Bayesian Source Identification With Dual Hierarchical Neural Networks for Urban Air Pollution

Pollutants dispersion emitted from road traffic is a dominant source of urban air pollution. Therefore, it is necessary to quantify emission levels in urban street canyon to evaluate their impacts on the public health and the environment. In this article, we study the effect of different street geometrical layouts on dispersion emissions of traffic exhausts for winds perpendicular to the roadway. A wind tunnel experiment modeling three different street geometrical layouts was executed to examine the flow fields and the concentration distributions in urban canyon. The flow and pollutants concentration were measured using a hot-wire anemometer with a split-fiber probe and a fast flame ionization detector under neutral atmospheric conditions. Flow and Dispersion characteristics were studied that included mean velocity, turbulence intensity, Reynolds stress, turbulent kinetic energy (TKE), mean concentrations, and fluctuation intensity of concentration in the street canyon. The results show that the vertical velocity and turbulent energy increases as the aspect ratio increases. The pollutant concentration increases as the aspect ratio decreases. The concentration fluctuation intensities of the aspect ratio W/H = 1 was found lower than that of the aspect ratios W/H = ½ and ¾. The pollutant concentration at the leeward side of the aspect ratios W/H = ¾ and 1 was higher than that in the aspect ratios W/H = ½. The pollutant concentration distributions measured in the experiment indicates that the variability of the street geometrical layouts in urban environment are important parameters for estimating air quality in the urban canyon.

The spatial distribution pattern of urban spatial structure affects air flow and local meteorological conditions, which in turn influence the diffusion of air pollutants. This study built the urban spatial structure index system based on DEM, urban road networks, and big data. The ordinary kriging interpolation method was used to analyze the spatial distribution of gaseous pollutant concentrations in Jinan City. Correlation analysis, stepwise regression analysis, and bivariate global spatial autocorrelation analysis were used to study the influence of the urban spatial structure index on the spatial distribution of gaseous pollutant concentration. The main conclusions were as follows: (1) Evident spatial and temporal differences were observed in the concentration distribution of gaseous pollutants in Jinan. The spatial distribution of NO2 and CO concentrations showed a gradual decrease from north to south. Spatial heterogeneity was observed in the distribution of SO2 and O3 concentrations. (2) The urban spatial structure indicators had varying effects on the spatial distribution of different gaseous pollutant concentrations. The important factors that influenced the spatial distribution of urban gaseous pollutant concentrations included terrain elevation, building density, building volume, and floor area ratio. The greater the terrain undulation, the denser the building distribution, the greater the difference in building volume, and the greater the plot ratio, the greater the impact on the diffusion and spatial distribution of urban gaseous pollutants. (3) The spatial distribution of urban gaseous pollutant concentrations was significantly affected by the urban spatial structure indicators in the surrounding areas. Furthermore, the spatial distributions of NO2, SO2, CO, and O3 concentrations had a significant negative spatial correlation with the average DEM and standard deviation of the surrounding adjacent areas and a significant positive spatial correlation with the average and standard deviation of building height, standard deviation of building area, and building density in the surrounding adjacent areas (in June).

Two-step AI-aided Bayesian source identification of urban-scale pollution

Accurate daily peak load forecasting (DPLF) is crucial for informed decision-making in energy management. Deep neural networks (DNNs) are particularly apt for DPLF because they can analyze multiple factors, such as timestamps, weather conditions, and historical electric loads. Interpretability of machine learning models is essential for ensuring stakeholders understand and trust the decision-making process. We proposed the RAID (robust and interpretable DPLF) model, which enhances DPLF accuracy by recognizing daily peak load patterns and building separate DNN models for each day of the week. This approach was accessible for energy providers with limited computational resources, as the DNN models could be configured without a graphics processing unit (GPU). We utilized scikit-learn’s MLPRegressor for streamlined implementation, Optuna for hyperparameter optimization, and the Shapley additive explanations (SHAP) method to ensure interpretability. Applied to a dataset from two commercial office buildings in Richland, Washington, RAID outperformed existing methods like recurrent neural networks, Cubist, and HYTREM, achieving the lowest mean absolute percentage error values: 14.67% for Building 1 and 12.74% for Building 2. The kernel SHAP method revealed the influence of the previous day’s peak load and temperature-related variables on the prediction. The RAID model substantially improved energy management through enhanced DPLF accuracy, outperforming competing methods, providing a GPU-free configuration, and ensuring interpretable decision-making, with the potential to influence energy providers’ choices and promote overall energy system sustainability.

