Depth prediction of urban flood under different rainfall return periods based on deep learning and data warehouse

Unraveling urban hydro-environmental response to climate change and MCDA-based area prioritization in a data-scarce developing city

Climate change leads to more frequent and intense heavy rainfall events, posing significant challenges for urban stormwater management, particularly in rapidly urbanizing cities of developing countries with constrained infrastructure. However, the quantitative assessment of urban stormwater, encompassing both its volume and quality, in these regions is impeded due to the scarcity of observational data and resulting limited understanding of drainage system dynamics. This study aims to elucidate the present and projected states of urban flooding, with a specific emphasis on fecal and organic contamination caused by combined sewer overflow (CSO). Leveraging a hydrological model incorporating physical and biochemical processes validated against invaluable observational data, we undertake simulations to estimate discharge, flood volume, and concentrations of suspended solids (SS), Escherichia coli (E. coli), and chemical oxygen demand (COD) within the drainage channel network of Phnom Penh City, Cambodia. Alterations in flood volumes, and pollutant concentrations and loads in overflow under two representative concentration pathways (RCPs 4.5 and 8.5) for extreme rainfall events are projected. Furthermore, we employ a multi-criteria decision analysis (MCDA) framework to evaluate flood risk, incorporating diverse indicators encompassing physical, social, and ecological dimensions. Our results demonstrate the exacerbating effects of climate change on flood volumes, expansion of flooded areas, prolonged durations of inundation, elevated vulnerability index, and heightened susceptibility to pollutant contamination under both scenarios, underscoring increased risks of flooding and fecal contamination. Spatial analysis identifies specific zones exhibiting heightened vulnerability to flooding and climate change, suggesting priority zones for investment in flood mitigation measures. These findings provide crucial insights for urban planning and stormwater management in regions with limited drainage infrastructure, offering essential guidance for decision-making in locales facing similar challenges.

Research on nowcasting prediction technology for flooding scenarios based on data-driven and real-time monitoring

With the impact of global climate change and the urbanization process, the risk of urban flooding has increased rapidly, especially in developing countries. Real-time monitoring and prediction of flooding extent and drainage system are the foundation of effective urban flood emergency management. Therefore, this paper presents a rapid nowcasting prediction method of urban flooding based on data-driven and real-time monitoring. The proposed method firstly adopts a small number of monitoring points to deduce the urban global real-time water level based on a machine learning algorithm. Then, a data-driven method is developed to achieve dynamic urban flooding nowcasting prediction with real-time monitoring data and high-accuracy precipitation prediction. The results show that the average MAE and RMSE of the urban flooding and conduit system in the deduction method for water level are 0.101 and 0.144, 0.124 and 0.162, respectively, while the flooding depth deduction is more stable compared to the conduit system by probabilistic statistical analysis. Moreover, the urban flooding nowcasting method can accurately predict the flooding depth, and the R2 are as high as 0.973 and 0.962 of testing. The urban flooding nowcasting prediction method provides technical support for emergency flood risk management.

A novel multi-strategy hydrological feature extraction (MHFE) method to improve urban waterlogging risk prediction, a case study of Fuzhou City in China

Reliable hydrological data ensure the precision of the urban waterlogging simulation. To reduce the simulation error caused by insufficient basic data, a multi-strategy method (MHFE) for extracting hydrological features is proposed, which includes land use/land cover (LULC) extraction (LE) and digital elevation model (DEM) reconstruction (DR). First, the high-resolution remote image, satellite DEM, precipitation, flood points and depth, and planned LULC were collected. Second, the buildings, roads, and other areas of the satellite image were segmented using the U-Net model, and the LULC data with drainage features were extracted by combining the segmentation result with the planned LULC and drainage data. Then, the terrain features of the road were enhanced to construct high-precision DEM based on the fusion of multi-source data, such as elevation points, LULC, and satellite DEM. Finally, the waterlogging model was implemented under different return periods of rainfalls and typhoon rainfall to obtain the waterlogging distribution and water depth. The simulation results were compared with historical waterlogging event data and water depth observations. The results indicated that the proposed method significantly improved the accuracy of the simulation. In terms of identifying the waterlogging points, the average F1 score increased by 0.36, 0.20, and 0.07 compared to the raw model and the single LE and DR methods, respectively. In terms of water depth simulation, the average Nash-Sutcliffe efficiency (NSE) was increased from -0.24 to 0.86, with DR and LE contributing to 79.1 % and 20.9 %, respectively. The principal contribution and novelty of this paper is to explore the generic method that enhance the hydrological data, and the findings of this study improved the performance of urban waterlogging simulation.

