Groundwater Table Level Research Articles

Investigation of submarine groundwater discharge and associated nutrient inputs into Laizhou Bay (China) using radium quartet

Radium is widely used to estimate flushing time, submarine groundwater discharge (SGD), and submarine fresh groundwater discharge (SFGD), however there are important sources of uncertainty in current methods. Here an improved method is proposed, incorporating all radium quartet information to estimate flushing time, SFGD, SGD, and associated nutrient fluxes during wet and dry seasons in Laizhou Bay, China. Both SGD and SFGD in dry season are comparable to that in wet season, likely due to higher groundwater hydraulic gradients resulting from higher groundwater table and lower mean sea level in dry season. Estimated dry and wet season SFGD are of the same order of magnitude as the annually-averaged Yellow River discharge, highlighting SFGD's importance to the bay environment. Nutrient inputs into Laizhou Bay were estimated for the wet season, suggesting that SGD-derived nutrients are indeed important and significant for coastal environments compared to local river discharge estimates.

EXPERIMENTAL INVESTIGATION ON MATERIAL QUALITY OF ASPHALT IN JIMMA TOWN ROAD PROJECT

The repetitive traffic loadings that the road experiences during its service life, combined with temperature fluctuations, cause rutting, fatigue and other forms of deteriorations, which ultimately degrade the performance and durability of pavement structures. According to test procedure specified by ASTM D1559 several hot asphalt mixture were prepared, the aggregate blend made by Job mix formula to obtain the percentage of mix material is give Hot-bin one is 26%, Hot-bin two is 23%, and Hot-bin three 51% where hot-bin one is (20-13.2mm), hot-bin two (13.2-5.0mm) and hot-bin three (5.0-0.00mm). The result of Marshall Test on mix design for hot asphalt mixture, for wearing coarse were conclude that the material used for mix design is good, which gives Marshall stability, 12.57 KN with optimum bitumen content of 5.2% (by weight of total aggregate). Hence the quality of aggregate is good but the influence of other factors such as poor drainage courses, level of ground water table, Varity of geological materials along the road rout and poor construction methodology caused the defect. The flow result of the Marshall mix design gives as 3.6 % which is approach of upper limit of specification 4%, So when flow become high in the mix it result long term deterioration of asphalt performance, hence the pavement condition along the study area has been affected by different failure types such as cracks, surface defect and disintegrating from site observation may result of this.

ФАКТОРЫ, УСИЛИВАЮЩИЕ ОТРИЦАТЕЛЬНОЕ ВОЗДЕЙСТВИЕ ДЛИТЕЛЬНОГО ОРОШЕНИЯ НА СВОЙСТВА ЧЕРНОЗЕМА ОБЫКНОВЕННОГО

Purpose: to identify factors enhancing the negative impact of long-term irrigation on soil fertility. Materials and methods. The influence of mineralization and quality of irrigation water on ordinary chernozems (Neklinovsky district), the level of groundwater table on the reclamation state and soil fertility of ordinary chernozems (Bagaevsky district of Rostov region), the structure of crop rotations was studied, and optimal moisture levels for different irrigation modes were established. Results. Long-term use of sulphate-sodium low-mineralized water led to the degradation of ordinary chernozems. They acquired the properties of medium alkaline and medium solonized soils: alkalinity – 1.29 mmol(eq)/100 g, solonetzicity – 7 % of exchangeable sodium from the total soil absorbing complex (SAC), soil bulk density – 1.34 t/m³, humus content decreased by 23 % during its transformation from fulvate-humate to humate-fulvate. The close ground waters table and their mineralization of 5 g/dm³ contributed to secondary salinization. Fertility reproduction is observed only with the introduction of organic fertilizers. The increase in humus content in the alfalfa-corn crop rotation was 0.68 % with the introduction of 60 t/ha of manure after 4 years of corn cultivation in comparison with the humus content after 3 years of alfalfa cultivation, and in the grain feed – 0.55 %. It was found that with an increase of irrigation rate up to 30 %, leaching of exchangeable calcium is observed with a simultaneous increase in the content of exchangeable sodium up to 4 % of the total SAC, which contributes to an increase in bulk density of ordinary chernozem to 1.38 t/m³. In the variant with over-irrigation, the humus content decreased by 0.22 % over 4 years of regular irrigation, and in the variant with the optimal and reduced by 40 and 60 % rates, its amount decreased from 0.04 to 0.07 %, as in dry land. Conclusions. The investigated factors enhance under certain conditions the negative impact of long-term irrigation on the properties of ordinary chernozem.

