Towards better flood risk management: Assessing flood risk and investigating the potential mechanism based on machine learning models

Chen, Jialei; Huang, Guoru; Chen, Wenjie

doi:10.1016/j.jenvman.2021.112810

Cited by 87 publications

(34 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the inputs used for flood susceptibility, such as elevation and land use, flood risk mapping may require also other inputs such as population density, spatial estimates of economic value, and building types. Up to now, only Chen et al (2021) combined DL and flood risk assessment. They showed that ML and DL approaches can estimate flood risk at regional scale, but do not compare their results against other methods, such as MCDA.…”

Section: Flood Applications and Usabilitymentioning

confidence: 99%

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Bentivoglio

Isufi

Jonkman

et al. 2022

Preprint

View full text Add to dashboard Cite

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

show abstract

Section: Flood Applications and Usabilitymentioning

confidence: 99%

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Bentivoglio

Isufi

Jonkman

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on a previous literature review, there are many indices used for disaster risk assessment. Most studies have identified that the risk is caused by the interaction of different factors, including disaster-causing factors (hazard), the disaster formative environment (sensitivity), and disaster bearers (vulnerability) [18,29,41]. Thus, the framework of the index system was established from the three aspects, hazard, sensitivity, and vulnerability (Figure 2).…”

Section: Study Areamentioning

confidence: 99%

“…Flood risk assessment and mapping is a crucial part of flood risk management, aiming to identify the location, magnitude, and distribution of risk areas under intense rainfall to provide key information for future urban planning and disaster mitigation [21,22]. At present, there are many kinds of methods for flood risk assessment, including hydrologic and hydraulic models [23,24], historical disaster mathematical statistics analysis [15,25], geographic information system (GIS) and remote sensing (RS) coupling analysis [26], scenario simulation analysis [27,28], machine learning models (MLMs) [29,30], and multi-criteria decision analysis (MCDA) [26,31,32]. Among these methods, historical disaster analysis is easy to implement based on the statistics of historical disasters, and its assessment results are generally consistent with reality.…”

Section: Introductionmentioning

confidence: 99%

Flood Risk Assessment under Land Use and Climate Change in Wuhan City of the Yangtze River Basin, China

Song

Lü

2021

Land

View full text Add to dashboard Cite

Frequently occurring flood disasters caused by extreme climate and urbanization processes have become the most common natural hazard and pose a great threat to human society. Therefore, urban flood risk assessment is of great significance for disaster mitigation and prevention. In this paper, the analytic hierarchy process (AHP) was applied to quantify the spatiotemporal variations in flood risk in Wuhan during 2000–2018. A comprehensive flood risk assessment index system was constructed from the hazard, sensitivity, and vulnerability components with seven indices. The results showed that the central urban area, especially the area in the west bank of the Yangtze river, had high risk due to its high flood sensitivity that was determined by land use type and high vulnerability with dense population and per unit GDP. Specifically, the Jianghan, Qiaokou, Jiangan, and Wuchang districts had the highest flood risk, more than 60% of whose area was in medium or above-medium risk regions. During 2000–2018, the flood risk overall showed an increasing trend, with Hongshan district increasing the most, and the year of 2010 was identified as a turning point for rapid risk increase. In addition, the comparison between the risk maps and actual historical inundation point records showed good agreement, indicating that the assessment framework and method proposed in this study can be useful to assist flood mitigation and management, and relevant policy recommendations were proposed based on the assessment results.

show abstract

“…The GBDT improves the capacity of the decision tree by reducing the residuals generated during the training procedure [22,23]. It has been widely applied in social science research [24][25][26][27][28] and gradually introduced into the field of natural science [1][2][3][4][5][6][7][29][30][31][32][33][34][35]. The GBDT exhibits much better performance in the retrieval of water depth compared with the single-band, dual-band, and BP neural network models [36].…”

Section: Introductionmentioning

confidence: 99%

Retrieval of Chlorophyll-a Concentrations in the Coastal Waters of the Beibu Gulf in Guangxi Using a Gradient-Boosting Decision Tree Model

et al. 2021

View full text Add to dashboard Cite

Remote sensing for the monitoring of chlorophyll-a (Chl-a) is essential to compensate for the shortcomings of traditional water quality monitoring, strengthen red tide disaster monitoring and early warnings, and reduce marine environmental risks. In this study, a machine learning approach called the Gradient-Boosting Decision Tree (GBDT) was employed to develop an algorithm for estimating the Chl-a concentrations of the coastal waters of the Beibu Gulf in Guangxi, using Landsat 8 OLI image data as the image source in combination with field measurements of Chl-a concentrations. The GBDT model with B4, B3 + B4, B3, B1 − B4, B2 + B4, B1 + B4, and B2 − B4 as input features exhibited higher accuracy (MAE = 0.998 μg/L, MAPE = 19.413%, and RMSE = 1.626 μg/L) compared with different physics models, providing a new method for remote sensing inversion of water quality parameters. The GBDT model was used to study the spatial distribution and temporal variation of Chl-a concentrations in the coastal sea surface of the Beibu Gulf of Guangxi from 2013 to 2020. The results showed a spatial distribution with high concentrations in nearshore waters and low concentrations in offshore waters. The Chl-a concentration exhibited seasonal changes (concentration in summer > autumn > spring ≈ winter).

show abstract

Towards better flood risk management: Assessing flood risk and investigating the potential mechanism based on machine learning models

Cited by 87 publications

References 37 publications

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Flood Risk Assessment under Land Use and Climate Change in Wuhan City of the Yangtze River Basin, China

Retrieval of Chlorophyll-a Concentrations in the Coastal Waters of the Beibu Gulf in Guangxi Using a Gradient-Boosting Decision Tree Model

Contact Info

Product

Resources

About