Exhaust gases from internal combustion engines are the main source of urban air pollution. Quantification of Polycyclic aromatic hydrocarbons (PAHs) in the exhaust gases is needed for emissions monitoring, enforcement, development, and testing of control technologies. The objective was to develop quantification of gaseous naphthalene in diesel engine exhaust based on diffusion-controlled extraction onto a retracted solid-phase microextraction (SPME) fiber coating and analysis on gas chromatography-mass spectrometry (GC-MS). Extraction of naphthalene with retracted fibers followed Fick’s law of diffusion. Extracted mass of naphthalene was proportional to Cg, t, Dg, T and inversely proportional to Z. Method detection limit (p = 0.95) was 11.5 ppb (0.06 mg·m−3) at t = 9 h, Z = 10 mm and T = 40 °C, respectively. It was found that the % mass extracted of naphthalene by SPME needle assembly depended on the type of fiber. Storage time at different temperatures did not affect analyte losses extracted by polydimethylsiloxane (PDMS) 100 µm fiber. The developed method was tested on exhaust gases from idling pickup truck and tractor, and compared side-by-side with a direct injection of sampled exhaust gas method. Time-weighted average (TWA) concentrations of naphthalene in exhaust gases from idling pickup truck and a tractor ranged from 0.08 to 0.3 mg·m−3 (15.3–53.7 ppb).

In the current paper, inverse problems are considered in which sources of urban air pollution are determined in accordance with observational data. A problem statement is provided, and a problem algorithm and the applied difference schemes of the numerical solution of equations are discussed. Moreover, a modification of G.I. Marchuk’s method for the solution of inverse problems is presented that enables the determination of urban districts with the highest intensity of harmful substance emission using multiprocessor computer systems. Examples of applying the considered approach for conditions of the city of Tomsk are given.

As urbanization intensifies, cities are facing escalating challenges related to environmental degradation and resource management, necessitating innovative and sustainable solutions. Biochar, a carbon-rich material derived from the pyrolysis of organic waste, has emerged as a versatile tool for advancing urban sustainability. This perspective synthesizes key findings regarding the global applications of biochar in promoting sustainable urban development, demonstrating its efficacy across multiple domains, including air quality improvement, waste valorization, carbon sequestration, soil regeneration, and water purification. By converting organic waste into a stable form of carbon, biochar provides a practical strategy to reduce landfill use and mitigate greenhouse gas emissions. Notably, biochar also contributes to reducing airborne pollutants. Recent studies have shown that certain metal-rich biochars can adsorb volatile organic compounds emitted from asphalt surfaces (up to 76%). Asphalt represents a less recognized yet significant source of urban air pollution, and this finding highlights an additional pathway through which biochar can improve air quality and extend infrastructure longevity. In the construction sector, the incorporation of biochar into cement and concrete not only enhances mechanical properties but also enables long-term carbon sequestration via carbonation processes. For soil regeneration, biochar improves porosity, water retention, and nutrient availability, increasing crop yields (e.g., 50% for chili in field trials). In water and wastewater treatment, biochar removes heavy metals (> 70% Pb²⁺), dyes (up to 95%), nutrients, and emerging contaminants such as PFAS. Additionally, it boosts methane yields in anaerobic digestion by 27%–42%. Furthermore, the potential of biochar in renewable energy systems and decentralized water treatment solutions underscores its value in building more resilient urban infrastructure. When integrated into circular economy models, biochar can facilitate the closure of resource loops, reduce environmental footprints, and support regenerative city planning. Despite its promising prospect, the large-scale adoption of biochar is hindered by several challenges, including technical limitations, economic constraints, and the lack of supportive policies and standards. By synthesizing current research findings and emerging applications, this perspective positions biochar as a versatile and foundational component in the transition toward climate-resilient, sustainable cities.

