Towards Integrated Air Pollution Monitoring and Health Impact Assessment Using Federated Learning: A Systematic Review

Systematic review of predictive maintenance and digital twin technologies challenges, opportunities, and best practices

Background

Maintaining machines effectively continues to be a challenge for industrial organisations, which frequently employ reactive or premeditated methods. Recent research has begun to shift its attention towards the application of Predictive Maintenance (PdM) and Digital Twins (DT) principles in order to improve maintenance processes. PdM technologies have the capacity to significantly improve profitability, safety, and sustainability in various industries. Significantly, precise equipment estimation, enabled by robust supervised learning techniques, is critical to the efficacy of PdM in conjunction with DT development. This study underscores the application of PdM and DT, exploring its transformative potential across domains demanding real-time monitoring. Specifically, it delves into emerging fields in healthcare, utilities (smart water management), and agriculture (smart farm), aligning with the latest research frontiers in these areas.

Methodology

Employing the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) criteria, this study highlights diverse modeling techniques shaping asset lifetime evaluation within the PdM context from 34 scholarly articles.

Results

The study revealed four important findings: various PdM and DT modelling techniques, their diverse approaches, predictive outcomes, and implementation of maintenance management. These findings align with the ongoing exploration of emerging applications in healthcare, utilities (smart water management), and agriculture (smart farm). In addition, it sheds light on the critical functions of PdM and DT, emphasising their extraordinary ability to drive revolutionary change in dynamic industrial challenges. The results highlight these methodologies' flexibility and application across many industries, providing vital insights into their potential to revolutionise asset management and maintenance practice for real-time monitoring.

Conclusions

Therefore, this systematic review provides a current and essential resource for academics, practitioners, and policymakers to refine PdM strategies and expand the applicability of DT in diverse industrial sectors.

A comprehensive review of urban vegetation as a Nature-based Solution for sustainable management of particulate matter in ambient air

Air pollution is one of the most pressing environmental threats worldwide, resulting in several health issues such as cardiovascular and respiratory disorders, as well as premature mortality. The harmful effects of air pollution are particularly concerning in urban areas, where mismanaged anthropogenic activities, such as growth in the global population, increase in the number of vehicles, and industrial activities, have led to an increase in the concentration of pollutants in the ambient air. Among air pollutants, particulate matter is responsible for most adverse impacts. Several techniques have been implemented to reduce particulate matter concentrations in the ambient air. However, despite all the threats and awareness, efforts to improve air quality remain inadequate. In recent years, urban vegetation has emerged as an efficient Nature-based Solution for managing environmental air pollution due to its ability to filter air, thereby reducing the atmospheric concentrations of particulate matter. This review characterizes the various mitigation mechanisms for particulate matter by urban vegetation (deposition, dispersion, and modification) and identifies key areas for further improvements within each mechanism. Through a systematic assessment of existing literature, this review also highlights the existing gaps in the present literature that need to be addressed to maximize the utility of urban vegetation in reducing particulate matter levels. In conclusion, the review emphasizes the urgent need for proper air pollution management through urban vegetation by integrating different fields, multiple stakeholders, and policymakers to support better implementation.

A bibliometric analysis of research on the health impacts of ozone air pollution

Ground-level ozone (O3) is one of the major air pollutants. A large body of literature has linked O3 air pollution to various adverse human health effects. The objective of this study is to attain a comprehensive and in-depth understanding of the progress and frontiers of research on O3 and human health. We used bibliometric methods to summarize publications on O3 air pollution and public health between 1990 and 2022 obtained from the Web of Science Core Collection database. VOSviewer and R software were used for bibliometric analysis and visualization. A total of 4501 relevant papers were included in the analysis. There has been a significant increase in the number of publications since 2013, with the USA being the major contributor, followed by China and England. Harvard University was the most prolific research institution, followed by the US Environmental Protection Agency and the University of North Carolina System. Professor Joel Schwartz was the most published author and has established a complex network of national and international collaborations. Co-occurrence analysis of keywords suggested evolving research hotspots, from toxicological studies to population-based epidemiological studies and from the respiratory system to the extra-pulmonary system. Research on O3 and its human health effects has progressed rapidly over the past few decades, but academic disparities still persist between developed and developing countries. There is an urgent need to strengthen international cooperation to address the public health challenges posed by rising O3 air pollution in the future.

Research progress on the effects of gut microbiome on lung damage induced by particulate matter exposure

Air pollution is one of the top five causes of death in the world and has become a research hotspot. In the past, the health effects of particulate matter (PM), the main component of air pollutants, were mainly focused on the respiratory and cardiovascular systems. However, in recent years, the intestinal damage caused by PM and its relationship with gut microbiome (GM) homeostasis, thereby affecting the composition and function of GM and bringing disease burden to the host lung through different mechanisms, have attracted more and more attention. Therefore, this paper reviews the latest research progress in the effect of PM on GM-induced lung damage and its possible interaction pathways and explores the potential immune inflammatory mechanism with the gut-lung axis as the hub in order to understand the current research situation and existing problems, and to provide new ideas for further research on the relationship between PM pollution, GM, and lung damage.

