Urban Hydrological Models Research Articles

Ex-situ estimation of interception storage capacity of small urban plant species

An important knowledge gap in current urban hydrological models are reliable, generic data about interception storage capacities of small urban plant species. These data are crucial to calculate interception losses and learning their effect on the urban hydrological cycle. This study addresses this knowledge gap through simulating rainfall events in an ex-situ, controlled environment on several urban plant species. Four plant species, Lonicera nitida, Lavandula angustifolia, Pennisetum alopecuroides and a grass mix were selected based on their abundance in urban environments and their morphological differences. Several vegetation characteristics such as height and diameter were altered to create as much variation as possible in the dataset to determine the underlying characteristics influencing the interception storage capacity. Estimating the interception storage capacity of each plant (SP) using multiple linear regression models, biomass (BP) was found to be the most important predictor variable for all species. Therefore predictive models to estimate the biomass of an individual plant were developed, using some easy to measure vegetation characteristics. When using the results of these biomass models as input in the storage capacity models, reasonable estimations of interception storage capacity were achieved with mean absolute errors between 17.7 and 40.8%, depending on the model. Extrapolating SP to a reference area of one m2 showed that L. angustifolia had the highest interception storage capacity due to its high biomass density, followed by P. alopecuroides, L. nitida and finally the grass mix. As a proof of concept, a mixed modelling approach was proposed to include species not covered in this research in the analysis. The findings in this research can be used to create a firm basis for calculations of intra- and interspecies interception storage capacities, essential for improving current urban hydrological models.

Improved reliability of stormwater detention basin performance through water quality data-informed real-time control

Stormwater detentions basins are designed to capture stormwater to reduce and delay peak flows and to improve water quality. A novel technology proposed to improve basin performance is real-time, active control of the basin outflow, in so-called “smart” stormwater systems. Existing studies demonstrate the performance of active controls that respond in real-time to basin water level, detention time, and rainfall forecast for one or a small number of rainfall events. We hypothesize that the performance of these active controls can be improved by incorporating real-time water quality data into the control algorithm. In addition, we hypothesize that active control performance depends on hydrologic variability, specifically the frequency and intensity of runoff inputs. In this paper, we test these hypotheses using a numerical modeling framework for systems-level reliability analysis of active and passive stormwater basin outflow control using a Monte Carlo method. The analysis is performed using the urban hydrology model EPA-SWMM driven by stochastic rainfall time-series generated from the Modified Bartlett-Lewis Rectangular Pulses Model. Water quality-informed real-time active control algorithms are developed, tested, and shown to display an improvement over traditional, passive (no control) systems and other storage-based active controls for water and pollutant capture. Seasonal and duration curve analysis showed that water level- and water quality- informed control performance varied for different storm return periods and this variability could partly be attributed to the fraction of time the valve is closed. In addition, control performance was sensitive to rainfall variability, generally decreasing as storms become less frequent and more intense. Therefore, control system performance may depend on seasonal and longer time-scale variability in climate and rainfall-runoff processes. We anticipate this study to be a starting point to incorporate theories of reliability to assess detention basin and conveyance network performance under more complex real-time control algorithms and failure modes.

An enhanced inundation method for urban flood hazard mapping at the large catchment scale

Urban flooding occurs frequently in the world and urban hydrological models are widely applied in urban flood management and disaster mitigation. In this study, an enhanced inundation method (EIM) for urban flood hazard mapping at the large catchment scale is proposed. EIM can be easily coupled with urban hydrological models and the coupled framework can consider both source flooding and non-source flooding in floodwater generation. In EIM, the floodwater spreading order in the positive process is based on the topological relationship between depression outlets; the floodwater from lower depression elements is considered as a feedback process. These improvements make this proposed method suitable for inundation estimation in large urban catchments. Dahongmen (DHM) catchment in Beijing, China was selected as the case study area to illustrate the applicability of the proposed method. Historical inundation records during one heavy storm were applied to test the performance of the method. EIM is compared with USISM (urban storm-inundation simulation method) on the flood hazard map in the DHM catchment, which reveals the effectiveness of the improvements. The results show that all inundation locations are successfully identified by EIM and are distributed in flooding areas (water depth greater than 0.15 m) in the catchment. The average relative error of simulated inundation depths is 15%, which indicates that EIM can successfully simulate flooding scopes and depths in the study area. The results revealed that EIM can be a valuable tool for mapping urban flood hazards at the large catchment scale based on GIS techniques.

