The precise correction of outliers within radar rainfall data is crucial for a wide range of applications, including the analysis of extreme rainfall events, hydrological modeling, and the ...forecasting and warning of flash floods. Despite its significance, the challenge of correcting these outliers has not yet been fully explored, mainly due to the high dimensionality and spatiotemporal intricacies of radar rainfall data. Furthermore, most existing techniques for outlier correction are overly simplistic, revealing limitations when it comes to effectively correcting sporadic outliers. In response, this study has developed a novel approach of detecting and correcting outliers based on radar rainfall statistics at local spatiotemporal scale. In this approach, an algorithm of detecting outliers based on the simple 3-sigma rule in spatiotemporal context and an algorithm of detecting abrupt change between adjacent radar cells in spatial context, all in local scale, are iterated to enhance the quality of radar rainfall data progressively and effectively. This correction method resulted in a radar rainfall data with the grid cell value closely resembling that of the ground gauge data as well as the probability distribution. In addition, when compared to the existing methods, it demonstrated its ability to selectively remove only the outliers while preserving the integrity of the normal data. What sets this proposed method apart is not only its practicality, as it relies solely on 2D radar reflectivity data and can be easily implemented, but also its contribution to improving the analysis accuracy across various domains reliant on radar rainfall data.
Discharge of pollution loads into natural water systems remains a global challenge that threatens water and food supply, as well as endangering ecosystem services. Natural rehabilitation of ...contaminated streams is mainly influenced by the longitudinal dispersion coefficient, or the rate of longitudinal dispersion (D
), a key parameter with large spatiotemporal fluctuations that characterizes pollution transport. The large uncertainty in estimation of D
in streams limits the water quality assessment in natural streams and design of water quality enhancement strategies. This study develops an artificial intelligence-based predictive model, coupling granular computing and neural network models (GrC-ANN) to provide robust estimation of D
and its uncertainty for a range of flow-geometric conditions with high spatiotemporal variability. Uncertainty analysis of D
estimated from the proposed GrC-ANN model was performed by alteration of the training data used to tune the model. Modified bootstrap method was employed to generate different training patterns through resampling from a global database of tracer experiments in streams with 503 datapoints. Comparison between the D
values estimated by GrC-ANN to those determined from tracer measurements shows the appropriateness and robustness of the proposed method in determining the rate of longitudinal dispersion. The GrC-ANN model with the narrowest bandwidth of estimated uncertainty (bandwidth-factor = 0.56) that brackets the highest percentage of true D
data (i.e., 100%) is the best model to compute D
in streams. Considering the significant inherent uncertainty reported in the previous D
models, the GrC-ANN model developed in this study is shown to have a robust performance for evaluating pollutant mixing (D
) in turbulent environmental flow systems.
AbstractThe Clark’s instantaneous unit hydrograph (IUH) has been developed to transform excess precipitation into a runoff hydrograph, dependent on basin characteristics with flow velocity in a ...basin. In this study, the relative effects of the time–area curve and storage coefficient on the shape of the Clark IUH are analytically evaluated under hypothetical conditions of an elliptical-shaped basin and a straight flow direction of raindrops throughout total travel lengths. The time–area curve of an ellipse is derived by considering constant flow velocity in the basin, which is then used as input to the linear reservoir with a given storage coefficient to derive the Clark IUH by solving the continuity equation. The derived Clark IUH is evaluated with various shapes of elliptical basins and different storage coefficients. The time–area curve of a basin is found to be the dominant factor influencing the shape of the Clark IUH. The storage coefficient controls the steepness of the curve, while maintaining the overall shape of the Clark IUH unchanged.
•The peak flow series from 158 gauging stations throughout the UK were modelled.•The majority of stations show non-stationarity with physically-based covariates.•Rainfall-related variables are ...significant predictors of flood non-stationarity.•Multi-covariate non-stationary models perform better for the majority of stations.
