Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
18,633
result(s) for
"FLOOD FORECASTING"
Sort by:
The Value of Forecasters‐in‐the‐Loop in Real‐Time Flood Forecasting in the Age of Machine Learning
Machine learning (ML) applications in hydrological forecasting are increasingly prevalent and show great potential. However, many previous studies have only evaluated performance through reanalysis or retrospective simulations compared to simplified baselines. This study provides the first assessment of ML performance against actual operational forecasting systems operated by the California Nevada River Forecast Center (CNRFC), which combines the Community Hydrologic Prediction System (CHPS) with forecasters‐in‐the‐loop. Results demonstrate that forecasters‐in‐the‐loop systems consistently outperform ML models in both general forecasts and flood alerting across lead times up to 96 hr, even when ML models use observed forcings, while CNRFC operational process relies on biased weather forecasts. Our analysis reveals that forecaster expertise maintains forecast reliability despite inaccurate precipitation inputs, with human‐guided systems showing superior performance degradation characteristics at extended lead times. These findings highlight the irreplaceable value of human expertise in operational forecasting and caution against overstating current ML capabilities in real‐world applications.
Journal Article
Probabilistic Forecasts of Flood Inundation Maps Using Surrogate Models
The use of data-driven surrogate models to produce deterministic flood inundation maps in a timely manner has been investigated and proposed as an additional component for flood early warning systems. This study explores the potential of such surrogate models to forecast multiple inundation maps in order to generate probabilistic outputs and assesses the impact of including quantitative precipitation forecasts (QPFs) in the set of predictors. The use of a k-fold approach for training an ensemble of flood inundation surrogate models that replicate the behavior of a physics-based hydraulic model is proposed. The models are used to forecast the inundation maps resulting from three out-of-the-dataset intense rainfall events both using and not using QPFs as a predictor, and the outputs are compared against the maps produced by a physics-based hydrodynamic model. The results show that the k-fold ensemble approach has the potential to capture the uncertainties related to the process of surrogating a hydrodynamic model. Results also indicate that the inclusion of the QPFs has the potential to increase the sharpness, with the tread-off also increasing the bias of the forecasts issued for lead times longer than 2 h.
Journal Article
Changes in flood risk in Europe
This title delivers a wealth of information on changes in flood risk in Europe, and considers causes for change. The temporal coverage is mostly focused on post-1900 events, reflecting the typical availability of data, but some information on earlier flood events is also included.
Book
Hybrid Surrogate Model for Timely Prediction of Flash Flood Inundation Maps Caused by Rapid River Overflow
Timely generation of accurate and reliable forecasts of flash flood events is of paramount importance for flood early warning systems in urban areas. Although physically based models are able to provide realistic reproductions of fast-developing inundation maps in high resolutions, the high computational demand of such hydraulic models makes them difficult to be implemented as part of real-time forecasting systems. This paper evaluates the use of a hybrid machine learning approach as a surrogate of a quasi-2D urban flood inundation model developed in PCSWMM for an urban catchment located in Toronto (Ontario, Canada). The capability to replicate the behavior of the hydraulic model was evaluated through multiple performance metrics considering error, bias, correlation, and contingency table analysis. Results indicate that the surrogate system can provide useful forecasts for decision makers by rapidly generating future flood inundation maps comparable to the simulations of physically based models. The experimental tool developed can issue reliable alerts of upcoming inundation depths on traffic locations within one to two hours of lead time, which is sufficient for the adoption of important preventive actions. These promising outcomes were achieved in a deterministic setup and use only past records of precipitation and discharge as input during runtime.
Journal Article
A review of flash‐floods management: From hydrological modeling to crisis management
In a context of climate change, flash‐floods are expected to increase in frequency. Considering their devastating impacts, it is primordial to safeguard the exposed population and infrastructure. This is the responsibility of crisis managers but they face difficulties due to the rapidity of these events. The focus of this study was to characterize the extent of the link between hydrologists and crisis managers. It also aimed to determine the limiting and the fostering factors to an effective integration of forecasting in crisis management during flash‐floods. This was achieved through an extensive and methodological study of available literature in selected platforms. The models encountered were characterized on multiple levels including the physical, geographical and crisis management level. The results revealed a limited link between the two involved parties with limiting factors such as the complexity of the modeling approach, the insufficient projection in the implications of operationality of the models proposed and the financial aspect. On the other hand, acknowledging the threat of flash‐floods and conducting cost–benefit‐analysis were pinpointed as fostering factors. This study showed to reconsider the forecasting methods employed, particularly, the integration of machine learning, and the needs of end‐user in these applications in a crisis management context.
Journal Article
Mountain flood forecasting in small watershed based on loop multi-step machine learning regression model
Mountain flood in small watershed is widely distributed disaster, which have the characteristics of strong suddenness, great harm, and frequently. The traditional hydrodynamic and manual forecasting methods have high error rates for hourly forecasting. In order to improve the accuracy and real-time of water level forecasting in small watershed, we extract effective disaster-causing information, integrate multi-dimensional disaster-causing factors (such as hydrology, meteorology, geography, etc.), use a short-term prediction window and loop multi-step input method to improve the Machine Learning (ML) regression models’ accuracy, which can reduce the ML model’s process error. The non-ensemble and ensemble ML regression models is constructed for forecasting by loop multi-step, the non-ensemble models including Linear Regression (LR), Support Vector Machine Regression (SVMR) and
k
-Nearest Neighbors Regression (
k-
NNR), and the ensemble ML models include Random Forest Regression (RFR) and Gradient Boosting Regression (GBR). The loop multi-step ensemble ML regression models have the characteristics of high accurate and low time consumption than the general ML regression models for mountain flood forecasting in small watershed.
Journal Article