Novel integrated modelling based on multiplicative long short-term memory (mLSTM) deep learning model and ensemble multi-criteria decision making (MCDM) models for mapping flood risk

Flood risk assessment is a key step in flood management and mitigation, and flood risk maps provide a quantitative measure of flood risk. Therefore, integration of deep learning - an updated version of machine learning techniques - and multi-criteria decision making (MCDM) models can generate high-resolution flood risk maps. In this study, a novel integrated approach has been developed based on multiplicative long short-term memory (mLSTM) deep learning models and an MCDM ensemble model to map flood risk in the Minab-Shamil plain, southern Iran. A flood hazard map generated by the mLSTM model is based on nine critical features selected by GrootCV (distance to the river, vegetation cover, variables extracted from DEM (digital elevation model) and river density) and a flood inventory map (70% and 30% data were randomly selected as training and test datasets, respectively). The values of all criteria used to assess model accuracy performance (except Cohens kappa for train dataset = 86, and for test dataset = 84) achieved values greater than 90, which indicates that the mLSTM model performed very well for the generation of a spatial flood hazard map. According to the spatial flood hazard map produced by mLSTM, the very low, low, moderate, high and very high classes cover 26%, 35.3%, 20.5%, 11.2% and 7% of the total area, respectively. Flood vulnerability maps were produced by the combinative distance-based assessment (CODAS), the evaluation based on distance from average solution (EDAS), and the multi-objective optimization on the basis of simple ratio analysis (MOOSRA), and then validated by Spearman's rank correlation coefficients (SRC). Based on the SRC, the three models CODAS, EDAS, and MOOSRA showed high-ranking correlations with each other, and all three models were then used in the ensemble process. According to the CODAS-EDAS-MOOSRA ensemble model, 21.5%, 34.2%, 23.7%, 13%, and 7.6% of the total area were classified as having a very low to very high flood vulnerability, respectively. Finally, a flood risk map was generated by the combination of flood hazard and vulnerability maps produced by the mLSTM and MCDM ensemble model. According to the flood risk map, 27.4%, 34.3%, 14.8%, 15.7%, and 7.8% of the total area were classified as having a very low, low, moderate, high, and very high flood risk, respectively. Overall, the integration of mLSTM and the MCDM ensemble is a promising tool for generating precise flood risk maps and provides a useful reference for flood risk management.

A noval approach based on TCN-LSTM network for predicting waterlogging depth with waterlogging monitoring station

As a result of climate change and rapid urbanization, urban waterlogging commonly caused by rainstorm, is becoming more frequent and more severe in developing countries. Urban waterlogging sometimes results in significant financial losses as well as human casualties. Accurate waterlogging depth prediction is critical for early warning system and emergency response. However, the existing hydrological models need to obtain more abundant hydrological data, and the model construction is complicated. The waterlogging depth prediction technology based on object detection model are highly dependent on image data. To solve the above problem, we propose a novel approach based on Temporal Convolutional Networks and Long Short-Term Memory networks to predicting urban waterlogging depth with Waterlogging Monitoring Station. The difficulty of data acquisition is small though Waterlogging Monitoring Station and TCN-LSTM model can be used to predict timely waterlogging depth. Waterlogging Monitoring Station is developed which integrates an automatic rain gauge and a water gauge. The rainfall and waterlogging depth can be obtained by periodic sampling at some areas with Waterlogging Monitoring Station. Precise hydrological data such as waterlogging depth and rainfall collected by Waterlogging Monitoring Station are used as training samples. Then training samples are used to train TCN-LSTM model, and finally a model with good prediction effect is obtained. The experimental results show that the difficulty of data acquisition is small, the complexity is low and the proposed TCN-LSTM hybrid model can properly predict the waterlogging depth of the current regional. There is no need for high dependence on image data. Meanwhile, compared with machine learning model and RNN model, TCN-LSTM model has higher prediction accuracy for time series data. Overall, the low-cost method proposed in this study can be used to obtain timely waterlogging warning information, and enhance the possibility of using existing social networks and traffic surveillance video systems to perform opportunistic waterlogging sensing.