Impact of alternative land cover descriptions on urban hydrological model simulations

ABSTRACTAvailability of remotely sensed and openly available land cover datasets is rapidly improving. This opens promising possibilities for utilizing such data in urban hydrological assessments. However, it remains unknown how the performance of readily available land cover data compares with manually collated information when used to construct detailed model parameterizations required in urban hydrological models. In this study, model runs with alternative land cover data are conducted for three small study areas with varying urban densities in Helsinki, Finland. The study demonstrates how different spatial data sources with varying resolutions produce different urban runoff simulation results. The results suggest that an openly available detailed land cover description can perform equally well with a laboriously collated manual land cover description. However, mixed land cover types of the pan-European Urban Atlas dataset are problematic in describing directly connected impervious areas, which leads to poor modelling results in low density urban areas.

Considering Rain Gauge Uncertainty Using Kriging for Uncertain Data

In urban hydrological models, rainfall is the main input and one of the main sources of uncertainty. To reach sufficient spatial coverage and resolution, the integration of several rainfall data sources, including rain gauges and weather radars, is often necessary. The uncertainty associated with rain gauge measurements is dependent on rainfall intensity and on the characteristics of the devices. Common spatial interpolation methods do not account for rain gauge uncertainty variability. Kriging for Uncertain Data (KUD) allows the handling of the uncertainty of each rain gauge independently, modelling space- and time-variant errors. The applications of KUD to rain gauge interpolation and radar-gauge rainfall merging are studied and compared. First, the methodology is studied with synthetic experiments, to evaluate its performance varying rain gauge density, accuracy and rainfall field characteristics. Subsequently, the method is applied to a case study in the Dommel catchment, the Netherlands, where high-quality automatic gauges are complemented by lower-quality tipping-bucket gauges and radar composites. The case study and the synthetic experiments show that considering measurement uncertainty in rain gauge interpolation usually improves rainfall estimations, given a sufficient rain gauge density. Considering measurement uncertainty in radar-gauge merging consistently improved the estimates in the tested cases, thanks to the additional spatial information of radar rainfall data but should still be used cautiously for convective events and low-density rain gauge networks.

Parameter transferability across spatial resolutions in urban hydrological modelling: a case study in Beijing, China

This study examined the influence of spatial resolution on model parameterization, output, and the parameter transferability between different resolutions using the Storm Water Management Model. High-resolution models, in which most subcatchments were homogeneous, and high-resolution-based low-resolution models (in 3 scenarios) were constructed for a highly urbanized catchment in Beijing. The results indicated that the parameterization and simulation results were affected by both spatial resolution and rainfall characteristics. The simulated peak inflow and total runoff volume were sensitive to the spatial resolution, but did not show a consistent tendency. High-resolution models performed very well for both calibration and validation events in terms of three indexes: 1) the Nash-Sutcliffe efficiency, 2) the peak flow error, and 3) the volume error; indication of the advantage of using these models. The parameters obtained from high-resolution models could be directly used in the low-resolution models and performed well in the simulation of heavy rain and torrential rain and in the study area where sub-area routing is insignificant. Alternatively, sub-area routing should be considered and estimated approximately. The successful scale conversion from high spatial resolution to low spatial resolution is of great significance for the hydrological simulation of ungauged large areas.

Scale effect challenges in urban hydrology highlighted with a distributed hydrological model

Abstract. Hydrological models are extensively used in urban water management, development and evaluation of future scenarios and research activities. There is a growing interest in the development of fully distributed and grid-based models. However, some complex questions related to scale effects are not yet fully understood and still remain open issues in urban hydrology. In this paper we propose a two-step investigation framework to illustrate the extent of scale effects in urban hydrology. First, fractal tools are used to highlight the scale dependence observed within distributed data input into urban hydrological models. Then an intensive multi-scale modelling work is carried out to understand scale effects on hydrological model performance. Investigations are conducted using a fully distributed and physically based model, Multi-Hydro, developed at Ecole des Ponts ParisTech. The model is implemented at 17 spatial resolutions ranging from 100 to 5 m. Results clearly exhibit scale effect challenges in urban hydrology modelling. The applicability of fractal concepts highlights the scale dependence observed within distributed data. Patterns of geophysical data change when the size of the observation pixel changes. The multi-scale modelling investigation confirms scale effects on hydrological model performance. Results are analysed over three ranges of scales identified in the fractal analysis and confirmed through modelling. This work also discusses some remaining issues in urban hydrology modelling related to the availability of high-quality data at high resolutions, and model numerical instabilities as well as the computation time requirements. The main findings of this paper enable a replacement of traditional methods of “model calibration” by innovative methods of “model resolution alteration” based on the spatial data variability and scaling of flows in urban hydrology.