Air pollution is threat to the lives of people living in big cities of Pakistan. In Lahore 1,250 people die annually because of air pollution. Mass transit system that can be put forth as solution to urban air pollution is contingent with right choice of system and its affiliation with motorized vehicles and nature of urban air pollution. Existing mass transit system in Lahore due to untrue operation causes surfeit discharge of motor vehicular carbon monoxide. Tended relationships of mass transit system with motorized vehicles and urban air pollution are quite noteworthy. The growing motor vehicles (a consequence of flawed public mass transit system) are potential source of urban air pollution. This paper attempts to highlight correlations and regression curves of existing mass transit system. Further it recommends a two facet approach for reduction of motor vehicular air pollution in Lahore.

Influence of Meteorological Conditions on Pollutant Dispersion in Street Canyon

With the rapid growth of motor vehicle ownership, vehicle exhaust has become a major source of urban air pollution. This study constructs a mathematical mod-eling system for carbon monoxide (CO) and hydrocarbon (HC) emissions based on real road observation data, focusing on speed-emission relationships, optimal driving speed, driving behavior impacts, and accident-induced idling emissions. Results show the "emission rate-speed" model outperforms "mileage emis-sion-speed" (CO emission rate R²≈0.994); HC’s optimal speed is ~25 mile/h (practical), while CO’s optimal speed exceeds real limits; variable-speed driving increases instantaneous emission fluctuations; 200 vehicles idling 30 minutes emit ~1754g CO and ~189g HC. This study provides a scientific basis for traffic emission management.

What Explains Cross-City Variation in Mortality During the 1918 Influenza Pandemic? Evidence from 438 U.S. Cities

Motor vehicles are the major source of urban air pollution. The abatement of air pollutant emissions is an urgent task for environmental protection. This paper simulated the abatement for carbon monoxide (CO), volatile organic compounds (VOCs), nitrogen oxides (NO x ), and particular matter (PM) emissions from vehicles under four scenarios in the year 2015 in Hangzhou, China. It was found that the emissions of CO, VOCs, NO x , and PM from vehicles were 440.551, 23.079, 44.255, and 6.532 kt/a in 2010 in Hangzhou, respectively. The vehicle population will increase to over 1.2 million with a 60.7% growth rate until 2015 (estimated). Based on the scenario analysis, it was found that eliminating substandard vehicles and upgrading vehicle’s standards could help reduce CO and VOCs effectively, while the expected abatement of NO x and PM would be offset by the rapid increase in the vehicle numbers. It was also found that integrated measurements, including eliminating substandard vehicles, upgrading vehicle standards, supplying low sulfur oil, and introducing alternative fuel vehicles could simultaneously reduce the four key pollutants. These integrated policies make it possible to reduce 250.197, 10.270, 1.791, and 0.335 kt/a CO, VOCs, NO x , and PM with 56.79%, 44.50%, 4.05%, and 5.14% decrease rates in 2015, respectively, when compared to those in 2010.

Vehicle emissions are a major source of urban air pollution, and therefore a real-time monitoring system can be very useful in analyzing such emission and consequently assisting the policy making process. In this work we discuss the principle and structure of three different types of remote sensing detectors, and also the key techniques to establish a networked remote sensing monitoring system. We finally conclude this paper with data analysis from some preliminary experiments.

Construction site dust is one of the main sources of urban air pollution. In order to improve urban air quality and reduce the probability of respiratory diseases among construction workers, effective measures must be taken to control construction site dust. Dust monitoring is an important measure to reduce construction pollution to the surrounding environment. Vigorously developing dust monitoring is the only way to build a civilized construction and green city. Improving dust monitoring at urban construction sites has important practical significance for urban air quality control and accurate treatment of dust at construction sites. Dust monitoring can improve the appearance of the city, increase the investment of investors, and promote the economic development of the city. At the same time, it can also increase the living comfort and happiness index of residents, so dust monitoring is very necessary. In this paper, the research status, necessity and development benefits of urban construction site dust monitoring are expounded, then sort out the key points of dust monitoring technology, and give some suggestions to the possible problems in the existing technology to ensure the smooth implementation of dust monitoring. And put forward the proposal with the dust treatment and control from construction unit, construction unit and supervision unit three aspects to help reduce the construction of dust pollution.

What Explains Cross-City Variation in Mortality During the 1918 Influenza Pandemic? Evidence from 438 U.S. Cities