Urban flood risk differentiation under land use scenario simulation

The frequent urban floods have seriously affected the regional sustainable development in recent years. It is significant to understand the characteristics of urban flood risk and reasonably predict urban flood risk under different land use scenarios. This study used the random forest and multi-criteria decision analysis models to assess the spatiotemporal characteristics of flood risk in Zhengzhou City, China, from 2005 to 2020, and proposed a robust method coupling Bayesian network and patch-generating land use simulation models to predict future flood risk probability. We found that the flood risk in Zhengzhou City presented an upward trend from 2005 to 2020, and its spatial pattern was "high in the middle and low in the surrounding areas". In addition, land use patterns under the sustainable development scenario would be more conducive to reducing flood risk. Our results can provide theoretical support for scientifically optimizing land use to improve urban flood risk management.

Prediction of monthly precipitation using various artificial models and comparison with mathematical models

Precipitation (PP) prediction is an interesting topic in the meteorology or hydrology field since it is directly related to agriculture, the management of water resources in hydrologic basins, and water scarcity. Selecting the right model to predict precipitation has always been a challenge because it could help researchers to use the proper model for their purposes. Accordingly, the performance of five artificial models (feed-forward neural network, cascade forward neural network, Elman neural network, multi-layer perceptron neural network, and radial basis neural network) and three mathematical models (Poisson regression model (PRM), quadratic model, and multiple linear regression) were evaluated for their ability to predict the monthly precipitation in Mediterranean coastal cities located in Eastern part of Mediterranean Sea for the first time. Twenty-seven Mediterranean coastal cities are considered case studies. For this aim, scenario 1 and scenario 2 with various input variables are proposed. Scenario 1 is developed using the number of months (MN), maximum temperature (Tmax), minimum temperature (Tmin), downward radiation (DR), wind speed (WS), vapor pressure (VP), and actual evapotranspiration (AE). Scenario 2 is developed by adding geographical coordinates (latitude, longitude, and altitude) to the global meteorological data to see the impact of geographical coordinates on the accuracy of the prediction of monthly precipitation. This study utilized the monthly data, which were obtained from TerraClimate for the period from 2010 to 2021. Based on the performance indexes, the PRM model performed best for the prediction of monthly precipitation in all selected locations compared to other models. Moreover, the results indicate that scenario 2 ([Formula: see text]) has shown higher prediction accuracy compared to scenario 1 ([Formula: see text]). In conclusion, PRM with the combination of [[Formula: see text]] had RMSE value that was lower by 12% relative to PRM with the combination of [[Formula: see text]]. Consequently, the PRM model can be recommended for modeling the complexity of interactions for precipitation-climate conditions-geographical coordinates and predicting precipitation.

Multi-Source Data Fusion and Hydrodynamics for Urban Waterlogging Risk Identification

The complex formation mechanism and numerous influencing factors of urban waterlogging disasters make the identification of their risk an essential matter. This paper proposes a framework for identifying urban waterlogging risk that combines multi-source data fusion with hydrodynamics (MDF-H). The framework consists of a source data layer, a model parameter layer, and a calculation layer. Using multi-source data fusion technology, we processed urban meteorological information, geographic information, and municipal engineering information in a unified computation-oriented manner to form a deep fusion of a globalized multi-data layer. In conjunction with the hydrological analysis results, the irregular sub-catchment regions are divided and utilized as calculating containers for the localized runoff yield and flow concentration. Four categories of source data, meteorological data, topographic data, urban underlying surface data, and municipal and traffic data, with a total of 12 factors, are considered the model input variables to define a real-time and comprehensive runoff coefficient. The computational layer consists of three calculating levels: total study area, sub-catchment, and grid. The surface runoff inter-regional connectivity is realized at all levels of the urban road network when combined with hydrodynamic theory. A two-level drainage capacity assessment model is proposed based on the drainage pipe volume density. The final result is the extent and depth of waterlogging in the study area, and a real-time waterlogging distribution map is formed. It demonstrates a mathematical study and an effective simulation of the horizontal transition of rainfall into the surface runoff in a large-scale urban area. The proposed method was validated by the sudden rainstorm event in Futian District, Shenzhen, on 11 April 2019. The average accuracy for identifying waterlogging depth was greater than 95%. The MDF-H framework has the advantages of precise prediction, rapid calculation speed, and wide applicability to large-scale regions.

