Development and Operational Testing of a Super‐Ensemble Artificial Intelligence Flood‐Forecast Model for a Pacific Northwest River

Fleming, Sean W.; Bourdin, Dominique R.; Campbell, D B J; Stull, Roland B.; Gardner, Tobi

doi:10.1111/jawr.12259

Cited by 40 publications

(36 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the precipitation and temperature forecasts are also underdispersed, we recommend an investigation into how the reliability of the precipitation and temperature forecasts can be improved, potentially by adding meteorological forecasts from other forecasting systems (i.e. creating "super-ensembles") (Bennett et al, 2014;Bougeault et al, 2010;Fleming et al, 2015;He et al, 2009) or by improved pre-processing.…”

Section: Discussionmentioning

confidence: 99%

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Benninga

Booij

Romanowicz

et al. 2017

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. The paper presents a methodology that gives insight into the performance of ensemble streamflowforecasting systems. We have developed an ensemble forecasting system for the Biała Tarnowska, a mountainous river catchment in southern Poland, and analysed the performance for lead times ranging from 1 to 10 days for low, medium and high streamflow and different hydrometeorological conditions. Precipitation and temperature forecasts from the European Centre for Medium-Range Weather Forecasts served as inputs to a deterministic lumped hydrological (HBV) model. Due to a non-homogeneous bias in time, pre-and post-processing of the meteorological and streamflow forecasts are not effective. The best forecast skill, relative to alternative forecasts based on meteorological climatology, is shown for high streamflow and snow accumulation lowstreamflow events. Forecasts of medium-streamflow events and low-streamflow events under precipitation deficit conditions show less skill. To improve performance of the forecasting system for high-streamflow events, the meteorological forecasts are most important. Besides, it is recommended that the hydrological model be calibrated specifically on lowstreamflow conditions and high-streamflow conditions. Further, it is recommended that the dispersion (reliability) of the ensemble streamflow forecasts is enlarged by including the uncertainties in the hydrological model parameters and the initial conditions, and by enlarging the dispersion of the meteorological input forecasts.

show abstract

Section: Discussionmentioning

confidence: 99%

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Benninga

Booij

Romanowicz

et al. 2017

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…Using the EPS model decreased uncertainty in forecasting, which resulted in the prediction system being evaluated as reliable and robust in estimating flood duration and destructive power. In another case, Reference[190] developed an EPS model of six ANNs for daily streamflow prediction based on daily high-flow data from the storm season of 2013-2014. The proposed model had a fast development time, which also provided probabilistic forecasts to deal with uncertainties in prediction.…”

mentioning

confidence: 99%

Flood Prediction Using Machine Learning Models: Literature Review

Mosavi

Öztürk

Chau

2018

Water

1,034

469

View full text Add to dashboard Cite

Floods are among the most destructive natural disasters, which are highly complex to model. The research on the advancement of flood prediction models contributed to risk reduction, policy suggestion, minimization of the loss of human life, and reduction the property damage associated with floods. To mimic the complex mathematical expressions of physical processes of floods, during the past two decades, machine learning (ML) methods contributed highly in the advancement of prediction systems providing better performance and cost-effective solutions. Due to the vast benefits and potential of ML, its popularity dramatically increased among hydrologists.Researchers through introducing novel ML methods and hybridizing of the existing ones aim at discovering more accurate and efficient prediction models. The main contribution of this paper is to demonstrate the state of the art of ML models in flood prediction and to give insight into the most suitable models. In this paper, the literature where ML models were benchmarked through a qualitative analysis of robustness, accuracy, effectiveness, and speed are particularly investigated to provide an extensive overview on the various ML algorithms used in the field. The performance comparison of ML models presents an in-depth understanding of the different techniques within the framework of a comprehensive evaluation and discussion. As a result, this paper introduces the most promising prediction methods for both long-term and short-term floods. Furthermore, the major trends in improving the quality of the flood prediction models are investigated. Among them, hybridization, data decomposition, algorithm ensemble, and model optimization are reported as the most effective strategies for the improvement of ML methods. This survey can be used as a guideline for hydrologists as well as climate scientists in choosing the proper ML method according to the prediction task. Keywords: flood prediction; flood forecasting; flash-flood model, big flood management; hydrologic model; rainfall-runoff, hybrid & ensemble machine learning; artificial neural networks (ANNs); support vector machines (SVM); natural hazards & disasters; adaptive neuro-fuzzy inference system (ANFIS); decision trees (DT); internet of things (IoT); random forest (RF); survey; classification and regression trees (CART), data science; deep learning; big data; bagging, boosting, artificial intelligence (AI); soft computing; extreme event management; time series prediction; multilayer perceptron (MLP); simulated annealing (SA); multivariate adaptive regression splines (MARS), supervised learning IntroductionAmong the natural disasters, floods are the most destructive, causing massive damage to human life, infrastructure, agriculture, and the socioeconomic system.Governments, therefore, are under pressure to develop reliable and accurate maps of flood risk areas and further plan for sustainable flood risk management focusing on prevention, protection, and preparedness [1]. Flood prediction models are of significant impor...

show abstract

“…The uncertainty in the relationship between the fraction of fast runoff and total streamflow to update initial states might be utilized to incorporate initial condition uncertainty. Since the precipitation and temperature forecasts are also underdispersed, we recommend to investigate how the reliability of the precipitation and temperature forecasts can be improved, by adding meteorological forecasts from other forecasting systems ('super-ensembles') (Bennett et al, 2014;Bougeault et al, 2010;Fleming et al, 2015;He et al, 2009) or by improved pre-processing.…”

Section: Discussionmentioning

confidence: 99%

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Benninga¹,

Booij²,

Romanowicz³

et al. 2016

Preprint

View full text Add to dashboard Cite

Abstract. The paper presents a methodology to give insight in the performance of ensemble streamflow forecasting systems. We developed an ensemble forecasting system for the Biała Tarnowska, a mountainous river catchment in southern Poland, and analysed the performance for lead times from 1 day to 10 days for low, medium and high streamflow and related runoff generating processes. Precipitation and temperature forecasts from the European Centre for Medium-Range Weather Forecasts serve as input to a deterministic lumped hydrological (HBV) model. Due to inconsistent bias, the best streamflow forecasts were obtained without pre- and post-processing of the meteorological and streamflow forecasts. Best forecast skill, relative to alternative forecasts based on historical measurements of precipitation and temperature, is shown for high streamflow and for snow accumulation low streamflow events. Forecasts of medium streamflow events and low streamflow events generated by precipitation deficit show less skill. To improve the performance of the forecasting system for high streamflow events, in particular the meteorological forecasts require improvement. For low streamflow forecasts, the hydrological model should be improved. The study recommends improving the reliability of the ensemble streamflow forecasts by including the uncertainties in hydrological model parameters and initial conditions, and by improving the dispersion of the meteorological input forecasts.

show abstract

Development and Operational Testing of a Super‐Ensemble Artificial Intelligence Flood‐Forecast Model for a Pacific Northwest River

Cited by 40 publications

References 40 publications

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Flood Prediction Using Machine Learning Models: Literature Review

Performance of ensemble streamflow forecasts under varied hydrometeorological conditions

Contact Info

Product

Resources

About