The role of deep learning in urban water management: A critical review

Water Research, Journal Year: 2022, Volume and Issue: 223, P. 118973 - 118973

Published: Aug. 11, 2022

Deep learning techniques and algorithms are emerging as a disruptive technology with the potential to transform global economies, environments societies. They have been applied planning management problems of urban water systems in general, however, there is lack systematic review current state deep applications an examination directions where can contribute solving challenges. Here we provide such review, covering demand forecasting, leakage contamination detection, sewer defect assessment, wastewater system prediction, asset monitoring flooding. We find that application still at early stage most studies used benchmark networks, synthetic data, laboratory or pilot test performance methods no practical adoption reported. Leakage detection perhaps forefront receiving implementation into day-to-day operation systems, compared other reviewed. Five research challenges, i.e., data privacy, algorithmic development, explainability trustworthiness, multi-agent digital twins, identified key areas advance management. Future expected drive towards high intelligence autonomy. hope this will inspire development harness power help achieve sustainable digitalise sector across world.

Language: Английский

---

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

Hydrology and earth system sciences, Journal Year: 2022, Volume and Issue: 26(16), P. 4345 - 4378

Published: Aug. 25, 2022

Abstract. Deep learning techniques have been increasingly used in flood management to overcome the limitations of accurate, yet slow, numerical models and improve results traditional methods for mapping. In this paper, we review 58 recent publications outline state art field, identify knowledge gaps, propose future research directions. The focuses on type deep various mapping applications, types considered, spatial scale studied events, data model development. show that based convolutional layers are usually more as they leverage inductive biases better process characteristics flooding events. Models fully connected layers, instead, provide accurate when coupled with other statistical models. showed increased accuracy compared approaches speed methods. While there exist several applications susceptibility, inundation, hazard mapping, work is needed understand how can assist real-time warning during an emergency it be employed estimate risk. A major challenge lies developing generalize unseen case studies. Furthermore, all reviewed their outputs deterministic, limited considerations uncertainties outcomes probabilistic predictions. authors argue these identified gaps addressed by exploiting fundamental advancements or taking inspiration from developments applied areas. graph neural networks operators arbitrarily structured thus should capable generalizing across different studies could account complex interactions natural built environment. Physics-based preserve underlying physical equations resulting reliable speed-up alternatives Similarly, resorting Gaussian processes Bayesian networks.

Language: Английский

---

Urban flood modeling using deep-learning approaches in Seoul, South Korea

Journal of Hydrology, Journal Year: 2021, Volume and Issue: 601, P. 126684 - 126684

Published: July 18, 2021

Identification of flood-prone sites in urban environments is necessary, but there insufficient hydraulic information and time series data on surface runoff. To date, several attempts have been made to apply deep-learning models for flood hazard mapping areas. This study evaluated the capability convolutional neural network (NNETC) recurrent (NNETR) mapping. A flood-inundation inventory (including 295 flooded sites) was used as response variable 10 flood-affecting factors were considered predictor variables. Flooded then spatially randomly split a 70:30 ratio building validation purposes. The prediction quality validated using area under receiver operating characteristic curve (AUC) root mean square error (RMSE). results indicated that performance NNETC model (AUC = 84%, RMSE 0.163) slightly better than NNETR 82%, 0.186). Both terrain ruggedness index most important predictor, followed by slope elevation. Although output had relative up 20% (based AUC), this modeling approach could still be reliable rapid tool generate map areas, provided inundation available.

Language: Английский

---

Flood Risk in Urban Areas: Modelling, Management and Adaptation to Climate Change. A Review

Hydrology, Journal Year: 2022, Volume and Issue: 9(3), P. 50 - 50

Published: March 18, 2022

The modelling and management of flood risk in urban areas are increasingly recognized as global challenges. complexity these issues is a consequence the existence several distinct sources risk, including not only fluvial, tidal coastal flooding, but also exposure to runoff local drainage failure, various strategies that can be proposed. high degree vulnerability characterizes such expected increase future due effects climate change, growth population living cities, densification. An increasing awareness socio-economic losses environmental impact flooding clearly reflected recent expansion number studies related sometimes within framework adaptation change. goal current paper provide general review advances flood-risk management, while exploring perspectives fields research.

