Examining the economic impact of noise pollution from a lens of household is a burgeoning field in the study of environmental sustainability. Economics studies cover the source, measure, consequence of noise pollution, as well as the econometric methods used to identify the causal impact of noise pollution on socioeconomic welfare. There are broadly four major noise origins along with the industrial growth and urban development, which are airport, railway, urban traffic, and neighborhood. Four general kinds of measures or data sources are used in economics studies to capture the noise variations, namely, proximity to noise origins, real-time noise monitor records, household surveys, and administrative records on noise complaints. The socioeconomic consequences of noise pollution span from physical or mental health to happiness, violence and suicide, housing market capitalization, and inequality. In economics studies, generally three types of econometric methods are used to identify causal impact of noise pollution on the household's welfare, which are instrumental variable estimation, difference-in-difference estimation, randomized and quasi-natural experiments. The causal impact o
Urban Visual Pollution (UVP) has emerged as a critical concern, yet research on automatic detection and application remains fragmented. This scoping review maps the existing deep learning-based approaches for detecting, classifying, and designing a comprehensive application framework for visual pollution management. Following the PRISMA-ScR guidelines, seven academic databases (Scopus, Web of Science, IEEE Xplore, ACM DL, ScienceDirect, SpringerNatureLink, and Wiley) were systematically searched and reviewed, and 26 articles were found. Most research focuses on specific pollutant categories and employs variations of YOLO, Faster R-CNN, and EfficientDet architectures. Although several datasets exist, they are limited to specific areas and lack standardized taxonomies. Few studies integrate detection into real-time application systems, yet they tend to be geographically skewed. We proposed a framework for monitoring visual pollution that integrates a visual pollution index to assess the severity of visual pollution for a certain area. This review highlights the need for a unified UVP management system that incorporates pollutant taxonomy, a cross-city benchmark dataset, a generalized
Random disturbances such as air pollution may affect cognitive performance, which, particularly in high-stakes settings, may have severe consequences for an individual's productivity and well-being. This paper examines the short-term effects of air pollution on school leaving exam results in Poland. I exploit random variation in air pollution between the days on which exams are held across three consecutive school years. I aim to capture this random variation by including school and time fixed effects. The school-level panel data is drawn from a governmental program where air pollution is continuously measured in the schoolyard. This localized hourly air pollution measure is a unique feature of my study, which increases the precision of the estimated effects. In addition, using distant and aggregated air pollution measures allows me for the comparison of the estimates in space and time. The findings suggest that a one standard deviation increase in the concentration of particulate matter PM2.5 and PM10 decreases students' exam scores by around 0.07-0.08 standard deviations. The magnitude and significance of these results depend on the location and timing of the air pollution readin
Acknowledging the effects of outdoor air pollution, the literature inadequately addresses indoor air pollution's impacts. Despite daily health risks, existing research primarily focused on monitoring, lacking accuracy in pinpointing indoor pollution sources. In our research work, we thoroughly investigated the influence of indoor activities on pollution levels. A survey of 143 participants revealed limited awareness of indoor air pollution. Leveraging 65 days of diverse data encompassing activities like incense stick usage, indoor smoking, inadequately ventilated cooking, excessive AC usage, and accidental paper burning, we developed a comprehensive monitoring system. We identify pollutant sources and effects with high precision through clustering analysis and interpretability models (LIME and SHAP). Our method integrates Decision Trees, Random Forest, Naive Bayes, and SVM models, excelling at 99.8% accuracy with Decision Trees. Continuous 24-hour data allows personalized assessments for targeted pollution reduction strategies, achieving 91% accuracy in predicting activities and pollution exposure.
Air pollution can be studied in the urban structure regulated by transport networks. Transport networks can be studied as geometric and topological graph characteristics through designed models. Current studies do not offer a comprehensive view as limited models with insufficient features are examined. Our study finds geometric patterns of pollution-indicated transport networks through 0.3 million image interpretations of global cities. These are then described as part of 12 indices to investigate the network-pollution correlation. Strategies such as improved connectivity, more balanced road types and the avoidance of extreme clustering coefficient are identified as beneficial for alleviated pollution. As a graph-only study, it informs superior urban planning by separating the impact of permanent infrastructure from that of derived development for a more focused and efficient effort toward pollution reduction.