Key Technologies for an Urban Overland Flow Simulation System to Support What-If Analysis

Urban flooding poses serious threats to human life. In China, many cities have recently experienced flooding during every rainy season. Several years ago, policies, scientific methods, and engineering measures were applied to address this systematic problem. However, flooding disasters remain frequent in urban areas in China. Therefore, this article discusses the human-earth relationship from a philosophical perspective to analyse the causes of urban water problems. This article mainly illustrates the value of the what-if analysis concept and how to use this concept to address urban flooding issues and improve the management of urban overland flow. However, the existing simulation models and software do not effectively support what-if analyses. In particular, most existing urban hydrological simulation models and software do not sufficiently consider the heterogeneity of geographical objects on urban surfaces and lack interactions to support what-if analyses. These limitations hinder effective implementation of what-if analysis. This article introduces three key technologies that allow an urban overland flow simulation system to effectively support what-if analyses: 1) urban spatial automatic discretization and topo-adjacency, which reflect the heterogeneity of an urban area; 2) hydrological models for the simulation of the hydrologicalprocesses of the main geographical objects in the urban area; and 3) key strategies for a visual analytic platform to support what-if analyses in well-perceived way. The experiment was conducted using a community in Chongqing as a case study. The results demonstrate that the designed key technologies and functions of the proposed system can support what-if analysis and that what-if analysis is an important and useful concept for urban water management.

Optimal Temporal Resolution of Rainfall for Urban Applications and Uncertainty Propagation

The optimal temporal resolution for rainfall applications in urban hydrological models depends on different factors. Accumulations are often used to reduce uncertainty, while a sufficiently fine resolution is needed to capture the variability of the urban hydrological processes. Merging radar and rain gauge rainfall is recognized to improve the estimation accuracy. This work explores the possibility to merge radar and rain gauge rainfall at coarser temporal resolutions to reduce uncertainty, and to downscale the results. A case study in the UK is used to cross-validate the methodology. Rainfall estimates merged and downscaled at different resolutions are compared. As expected, coarser resolutions tend to reduce uncertainty in terms of rainfall estimation. Additionally, an example of urban application in Twenterand, the Netherlands, is presented. The rainfall data from four rain gauge networks are merged with radar composites and used in an InfoWorks model reproducing the urban drainage system of Vroomshoop, a village in Twenterand. Fourteen combinations of accumulation and downscaling resolutions are tested in the InfoWorks model and the optimal is selected comparing the results to water level observations. The uncertainty is propagated in the InfoWorks model with ensembles. The results show that the uncertainty estimated by the ensemble spread is proportional to the rainfall intensity and dependent on the relative position between rainfall cells and measurement points.

A framework for the case-specific assessment of Green Infrastructure in mitigating urban flood hazards

This research outlines a framework for the case-specific assessment of Green Infrastructure (GI) performance in mitigating flood hazard in small urban catchments. The urban hydrologic modeling tool (MUSIC) is coupled with a fine resolution 2D hydrodynamic model (BreZo) to test to what extent retrofitting an urban watershed with GI, rainwater tanks and infiltration trenches in particular, can propagate flood management benefits downstream and support intuitive flood hazard maps useful for communicating and planning with communities. The hydrologic and hydraulic models are calibrated based on current catchment conditions, then modified to represent alternative GI scenarios including a complete lack of GI versus a full implementation of GI. Flow in the hydrologic/hydraulic models is forced using a range of synthetic rainfall events with annual exceedance probabilities (AEPs) between 1–63% and durations from 10 min to 24 h. Flood hazard benefits mapped by the framework include maximum flood depths and extents, flow intensity (m2/s), flood duration, and critical storm duration leading to maximum flood conditions. Application of the system to the Little Stringybark Creek (LSC) catchment shows that across the range of AEPs tested and for storm durations equal or less than 3 h, presently implemented GI reduces downstream flooded area on average by 29%, while a full implementation of GI would reduce downstream flooded area on average by 91%. A full implementation of GI could also lower maximum flow intensities by 83% on average, reducing the drowning hazard posed by urban streams and improving the potential for access by emergency responders. For storm durations longer than 3 h, a full implementation of GI lacks the capacity to retain the resulting rainfall depths and only reduces flooded area by 8% and flow intensity by 5.5%.

