Fast simulation and prediction of urban pluvial floods using a deep convolutional neural network model

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 624, P. 129945 - 129945

Published: July 18, 2023

Language: Английский

---

LISFLOOD-FP 8.1: new GPU-accelerated solvers for faster fluvial/pluvial flood simulations

Geoscientific model development, Journal Year: 2023, Volume and Issue: 16(9), P. 2391 - 2413

Published: May 5, 2023

Abstract. The local inertial two-dimensional (2D) flow model on LISFLOOD-FP, the so-called ACCeleration (ACC) uniform grid solver, has been widely used to support fast, computationally efficient fluvial/pluvial flood simulations. This paper describes new releases, LISFLOOD-FP 8.1, for parallelised simulations graphical processing units (GPUs) boost efficiency of existing ACC solver central (CPUs) and enhance it further by enabling a non-uniform version. generates its using multiresolution analysis (MRA) multiwavelets (MWs) Galerkin polynomial projection digital elevation (DEM). sensibly coarsens resolutions where topographic details are below an error threshold ε allows classes land use be properly adapted. Both generator adapted implemented in GPU codebase, indexing Z-order curves alongside parallel tree traversal approach. performance solvers is assessed five case studies, accuracy latter explored ε=10-4 10−3 terms how close can reproduce prediction former. On GPU, found 2–28 times faster than CPU predecessor with increased number elements grid, increase speed up 320 reduction grid's decreased variability resolution. therefore, inundation modelling performed at both urban catchment scales. It openly available under GPL v3 license, additional documentation https://www.seamlesswave.com/LISFLOOD8.0 (last access: 12 March 2023).

Language: Английский

---

Future sea level rise exacerbates compound floods induced by rainstorm and storm tide during super typhoon events: A case study from Zhuhai, China

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 911, P. 168799 - 168799

Published: Nov. 22, 2023

Language: Английский

---

A Framework on Fast Mapping of Urban Flood Based on a Multi-Objective Random Forest Model

International Journal of Disaster Risk Science, Journal Year: 2023, Volume and Issue: 14(2), P. 253 - 268

Published: April 1, 2023

Abstract Fast and accurate prediction of urban flood is considerable practical importance to mitigate the effects frequent disasters in advance. To improve efficiency accuracy, we proposed a framework for fast mapping flood: coupled model based on physical mechanisms was first constructed, rainfall-inundation database generated, hybrid finally using multi-objective random forest (MORF) method. The results show that had good reliability modelling flood, 48 scenarios were then specified. MORF also demonstrated performance predicting inundated depth under observed scenario rainfall events. spatial depths predicted by close those model, with differences typically less than 0.1 m an average correlation coefficient reaching 0.951. however, achieved computational speed 200 times faster model. overall better k-nearest neighbor Our research provides novel approach rapid early warning.

Language: Английский

---

High efficiency integrated urban flood inundation simulation based on the urban hydrologic unit

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 630, P. 130724 - 130724

Published: Jan. 24, 2024

Language: Английский

---

Advancing rapid urban flood prediction: a spatiotemporal deep learning approach with uneven rainfall and attention mechanism

Journal of Hydroinformatics, Journal Year: 2024, Volume and Issue: 26(6), P. 1409 - 1424

Published: May 28, 2024

ABSTRACT Urban floods pose a significant threat to human communities, making its prediction essential for comprehensive flood risk assessment and the formulation of effective resource allocation strategies. Data-driven deep learning approaches have gained traction in urban emergency prediction, addressing efficiency constraints physical models. However, spatial structure rainfall, which has profound influence on flooding, is often overlooked many investigations. In this study, we introduce novel model known as CRU-Net equipped with an attention mechanism predict inundation depths terrains based spatiotemporal rainfall patterns. This method utilizes eight topographic parameters related height waterlogging, combined data inputs model. Comparative evaluations between developed two other models, U-Net ResU-Net, reveal that adeptly interprets traits accurately estimates depths, emphasizing flood-vulnerable regions. The demonstrates exceptional accuracy, evidenced by root mean square error 0.054 m Nash–Sutcliffe 0.975. also predicts over 80% locations exceeding 0.3 m. Remarkably, delivers predictions 3 million grids 2.9 s, showcasing efficiency.

Language: Английский

---

Quantitative assessment of building risks and loss ratios caused by storm surge disasters: A case study of Xiamen, China

Applied Ocean Research, Journal Year: 2024, Volume and Issue: 145, P. 103934 - 103934

Published: Feb. 19, 2024

Language: Английский

---

The spatial overlay effect of urban waterlogging risk and land use value

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 947, P. 174290 - 174290

Published: July 3, 2024

Language: Английский

---

Enhancing transparency in data-driven urban pluvial flood prediction using an explainable CNN model

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132228 - 132228

Published: Oct. 1, 2024

Language: Английский

---

Improving the explainability of CNN-LSTM-based flood prediction with integrating SHAP technique

Ecological Informatics, Journal Year: 2024, Volume and Issue: 84, P. 102904 - 102904

Published: Nov. 17, 2024

Language: Английский

---