A practical method for rehabilitation of stormwater collecting system by node flooding detection and regional hydraulic redesign: a case study of eastern Tehran metropolis

This study investigates the effect of structural modification actions on the existing stormwater collecting system in Eastern Tehran to increase the hydraulic capacity and create suitable conditions for the passage of runoff in the critical points of the canal. First, the hydraulic conditions within the stormwater collecting system were simulated using the Stormwater Management Model (SWMM) model before/after the modification to investigate the rehabilitation results. Three critical locations along the main canal were recognized as the most vulnerable points. Then, based on field visits and brainstorming sessions, rehabilitation methods were presented, and three practical solutions, including canal deepening, canal widening, and their combination, were investigated for each. Then, local investigating based on the rehabilitation alternatives for each critical location was conducted using the HEC-RAS. Finally, the SWMM model was used again to evaluate the overall operational performance of the stormwater collecting system after the rehabilitation. The results revealed that it is necessary to implement two alternatives of deepening and widening to provide adequate transmission runoff capacity during rainfalls with various return periods. More specifically, the localized redesign of the eastern flood diversion canal had an acceptable improvement in reducing flooding problems so that for floods with a return period of 10 years, the number of node flooding dropped from 4 to 0, inundated areas from 17% to 0, and the overflow volume from (10-45) to 0. Moreover, the proposed local rehabilitation reduced the overflow volume from (30-65), (43-74), and (70-92) in the status quo to (4-12), (11-27), and (24-36) for rainfall with 25, 50, and 100-year return periods.

Rainstorm Disaster Risk Assessment and Influence Factors Analysis in the Yangtze River Delta, China

Rainstorm disasters have had a serious impact on the sustainable development of society and the economy. However, due to the complexity of rainstorm disasters, it is difficult to measure the importance of each indicator. In this paper, the rainstorm disaster risk assessment framework was systematically proposed based on the disaster system theory and a system of corresponding indicators was established. Furthermore, the genetic algorithm optimized projection pursuit and XGBoost were coupled to assess the rainstorm disaster risk and to measure the relative importance of each indicator. Finally, the Yangtze River Delta was taken as the case study area. The results show that: the rainstorm disaster risk in the eastern and southeast is higher than those in the central and northwest of the Yangtze River Delta; the total precipitation from June to September and the top ten indicators contribute 9.34% and 74.20% to the rainstorm disaster risk assessment results, respectively. The results can provide references for decision makers and are helpful for the formulation of rainstorm adaptation strategies.

Understanding the Use of Heterogenous Data in Tackling Urban Flooding: An Integrative Literature Review

Data-driven approaches to urban flooding management require a comprehensive understanding of how heterogenous data are leveraged in tackling this problem. In this paper, we conduct an integrative review of related studies, and this is structured based on two angles: tasks and data. From the selected 69 articles on this topic, diverse tasks in tackling urban flooding are identified and categorized into eight categories, and heterogeneous data are summarized by their content type and source into eight categories. The links between tasks and data are identified by synthesizing what data are used to support the tasks in the studies. The task–data links are a many-to-many relationship in the sense that one particular data category supports multiple tasks, and one particular task uses data from multiple categories. The future research opportunities are also discussed based on our observations. This paper serves a signpost for researchers who wish to gain an overview of the heterogenous data and their use in this field and lays a foundation for studies that aim to develop a data-driven approach to tackle urban flooding.

