication date

  2021-06-01

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1016/J.ENVSOFT.2021.105094
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Untangling hybrid hydrological models with explainable artificial intelligence

  2021cited by this paper
• A wavelet-based tool to modulate variance in predictors: An application to predicting drought anomalies

  2021cited by this paper
• Coupling the Xinanjiang model and wavelet-based random forests method for improved daily streamflow simulation

  2021cited by this paper
• A physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data

  2020influential reference
• Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US

  2020cited by this paper
• Predicting algal biochar yield using eXtreme Gradient Boosting (XGB) algorithm of machine learning methods

  2020influential reference
• Prediction of sediment heavy metal at the Australian Bays using newly developed hybrid artificial intelligence models.

  2020cited by this paper
• Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier

  2020cited by this paper
• Super ensemble learning for daily streamflow forecasting: large-scale demonstration and comparison with multiple machine learning algorithms

  2020influential reference
• Bayesian Optimized Echo State Network Applied to Short-Term Load Forecasting

  2020cited by this paper
• A stochastic wavelet-based data-driven framework for forecasting uncertain multiscale hydrological and water resources processes

  2020cited by this paper
• Multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms

  2020cited by this paper
• Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination

  2020cited by this paper
• Data Assimilation for Streamflow Forecasting Using Extreme Learning Machines and Multilayer Perceptrons

  2020cited by this paper
• Flood-type trend analysis for alpine catchments

  2020cited by this paper
• Role of Data Analytics in Infrastructure Asset Management: Overcoming Data Size and Quality Problems

  2020cited by this paper
• Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model

  2020influential reference
• Imputation of missing sub-hourly precipitation data in a large sensor network: a machine learning approach

  2020cited by this paper
• Hydrological model calibration with uncertain discharge data

  2020cited by this paper
• River Flow Prediction Using Dynamic Method for Selecting and Prioritizing K-Nearest Neighbors Based on Data Features

  2020cited by this paper
• Water table depth forecasting in cranberry fields using two decision-tree-modeling approaches

  2020cited by this paper
• Downsizing parameter ensembles for simulations of rare floods

  2020cited by this paper
• Selection of Multiple Donor Gauges via Graphical Lasso for Estimation of Daily Streamflow Time Series

  2020cited by this paper
• A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources

  2019cited by this paper
• Combing Random Forest and Least Square Support Vector Regression for Improving Extreme Rainfall Downscaling

  2019cited by this paper
• Coupled machine learning and the limits of acceptability approach applied in parameter identification for a distributed hydrological model

  2019cited by this paper
• Probabilistic Hydrological Post-Processing at Scale: Why and How to Apply Machine-Learning Quantile Regression Algorithms

  2019cited by this paper
• Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes

  2019cited by this paper
• Coupling machine-learning techniques with SWAT model for instantaneous peak flow prediction

  2019cited by this paper
• A bootstrap approach for the parameter uncertainty of an urban-specific rainfall-runoff model

  2019cited by this paper
• MELPF version 1: Modeling Error Learning based Post-Processor Framework for Hydrologic Models Accuracy Improvement

  2019influential reference
• Non-Linear Input Variable Selection Approach Integrated With Non-Tuned Data Intelligence Model for Streamflow Pattern Simulation

  2019cited by this paper
• Quantification of predictive uncertainty in hydrological modelling by harnessing the wisdom of the crowd: A large-sample experiment at monthly timescale

  2019cited by this paper
• Tree-ring-width based streamflow reconstruction based on the random forest algorithm for the source region of the Yangtze River, China

  2019cited by this paper
• Hydrological post-processing using stacked generalization of quantile regression algorithms: Large-scale application over CONUS

  2019cited by this paper
• Using a simple post-processor to predict residual uncertainty for multiple hydrological model outputs

  2019cited by this paper
• Enhancing Explainability of Neural Networks Through Architecture Constraints

  2019influential reference
• A Stochastic Data‐Driven Ensemble Forecasting Framework for Water Resources: A Case Study Using Ensemble Members Derived From a Database of Deterministic Wavelet‐Based Models

  2019cited by this paper
• Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach

  2019cited by this paper
• Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning

  2019cited by this paper
• Two-stage variational mode decomposition and support vector regression for streamflow forecasting

  2019cited by this paper
• Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms

  2019cited by this paper
• A feature selection and multi-model fusion-based approach of predicting air quality.