Sensitivity of Surface Urban Energy and Water Balance Scheme (SUEWS) to downscaling of reanalysis forcing data

Often the meteorological forcing data required for urban hydrological models are unavailable at the required temporal resolution or for the desired period. Although reanalysis data can provide this information, the spatial resolution is often coarse relative to cities, so downscaling is required prior to use as realistic forcing. In this study, WATCH WFDEI reanalysis data are used to force the Surface Urban Energy and Water Balance Scheme (SUEWS). From sensitivity tests in two cities, Vancouver and London with different orography, we conclude precipitation is the most important meteorological variable to be properly downscaled to obtain reliable surface hydrology results, with relative humidity being the second most important. Overestimation of precipitation in reanalysis data at the three sites gives 6–21% higher annual modelled evaporation, 26–39% higher runoff at one site and 4% lower value at one site when compared to modelled values using observed forcing data. Application of a bias correction method to the reanalysis precipitation reduces the model bias compared to using observed forcing data, when evaluated using eddy covariance evaporation measurements.

Fractal analysis of urban catchments and their representation in semi-distributed models: imperviousness and sewer system

Abstract. Fractal analysis relies on scale invariance and the concept of fractal dimension enables one to characterize and quantify the space filled by a geometrical set exhibiting complex and tortuous patterns. Fractal tools have been widely used in hydrology but seldom in the specific context of urban hydrology. In this paper, fractal tools are used to analyse surface and sewer data from 10 urban or peri-urban catchments located in five European countries. The aim was to characterize urban catchment properties accounting for the complexity and inhomogeneity typical of urban water systems. Sewer system density and imperviousness (roads or buildings), represented in rasterized maps of 2 m × 2 m pixels, were analysed to quantify their fractal dimension, characteristic of scaling invariance. The results showed that both sewer density and imperviousness exhibit scale-invariant features and can be characterized with the help of fractal dimensions ranging from 1.6 to 2, depending on the catchment. In a given area consistent results were found for the two geometrical features, yielding a robust and innovative way of quantifying the level of urbanization. The representation of imperviousness in operational semi-distributed hydrological models for these catchments was also investigated by computing fractal dimensions of the geometrical sets made up of the sub-catchments with coefficients of imperviousness greater than a range of thresholds. It enables one to quantify how well spatial structures of imperviousness were represented in the urban hydrological models.

Geostatistical upscaling of rain gauge data to support uncertainty analysis of lumped urban hydrological models

Abstract. In this study we develop a method to estimate the spatially averaged rainfall intensity together with associated level of uncertainty using geostatistical upscaling. Rainfall data collected from a cluster of eight paired rain gauges in a 400 m × 200 m urban catchment are used in combination with spatial stochastic simulation to obtain optimal predictions of the spatially averaged rainfall intensity at any point in time within the urban catchment. The uncertainty in the prediction of catchment average rainfall intensity is obtained for multiple combinations of intensity ranges and temporal averaging intervals. The two main challenges addressed in this study are scarcity of rainfall measurement locations and non-normality of rainfall data, both of which need to be considered when adopting a geostatistical approach. Scarcity of measurement points is dealt with by pooling sample variograms of repeated rainfall measurements with similar characteristics. Normality of rainfall data is achieved through the use of normal score transformation. Geostatistical models in the form of variograms are derived for transformed rainfall intensity. Next spatial stochastic simulation which is robust to nonlinear data transformation is applied to produce realisations of rainfall fields. These realisations in transformed space are first back-transformed and next spatially aggregated to derive a random sample of the spatially averaged rainfall intensity. Results show that the prediction uncertainty comes mainly from two sources: spatial variability of rainfall and measurement error. At smaller temporal averaging intervals both these effects are high, resulting in a relatively high uncertainty in prediction. With longer temporal averaging intervals the uncertainty becomes lower due to stronger spatial correlation of rainfall data and relatively smaller measurement error. Results also show that the measurement error increases with decreasing rainfall intensity resulting in a higher uncertainty at lower intensities. Results from this study can be used for uncertainty analyses of hydrologic and hydrodynamic modelling of similar-sized urban catchments as it provides information on uncertainty associated with rainfall estimation, which is arguably the most important input in these models. This will help to better interpret model results and avoid false calibration and force-fitting of model parameters.