Greening the city: Thriving for biodiversity and sustainability

Urban population and urbanisation are increasing rapidly, mainly in developing countries, usually at the expense of green and blue areas. This trend will decrease the ecosystems' capacity to supply ecosystem services (ES) and threaten human wellbeing. Therefore, it is key to establish greening policies in urbanising areas, which are essential to improve the liveability of cities. Restoring and developing green and blue infrastructures using nature-based solutions is vital to improving urban biodiversity and urban ecosystems. Healthy urban ecosystems have a high capacity to supply regulating (e.g., air, noise, climate and water regulation), provisioning (e.g., food, medicinal plants, biomass) and cultural (e.g., recreation, landscape aesthetics, social cohesion) ES. This multifunctionality can provide diverse environmental, social and economic benefits to urban residents, hence contributing to the sustainability of urban areas. However, urban green and blue areas are also associated with ecosystem disservices (e.g., plant allergies or poisoning, emission of biogenic volatile organic compounds, unpleasant smells), tradeoffs (e.g., increased water consumption, wildfire risk, associated management costs) and implementation barriers (e.g., political motivation, lack of knowledge, time and workload). Overall, the SI published 8 articles from different parts of the world, such as China, the USA, Italy or Spain, focused on important aspects of greening the city (e.g., green roofs, green walls, green infrastructures, sustainable mobility).

Likelihood of Transformation to Green Infrastructure Using Ensemble Machine Learning Techniques in Jinan, China

Rapid urbanization influences green infrastructure (GI) development in cities. The government plans to optimize GI in urban areas, which requires understanding GI spatiotemporal trends in urban areas and driving forces influencing their pattern. Traditional GIS-based methods, used to determine the greening potential of vacant land in urban areas, are incapable of predicting future scenarios based on the past trend. Therefore, we propose a heterogeneous ensemble technique to determine the spatial pattern of GI development in Jinan, China, based on driving biophysical and socioeconomic factors. Data-driven artificial neural networks (ANN) and random forests (RF) are selected as base learners, while support vector machine (SVM) is used as a meta classifier. Results showed that the stacking model ANN-RF-SVM achieved the best test accuracy (AUC 0.941) compared to the individual ANN, RF, and SVM algorithms. Land surface temperature, distance to water bodies, population density, and rainfall are found to be the most influencing factors regarding vacant land conversion to GI in Jinan.

Runoff Prediction Based on the Discharge of Pump Stations in an Urban Stream Using a Modified Multi-Layer Perceptron Combined with Meta-Heuristic Optimization

Runoff in urban streams is the most important factor influencing urban inundation. It also affects inundation in other areas as various urban streams and rivers are connected. Current runoff predictions obtained using a multi-layer perceptron (MLP) exhibit limited accuracy. In this study, the runoff of urban streams was predicted by applying an MLP using a harmony search (MLPHS) to overcome the shortcomings of MLPs using existing optimizers and compared with the observed runoff and the runoff predicted by an MLP using a real-coded genetic algorithm (RCGA). Furthermore, the results of the MLPHS were compared with the results of the MLP with existing optimizers such as the stochastic gradient descent, adaptive gradient, and root mean squared propagation. The runoff of urban steams was predicted based on the discharge of each pump station and rainfall information. The results obtained with the MLPHS exhibited the smallest error of 39.804 m3/s when compared to the peak value of the observed runoff. The MLPHS gave more accurate runoff prediction results than the MLP using the RCGA and that using existing optimizers. The accurate prediction of the runoff in an urban stream using an MLPHS based on the discharge of each pump station is possible.

Research Progress of Urban Floods under Climate Change and Urbanization: A Scientometric Analysis

Urban floods research has been attracting extensive attention with the increasing threat of flood risk and environmental hazards due to global climate change and urbanization. However, there is rarely a comprehensive review of this field and it remains unclear how the research topics on urban floods have evolved. In this study, we analyzed the development of urban floods research and explored the hotspots and frontiers of this field by scientific knowledge mapping. In total, 3314 published articles from 2006 to 2021 were analyzed. The results suggest that the number of published articles in the field of urban floods generally has an upward trend year by year, and the research focus has shifted from exploring hydrological processes to adopting advanced management measures to solve urban flood problems. Moreover, urban stormwater management and low impact development in the context of climate change and urbanization have gradually become research hotspots. Future research directions based on the status and trends of the urban floods field were also discussed. This research can not only inspire other researchers and policymakers, but also demonstrates the effectiveness of scientific knowledge mapping analysis by the use of the software CiteSpace and VOSviewer.

