RESUMO
Urban flood risks have intensified due to climate change and dense infrastructural development, necessitating innovative assessment approaches. This study aimed to integrate advanced hydrodynamic models with machine learning (ML) techniques to improve urban flood prediction and hazard analysis. Integrating 1D and 2D hydrodynamic models calibrated with precise parameters demonstrated exceptional predictive accuracy for flood dynamics. The high-resolution Lidar images and sophisticated modeling were used to simulate flood scenarios for the River Thames in West London. The socioeconomic data were incorporated to map vulnerable zones accurately. The findings revealed that 2D hydrodynamic models, while computationally intensive, offered superior accuracy in predicting flood dynamics. In contrast, 1D models could have been more accurate in predicting inundation depth and extent in adjacent urban areas. Advanced ML models, such as the Extra Trees-Principal Component Analysis (ET-PCA) model, further instilled confidence in the reliability of the research findings, demonstrating near-perfect predictive reliability with an R2 of 0.999. This model provided near-perfect predictions and enabled precise flood risk zoning. The integration of socioeconomic data further highlighted the vulnerability of certain urban areas. It emphasized the importance of targeted flood mitigation strategies. Beyond the specific case study, this research demonstrated the potential of combining hydrodynamic simulations with ML to enhance urban flood resilience globally. This framework helps urban planners and policymakers devise effective flood mitigation strategies and improve infrastructure resilience against future flood events.
RESUMO
Machine learning methodology has recently been considered a smart and reliable way to monitor water quality parameters in aquatic environments like reservoirs and lakes. This study employs both individual and hybrid-based techniques to boost the accuracy of dissolved oxygen (DO) and chlorophyll-a (Chl-a) predictions in the Wadi Dayqah Dam located in Oman. At first, an AAQ-RINKO device (CTD+ sensor) was used to collect water quality parameters from different locations and varying depths in the reservoir. Second, the dataset is segmented into homogeneous clusters based on DO and Chl-a parameters by leveraging an optimized K-means algorithm, facilitating precise estimations. Third, ten sophisticated variational-individual data-driven models, namely generalized regression neural network (GRNN), random forest (RF), gaussian process regression (GPR), decision tree (DT), least-squares boosting (LSB), bayesian ridge (BR), support vector regression (SVR), K-nearest neighbors (KNN), multilayer perceptron (MLP), and group method of data handling (GMDH) are employed to estimate DO and Chl-a concentrations. Fourth, to improve prediction accuracy, bayesian model averaging (BMA), entropy weighted (EW), and a new enhanced clustering-based hybrid technique called Entropy-ORNESS are employed to combine model outputs. The Entropy-ORNESS method incorporates a Genetic Algorithm (GA) to determine optimal weights and then combine them with EW weights. Finally, the inclusion of bootstrapping techniques introduces a stochastic assessment of model uncertainty, resulting in a robust estimator model. In the validation phase, the Entropy-ORNESS technique outperforms the independent models among the three fusion-based methods, yielding R2 values of 0.92 and 0.89 for DO and Chl-a clusters, respectively. The proposed hybrid-based methodology demonstrates reduced uncertainty compared to single data-driven models and two combination frameworks, with uncertainty levels of 0.24% and 1.16% for cluster 1 of DO and cluster 2 of Chl-a parameters. As a highlight point, the spatial analysis of DO and Chl-a concentrations exhibit similar pattern variations across varying depths of the dam according to the comparison of field measurements with the best hybrid technique, in which DO concentration values notably decrease during warmer seasons. These findings collectively underscore the potential of the upgraded weighted-based hybrid approach to provide more accurate estimations of DO and Chl-a concentrations in dynamic aquatic environments.
Assuntos
Qualidade da Água , Incerteza , Algoritmos , Análise Espacial , Teorema de Bayes , Análise por Conglomerados , Monitoramento Ambiental/métodos , Redes Neurais de Computação , Aprendizado de Máquina , Clorofila A/análiseRESUMO
This cross-sectional geospatial analysis explores the prevalence of Chronic Obstructive Pulmonary Disease (COPD) concerning the proximity to toxic release inventory (TRI) facilities in Jefferson County, Alabama. Employing the fuzzy analytical hierarchy process (FAHP), the study evaluates COPD prevalence, comorbidities, healthcare access, and individual health assessments. Given the mounting evidence linking environmental pollutants to COPD exacerbations, the research probes the influence of TRI sites on respiratory health, integrating Geographic Information Systems (GIS) to scrutinize the geospatial vulnerability of communities neighboring TRI sites. Socio-demographic disparities, economic conditions, and air pollution are emphasized in the analysis. The EPA's Toxic Release Inventory serves as the cornerstone for assessing the association between TRI proximity and COPD prevalence. The analysis uncovers a notable inverse correlation between distance from TRI sites and COPD prevalence, signaling potential health risks for populations residing closer to these facilities. Moreover, factors such as minority status, low income, and air pollution are associated with higher COPD prevalence, underscoring the imperative of comprehending the interplay between environmental exposure and respiratory health. This study bridges gaps in the literature by addressing the geographical nexus between COPD prevalence and pollution exposure. By leveraging FAHP, the research furnishes a holistic understanding of the multifaceted factors influencing vulnerability to COPD. The findings underscore the necessity for targeted public health interventions and policy measures to redress environmental disparities and alleviate the repercussions of TRI facilities on respiratory health.