Air pollution has become a major threat to human health, making accurate forecasting crucial for pollution control. Traditional physics-based models forecast global air pollution by coupling meteorology and pollution processes, using either online or offline methods depending on whether fully integrated with meteorological models and run simultaneously. However, the high computational demands of both methods severely limit real-time prediction efficiency. Existing deep learning (DL) solutions employ online coupling strategies for global air pollution forecasting, which finetune pollution forecasting based on pretrained atmospheric models, requiring substantial training resources. This study pioneers a DL-based offline coupling framework that utilizes bilinear pooling to achieve offline coupling between meteorological fields and pollutants. The proposed model requires only 13% of the parameters of DL-based online coupling models while achieving competitive performance. Compared with the state-of-the-art global air pollution forecasting model CAMS, our approach demonstrates superiority in 63% variables across all forecast time steps and 85% variables in predictions exceeding 48 hours
The Lancet Commission on pollution and health reported that pollution was responsible for 9 million premature deaths in 2015, making it the world's largest environmental risk factor for disease and premature death. We have now updated this estimate using data from the Global Burden of Diseases, Injuriaes, and Risk Factors Study 2019. We find that pollution remains responsible for approximately 9 million deaths per year, corresponding to one in six deaths worldwide. Reductions have occurred in the number of deaths attributable to the types of pollution associated with extreme poverty. However, these reductions in deaths from household air pollution and water pollution are offset by increased deaths attributable to ambient air pollution and toxic chemical pollution (ie, lead). Deaths from these modern pollution risk factors, which are the unintended consequence of industrialisation and urbanisation, have risen by 7% since 2015 and by over 66% since 2000. Despite ongoing efforts by UN agencies, committed groups, committed individuals, and some national governments (mostly in high-income countries), little real progress against pollution can be identified overall, particularly in the low-income and middle-income countries, where pollution is most severe. Urgent attention is needed to control pollution and prevent pollution-related disease, with an emphasis on air pollution and lead poisoning, and a stronger focus on hazardous chemical pollution. Pollution, climate change, and biodiversity loss are closely linked. Successful control of these conjoined threats requires a globally supported, formal science-policy interface to inform intervention, influence research, and guide funding. Pollution has typically been viewed as a local issue to be addressed through subnational and national regulation or, occasionally, using regional policy in higher-income countries. Now, however, it is increasingly clear that pollution is a planetary threat, and that its drivers, its dispersion, and its effects on health transcend local boundaries and demand a global response. Global action on all major modern pollutants is needed. Global efforts can synergise with other global environmental policy programmes, especially as a large-scale, rapid transition away from all fossil fuels to clean, renewable energy is an effective strategy for preventing pollution while also slowing down climate change, and thus achieves a double benefit for planetary health.
In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving emission sources. We formulate a robust variational framework for the time-dependent advection-diffusion problem and establish the boundedness and inf-sup stability of the corresponding discrete weak formulation. Based on this mathematical foundation, we construct a robust loss function that is directly related to the true approximation error, defined as the difference between the neural network approximation and the (unknown) exact solution. Additionally, a collocation-based strategy is introduced to speed up neural network training. As a case study, we investigate pollution propagation caused by snowmobile traffic in Longyearbyen, Spitsbergen, supported by detailed in-field measurements collected using dedicated sensors. The proposed framework is applied to analyze the effects of thermal inversion on pollutant accumulation. Our results demonstrate that thermal inversion traps dense and humid air masses near the ground, significantly enhancing particulate matter (PM) concentration and worsening local air quality.
Few studies quantify how traffic management dynamically reshapes modal split and emission-exposure outcomes over pollution severities. This paper proposes a novel day-to-day assignment model integrating exposure cost, which includes exposure perception and emissions-dispersion-exposure algorithm. Numerical experiments reveal that and various levels of traffic-related measures have an air pollution scenario-dependent effect on the MT system. In light pollution scenarios, vehicle restrictions and reduced fares for buses or ridesharing help lower car usage and reduce emissions and exposure. However, under heavy pollution, higher-level restrictions and ridesharing fares paradoxically increase travelers' exposure by 18% and 6.3%, respectively, due to modal shift. Furthermore, timely pollution information updates could plausibly encourage healthier travel. This paper also proposes practical strategies for both routine and emergency traffic management, considering the trade-offs among travel cost, emission, and exposure, and emphasizes the need for measures tailored to different air pollution contexts to offer deeper insights for urban traffic policies.
Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: generative recommenders may consume polluted web content, such as fake reviews and promotional pages crafted to mislead recommendations. We ask: to what extent do search-augmented LLMs become unwitting promoters of fake products when consuming polluted retrieval results? To answer this, we introduce FORGE (Fake Online Recommendations in Generative Environments), a benchmark for measuring fake-product promotion under controlled web-content pollution. Given an upstream search result, FORGE locally rewrites real products in retrieved web pages into fake ones to simulate web-content pollution, and measures how often the LLM recommends the fake product. FORGE covers 225 real-world products across 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies substantially across categories, increasing when models lack stable prior knowledge of the relevant products. Reasoning d
Von Zeipel-Lidov-Kozai (ZLK) oscillations, induced by bound, perturbative companions to white dwarfs, have been suggested as a dynamical mechanism that may contribute to white dwarf pollution. To trigger ZLK oscillations, however, a 3-body system must reach a sufficiently large mutual inclination between orbits. The occurrence of these high-mutual-inclination configurations can be curtailed by dissipative precession at the protoplanetary disk stage, which pushes exoplanet-hosting close binary systems toward preferential orbit-orbit alignment. In this work, we constrain the fraction of white dwarfs with binary companions that can undergo ZLK-driven pollution given the effects of dissipative precession. To accrete pollution via ZLK oscillations, a white dwarf binary system must be sufficiently inclined and the characteristic timescale of the oscillations must be sufficiently short to perturb material within the white dwarf's cooling age. Considering a sample of 4400 known white dwarf/main sequence binaries, we find that $50-70\%$ have favorable parameters for ZLK pollution, depending on the orbital separation of the polluting body. While the conditions for oscillations are favorable,
What happens to pollution when developing countries open their borders to trade? Theoretical predictions are ambiguous, and empirical evidence remains limited. We study the effects of the 1991 Indian trade liberalization reform on water pollution. The reform abruptly and unexpectedly lowered import tariffs, increasing exposure to trade. Larger tariff reductions are associated with relative increases in water pollution. The estimated effects imply a 0.11 standard deviation increase in water pollution for the median district exposed to the tariff reform.
Air pollution remains a leading global health risk, exacerbated by rapid industrialization and urbanization, contributing significantly to morbidity and mortality rates. In this paper, we introduce AirCast, a novel multi-variable air pollution forecasting model, by combining weather and air quality variables. AirCast employs a multi-task head architecture that simultaneously forecasts atmospheric conditions and pollutant concentrations, improving its understanding of how weather patterns affect air quality. Predicting extreme pollution events is challenging due to their rare occurrence in historic data, resulting in a heavy-tailed distribution of pollution levels. To address this, we propose a novel Frequency-weighted Mean Absolute Error (fMAE) loss, adapted from the class-balanced loss for regression tasks. Informed from domain knowledge, we investigate the selection of key variables known to influence pollution levels. Additionally, we align existing weather and chemical datasets across spatial and temporal dimensions. AirCast's integrated approach, combining multi-task learning, frequency weighted loss and domain informed variable selection, enables more accurate pollution forec
Weather conditions significantly influence the formation and dispersion of pollution variations. Here we study networks of pollution as well as climate networks and find that pollutants may not only have an impact close to their source but also show a significant correlation with pollutant concentrations thousands of kilometers away. We develop a pollution network model based on cross-correlation between PM2.5 concentration time series in different sites in China to detect stable long-range links during the last ten years. A multi-network analysis of the 500 hPa geopotential height and PM2.5 concentration suggests that long-range correlations in PM2.5 levels are also influenced by synoptic activity.