Toward an Integrated Disaster Management Approach: How Artificial Intelligence Can Boost Disaster Management

Technical and methodological enhancement of hazards and disaster research is identified as a critical question in disaster management. Artificial intelligence (AI) applications, such as tracking and mapping, geospatial analysis, remote sensing techniques, robotics, drone technology, machine learning, telecom and network services, accident and hot spot analysis, smart city urban planning, transportation planning, and environmental impact analysis, are the technological components of societal change, having significant implications for research on the societal response to hazards and disasters. Social science researchers have used various technologies and methods to examine hazards and disasters through disciplinary, multidisciplinary, and interdisciplinary lenses. They have employed both quantitative and qualitative data collection and data analysis strategies. This study provides an overview of the current applications of AI in disaster management during its four phases and how AI is vital to all disaster management phases, leading to a faster, more concise, equipped response. Integrating a geographic information system (GIS) and remote sensing (RS) into disaster management enables higher planning, analysis, situational awareness, and recovery operations. GIS and RS are commonly recognized as key support tools for disaster management. Visualization capabilities, satellite images, and artificial intelligence analysis can assist governments in making quick decisions after natural disasters.

Ensemble Learning Technology for Coastal Flood Forecasting in Internet-of-Things-Enabled Smart City

Flooding is becoming a prominent issue in coastal cities, flood forecasting is the key to solving this problem. However, the lack and imbalance of research data and the insufficient performance of the model have led to the complexity and uncontrollability of flood forecasting. To forecast coastal floods accurately and reliably, the Internet of Things technology is used to collect data on floods and flood factors in smart cities. An ensemble learning method based on Bayesian model combination (BMC-EL) is designed to predict flood depth. First, flood intensity classification and K-fold cross-validation are introduced to generate multiple training subsets from the training set to realize uniform sampling and increase the diversity of subsets. Second, the backpropagation neural network (BPNN) and random forest (RF) are used as the base learners to build the prediction model and then import it into training subsets for training purposes. Finally, based on the prediction performance of the base learner in the validation sets, the Bayesian model combination strategy is formulated to integrate and output predicted values. We describe experiments conducted to forecast flood depth 1 h in advance that several machine learning models were trained and tested using real flood data taken from Macao, China. The models include linear regression, support vector machine, BPNN, RF and BMC-EL models. Results prove the accuracy and reliability of the BMC-EL method in flood forecasting for coastal cities.

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

Integrating powerful machine learning models with flood risk assessment and determining the potential mechanism between risk and the driving factors are crucial for improving flood management. In this study, six machine learning models were utilized for flood risk assessment of the Pearl River Delta, in which the Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGBoost), and Convolutional Neural Network (CNN) models were firstly applied in this field. Twelve indices were chosen and 2000 sample points were created for model training and testing. Hyperparameter optimization of the models was conducted to ensure fair comparisons. Due to uncertainty in the sample dataset, recorded inundation hot-spots were utilized to validate the rationality of the flood risk zoning maps. After determining the optimal model, the driving factors of different flood risk levels were investigated. Urban and rural areas and coastal and inland areas were also compared to determine the flood risk mechanism in different highest-risk areas. The results showed that the GBDT performed best and provided the most reasonable flood risk result among the six models. A comparison of the driving factors at different risk levels indicated that the disaster-inducing factor, disaster-breeding environment, and disaster-bearing body were not definitely becoming more serious as the flood risk increased. In the highest-risk areas, rural areas were featured by worse disaster-breeding environment than urban areas, and the disaster-inducing factors of coastal areas were more serious than those of inland areas. Moreover, the Digital Elevation Model (DEM), maximum 1-day precipitation (M1DP), and road density (RD) were the top three significant driving factors and contributed 52% to flood risk. This study not only expands the application of machine learning and deep learning methods for flood risk assessment, but also deepens our understanding of the potential mechanism of flood risk and provides insights into better flood risk management.