Assuntos
Poluentes Atmosféricos , Poluição do Ar , Exposição Ambiental , Doença Pulmonar Obstrutiva Crônica , Doença Pulmonar Obstrutiva Crônica/epidemiologia , Humanos , Exposição Ambiental/estatística & dados numéricos , Prevalência , Poluição do Ar/estatística & dados numéricos , Poluentes Atmosféricos/análise , Estudos Transversais , Alabama/epidemiologia , Masculino , Feminino , Pessoa de Meia-Idade , Idoso , Sistemas de Informação GeográficaRESUMO
Water quality indicators (WQIs), such as chlorophyll-a (Chl-a) and dissolved oxygen (DO), are crucial for understanding and assessing the health of aquatic ecosystems. Precise prediction of these indicators is fundamental for the efficient administration of rivers, lakes, and reservoirs. This research utilized two unique DL algorithms-namely, convolutional neural network (CNNs) and gated recurrent units (GRUs)-alongside their amalgamation, CNN-GRU, to precisely gauge the concentration of these indicators within a reservoir. Moreover, to optimize the outcomes of the developed hybrid model, we considered the impact of a decomposition technique, specifically the wavelet transform (WT). In addition to these efforts, we created two distinct machine learning (ML) algorithms-namely, random forest (RF) and support vector regression (SVR)-to demonstrate the superior performance of deep learning algorithms over individual ML ones. We initially gathered WQIs from diverse locations and varying depths within the reservoir using an AAQ-RINKO device in the study area to achieve this. It is important to highlight that, despite utilizing diverse data-driven models in water quality estimation, a significant gap persists in the existing literature regarding implementing a comprehensive hybrid algorithm. This algorithm integrates the wavelet transform, convolutional neural network (CNN), and gated recurrent unit (GRU) methodologies to estimate WQIs accurately within a spatiotemporal framework. Subsequently, the effectiveness of the models that were developed was assessed utilizing various statistical metrics, encompassing the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE) throughout both the training and testing phases. The findings demonstrated that the WT-CNN-GRU model exhibited better performance in comparison with the other algorithms by 13% (SVR), 13% (RF), 9% (CNN), and 8% (GRU) when R-squared and DO were considered as evaluation indices and WQIs, respectively.
Assuntos
Algoritmos , Redes Neurais de Computação , Qualidade da Água , Aprendizado de Máquina , Monitoramento Ambiental/métodos , Lagos , Clorofila A/análise , Análise de OndaletasRESUMO
Under changing climate, groundwater resources are the main drivers of socioeconomic development and ecosystem sustainability. This study assessed the contribution of two adjacent watersheds, Muse Street (MS) and West Wood (WW), with low and high urban development, to the Memphis aquifer recharge process in central Jackson, Tennessee, USA. The numerical MODFLOW model was created using data from 2017 to 2019 and calibrated using reported water budget components derived from in-situ data. The calibrated MODFLOW model was then used to investigate the impact of high and low urban developments on the recharge rate. The hydraulic parameters and recharge rates were optimized by adjusting the groundwater level based on the observed water level using PEST. The stochastic modeling was also carried out using the Latin Hypercube approach to reduce the uncertainty. The calibration results were satisfactory, with RMSE of 0.124 and 0.63 obtained in the WW and MS watersheds, respectively, indicating accurate estimation of the input parameters, precisely the hydrodynamic coefficients. The study results indicate that, per unit area, the MS watershed contributes 119% more to recharge and 186% more to riverbed leakage compared to the WW watershed. However, regarding total recharge and riverbed leakage, the WW watershed contributed more than the MS watershed. The results of this study have enhanced the knowledge of the impact of urbanization on hydrology and the recharge process in watersheds with diverse land uses.
RESUMO
Understanding pathways connecting urbanization to the recharge process across the land surface and river environment is of great significance in achieving low-impact development. Accordingly, the contribution of an urbanized region with a low and high development rate, along with the expected overflow into the river network resulting from increased impervious surfaces, was assessed in the recharge rate at Jackson, Tennessee. To this end, first, the losses were calculated using the standard and modified SCS-CN methods for the maximum probable flood condition. Then, TUFLOW was applied to simulate the two-dimensional flood for a historic 24-h probable maximum precipitation event with a 100-year return period. The results of TUFLOW were later calibrated using the results of standard and modified SCS-CN methods. A calibrated MODFLOW was employed to assess the effects of urbanization and, consequently, the plausible extended river network on the recharge rate. Results revealed that the West Wood contribution in groundwater recharge was 19 % less than the Musa Street, while it supplies approximately 2.7 % more flow than Musa Street. The performance evaluation results of TUFLOW showed 0.4916 and 0.689 as Nash-Sutcliffe, respectively, for the standard and modified SCS-CN methods. Although the flow velocity and depth were respectively increased by 3.3 % and 8.3 % under modified SCS-CN compared to the standard one, the soil water storage capacity remained constant at equal to 0.16 mm. Results revealed that the maximum soil water storage capacity was fulfilled soon through the modified SCS-CN than the standard method leading to higher flood volume and discharge. To this end, the discharge resulting from modified SCS-CN was approximately 1.5 times higher than that in the standard method under the same precipitation condition. Our findings suggest that designing any construction, mainly dams downstream, based on the modified SCS-CN estimations will provide more safety, particularly in crowded regions. Also, overflowing the excess surface runoff into the river network resulted from the increased impervious surface amplifying the flow volume, depth, and velocity across the river networks, finally leaving the area without increasing the aquifer's recharge rate. The results provide insights into possible sustainable development options and flood management in the built-up area.