Artificial light plays an integral role in modern cities, significantly enhancing human productivity and the efficiency of civilization. However, excessive illumination can lead to light pollution, posing non-negligible threats to economic burdens, ecosystems, and human health. Despite its critical importance, the exploration of its causes remains relatively limited within the field of artificial intelligence, leaving an incomplete understanding of the factors contributing to light pollution and sustainable illumination planning distant. To address this gap, we introduce a novel framework named Causally Aware Generative Adversarial Networks (CAGAN). This innovative approach aims to uncover the fundamental drivers of light pollution within cities and offer intelligent solutions for optimal illumination resource allocation in the context of sustainable urban development. We commence by examining light pollution across 33,593 residential areas in seven global metropolises. Our findings reveal substantial influences on light pollution levels from various building types, notably grasslands, commercial centers and residential buildings as significant contributors. These discovered causal
Recently, air pollution is one of the most concerns for big cities. Predicting air quality for any regions and at any time is a critical requirement of urban citizens. However, air pollution prediction for the whole city is a challenging problem. The reason is, there are many spatiotemporal factors affecting air pollution throughout the city. Collecting as many of them could help us to forecast air pollution better. In this research, we present many spatiotemporal datasets collected over Seoul city in Korea, which is currently much suffered by air pollution problem as well. These datasets include air pollution data, meteorological data, traffic volume, average driving speed, and air pollution indexes of external areas which are known to impact Seoul's air pollution. To the best of our knowledge, traffic volume and average driving speed data are two new datasets in air pollution research. In addition, recent research in air pollution has tried to build models to interpolate and predict air pollution in the city. Nevertheless, they mostly focused on predicting air quality in discrete locations or used hand-crafted spatial and temporal features. In this paper, we propose the usage of
Atmospheric composition of exoplanets is often considered as a probe of the planet's formation condition. How exactly the initial chemical memory may be altered from the birth to the final state of the planet, however, remains unknown. Here, we develop a simple model of pollution of planetary atmosphere by the vaporization of infalling planetesimal of varying sizes and composition (SiO$_2$ inside 1 au and H$_2$O outside 1 au), following their trajectory and thermal evolution through the upper advective and radiative layers of a sub-Neptune class planet during the late stage of disk evolution. We vary the rate of pollution by changing the solid content of the disk and by dialing the level of disk gas depletion which in turn determines the rate of planetary migration. We find that pollution by silicate grains will always be limited by the saturation limit set by the thermal state of the atmosphere. By contrast, pollution by water ice can lead to $\sim$2--4 orders of magnitude variation in the atmospheric water mass fraction depending on the solid and gas content of the disk. Both cases suggest that post-formation pollution can erase the initial compositional memory of formation. Post
We study the design of fair allocation rules for the abatement of riparian pollution. To do so, we consider the so-called river pollution claims model, recently introduced by Yang et al. (2025) to distribute a budget of emissions permits among agents (cities, provinces, or countries) located along a river. In such a model, each agent has a claim reflecting population, emission history, and business-as-usual emissions, and the issue is to allocate among them a budget that is lower (or equal) than the aggregate claim. For environmental reasons, the specific location along the river where pollutants are emitted is an important concern (the more upstream the location is the higher the damage of polluting the river). We characterize a class of geometric rules that adjust proportional allocations to compromise between fairness and environmental concerns. Our class is an alternative to the one proposed by Yang et al. (2025). We compare both alternatives through an axiomatic study, as well as an illustration for the case study of the Tuojiang Basin in China.
Air pollution is the origination of particulate matter, chemicals, or biological substances that brings pain to either humans or other living creatures or instigates discomfort to the natural habitat and the airspace. Hence, air pollution remains one of the paramount environmental issues as far as metropolitan cities are concerned. Several air pollution benchmarks are even said to have a negative influence on human health. Also, improper detection of air pollution benchmarks results in severe complications for humans and living creatures. To address this aspect, a novel technique called, Discretized Regression and Least Square Support Vector (DR-LSSV) based air pollution forecasting is proposed. The results indicate that the proposed DR-LSSV Technique can efficiently enhance air pollution forecasting performance and outperforms the conventional machine learning methods in terms of air pollution forecasting accuracy, air pollution forecasting time, and false positive rate.
In this paper investigations by the same authors on environmental issues concerning the control of the pollution produced by human activities have been extended to include costs related to environmental interventions. The proposed model consists of a spatially structured dynamic economic growth model which takes into account the level of pollution induced by production, a possible taxation based on the amount of produced pollution, and possible environmental interventions. It has been analyzed an optimal harvesting control problem with an objective function composed of four terms, namely the intertemporal utility of the decision maker, the space-time average of the level of pollution in the habitat, the disutility due to the imposition of taxation and the cost of environmental interventions. A specific novelty in the model proposed here is the localization of the possible interventions to a subregion of the whole habitat. Computational experiments have been carried out to exemplify the outcomes of the proposed model.