Artificial intelligence-assisted air quality monitoring for smart city management

Background

The environment has been significantly impacted by rapid urbanization, leading to a need for changes in climate change and pollution indicators. The 4IR offers a potential solution to efficiently manage these impacts. Smart city ecosystems can provide well-designed, sustainable, and safe cities that enable holistic climate change and global warming solutions through various community-centred initiatives. These include smart planning techniques, smart environment monitoring, and smart governance. An air quality intelligence platform, which operates as a complete measurement site for monitoring and governing air quality, has shown promising results in providing actionable insights. This article aims to highlight the potential of machine learning models in predicting air quality, providing data-driven strategic and sustainable solutions for smart cities.

Methods

This study proposed an end-to-end air quality predictive model for smart city applications, utilizing four machine learning techniques and two deep learning techniques. These include Ada Boost, SVR, RF, KNN, MLP regressor and LSTM. The study was conducted in four different urban cities in Selangor, Malaysia, including Petaling Jaya, Banting, Klang, and Shah Alam. The model considered the air quality data of various pollution markers such as PM2.5, PM10, O3, and CO. Additionally, meteorological data including wind speed and wind direction were also considered, and their interactions with the pollutant markers were quantified. The study aimed to determine the correlation variance of the dependent variable in predicting air pollution and proposed a feature optimization process to reduce dimensionality and remove irrelevant features to enhance the prediction of PM2.5, improving the existing LSTM model. The study estimates the concentration of pollutants in the air based on training and highlights the contribution of feature optimization in air quality predictions through feature dimension reductions.

Results

In this section, the results of predicting the concentration of pollutants (PM2.5, PM10, O3, and CO) in the air are presented in R2 and RMSE. In predicting the PM10 and PM2.5concentration, LSTM performed the best overall high R2values in the four study areas with the R2 values of 0.998, 0.995, 0.918, and 0.993 in Banting, Petaling, Klang and Shah Alam stations, respectively. The study indicated that among the studied pollution markers, PM2.5,PM10, NO2, wind speed and humidity are the most important elements to monitor. By reducing the number of features used in the model the proposed feature optimization process can make the model more interpretable and provide insights into the most critical factor affecting air quality. Findings from this study can aid policymakers in understanding the underlying causes of air pollution and develop more effective smart strategies for reducing pollution levels.

Green effects of research and development on industrial waste reduction during the production phase: Evidence from China and policy implications

Maintaining public health requires a clean environment; however, some industrial wastes can damage the water, atmosphere, and living environment seriously. To promote green development, policy makers in China have developed and implemented strict environmental regulations to limit the pollutant emissions and improve the environmental quality. Industrial producers implement research and development (R&D) activities to gain more profits in competitive markets. A comprehensive understanding of the green effects of R&D on different industrial wastes could provide important policy recommendations, especially regarding the coordination of innovative and green developments. In this study, the author empirically analyzed the influence of R&D input, including the intramural expenditure on R&D and full-time equivalent of R&D personnel, on industrial wastes, including the discharge of chemical oxygen demand (COD) and ammonia nitrogen, emission of sulfur dioxide, nitrogen oxides, and particulate matter, and generation of common industrial solid and hazardous wastes, based on the data from Chinese industrial sectors for 2016-2020. The main findings of empirical analyses were robust and indicated that R&D activities significantly reduced the emissions of all three industrial waste gases and decreased the discharge of COD; however, in the case of China, the partial effects on the discharge of ammonia nitrogen and the industrial solid wastes were not statistically significant. The green effects of R&D on different industrial wastes may vary and generally depend on environmental regulations, with various limitations. The most viable policy recommendations indicate that by expanding and initiating the green effect of R&D on different industrial wastes, innovative and green developments are more likely to be achieved in a coordinated manner. Additionally, this can also support special R&D activities, with the added benefit of actively developing cleaner technology to treat pollutant emissions. Development, while maintaining a clean environment to ensure public health, could be more sustainable if innovative activities reduce the production of industrial wastes. This study analyzes the green effects of R&D on industrial waste and can serve as a viable framework for future studies on sustainable development.

An automated solid waste detection using the optimized YOLO model for riverine management

Due to urbanization, solid waste pollution is an increasing concern for rivers, possibly threatening human health, ecological integrity, and ecosystem services. Riverine management in urban landscapes requires best management practices since the river is a vital component in urban ecological civilization, and it is very imperative to synchronize the connection between urban development and river protection. Thus, the implementation of proper and innovative measures is vital to control garbage pollution in the rivers. A robot that cleans the waste autonomously can be a good solution to manage river pollution efficiently. Identifying and obtaining precise positions of garbage are the most crucial parts of the visual system for a cleaning robot. Computer vision has paved a way for computers to understand and interpret the surrounding objects. The development of an accurate computer vision system is a vital step toward a robotic platform since this is the front-end observation system before consequent manipulation and grasping systems. The scope of this work is to acquire visual information about floating garbage on the river, which is vital in building a robotic platform for river cleaning robots. In this paper, an automated detection system based on the improved You Only Look Once (YOLO) model is developed to detect floating garbage under various conditions, such as fluctuating illumination, complex background, and occlusion. The proposed object detection model has been shown to promote rapid convergence which improves the training time duration. In addition, the proposed object detection model has been shown to improve detection accuracy by strengthening the non-linear feature extraction process. The results showed that the proposed model achieved a mean average precision (mAP) value of 89%. Hence, the proposed model is considered feasible for identifying five classes of garbage, such as plastic bottles, aluminum cans, plastic bags, styrofoam, and plastic containers.