Implementation of biocementation for a partially saturated problematic soil of the UK railway network

This paper refers to biocementation of a problematic soil of the UK railway network as a potential stabilisation technique of this soil using indigenous ureolytic bacteria. The soil is peat, a soft foundation soil also subject to oxidation wastage. As the peat is under existing embankments, electrokinetics (EK) is proposed as a promising technique to implement treatments. In the context of unsaturated soils the paper thus focuses on two particular aspects relevant for the implementation of treatments and the stability of this soil, namely: a) the effect of degree of saturation of the peat on the bio-electrokinetic treatment ; b) the soil water retention curve of the soil affecting flow and transport; these are relevant as we focus on understanding and modelling the implementation of treatments through electrokinetics; moreover for the peat it is of importance to understand moisture exchange in the vadose zone and control groundwater table levels (e.g. during electrokinetics) in order to prevent further oxidation. After isolation and screening of indigenous microorgansisms Bacillus licheniformis was selected for further testing. The results in terms of unconfined compressive strength, CaCO3 content, swelling and compression behaviour and water retention proved the feasibility of biocementation using this indigenous microorganism. Ongoing work is assessing the required treated soil characteristics and related required biocementation degree to solve UK rail's peat foundation problems. Upscaling of the techniques towards in situ implementation is also planned in the next stage of the research.

Dynamic analysis of an axially loaded pile embedded in elastic‐poroelasitc layered soil of finite thickness

SummaryThis paper presents an analytical solution for determining the dynamic characteristics of axially loaded piles embedded in elastic‐poroelastic layered soil of finite thickness. The interface between the elastic and poroelastic soil coincides with the groundwater table level, which is explicitly taken into account in the solution. The pile is modelled as elastic one‐dimensional rod to account for the effect of its dynamic characteristics on the response of the soil‐pile system. The solution is based on Biot's poroelastodynamic theory and the classical elastodynamic theory, which we use to establish the governing equations of the soil and pile. Accordingly, the pile base resistance, shaft reaction, and the complex impedance of soil‐pile system are obtained using the method of Hankel integral transformation. Following the validation of the derived solution, we identify the main parameters affecting the vertical dynamic impedance of the pile via a parametric study. The presented method poses as an efficient alternative for quickly estimating the dynamic characteristics of axially loaded piles, without having to resort to complex numerical analyses.

Water Reseachfor Local Recharging of Ground Water Table

The proposed system, helps to increase ground water table level to decrease the water crisis encountered by the people. The rain water harvesting system implemented by the government was a good system by the way but very less monsoon and unpredictable rain has made it unreliable for water table recharging. But an average household of 4 uses nearly 220 litres for bathing and nearly 200 litres for cleaning clothes and utensils per day all the water goes down for the sewage. This project aims in segregating these 400 litres of used water. By collecting all the used water in house and finding out its turbidity using led and photo detector. If water is turbid contents it is discharged into the sewage if the water is not turbid then the water is filtered using corn cobs and then diverted into the rain water harvesting system. This way at least 30 % (120 litres) out of the 400 litres of the used water can be diverted into the rain water harvesting system. When calculated for a month nearly 3600 litres can be recharged into the ground. The water diversion can be done with the help of a valve controlled by a solenoid. These are connected to the microcontroller to control all the process and send to Wi-Fi module.

Estimation of groundwater storage from seismic data using deep learning

ABSTRACTConvolutional neural networks can provide a potential framework to characterize groundwater storage from seismic data. Estimation of key components, such as the amount of groundwater stored in an aquifer and delineate water table level, from active‐source seismic data are performed in this study. The data to train, validate and test the neural networks are obtained by solving wave propagation in a coupled poroviscoelastic–elastic media. A discontinuous Galerkin method is applied to model wave propagation, whereas a deep convolutional neural network is used for the parameter estimation problem. In the numerical experiment, the primary unknowns estimated are the amount of stored groundwater and water table level, while the remaining parameters, assumed to be of less of interest, are marginalized in the convolutional neural network‐based solution. Results, obtained through synthetic data, illustrate the potential of deep learning methods to extract additional aquifer information from seismic data, which otherwise would be impossible based on a set of reflection seismic sections or velocity tomograms.