Language: Английский

---

Flood Inundation Prediction

Annual Review of Fluid Mechanics, Journal Year: 2021, Volume and Issue: 54(1), P. 287 - 315

Published: Oct. 13, 2021

Every year flood events lead to thousands of casualties and significant economic damage. Mapping the areas at risk flooding is critical reducing these losses, yet until last few years such information was available for only a handful well-studied locations. This review surveys recent progress address this fundamental issue through novel combination appropriate physics, efficient numerical algorithms, high-performance computing, new sources big data, model automation frameworks. The describes fluid mechanics inundation models used predict it, before going on consider developments that have led in five creation first true over entire terrestrial land surface.

Language: Английский

---

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

Journal of Hydrology, Journal Year: 2021, Volume and Issue: 603, P. 126898 - 126898

Published: Sept. 4, 2021

This study investigates how deep-learning can be configured to optimise the prediction of 2D maximum water depth maps in urban pluvial flood events. A neural network model is trained exploit patterns hyetographs as well topographical data, with specific aim enabling fast predictions depths for observed rain events and spatial locations that have not been included training dataset. architecture widely used image segmentation (U-NET) adapted this purpose. Key novelties are a systematic investigation which inputs should provided deep learning model, hyper-parametrization optimizes predictive performance, evaluation performance were considered training. We find input dataset only 5 variables describe local terrain shape imperviousness optimal generate depth. Neural architectures between 97,000 260,000,000 parameters tested, 28,000,000 found optimal. U-FLOOD demonstrated yield similar existing screening approaches, even though assessment performed natural unknown network, generated within seconds. Improvements likely obtained by ensuring balanced representation temporal rainfall dataset, further improved datasets, linking dynamic sewer system models.

Language: Английский

---

Hydraulic modelling of inland urban flooding: Recent advances

Journal of Hydrology, Journal Year: 2022, Volume and Issue: 609, P. 127763 - 127763

Published: March 25, 2022

Language: Английский

---

A Review of Hydrodynamic and Machine Learning Approaches for Flood Inundation Modeling

Water, Journal Year: 2023, Volume and Issue: 15(3), P. 566 - 566

Published: Feb. 1, 2023

Machine learning (also called data-driven) methods have become popular in modeling flood inundations across river basins. Among data-driven methods, traditional machine (ML) approaches are widely used to model events, and recently deep (DL) gained more attention the world. In this paper, we reviewed published literature on ML DL applications for various hydrologic catchment characteristics. Our extensive review shows that models produce better accuracy compared approaches. Unlike physically based models, ML/DL suffer from lack of using expert knowledge events. Apart challenges implementing a uniform approach basins, benchmark data evaluate performance is limiting factor developing efficient inundation modeling.

Language: Английский

---

A review of recent advances in urban flood research

Water Security, Journal Year: 2023, Volume and Issue: 19, P. 100141 - 100141

Published: July 13, 2023

Due to a changing climate and increased urbanization, an escalation of urban flooding occurrences its aftereffects are ever more dire. Notably, the frequency extreme storms is expected increase, as built environments impede absorption water, threat loss human life property damages exceeding billions dollars heightened. Hence, agencies organizations implementing novel modeling methods combat consequences. This review details concepts, impacts, causes flooding, along with associated endeavors. Moreover, this describes contemporary directions towards flood resolutions, including recent hydraulic-hydrologic models that use modern computing architecture trending applications artificial intelligence/machine learning techniques crowdsourced data. Ultimately, reference utility provided, scientists engineers given outline advances in research.

Language: Английский

---

Deep learning enables super-resolution hydrodynamic flooding process modeling under spatiotemporally varying rainstorms

Water Research, Journal Year: 2023, Volume and Issue: 239, P. 120057 - 120057

Published: May 6, 2023

Language: Английский

---