☆ 4.6 Article

A Spatiotemporal Deep Learning Approach for Urban Pluvial Flood Forecasting with Multi-Source Data

WATER (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Civil

Generalizing rapid flood predictions to unseen urban catchments with conditional generative adversarial networks

Cesar A. F. do Lago et al.

Summary: This paper proposes a method called cGAN-Flood for flood prediction using conditional generative adversarial networks. The method is trained and tested on urban catchment data with different characteristics and compared to existing flood models. The results show that cGAN-Flood successfully predicts water depths in testing areas and has high computational efficiency, making it a viable solution for flood forecasts in large-scale watersheds.

JOURNAL OF HYDROLOGY (2023)

Add to Collection

Article Geosciences, Multidisciplinary

Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany

Omar Seleem et al.

Summary: Data-driven models, including CNN and RF, were evaluated for predicting flood water depth. The RF models outperformed the CNN models within the training domain, while the CNN models had higher potential to generalize beyond the training domain. Transfer learning techniques improved the performance of CNN models outside training domains.

NATURAL HAZARDS AND EARTH SYSTEM SCIENCES (2023)

Add to Collection

Article Engineering, Civil

Data-driven rapid flood prediction mapping with catchment generalizability

Zifeng Guo et al.

Summary: This study explores the generalizability potential of convolutional neural networks (CNNs) as flood prediction models. The proposed CNN-based model can be reused in different catchment areas with different topography, and it predicts accurately on unseen catchment areas with significantly less computational time. The patch-based option is found to be more effective than the resizing-based option in terms of prediction accuracy.

JOURNAL OF HYDROLOGY (2022)

Add to Collection

Article Multidisciplinary Sciences

Combining graph neural networks and spatio-temporal disease models to improve the prediction of weekly COVID-19 cases in Germany

Cornelius Fritz et al.

Summary: The study investigates the infection rate of COVID-19 and emphasizes the importance of considering human mobility in disease spread. They propose a multimodal learning framework that combines statistical regression and machine learning models to predict local COVID-19 cases in Germany. The results show that more dispersed meeting patterns and a lower percentage of people staying put are associated with higher infection rates.

SCIENTIFIC REPORTS (2022)

Add to Collection

Article Meteorology & Atmospheric Sciences

Hydrometeorological analysis of a flash flood event in an ungauged Mediterranean watershed under an operational forecasting and monitoring context

Christos Giannaros et al.

Summary: This study is the first attempt to investigate the catastrophic flash flood in Olympiada (North Greece) in November 2019 using the WRF model and the GPM-IMERG algorithm. The WRF model showed an adequate predictive capability for the severity of the observed rainfall, while the GPM-IMERG algorithm performed well in capturing the timing of excessive rainfall. Furthermore, the WRF-based HEC-HMS simulation provided a strong indication of the forthcoming flash flood at least 2 days in advance.

METEOROLOGICAL APPLICATIONS (2022)

Add to Collection

Article Geosciences, Multidisciplinary

Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany

Omar Seleem et al.

Summary: Identifying urban areas prone to pluvial flooding is important, but the use of traditional hydrodynamic models is limited. This study explores the use of data-driven models, such as convolutional neural network, artificial neural network, random forest, and support vector machine, to map flood susceptibility in Berlin. The models were validated and compared using different spatial resolutions. The results show that the random forest models performed the best and can be a reliable tool for flood susceptibility mapping, as long as a reliable flood inventory is available.

GEOMATICS NATURAL HAZARDS & RISK (2022)

Add to Collection

Review Geosciences, Multidisciplinary

Deep learning methods for flood mapping: a review of existing applications and future research directions

Roberto Bentivoglio et al.

Summary: This paper reviews 58 recent publications on the use of deep learning techniques in flood management. The results show that models based on convolutional layers are generally more accurate, while models based on fully connected layers provide accurate results when combined with other statistical models. Deep learning models have shown improved accuracy compared to traditional methods and increased speed compared to numerical models. However, further research is needed to understand the application of deep learning in real-time flood warning and flood risk estimation, as well as addressing issues related to model generalization and uncertainty in output.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2022)

Add to Collection

Article Environmental Sciences

Multi-Scale Target-Specified Sub-Model Approach for Fast Large-Scale High-Resolution 2D Urban Flood Modelling

Guohan Zhao et al.