Urban Flood Analysis in Ungauged Drainage Basin Using Short-Term and High-Resolution Remotely Sensed Rainfall Records

Analyzing flooding in urban areas is a great challenge due to the lack of long-term rainfall records. This study hereby seeks to propose a modeling framework for urban flood analysis in ungauged drainage basins. A platform called “RainyDay” combined with a nine-year record of hourly, 0.1° remotely sensed rainfall data are used to generate extreme rainfall events. These events are used as inputs to a hydrological model. The comprehensive characteristics of urban flooding are reflected through the projection pursuit method. We simulate runoff for different return periods for a typical urban drainage basin. The combination of RainyDay and short-record remotely sensed rainfall can reproduce recent observed rainfall frequencies, which are relatively close to the design rainfall calculated by the intensity-duration-frequency formula. More specifically, the design rainfall is closer at high (higher than 20-yr) return period or long duration (longer than 6 h). Contrasting with the flood-simulated results under different return periods, RainyDay-based estimates may underestimate the flood characteristics under low return period or short duration scenarios, but they can reflect the characteristics with increasing duration or return period. The proposed modeling framework provides an alternative way to estimate the ensemble spread of rainfall and flood estimates rather than a single estimate value.

Key Disaster-Causing Factors Chains on Urban Flood Risk Based on Bayesian Network

Drivers of urban flood disaster risk may be related to many factors from nature and society. However, it is unclear how these factors affect each other and how they ultimately affect the risk. From the perspective of risk uncertainty, flood inundation risk is considered to be the probability of inundation consequences under the influence of various factors. In this paper, urban flood inundation risk assessment model is established based on Bayesian network, and then key disaster-causing factors chains are explored through influence strength analysis. Jingdezhen City is selected as study area, where the flood inundation probability is calculated, and the paths of these influential factors are found. The results show that the probability of inundation in most areas is low. Risk greater than 0.8 account for about 9%, and most of these areas are located in the middle and southern section of the city. The influencing factors interact with each other in the form of factor chain and, finally, affect the flood inundation. Rainfall directly affects inundation, while river is the key factor on inundation which is influenced by elevation and slope. In addition, in the chain of socio-economic factors, the population will determine the pipe density through affecting gross domestic product (GDP), and lead to the inundation. The approach proposed in this study can be used to find key disaster-causing factors chains, which not only quantitatively reveal the formation of risks but also provide reference for early warning.

Using Multi-Factor Analysis to Predict Urban Flood Depth Based on Naive Bayes

With global warming, the number of extreme weather events will increase. This scenario, combined with accelerating urbanization, increases the likelihood of urban flooding. Therefore, it is necessary to predict the characteristics of flooded areas caused by rainstorms, especially the flood depth. We applied the Naive Bayes theory to construct a model (NB model) to predict urban flood depth here in Zhengzhou. The model used 11 factors that affect the extent of flooding—rainfall, duration of rainfall, peak rainfall, the proportion of roads, woodlands, grasslands, water bodies and building, permeability, catchment area, and slope. The forecast depth of flooding from the NB model under different rainfall conditions was used to draw an urban inundation map by ArcGIS software. The results show that the probability and degree of urban flooding in Zhengzhou increases significantly after a return period of once every two years, and the flooded areas mainly occurred in older urban areas. The average root mean square error of prediction results was 0.062, which verifies the applicability and validity of our model in the depth prediction of urban floods. Our findings suggest the NB model as a feasible approach to predict urban flood depth.

Improving the Resolution and Accuracy of Groundwater Level Anomalies Using the Machine Learning-Based Fusion Model in the North China Plain