  2019cited by this paper
• The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction

  2019influential reference
• Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework

  2018cited by this paper
• Simulation and forecasting of streamflows using machine learning models coupled with base flow separation

  2018cited by this paper
• A combination strategy of random forest and back propagation network for variable selection in spectral calibration

  2018cited by this paper
• Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China

  2018cited by this paper
• Appropriate temporal resolution of precipitation data for discharge modelling in pre-alpine catchments

  2018cited by this paper
• Boosting Random Forests to Reduce Bias; One-Step Boosted Forest and Its Variance Estimate

  2018cited by this paper
• A high-bias, low-variance introduction to Machine Learning for physicists

  2018cited by this paper
• Ensemble committee-based data intelligent approach for generating soil moisture forecasts with multivariate hydro-meteorological predictors

  2018cited by this paper
• Evaluation of random forests and Prophet for daily streamflow forecasting

  2018cited by this paper
• Hyperparameters and tuning strategies for random forest

  2018cited by this paper
• Application of multi-scale wavelet entropy and multi-resolution Volterra models for climatic downscaling

  2018cited by this paper
• Calibrating a hydrological model in stage space to account for rating curve uncertainties: general framework and key challenges

  2017cited by this paper
• A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

  2017cited by this paper
• To tune or not to tune the number of trees in random forest?

  2017cited by this paper
• Variable Selection in Time Series Forecasting Using Random Forests

  2017cited by this paper
• Residual uncertainty estimation using instance-based learning with applications to hydrologic forecasting.

  2017cited by this paper
• Evaluating Probabilistic Forecasts with scoringRules

  2017cited by this paper
• Application of soft computing based hybrid models in hydrological variables modeling: a comprehensive review

  2017influential reference
• Improving probabilistic prediction of daily streamflow by identifying Pareto optimal approaches for modeling heteroscedastic residual errors

  2017cited by this paper
• A non-linear and non-stationary perspective for downscaling mean monthly temperature: a wavelet coupled second order Volterra model

  2017cited by this paper
• Are modern metaheuristics successful in calibrating simple conceptual rainfall–runoff models?

  2017cited by this paper
• KNN-based local linear regression for the analysis and simulation of low flow extremes under climatic influence

  2017cited by this paper
• Combining k-nearest-neighbor models for annual peak breakup flow forecasting

  2017cited by this paper
• Bootstrap rank‐ordered conditional mutual information (broCMI): A nonlinear input variable selection method for water resources modeling

  2016influential reference
• Robust informational entropy-based descriptors of flow in catchment hydrology

  2016cited by this paper
• Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds

  2016cited by this paper
• Random forest in remote sensing: A review of applications and future directions

  2016cited by this paper
• XGBoost: A Scalable Tree Boosting System

  2016influential reference
• Driving a lumped hydrological model with precipitation output from weather generators of different complexity

  2016cited by this paper
• On the deterministic and stochastic use of hydrologic models

  2016cited by this paper
• Assessing the benefit of snow data assimilation for runoff modeling in Alpine catchments

  2016cited by this paper
• Estimating the Uncertainty of Hydrological Predictions through Data-Driven Resampling Techniques

  2015cited by this paper
• Modeling the Relationship between Catchment Attributes and In-stream Water Quality

  2015influential reference
• Reconstruction of missing daily streamflow data using dynamic regression models

  2015cited by this paper
• Flood hazard risk assessment model based on random forest

  2015cited by this paper
• Modeling residual hydrologic errors with Bayesian inference

  2015cited by this paper
• caret: Classification and Regression Training

  2015cited by this paper
• ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R

  2015cited by this paper
• Simulation of nonlinear bridge aerodynamics: A sparse third-order Volterra model

  2014cited by this paper
• Random forests: from early developments to recent advancements

  2014cited by this paper
• An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam, India

  2014cited by this paper
• Evolutionary algorithms and other metaheuristics in water resources: Current status, research challenges and future directions

  2014cited by this paper
• An information theoretic alternative to model a natural system using observational information alone

  2014influential reference
• An evaluation framework for input variable selection algorithms for environmental data-driven models

  2014influential reference
• Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling

  2014cited by this paper
• Improving uncertainty estimation in urban hydrological modeling by statistically describing bias

  2013cited by this paper
• Long term forecasting of groundwater levels with evidence of non-stationary and nonlinear characteristics