Water infrastructure design and flood mitigation projects are currently based on a so-called stationary assumption. However, this assumption has been challenged in recent years due to increased extreme weather, potentially leading to the underestimation of flood quantiles and an increased risk of structural failures. In the present study, peak flow series from 158 gauging stations in the UK are analysed using both stationary and non-stationary models based on the generalised additive models for location, scale and shape (GAMLSS) framework. Nine candidate covariates are used for non-stationary models to obtain information on the significant drivers of non-stationarity in each flood series. Very few stations are thus found to show temporal trends, which suggests that time-varying non-stationary flood models may not always be suitable, and the use of physically-based covariates can provide better-fitting models. In particular, the non-stationary models using rainfall-related covariates display the best performance for the vast majority of stations, thus suggesting that the variability of the rainfall regime remains the dominant driver for changes in flooding. Moreover, two atmospheric circulation patterns, namely the North Atlantic Oscillation (NAO) and the East Atlantic Pattern, were found to be closely related to the non-stationarity of flooding at a number of stations. Unlike rainfall, however, the influence of these climate indices is not particularly dominant; hence, they are more suitably employed as components of a multiple-covariate non-stationary model. Besides, a direct linkage between the variability of flooding and climate changes has not been identified either regionally or globally. For the majority of stations (70%), the use of multiple covariates can provide a better non-stationary model than the use of a single covariate.
This study investigated the temporal rainfall pattern in order to facilitate rainfall design, which normally requires a good understanding of the temporal patterns of rainstorm events. The analysis ...employed a storm-event-based approach using the concept of inter-event time definition (IETD) and rainfall depth/duration/intensity thresholds. The 5-min rainfall data at three raingauge stations were analysed to determine representative quartiles of a design storm in a tropical city. The temporal characteristics of the design storm could be determined from the rainfall depth ratios of consecutive peak rainfalls for each interval of storm duration, and time to the first peak rainfall depending on each quartile's rainstorm events. The determination of the quantile distribution of tropical rainfall could help improve the representativeness of design rainfall and facilitate rainfall-runoff modelling for urban flood control in a tropical region.
This study presents a new research direction for predicting rainfall amount using cloud image data. Herein, we employ a convolutional neural networks (CNNs) to develop an image-value model from cloud ...image data collected from May 20, 2020 to October 24, 2020 using the Internet of Things (IoT) sensors installed at two research locations in Seoul, Republic of Korea. First, we refine the dataset using data preprocessing in three steps: 1) day/night discrimination; 2) ratio adjustment; and 3) image augmentation. Second, we construct a binary classification model using one-hot encoding for the existence of rainfall. This reduces no-rain data instances and increases model performance, thereby enabling the model to extract image features. Finally, we develop a CNN-based image-value model for rainfall prediction with a well-organized model configuration. Rainfall existence results derived from the binary classification model used for model input as preprocessed cloud image data. The proposed rainfall prediction model exhibited 85.59% accuracy on cloud images with an average mean squared error (MSE) of 3.05 for observation data under 3 mm/h. In particular, single application of the function that divides Boolean input by the standard deviation of the dataset within each characteristic resulted in a 17% increase in predicted rainfall accuracy. To the best of our knowledge, this is the first study to train CNN model to predict value (rainfall) with matched image data (cloud), which could be denoted as CNN-based image-value model. Notably, the proposed model can be further extended into other image datasets, including rain streaks with various backgrounds under different climatic conditions.