Summary: This paper introduces a sub-model approach that tailors high-resolution 2D model grids to specified targets by adapting 1D static models, resulting in faster processing without significant loss of accuracy. This approach significantly reduces the computing expenses of 2D models, paving the way for large-scale high-resolution 2D real-time forecasting.

WATER (2021)

Add to Collection

Article Engineering, Civil

U-FLOOD - Topographic deep learning for predicting urban pluvial flood water depth

Roland Loewe et al.

Summary: This study investigates how deep learning can optimize the prediction of 2D maximum water depth maps in urban pluvial flood events by training a neural network model to exploit patterns in hyetographs and topographical data. The U-NET architecture is adapted for this purpose, and a model with 28,000,000 parameters is found to be optimal. U-FLOOD demonstrates similar predictive performance to existing screening approaches for natural rain events and unknown locations, generating flood predictions within seconds.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Multidisciplinary Sciences

Skilful precipitation nowcasting using deep generative models of radar

Suman Ravuri et al.

Summary: Advanced nowcasting methods using deep generative models with radar observations can provide accurate and operationally useful precipitation predictions, overcoming the limitations of traditional approaches. These models show improved forecast quality, consistency, and value, making them a valuable tool for various sectors reliant on weather-dependent decision-making.

NATURE (2021)

Add to Collection

Article Multidisciplinary Sciences

Towards global flood mapping onboard low cost satellites with machine learning

Gonzalo Mateo-Garcia et al.

Summary: Spaceborne Earth observation technology provides valuable information for flood response; large constellations of small satellites can reduce revisit time in disaster areas; onboard processing helps reduce data transmission, with PhiSat-1 mission demonstrating hardware support for this approach.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Environmental Sciences

floodGAN: Using Deep Adversarial Learning to Predict Pluvial Flooding in Real Time

Julian Hofmann et al.

Summary: Machine learning for pluvial flood prediction has gained attention recently, with the floodGAN model using deep convolutional generative adversarial networks showing promising results in predicting flooding more accurately and efficiently, bridging the gap between detailed flood modeling and real-time applications.

WATER (2021)

Add to Collection

Article Geosciences, Multidisciplinary

The Bellinge data set: open data and models for community-wide urban drainage systems research

Agnethe Nedergaard Pedersen et al.

Summary: This paper presents a comprehensive and unique open-access data set from the urban drainage system in Bellinge, Denmark, providing valuable information for research in urban hydrology and urban drainage systems. The data set includes observations from various sensors, rainfall data, meteorological data, as well as detailed characteristics of the system. The data set also includes two simulation models in MIKE URBAN and EPA SWMM, allowing for independent testing and replication of research results in the field.

EARTH SYSTEM SCIENCE DATA (2021)

Add to Collection

Article Environmental Sciences

A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area

Dieu Tien Bui et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning

Junbo Zhang et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

Add to Collection

Article Geosciences, Multidisciplinary

Prediction of Maximum Flood Inundation Extents With Resilient Backpropagation Neural Network: Case Study of Kulmbach

Qing Lin et al.

FRONTIERS IN EARTH SCIENCE (2020)

Add to Collection

Article Engineering, Civil

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Ling Zhao et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2020)

Add to Collection

Article Environmental Sciences

Risk-Based and Hydrodynamic Pluvial Flood Forecasts in Real Time

Julian Hofmann et al.

WATER (2020)

Add to Collection

Article Engineering, Civil

Urban flood susceptibility assessment based on convolutional neural networks

Gang Zhao et al.

JOURNAL OF HYDROLOGY (2020)

Add to Collection

Article Engineering, Civil

A deep convolutional neural network model for rapid prediction of fluvial flood inundation

Syed Kabir et al.