  2013cited by this paper
• Travel patterns during pregnancy: comparison between Global Positioning System (GPS) tracking and questionnaire data

  2013influential reference
• OpenML: A Collaborative Science Platform

  2013cited by this paper
• A new way to share, organize and learn from experiments

  2012cited by this paper
• Conditional Likelihood Maximisation: A Unifying Framework for Mutual Information Feature Selection

  2012influential reference
• Practical Bayesian Optimization of Machine Learning Algorithms

  2012influential reference
• Benchmarking observational uncertainties for hydrology: rainfall, river discharge and water quality

  2012cited by this paper
• Wavelet–Volterra coupled model for monthly stream flow forecasting

  2012cited by this paper
• Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting

  2012influential reference
• Dynamic modeling of predictive uncertainty by regression on absolute errors

  2012cited by this paper

• Knowledge-Guided Deep Learning Framework for Source Apportionment and Mitigation of Perchlorate Contamination in River Basins.

  2026cites this paper
• Machine Learning Approach for Predicting Fluoroquinolone Adsorption on Metal-Organic Frameworks

  2026cites this paper
• Exploring viable approaches for long-term seasonal streamflow forecasting under different forcing mechanisms

  2026cites this paper
• Enhancing Streamflow Prediction Using Cutting-edge Deep Learning Models and Seasonal-Trend Decomposition

  2026cites this paper
• Latent data assimilation with non‐explicit observation operator in hydrology

  2025cites this paper
• An optimized boosting-based machine learning model for predicting maximum scour depth around spur dikes

  2025cites this paper
• Evolution of ensemble machine learning approaches in water resources management: a review

  2025cites this paper
• Use of Ensemble-Based Forecasting Methods in Reservoir Operation: Issues and Implementation Challenges

  2025cites this paper
• Evaluation of Data-Driven and Empirical Models for the Estimation of Sediment Removal Efficiency in Settling Basins

  2025cites this paper
• Exploring controls on precipitation-runoff dependencies: Implications for non-stationary and spatially heterogeneous analyses

  2025cites this paper
• The enhanced integration of proven techniques to quantify the uncertainty of forecasting extreme flood events based on numerical weather prediction models

  2025cites this paper
• Exploring the potential processes controlling changes in precipitation–runoff relationships in non-stationary environments

  2025cites this paper
• Harnessing Novel Data‐Driven Techniques for Precise Rainfall–Runoff Modeling

  2025cites this paper
• An efficient hybrid downscaling framework to estimate high-resolution river hydrodynamics

  2025cites this paper
• Coupled SWAT, Stationary Wavelet Transform, and Interpretable Machine Learning to Improve Watershed Streamflow Simulation

  2025cites this paper
• Assessing Environmental Flow Violations in US Rivers: Exploring the Impact of Human Activities and Climate Change Using Machine Learning

  2025cites this paper
• A hybrid process-data driven framework for real-time hydrological forecasting with interpretable deep learning

  2025cites this paper
• Machine learning optimization of operating parameters to achieve high power density and efficiency of polymer electrolyte membrane fuel cell

  2024cites this paper
• Temporal trends and predictive modeling of air pollutants in Delhi: a comparative study of artificial intelligence models

  2024cites this paper
• A novel physical process-ensemble learning model framework with residual error decomposition to upskill daily runoff prediction

  2024cites this paper
• Investigating the potential of EMA-embedded feature selection method for ESVR and LSTM to enhance the robustness of monthly streamflow forecasting from local meteorological information

  2024cites this paper
• AI‐Based Ensemble Flood Forecasts and Its Implementation in Multi‐Objective Robust Optimization Operation for Reservoir Flood Control

  2024cites this paper
• An ensemble deep learning approach to spatiotemporal tropospheric ozone forecasting: A case study of Tehran, Iran

  2024cites this paper
• Enhancing the streamflow simulation of a process-based hydrological model using machine learning and multi-source data

  2024cites this paper
• Parsimonious streamflow forecasting system based on a dynamical systems approach

  2024cites this paper
• Pollution loads in the middle-lower Yangtze river by coupling water quality models with machine learning.