This study developed a Deep Neural Network (DNN) based distributed hydrologic model for an urban watershed in Republic of Korea. The developed model is composed of multiple Long Short-Term Memory ...(LSTM) hidden units connected by a fully connected layer. To examine the study area using the developed model, time series of 10-minute radar-gauge composite precipitation data and 10-minute temperature data at 239 model grid cells with 1km resolution were used as inputs to simulate 10-minute watershed flow discharge as an output. The model performed well for the calibration period (2013-2016) and validation period (2017-2019), with Nash-Sutcliffe Efficiency coefficient values being 0.99 and 0.67, respectively. Further in-depth analyses were performed to derive the following conclusions: (1) the map of runoff-precipitation ratios produced using the developed DNN model resembled imperviousness ratio map of the study area from the land cover data, revealing that the DNN successfully deep-learned the precipitation partitioning processes only with the input and output data without depending on any priori information about hydrology; (2) the model successfully reproduced the soil moisture dependent runoff process, an essential prerequisite of continuous hydrologic models; (3) each LSTM unit has different temporal sensitivity to the precipitation stimulus, with fast-response LSTM units having greater output weight factors near the watershed outlet, which implies that the developed model has a mechanism to separately consider the hydrological components with distinct response time such as direct runoff and the groundwater-driven baseflow.
A haptic sensor coupled to a gamepad or headset is frequently used to enhance the sense of immersion for game players. However, providing haptic feedback for appropriate sound effects involves ...specialized audio engineering techniques to identify target sounds that vary according to the game. We propose a deep learning-based method for sound event detection (SED) to determine the optimal timing of haptic feedback in extremely noisy environments. To accomplish this, we introduce the
dataset, which contains a large volume of game sound recordings of game effects and other distracting sounds, including voice chats from a
(PUBG) game. Given the highly noisy and distracting nature of war-game environments, we set the annotation interval to 0.5 s, which is significantly shorter than the existing benchmarks for SED, to increase the likelihood that the annotated label contains sound from a single source. As a baseline, we adopt mobile-sized deep learning models to perform two tasks: weapon sound event detection (WSED) and voice chat activity detection (VCAD). The accuracy of the models trained on
was greater than 90% for both tasks; thus,
enables real-time game sound recognition in noisy environments via deep learning. In addition, we demonstrated that performance degraded significantly when the annotation interval was greater than 0.5 s, indicating that the
with short annotation intervals is advantageous for SED applications that demand real-time inferences.
Understanding nitrate–nitrite (NO3− −NO2−) levels in drinking water and the associated non-carcinogenic and carcinogenic health risks are essential to protect public health. The non-carcinogenic risk ...assessment of NO3−–NO2− in drinking water has been well documented, however, there remains a knowledge gap in understanding and quantification of the carcinogenic risk of NO3−–NO2−. This study develops a non-threshold–based model for estimation of carcinogenic risk of NO3−–NO2− ingested through drinking water for a densely populated urban area with a case study of Tehran's potable water (TPW). In this regard, 200 tap water samples from different parts of the city were taken in wet (May 2018) and dry (October 2018) periods to determine NO3−–NO2− concentration in the TPW and the associated health risks across different groups of end-users. Sampling results reveal higher concentrations of NO3−–NO2− during the dry period, which can be associated to the significant contribution of nitrogen–rich groundwater in supplying the city's water demands during the dry period. Findings suggest concerns associated with the non-carcinogenic risk of NO3−–NO2− in the TPW, especially for children. More than 55% of the samples taken during the dry period show a positive carcinogenic risk for all groups of end-users (68% for men, 72% for women, and 56% for children) whilst just 8% of the samples are deemed unsafe with regards to the permissible NO3− level in drinking water, i.e. 50 mg/L. Approximately, 45% of the samples taken during the wet period show a positive carcinogenic risk for adults whilst the maximum concentration of NO3− was about 23 mg/L, i.e. two times less than the permissible level in drinking water. The findings emphasize on the necessity of reducing the permissible level of NO3− in drinking water, set out by the existing water quality standards, to safeguard public health against the carcinogenic risks. The model developed within this study recommends the urgent need for reduction of NO3− level in Tehran's water resources to protect public health of over 13 M population who incessantly use the TPW.
•A model is developed to estimate carcinogenic risk of NO3− in drinking water.•Non-carcinogenic risk of NO3−–NO2− was observed in Tehran's drinking water.•Majority of samples taken in dry period show a positive carcinogenic risk of NO3−•The permissible level of NO3− does not safeguard human health vs carcinogenic risks.