RESUMO
PURPOSE: Millions of workers exposed to the outdoor environment are extremely susceptible to extreme heat. Although several articles analyzed heat-related illnesses, injuries, fatalities at the country level, few investigated regional and state statistics especially for OSHA Region 4 and the state of Alabama, U.S, which we explored in this study. METHODS: We studied the number of heat-days over 90 °F (32.2 °C) heat-index within our study area, analyzed heat-related injury and illnesses to calculate their incidence rate during 2015 to 2019, observed the nature of such incidents, their monthly occurrence, and incidence trend over average air temperature. We conducted a comparative analysis of heat-related fatalities between construction and all industries. The existing heat regulations by OSHA and some state agencies have also been summarized. RESULTS: We observed the highest mean, maximum heat-days and injury-illness rate in the south and southeast part of Region 4; increase in incidence rate from 0.03 in 2017 to 0.28 per 10,000 employees in 2018 for the contiguous U.S; highest injury-illness rate (HIR) in OSHA Region 1, 4 and 6; highest HIR in Lee, Montgomery, Mobile and Madison counties of Alabama; 34.7% (construction) and 31.3% (all industries) of all cases experiencing nonclassifiable heat-light effects; high fatalities in construction industry with a trend of 1 death/5 years; increased mortality in all occupations with 1 death/2.4 years. We also proposed a Heat-Stress Index (HSI) as a routine heat-stress measure on jobsite. CONCLUSION: The findings from this research and the proposed index can help in understanding heat-related risk at a regional level and implementing workplace interventions.
Assuntos
Transtornos de Estresse por Calor/epidemiologia , Resposta ao Choque Térmico , Temperatura Alta/efeitos adversos , Doenças Profissionais/epidemiologia , Humanos , Indústrias , Exposição Ocupacional/efeitos adversos , Estados Unidos/epidemiologiaRESUMO
Subsurface elevated temperatures (SETs) often occur in landfills and pose great threats to their structural and environmental integrity. Current landfill gas monitoring practices only recommend maintaining certain soil gases percentages, with no integrated strategy for predicting subsurface temperature. As a solution, this paper proposes a comprehensive risk assessment framework specific to SET mitigation. The risk model (RSET) was constructed by incorporating independent gas variables (methane, carbon dioxide, oxygen, residual nitrogen, and temperature) identified in the existing literature as SET indicators, and analyzing gas-well data from the Bridgeton Landfill. Upon identifying these gas indictors and their safety thresholds, we found a significant association (p-value < 0.05) between safe-unsafe ranges of gas variables and subsurface temperature. Temperatures above 80 °C were found to be associated with 100%, 92.3%, and only 4% of the unsafe ranges of methane, residual nitrogen, and oxygen, respectively. As the correlation between gases and temperature seemed to vary for different gas combinations, we developed the RSET by incorporating into these correlation coefficients event intensities specific to certain gas combinations, and then normalizing the RSET scale over a 0-10 range. Over the study period, we identified 22.29% of cases as medium risk at the Bridgeton Landfill and 17.7% as high risk. SETs are governed by different combinations of safe-unsafe ranges of parameters rather than any individual parameters alone. Subsequently, we used a decision tree algorithm to assess the risk types associated with RSET values. The proposed RSET can serve as a monitoring and decision-making tool for landfill authorities for managing and preventing SET incidents.
RESUMO
Since the beginning of the pandemic in the U.S., most jurisdictions issued mitigation strategies, such as restricting businesses and population movements. This provided an opportunity to measure any positive implications on air quality and COVID-19 mortality rate during a time of limited social interactions. Four broad categories of stay-at-home orders (for states following the order for at least 40 days, for states with less than 40 days, for states with the advisory order, and the states with no stay-at-home order) were created to analyze change in air quality and mortality rate. Ground-based monitoring data for particulate matter (PM2.5, PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2) and carbon monoxide (CO) was collected during the initial country-wide lockdown period (15 March-15 June 2020). Data on confirmed COVID-19 cases and deaths were also collected to analyze the effects of the four measures on the mortality trend. Findings show air quality improvement for the states staying under lockdown longer compared to states without a stay-at-home order. All stay-at-home order categories, except states without measures were observed a decrease in PM2.5 and the core-based statistical areas (CBSAs) within the longer mitigation states had an improvement of their air quality index (AQI).