  2024cites this paper
• Identifying the possible driving mechanisms in Precipitation-Runoff relationships with nonstationary and nonlinear theory approaches

  2024cites this paper
• A hybrid model coupling process-driven and data-driven models for improved real-time flood forecasting

  2024cites this paper
• Optimizing building energy performance predictions: A comparative study of artificial intelligence models

  2024cites this paper
• Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

  2024cites this paper
• Data driven insights for parabolic trough solar collectors: Artificial intelligence-based energy and exergy performance analysis

  2024cites this paper
• Application of an explainable glass-box machine learning approach for prognostic analysis of a biogas-powered small agriculture engine

  2023cites this paper
• A quantile-based encoder-decoder framework for multi-step ahead runoff forecasting

  2023cites this paper
• A Comprehensive Experimental and Computational Investigation on Estimation of Scour Depth at Bridge Abutment: Emerging Ensemble Intelligent Systems

  2023cites this paper
• A novel framework for the evaluation of coastal protection schemes through integration of numerical modelling and artificial intelligence into the Sand Engine App

  2023cites this paper
• Designing a decomposition-based multi-phase pre-processing strategy coupled with EDBi-LSTM deep learning approach for sediment load forecasting

  2023cites this paper
• Spatial Downscaling of Streamflow Data with Attention Based Spatio-Temporal Graph Convolutional Networks

  2023cites this paper
• A stochastic deep-learning-based approach for improved streamflow simulation

  2023cites this paper
• Hourly rainfall-runoff modelling by combining the conceptual model with machine learning models in mostly karst Ljubljanica River catchment in Slovenia

  2023cites this paper
• GHCen: a stochastic-conceptual approach for generating synthetic streamflow scenarios

  2023cites this paper
• Impacts of observational uncertainty on analysis and modelling of hydrological processes: Preface

  2022cites this paper
• Streamflow prediction in mountainous region using new machine learning and data preprocessing methods: a case study

  2022cites this paper
• A systematic and critical review on development of machine learning based-ensemble models for prediction of adsorption process efficiency

  2022cites this paper
• Expectile-based hydrological modelling for uncertainty estimation: Life after mean

  2022cites this paper
• Coupling Machine Learning Into Hydrodynamic Models to Improve River Modeling With Complex Boundary Conditions

  2022cites this paper
• Air quality monitoring based on chemical and meteorological drivers: Application of a novel data filtering-based hybridized deep learning model

  2022cites this paper
• Enhanced streamflow simulations using nudging based optimization coupled with data-driven and hydrological models

  2022cites this paper
• Ensemble and stochastic conceptual data-driven approaches for improving streamflow simulations: Exploring different hydrological and data-driven models and a diagnostic tool

  2022cites this paper
• Machine Learning for Postprocessing Medium-range Ensemble Streamflow Forecasts

  2022cites this paper
• IHACRES, GR4J and MISD-based multi conceptual-machine learning approach for rainfall-runoff modeling

  2022cites this paper
• A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecasting

  2022cites this paper
• Forecasting weekly reference evapotranspiration using Auto Encoder Decoder Bidirectional LSTM model hybridized with a Boruta-CatBoost input optimizer

  2022cites this paper
• KNN vs. Bluecat—Machine Learning vs. Classical Statistics

  2022cites this paper
• Hybrid Data-Driven Models for Hydrological Simulation and Projection on the Catchment Scale

  2022cites this paper
• A stochastic conceptual-data-driven approach for improved hydrological simulations

  2022cites this paper
• Hydrological post-processing for predicting extreme quantiles

  2022cites this paper
• Application of a modern multi-level ensemble approach for the estimation of critical shear stress in cohesive sediment mixture

  2022cites this paper
• Machine Learning for Postprocessing Ensemble Streamflow Forecasts

  2021cites this paper
• Probabilistic Water Demand Forecasting Using Quantile Regression Algorithms

  2021cites this paper
• Delineating modelling uncertainty in river flow indicators with representative parameter sets

  2021cites this paper
• Quantile-Based Hydrological Modelling

  2021cites this paper
• Determination of cotton and wheat yield using the standard precipitation evaporation index in Pakistan

  2021cites this paper
• Improving the Pareto Frontier in multi-dataset calibration of hydrological models using metaheuristics

  2021cites this paper
• Investigating the impact of input variable selection on daily solar radiation prediction accuracy using data-driven models: a case study in northern Iran

  2021cites this paper
• Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale

  2021cites this paper
• Exploring the Potential Processes Controls for Changes of Precipitation-Runoff Relationships in Non-stationary Environments

  year unknowncites this paper