The launch of GRACE satellites has provided a new avenue for studying the terrestrial water storage anomalies (TWSA) with unprecedented accuracy. However, the coarse spatial resolution greatly limits its application in hydrology researches on local scales. To overcome this limitation, this study develops a machine learning-based fusion model to obtain high-resolution (0.25°) groundwater level anomalies (GWLA) by integrating GRACE observations in the North China Plain. Specifically, the fusion model consists of three modules, namely the downscaling module, the data fusion module, and the prediction module, respectively. In terms of the downscaling module, the GRACE-Noah model outperforms traditional data-driven models (multiple linear regression and gradient boosting decision tree (GBDT)) with the correlation coefficient (CC) values from 0.24 to 0.78. With respect to the data fusion module, the groundwater level from 12 monitoring wells is incorporated with climate variables (precipitation, runoff, and evapotranspiration) using the GBDT algorithm, achieving satisfactory performance (mean values: CC: 0.97, RMSE: 1.10 m, and MAE: 0.87 m). By merging the downscaled TWSA and fused groundwater level based on the GBDT algorithm, the prediction module can predict the water level in specified pixels. The predicted groundwater level is validated against 6 in-situ groundwater level data sets in the study area. Compare to the downscaling module, there is a significant improvement in terms of CC metrics, on average, from 0.43 to 0.71. This study provides a feasible and accurate fusion model for downscaling GRACE observations and predicting groundwater level with improved accuracy.

Machine learning for predicting greenhouse gas emissions from agricultural soils

Machine learning (ML) models are increasingly used to study complex environmental phenomena with high variability in time and space. In this study, the potential of exploiting three categories of ML regression models, including classical regression, shallow learning and deep learning for predicting soil greenhouse gas (GHG) emissions from an agricultural field was explored. Carbon dioxide (CO₂) and nitrous oxide (N₂O) fluxes, as well as various environmental, agronomic and soil data were measured at the site over a five-year period in Quebec, Canada. The rigorous analysis, which included statistical comparison and cross-validation for the prediction of CO₂ and N₂O fluxes, confirmed that the LSTM model performed the best among the considered ML models with the highest R coefficient and the lowest root mean squared error (RMSE) values (R = 0.87 and RMSE = 30.3 mg·m^-2·hr^-1 for CO₂ flux prediction and R = 0.86 and RMSE = 0.19 mg·m^-2·hr^-1 for N₂O flux prediction). The predictive performances of LSTM were more accurate than those simulated in a previous study conducted by a biophysical-based Root Zone Water Quality Model (RZWQM2). The classical regression models (namely RF, SVM and LASSO) satisfactorily simulated cyclical and seasonal variations of CO₂ fluxes (R = 0.75, 0.71 and 0.68, respectively); however, they failed to reasonably predict the peak values of N₂O fluxes (R < 0.25). Shallow ML was found to be less effective in predicting GHG fluxes than other considered ML models (R < 0.7 for CO₂ flux and R < 0.3 for estimating N₂O fluxes) and was the most sensitive to hyperparameter tuning. Based on this comprehensive comparison study, it was elicited that the LSTM model can be employed successfully in simulating GHG emissions from agricultural soils, providing a new perspective on the application of machine learning modeling for predicting GHG emissions to the environment.

Soil Temperature Estimation with Meteorological Parameters by Using Tree-Based Hybrid Data Mining Models

The temperature of the soil at different depths is one of the most important factors used in different disciplines, such as hydrology, soil science, civil engineering, construction, geotechnology, ecology, meteorology, agriculture, and environmental studies. In addition to physical and spatial variables, meteorological elements are also effective in changing soil temperatures at different depths. The use of machine-learning models is increasing day by day in many complex and nonlinear branches of science. These data-driven models seek solutions to complex and nonlinear problems using data observed in the past. In this research, decision tree (DT), gradient boosted trees (GBT), and hybrid DT–GBT models were used to estimate soil temperature. The soil temperatures at 5, 10, and 20 cm depths were estimated using the daily minimum, maximum, and mean temperature; sunshine intensity and duration, and precipitation data measured between 1993 and 2018 at Divrigi station in Sivas province in Turkey. To predict the soil temperature at different depths, the time windowing technique was used on the input data. According to the results, hybrid DT–GBT, GBT, and DT methods estimated the soil temperature at 5 cm depth the most successfully, respectively. However, the best estimate was obtained with the DT model at soil depths of 10 and 20 cm. According to the results of the research, the accuracy rate of the models has also increased with increasing soil depth. In the prediction of soil temperature, sunshine duration and air temperature were determined as the most important factors and precipitation was the most insignificant meteorological variable. According to the evaluation criteria, such as Nash-Sutcliffe coefficient, R, MAE, RMSE, and Taylor diagrams used, it is recommended that all three (DT, GBT, and hybrid DT–GBT) data-based models can be used for predicting soil temperature.