Formulating and testing a method for perturbing precipitation time series to reflect anticipated climatic changes

Abstract. Urban water infrastructure has very long planning horizons, and planning is thus very dependent on reliable estimates of the impacts of climate change. Many urban water systems are designed using time series with a high temporal resolution. To assess the impact of climate change on these systems, similarly high-resolution precipitation time series for future climate are necessary. Climate models cannot at their current resolutions provide these time series at the relevant scales. Known methods for stochastic downscaling of climate change to urban hydrological scales have known shortcomings in constructing realistic climate-changed precipitation time series at the sub-hourly scale. In the present study we present a deterministic methodology to perturb historical precipitation time series at the minute scale to reflect non-linear expectations to climate change. The methodology shows good skill in meeting the expectations to climate change in extremes at the event scale when evaluated at different timescales from the minute to the daily scale. The methodology also shows good skill with respect to representing expected changes of seasonal precipitation. The methodology is very robust against the actual magnitude of the expected changes as well as the direction of the changes (increase or decrease), even for situations where the extremes are increasing for seasons that in general should have a decreasing trend in precipitation. The methodology can provide planners with valuable time series representing future climate that can be used as input to urban hydrological models and give better estimates of climate change impacts on these systems.

Identifying Urban Features from LiDAR for a High‐Resolution Urban Hydrologic Model

AbstractLight Detection and Ranging (LiDAR), is relatively inexpensive, provides high spatial resolution sampling at great accuracy, and can be used to generate surface terrain and land cover datasets for urban areas. These datasets are used to develop high‐resolution hydrologic models necessary to resolve complex drainage networks in urban areas. This work develops a five‐step algorithm to generate indicator fields for tree canopies, buildings, and artificial structures using Geographic Resources Analysis Support System (GRASS‐GIS), and a common computing language, Matrix Laboratory. The 54 km2 study area in Parker, Colorado consists of twenty‐four 1,500 × 1,500 m LiDAR subsets at 1 m resolution with varying degrees of urbanization. The algorithm correctly identifies 96% of the artificial structures within the study area; however, application success is dependent upon urban extent. Urban land use fractions below 0.2 experienced an increase in falsely identified building locations. ParFlow, a three‐dimensional, grid‐based hydrological model, uses these building and artificial structure indicator fields and digital elevation model for a hydrologic simulation. The simulation successfully develops the complex drainage network and simulates overland flow on the impervious surfaces (i.e., along the gutters and off rooftops) made possible through this spatial analysis process.

Assessing impervious area ratios of grid-based land-use classifications on the example of an urban watershed

ABSTRACTWhen applying a distributed hydrological model in urban watersheds, grid-based land-use classification data with 10 m resolution are typically used in Japan. For urban hydrological models, the estimation of the impervious area ratio (IAR) of each land-use classification is a crucial factor for accurate runoff analysis. In order to assess the IAR accurately, we created a set of vector-based “urban landscape GIS delineation” data for a typical urban watershed in Tokyo. By superimposing the vector-based delineation map on the grid-based map, the IAR of each grid-based land-use classification was estimated, after calculating the IARs of all grid cells in the entire urban watershed. As a result, we were able to calculate the frequency distribution of IAR for each land-use classification, as well as the spatial distribution of IARs for the urban watershed. It is evident from the results that the reference values of IAR for the land-use classifications were estimated very roughly and inherited errors of between about 7% and 70%, which corresponds to more than 100 mm increase of direct runoff for the 1500 mm annual average precipitation.Editor D. Koutsoyiannis; Guest editor E. Volpi

Urban water hydrological modelling

Urban water hydrological modelling

Assessing Impervious Area Ratios of Grid-based Land Use Classifications on the Example of an Urban Watershed

When applying a distributed hydrological model in urban watersheds, grid-based land use classification data with 10 m resolution are typically used in Japan. Land use classifications into 17 categories are made without taking into account their impermeable properties. Thus, for such a grid-based urban hydrological model, the estimation of the Impervious Area Ratio (IAR) of each land use classification is a crucial factor for accurate runoff analysis in urban watersheds. However, so far IAR of each classification is estimated very roughly and applied in the corresponding hydrologic models almost empirically. Thus in order to assess the IAR accurately, we created a set of vector-based “urban landscape GIS delineation” data for a typical urban watershed in Tokyo using detailed land use recognition, which exactly delineated the pervious and impervious features into 20 land use types in the watershed. These vector data are used to improve the impervious area depiction of grid-based land use classifications. By superimposing the vector-based delineation map on the grid-based map, the IAR of each grid-based land use classification was estimated with very little uncertainty, after calculating the IARs of all grid cells in the entire urban watershed. As a result, we were able to calculate the frequency distribution of IAR for each land use classification as well as the spatial distribution of IARs for the urban watershed.

