Urban pluvial flooding prediction by machine learning approaches – a case study of Shenzhen city, China

Ke, Qian; Tian, Xuemin; Bricker, Jeremy D.; Tian, Zhan; Guan, Guanghua; Cai, Huayang; Huang, Xinxing; Yang, Haiguang; Liu, Junguo

doi:10.1016/j.advwatres.2020.103719

Cited by 82 publications

(35 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Urban floods are one of the most important hydrometeorological risks faced by urban areas [6][7][8][9] and their impacts affect a large percentage of the population and the economic activities given the tendency for people to live in cities [10][11][12][13][14]. Various studies [10,[15][16][17][18][19][20][21] consider that the increase in the frequency of intense storms is directly responsible for the occurrence of more urban floods. However, concentrating only on the effect of the meteorological hazards [11,22,23] would reduce the problem to a "naturalistic" focus on natural disasters.…”

Section: Introductionmentioning

confidence: 99%

Effect of Urban Development in Risk of Floods in Veracruz, Mexico

2020

View full text Add to dashboard Cite

Urban floods have adverse effects on the population and the economy, and they are increasing in frequency and magnitude. The State of Veracruz is the region of Mexico with the highest number of disasters, more than 50% of the total number nationwide, in the 1970–2015 period. During the 1990s, disasters in this region increased from 5 to 10 events per year, mostly in relation to intense rains and floods. This study analyzes the factors that increase the risk of urban floods in the regions: (i) the Pánuco River, (ii) the Papaloapan River, and (iii) the Coatzacoalcos River regions, combining hazard data and estimates of vulnerability factors. The 95th percentile of daily precipitation (P95) is used as a threshold of heavy rain, i.e., the natural hazard. Vulnerability is estimated in terms of the percentage of natural vegetation loss due to changes in land cover and land use in the hydrological basins and the expansion of the urban areas in the regions under study. The risk of flood was compared with records of flood events focusing on the low-frequency variations of risks and disaster activity. The trends in urban flood activity are related to the loss of natural vegetation and deterioration of the basins leading to a loss of infiltration, i.e., larger runoffs. Even when the intensity of precipitation in recent decades remains without clear trends, or shows negative tendencies in the number of intense events, the number of floods is higher mostly because of the deterioration of hydrologic basins. Therefore, the risk of flooding in the state of Veracruz is mainly related to environmental factors that result in vulnerability rather than changes in the trends of extreme precipitation activity. This result means that disaster risk reduction actions should be mainly related to rehabilitation of the basins.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of Urban Development in Risk of Floods in Veracruz, Mexico

2020

View full text Add to dashboard Cite

show abstract

“…Some scholars also applied integrated algorithms such as adaptive-network-based fuzzy inference system (ANFIS) and genetic algorithm based artificial neural network to identify waterlogging risk areas [10]. Ke et al applied machine learning approaches to simulate urban flooding in the Shenzhen city [2].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Almost all rainwater discharge outlets in the Futian District are flat rectangular discharge outlets. According to the number, shape and size of the drainage outlets in each subcatchment area, the drainage capacity per unit time can be expressed as Equation (2). Combined with rainfall duration, the total drainage volume of each subcatchment area can be calculated [15].…”

Section: Evaluation Of Drainage Capacitymentioning

confidence: 99%

“…When encountering some extreme rainstorm or typhoon events, the intensity of the rainstorm far exceeds the designed drainage capacity, and the surface water cannot be discharged in time, resulting in surface runoff and stagnant water [2]. The identification of urban waterlogging and inundation risk can help predict the distribution range, depth and flow rate of accumulated water under different rainstorm intensities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Urban Rainstorm Waterlogging Based on Multi-source Information Fusion：A Case Study in Futian District, Shenzhen

et al. 2021

Self Cite

View full text Add to dashboard Cite

Flood disasters have become one of the most threatening natural disasters in the world, in which waterlogging is the most common form in the context of highly urbanized megacities. The formation of flood disaster is related to many factors and involves information from multiple sources, making it difficult be predicted. This paper integrates multi-source information data, classifies the study area into different categories according to hydrological analysis results, and combines hydrodynamic theory and ArcGIS to get the quantitative prediction of the range and depth of waterlogging under different rainfall inputs. The evaluation results provide the government with accurate and timely information of waterlogging risks and locations in order to improve promptness of emergency management such as evacuation and managing traffics.

show abstract

“…Recent advancements in Machine Learning (ML) modeling techniques can address and overcome the difficulties that beset physically-based models, giving impetus to using data-driven algorithms and ML modeling in reservoir inflow forecasting, among others. ML algorithms can be applied to forecast reservoir inflow by relying on relevant data rather than simulating the hydrological processes involved 16 . The advantages of using ML algorithms are easier and faster implementation, less computational effort, and reduced complexity compared to the physically-based models, particularly the distributed type variety 17 , 18 .…”

Section: Introductionmentioning

confidence: 99%

Machine-learning algorithms for forecast-informed reservoir operation (FIRO) to reduce flood damages

Zarei

Bozorg‐Haddad

Baghban

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Water is stored in reservoirs for various purposes, including regular distribution, flood control, hydropower generation, and meeting the environmental demands of downstream habitats and ecosystems. However, these objectives are often in conflict with each other and make the operation of reservoirs a complex task, particularly during flood periods. An accurate forecast of reservoir inflows is required to evaluate water releases from a reservoir seeking to provide safe space for capturing high flows without having to resort to hazardous and damaging releases. This study aims to improve the informed decisions for reservoirs management and water prerelease before a flood occurs by means of a method for forecasting reservoirs inflow. The forecasting method applies 1- and 2-month time-lag patterns with several Machine Learning (ML) algorithms, namely Support Vector Machine (SVM), Artificial Neural Network (ANN), Regression Tree (RT), and Genetic Programming (GP). The proposed method is applied to evaluate the performance of the algorithms in forecasting inflows into the Dez, Karkheh, and Gotvand reservoirs located in Iran during the flood of 2019. Results show that RT, with an average error of 0.43% in forecasting the largest reservoirs inflows in 2019, is superior to the other algorithms, with the Dez and Karkheh reservoir inflows forecasts obtained with the 2-month time-lag pattern, and the Gotvand reservoir inflow forecasts obtained with the 1-month time-lag pattern featuring the best forecasting accuracy. The proposed method exhibits accurate inflow forecasting using SVM and RT. The development of accurate flood-forecasting capability is valuable to reservoir operators and decision-makers who must deal with streamflow forecasts in their quest to reduce flood damages.

show abstract

Urban pluvial flooding prediction by machine learning approaches – a case study of Shenzhen city, China

Cited by 82 publications

References 46 publications

Effect of Urban Development in Risk of Floods in Veracruz, Mexico

Effect of Urban Development in Risk of Floods in Veracruz, Mexico

Identification of Urban Rainstorm Waterlogging Based on Multi-source Information Fusion：A Case Study in Futian District, Shenzhen

Machine-learning algorithms for forecast-informed reservoir operation (FIRO) to reduce flood damages

Contact Info

Product

Resources

About