Forecasting Groundwater Table in a Flood Prone Coastal City with Long Short-term Memory and Recurrent Neural Networks

Many coastal cities are facing frequent flooding from storm events that are made worse by sea level rise and climate change. The groundwater table level in these low relief coastal cities is an important, but often overlooked, factor in the recurrent flooding these locations face. Infiltration of stormwater and water intrusion due to tidal forcing can cause already shallow groundwater tables to quickly rise toward the land surface. This decreases available storage which increases runoff, stormwater system loads, and flooding. Groundwater table forecasts, which could help inform the modeling and management of coastal flooding, are generally unavailable. This study explores two machine learning models, Long Short-term Memory (LSTM) networks and Recurrent Neural Networks (RNN), to model and forecast groundwater table response to storm events in the flood prone coastal city of Norfolk, Virginia. To determine the effect of training data type on model accuracy, two types of datasets (i) the continuous time series and (ii) a dataset of only storm events, created from observed groundwater table, rainfall, and sea level data from 2010–2018 are used to train and test the models. Additionally, a real-time groundwater table forecasting scenario was carried out to compare the models’ abilities to predict groundwater table levels given forecast rainfall and sea level as input data. When modeling the groundwater table with observed data, LSTM networks were found to have more predictive skill than RNNs (root mean squared error (RMSE) of 0.09 m versus 0.14 m, respectively). The real-time forecast scenario showed that models trained only on storm event data outperformed models trained on the continuous time series data (RMSE of 0.07 m versus 0.66 m, respectively) and that LSTM outperformed RNN models. Because models trained with the continuous time series data had much higher RMSE values, they were not suitable for predicting the groundwater table in the real-time scenario when using forecast input data. These results demonstrate the first use of LSTM networks to create hourly forecasts of groundwater table in a coastal city and show they are well suited for creating operational forecasts in real-time. As groundwater table levels increase due to sea level rise, forecasts of groundwater table will become an increasingly valuable part of coastal flood modeling and management.

Water flow in unsaturated soils subjected to multiple infiltration events

In this paper, water flow in a 4 m height column with an unsaturated soil that is subjected to multiple infiltration events for a 62 day period is investigated. One-dimensional (1D) numerical analysis is also undertaken to analyze the flow, extending the seepage theory for unsaturated soils. Results highlight the formation of two wetting fronts; namely, wetting front I and wetting front II that are induced by the first and subsequent infiltration events, respectively. There is a stable zone where the water content is approximately constant; it forms between the two fronts. A conceptual model of the suction profile is proposed for interpreting in situ water flow by dividing the unsaturated zone into four distinct zones; namely, active, steady, transition, and capillary fringe zones. This division is helpful for providing a rational explanation of water flow in different zones. Novel contributions from this study include a relationship between the hydraulic properties in the steady zone and the flow velocity, which is determined by an average influx rate. In addition, the rate of groundwater recharge can also be estimated using the average influx rate. Results of the present study are useful to understand and interpret the relationship between water infiltration and suction or water content profile in the unsaturated zone as well as variation of groundwater table level.

Evaluation of Moisture Damage under Crack-Sealed Asphalt Pavements in Louisiana

Crack sealing prevents the ingress of water in the pavement structure, thus preventing the weakening of the pavement and delaying its deterioration. Earlier studies indicate that sealing pavements in areas with a high ground water table (GWT) may prevent moisture from escaping upwards through cracks in asphalt pavements, therefore, accelerating stripping. The objective of this study was to provide guidelines for using crack sealing to minimize moisture entrapment under cracks, thus reducing stripping on low volume roadways. To achieve this, a calibrated Finite Element (FE) model was used to model a field experiment consisting of cracked and crack-sealed asphalt pavement sections. Sensitivity analysis was then conducted to compare crack-sealed and unsealed sections under different GWT levels, air relative humidity, air temperatures, rain intensities, and asphalt hydraulic conductivities. Results indicate that crack sealing could be applied under common rain intensities in Louisiana and any GWT depth without potential for stripping because of moisture entrapment if the hydraulic conductivity of the original pavement does not exceed 2 × 10–6 m/s. Yet, crack sealing should be applied after a dry period to ensure that the existing moisture in the original pavement is minimal. A non-linear regression model was developed for use in the Southern United States to help determine whether crack sealing should be used to avoid moisture damage in a cracked pavement at a given site based on the GWT and air relative humidity without the need for FE simulations. This can be a useful tool when planning maintenance activities.