Singularity-sensitive gauge-based radar rainfall adjustment methods for urban hydrological applications

Abstract. Gauge-based radar rainfall adjustment techniques have been widely used to improve the applicability of radar rainfall estimates to large-scale hydrological modelling. However, their use for urban hydrological applications is limited as they were mostly developed based upon Gaussian approximations and therefore tend to smooth off so-called "singularities" (features of a non-Gaussian field) that can be observed in the fine-scale rainfall structure. Overlooking the singularities could be critical, given that their distribution is highly consistent with that of local extreme magnitudes. This deficiency may cause large errors in the subsequent urban hydrological modelling. To address this limitation and improve the applicability of adjustment techniques at urban scales, a method is proposed herein which incorporates a local singularity analysis into existing adjustment techniques and allows the preservation of the singularity structures throughout the adjustment process. In this paper the proposed singularity analysis is incorporated into the Bayesian merging technique and the performance of the resulting singularity-sensitive method is compared with that of the original Bayesian (non singularity-sensitive) technique and the commonly used mean field bias adjustment. This test is conducted using as case study four storm events observed in the Portobello catchment (53 km2) (Edinburgh, UK) during 2011 and for which radar estimates, dense rain gauge and sewer flow records, as well as a recently calibrated urban drainage model were available. The results suggest that, in general, the proposed singularity-sensitive method can effectively preserve the non-normality in local rainfall structure, while retaining the ability of the original adjustment techniques to generate nearly unbiased estimates. Moreover, the ability of the singularity-sensitive technique to preserve the non-normality in rainfall estimates often leads to better reproduction of the urban drainage system's dynamics, particularly of peak runoff flows.

Automatic classification of high resolution land cover using a new data weighting procedure: The combination of k-means clustering algorithm and central tendency measures (KMC–CTM)

Information on a well-scale urban land cover is important for a number of urban planning practices involving tree shade mapping, green space analysis, urban hydrologic modeling and urban land use mapping. In this study, an urban land cover dataset received from the database of UCI (University of California at Irvine) machine learning was used as the urban land cover data. This dataset is the urban area located in Deerfield Beach, FL, USA. Separately, this dataset is a high definition atmospheric image consisting of 9 different urban land covers. The characteristics of a multi-scale spectral, magnitude and formal tectology were used to sort out and classify these different images. The dataset comprises a total of 147 features and land covers of 9 different areas involving trees, grass, soil, concrete, asphalt, buildings, cars, pools and shadows. A new data weighting method was recommended to classify these 9 different patterns automatically. This recommended data weighting method is based on the combination of the measures of central tendency composed of mean value, harmonic value, mode and median along with the k-means clustering method. In the data weighting method, the data sets belonging to each class within the dataset are first calculated by using k-means clustering method, after which the measures of central tendency belonging to each class are calculated, as well. The measure of central tendency belonging to each class is divided by the set central value belonging to the class in question, as the result of which the data weight coefficient of that class has already been calculated. This calculation process is performed separately for 9 different land covers, and afterwards, these data weighting coefficients found are multiplied by the dataset, and thus, the dataset has been weighted. In the second stage, on the other hand, 3 different classification algorithms containing k-NN (k-nearest neighbor), extreme learning machine (ELM) and support vector machine (SVM) were used to classify 9 different urban land covers after the data weighting method. In determining the educational and test data sets, the 10-fold cross validation was used. When classification through raw data was performed along with k-NN (for k=1), ELM and SVM classification algorithms, the overall classification accuracy obtained was 77.15%, 84.70% and 84.79%, respectively.When classification through data weighting method (the combination of k-means clustering and mode measure) along with k-NN (for k=1), ELM and SVM classification algorithms was made, the overall classification accuracy obtained proved to be 98.58%, 98.62% and 98.77%, respectively. The obtained results suggest that the urban land cover in an atmospheric image via the recommended data weighting method was classified as 9 different areas with a high classification success rate.