JOURNAL OF HYDROLOGY (2020)

Add to Collection

Article Multidisciplinary Sciences

Deep learning and process understanding for data-driven Earth system science

Markus Reichstein et al.

NATURE (2019)

Add to Collection

Article Engineering, Civil

An ensemble neural network model for real-time prediction of urban floods

Simon Berkhahn et al.

JOURNAL OF HYDROLOGY (2019)

Add to Collection

Article Environmental Sciences

A Cellular Automata Fast Flood Evaluation (CA-ffe) Model

Behzad Jamali et al.

WATER RESOURCES RESEARCH (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network

Matthew Moy de Vitry et al.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

All convolutional neural networks for radar-based precipitation nowcasting

G. Ayzel et al.

PROCEEDINGS OF THE 13TH INTERNATIONAL SYMPOSIUM INTELLIGENT SYSTEMS 2018 (INTELS'18) (2019)

Add to Collection

Article Ergonomics

A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data

Jie Bao et al.

ACCIDENT ANALYSIS AND PREVENTION (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

An integrated framework for high-resolution urban flood modelling considering multiple information sources and urban features

Yuntao Wang et al.

ENVIRONMENTAL MODELLING & SOFTWARE (2018)

Add to Collection

Article Engineering, Civil

Validation of 2D flood models with insurance claims

Andreas Paul Zischg et al.

JOURNAL OF HYDROLOGY (2018)

Add to Collection

Article Engineering, Civil

Development and Comparison of Two Fast Surrogate Models for Urban Pluvial Flood Simulations

Maria Bermudez et al.

WATER RESOURCES MANAGEMENT (2018)

Add to Collection

Review Environmental Sciences

Pluvial flood risk and opportunities for resilience

Bernice R. Rosenzweig et al.

WILEY INTERDISCIPLINARY REVIEWS-WATER (2018)

Add to Collection

Article Engineering, Civil

A rapid urban flood inundation and damage assessment model

Behzad Jamali et al.

JOURNAL OF HYDROLOGY (2018)

Add to Collection

Review Environmental Sciences

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Chaopeng Shen

WATER RESOURCES RESEARCH (2018)

Add to Collection

Article Engineering, Civil

An integrated two-stage support vector machine approach to forecast inundation maps during typhoons

Bing-Chen Jhong et al.

JOURNAL OF HYDROLOGY (2017)

Add to Collection

Article Chemistry, Analytical

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

Xiaolei Ma et al.

SENSORS (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Image-to-Image Translation with Conditional Adversarial Networks

Phillip Isola et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Add to Collection

Article Meteorology & Atmospheric Sciences

USE OF NWP FOR NOWCASTING CONVECTIVE PRECIPITATION

Juanzhen Sun et al.

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY (2014)

Add to Collection

Article Engineering, Civil

A 2D parallel diffusive wave model for floodplain inundation with variable time step (P-DWave)

J. Leandro et al.

JOURNAL OF HYDROLOGY (2014)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Development of a real-time regional-inundation forecasting model for the inundation warning system

Gwo-Fong Lin et al.

JOURNAL OF HYDROINFORMATICS (2013)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Real-time urban flood forecasting and modelling - a state of the art

Justine Henonin et al.

JOURNAL OF HYDROINFORMATICS (2013)

Add to Collection

Article Engineering, Electrical & Electronic

Information Extraction From Remote Sensing Images for Flood Monitoring and Damage Evaluation

Sebastiano B. Serpico et al.

PROCEEDINGS OF THE IEEE (2012)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A comparison of three parallelisation methods for 2D flood inundation models

Jeffrey C. Neal et al.

ENVIRONMENTAL MODELLING & SOFTWARE (2010)

Add to Collection

Article Engineering, Civil

A simple inertial formulation of the shallow water equations for efficient two-dimensional flood inundation modelling

Paul D. Bates et al.

JOURNAL OF HYDROLOGY (2010)

Add to Collection

Article Computer Science, Artificial Intelligence

The Graph Neural Network Model

Franco Scarselli et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.