Soil liquefaction potential in Kahramanmaras, Turkey

This study presents the liquefaction potential in Kahramanmaras city, which is located on the seismically active zones of East Anatolian and Dead Sea Faults in southern central Turkey. Geotechnical investigations in the city were carried out both in situ and laboratory. A total of 238 boreholes in the city were drilled in order to perform Standard Penetration Tests (SPT) and to define the physical properties (sieve analysis, Atterberg limits, soil classification) of the soils obtained from these boreholes. The stratigraphic structure underlying the city consists of various amounts of silt, clay, gravel and sand. Ground water table levels were found to vary from 0–6 m to 15 m or more in the study area. Liquefaction potential was studied based on the SPT results and a hypothetical earthquake with a magnitude of 7.5. The results indicate that the southern areas of the city have a high potential to liquefy, while the northern parts of the city lie mainly within nonliquefaction area. Analyses of liquefaction potential were mapped by using geographical information system (GIS)-based computer software. Evidently, the complied GIS maps could be effectively used by researchers and engineers for further studies on the purpose of land-use planning and urban development.

Impact of different cropping systems and irrigation schedules on evapotranspiration, grain yield and groundwater level in the North China Plain

Water shortage is the most limiting factors for the crop production in the North China Plain (NCP). The alternative cropping systems and the water-saving irrigation schedules are the main measures to reduce the groundwater level decline. In this study, APSIM model was used to simulate the effects of four different cropping systems (winter wheat and summer maize cropping system (WW-SM); winter wheat cropping system (WW); summer maize cropping system (SM); winter wheat –summer maize – spring maize cropping systems (WW-SM-sM)) under four different irrigation schedules (normal irrigation (NI); critical irrigation (CI); minimum irrigation (MI); and rain-fed (RF)) on evapotranspiration (ET), water use efficiency (WUE) groundwater table level and crop water productivities in the NCP. Results showed that the WW-SM cropping system had the higher grain yield and ET under NI, CI, MI, and RF conditions. Grain yield reduction (GYR) was decreased with the irrigation amount decreased for the WW cropping system, SM cropping system, and WW-SM-Sm cropping systems which ranged from 21.59% to 48.11%, from 16.71% to 46.93%, from 15.82% to 43.92%, and from 5.09% to 27.22% under the NI, CI, MI and RF irrigation schedules, respectively. For WUE and the economic water use efficiency (WUEe), WW-SM and WW-SM-sM had the higher value, WW and SM had the lower value. The differences for the different cropping systems were mostly caused by the grain yield and the soil evaporation. Meanwhile, the water-saving irrigation schedules and cropping systems both could reduce the groundwater table decline compared to that under normal irrigation and traditional cropping system. There all had the significant impact on groundwater table changes for both the irrigation schedules and cropping systems. However, water restriction will lead to crop yield reduction and water saving depending on the chosen alternative cropping systems and irrigation schedules. Results strongly suggest that the critical irrigation and WW-SM-sM cropping system could mitigate the groundwater over-exploitation and ensure the food safety in the NCP.

Investigation of Flood Distribution and Feeding Performance of Artificial RED Garden in Shahr-E-Reza on Quantity and Quality of Groundwater Table, Isfahan, Iran

Increasing water consumption has increased using of synthetic nutritional methods for enriching groundwater resources. Artificial feeding is a method that can save excess water for using in low level water time in underground. The purpose of this study is to evaluate the performance of the flood dispersal and artificial feeding system in the Red Garden of Shahr-e-Daghshan and improving, saving quality of the groundwater table in the area. In order to investigate the performance of these plans, an area of 1570 km2 was considered in the Southern of Shah-Reza. The statistics data from 5 years before the design of the plans (1986-2002) related to flood control fluctuations in 20 observation wells and many indicator Qanat were surveyed in this area. The annual fluctuations in the level of the station show a rise in the level of the station after the depletion of the plan. Dewatering of the first and second turns, with an increase of more than one meter above groundwater level, has had the highest impact on the level of groundwater table in the region. Reduced permeability at sediment levels, wasted flood through evaporation and wasteful exploitation of groundwater resources, cause to loss of the impact on the increase in the level and quality of groundwater in the area, especially in the dry, drought season and recent high droughts.

Groundwater Level Prediction/Forecasting and Assessment of Uncertainty Using SGS and ARIMA Models: A Case Study in the Bauru Aquifer System (Brazil)

Best water management practices should involve the prediction of the availability of groundwater resources. To predict/forecast and consequently manage these water resources, two known methods are discussed: a time series method using the autoregressive integrated moving average (ARIMA) and a geostatistical method using sequential Gaussian simulation (SGS). This study was conducted in the Ecological Station of Santa Barbara (EEcSB), located at the Bauru Aquifer System domain, a substantial water source for the countryside of Sao Paulo State, Brazil. The relevance of this study lies in the fact that the 2013/2014 hydrological year was one of the driest periods ever recorded in Sao Paulo State, which was directly reflected in the groundwater table level behavior. A hydroclimatological network comprising 49 wells was set up to monitor the groundwater table depths at EEcSB to capture this response. The traditional time series has the advantage that it has been created to forecast and the disadvantage that an interpolation method must also be used to generate a spatially distributed map. On the other hand, a geostatistical approach can generate a map directly. To properly compare the results, both methods were used to predict/forecast the groundwater table levels at the next four measured times at the wells’ locations. The errors show that SGS achieves a slightly higher level of accuracy and considered anomalous events (e.g., severe drought). Meanwhile, the ARIMA models are considered better for monitoring the aquifer because they achieved the same accuracy level as SGS in the 2-month forecast and a higher precision at all periods and can be optimized automatically by using the Akaike information criterion.

Effects of shallow groundwater table and fertilization level on soil physico-chemical properties, enzyme activities, and winter wheat yield

Waterlogging adversely affects winter wheat (Triticum aestivum L.) growth by deteriorating soil environmental factors. The objective of this study is to test the effects of groundwater depth and fertilization level on soil properties, enzyme activities, and wheat yield. Experiments were carried out in micro-lysimeters at the groundwater depths of 0.2, 0.4, 0.5, 0.6, and 0.8 m under low, normal, and high fertilization levels in the winter wheat growth season from Oct. 2015 to May 2016. Soil water content, pH, organic matter content, total N, available P, available K as well as sucrase, urease, and phosphatase activities were measured in various growth stages of winter wheat, and yield component and grain yield were also measured after its harvest. Results indicated that soil water content and pH decreased with the increased groundwater depth. The lower contents of soil organic matter and nutrients appeared when groundwater depth was 0.5–0.6 m. Sucrase in the heading stage, urease in the jointing stage, and phosphatase activities increased significantly with the increased groundwater depth. Grain yield increased with groundwater depth to its maximum or approximate steady value. Total N and available P contents and urease activity appeared to increase with fertilizer application rate but available K content showed a contrary tendency. Grain yield increased with fertilizer application rate, but the effect of fertilization level on grain yield was lower than that of groundwater depth. A significant interaction between groundwater depth and fertilization level on grain yield existed. Soil enzyme activities were significantly correlated with available P content, and phosphatase activity was correlated with soil water, pH, organic matter, total N, and available K contents. It can be concluded that controlling groundwater depth and appropriate fertilizer application level can improve crop growth environment and promote winter wheat growth and its grain yield.

Reducing the risk of building degradation caused by groundwater table level variations in an area in Bucharest

AbstractIn Bucharest, wastewater is collected through main and secondary collectors, all of them discharging in the wastewater collector channel situated under the Dambovita River floor. Given the modifications of the groundwater table level fallowing the building of a metro line and, therefore, the necessity to reduce the intake of water coming from rain and groundwater infiltrations (conventionally considered clean) at Glina wastewater treatment plant, one of the solutions identified has been to build a drainage system next to the river. In this scenario, a groundwater table level variation would appear, and the study aimed to estimate the influence of the drainage system on the buildings in terms of settlements.

Semi-seasonal groundwater forecast using multiple data-driven models in an irrigated cropland

Abstract In agricultural areas where groundwater is the main water supply for irrigation, forecasts of the water table are key to optimal water management. However, water management can be constrained by semiseasonal to seasonal forecast. The objective is to create an ensemble of water table one- to five-month lead-time forecasts based on multiple data-driven models (DDMs). We hypothesize that data-driven modeling capabilities (e.g., random forests, support vector machines, artificial neural networks (ANNs), extreme learning machines, and genetic programming) will improve naïve and autoregressive simulations of groundwater tables. An input variable selection method was used to carry the maximum information in the input (precipitation, crop water demand, changes in groundwater table, snowmelt, and evapotranspiration) and output relationship for the DDMs. Five DDMs were implemented to forecast groundwater tables in an unconfined aquifer in the Northern High Plains (Nebraska, USA). Root mean squared error (RMSE) and Nash–Sutcliffe efficiency index were used to evaluate the skill of the model and three hydrologic regimes were determined statistically as high, mid, and low groundwater table levels. Additionally, varying storage regimes were used to construct rising and falling limbs in the tested well. Results show that all models outperform the baseline for all the lead times, ANNs being the best of all.

Losses and alternatives measures towards environmental degradation in rural area of Haryana

In India, the globally accepted threats caused by environmental degradation are soil degradation and desertification, pollution, droughts, floods and water scarcity. The study was conducted in two districts of Haryana state namely, Hisar and Kaithal and a total number of one hundred twenty women were selected and interviewed with the help of well structured schedule. The study revealed that majority of the women were of middle age group (36-50 years), educated up to higher education, belonged to nuclear family with 4 members, performed government, private jobs and self employment. Very serious losses due to environment degradation were air pollutant effect on human health, animals and plants (1.47), deeper level of ground water table leads to irrigation scarcity (1.35), quality deterioration of crop produce and fertilizers cause toxicity in food products (1.23), lost of biodiversity and tropical forest, extinction of plant and animal species (0.41) as per their ‘Z’ score. Least smoky trees should be planted and used, Baval, Neem, Pipal, Bargad, Shisham, Aam, Jamun (94.16%), Installing chimneys to rent smoke from indoor stoves (90.83%) Storage and disposal of farm wastes properly (79.16%), Campaigning for healthy environment (74.16%), enhancing the area under agro and social forestry (69.16), empowerment of women for different development programs (66.66%) were found very effective among the women to making the environment healthy. To reach the results the aggregate total score was calculated to each alternative measure separately, and on the basis of calculated total score, a weighted mean score were obtained which were ranked according to the maximum or minimum mean scores for assessing the effectiveness of alternative measure.

Behavior of a colluvial slope located in Southeastern Brazil

Colluvial deposits are commonly found throughout the Serra do Mar escarpment in Brazil. This article discusses predisposing geotechnical and geological factors related to the movement of a colluvium deposit located at km 29 of the Brazilian Federal Highway 116, Rio de Janeiro/RJ (BR-116/RJ). During the highway construction in mid-1976, an excavation of the toe of the slope was implemented, exacerbating preexisting movement. In order to understand the behavior of this deposit, field investigations, monitoring, and laboratory tests, as well as theoretical analyses were carried out. A subsoil survey in the area indicated the presence of a colluvium-filled paleo-thalweg. The site is located in a region with a specific geomorphology that favors significant sources of recharge to groundwater. The highly foliated rock has persistent parallel fractures, with a dip favorable to the groundwater flow in the direction of the slope. Statistical analyses were performed and good correlations were observed for rainfall, movements, groundwater table (GWT) levels, piezometer readings, and the discharge from deep horizontal drains (DHDs). The installation of the DHDs led to a GWT draw-down of 15 m, as well as reductions in movement and artesian pressure. The drains that presented the best performance were those installed in the colluvium-filled paleo-thalweg. Nevertheless, the present number of DHDs installed is not sufficient to permanently lower the GWT and stop the creep movement in the slope which was reactivated during a period of intense rainfall. Stability analysis indicates that a proper slope stability condition may be achieved by reducing the GWT level.

Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and Random Forest

Sea level rise has already caused more frequent and severe coastal flooding and this trend will likely continue. Flood prediction is an essential part of a coastal city’s capacity to adapt to and mitigate this growing problem. Complex coastal urban hydrological systems however, do not always lend themselves easily to physically-based flood prediction approaches. This paper presents a method for using a data-driven approach to estimate flood severity in an urban coastal setting using crowd-sourced data, a non-traditional but growing data source, along with environmental observation data. Two data-driven models, Poisson regression and Random Forest regression, are trained to predict the number of flood reports per storm event as a proxy for flood severity, given extensive environmental data (i.e., rainfall, tide, groundwater table level, and wind conditions) as input. The method is demonstrated using data from Norfolk, Virginia USA from September 2010 to October 2016. Quality-controlled, crowd-sourced street flooding reports ranging from 1 to 159 per storm event for 45 storm events are used to train and evaluate the models. Random Forest performed better than Poisson regression at predicting the number of flood reports and had a lower false negative rate. From the Random Forest model, total cumulative rainfall was by far the most dominant input variable in predicting flood severity, followed by low tide and lower low tide. These methods serve as a first step toward using data-driven methods for spatially and temporally detailed coastal urban flood prediction.