Urban Air Pollution Monitoring Research Articles

AI-driven environmental sensor networks and digital platforms for urban air pollution monitoring and modelling

Recent advances in Artificial Intelligence (AI) research have opened up new opportunities for leveraging AI research for societal impacts. AI research offers novel ways of tackling societal problems including environmental, health, and education challenges. Despite the potential, there are limited documented use cases and methodologies for translating AI research to societal impact at a large scale. This paper presents AirQo, an AI and advanced technology-driven use case for urban environmental pollution monitoring and modelling and the resulting societal impacts that have been realised. The research outputs include a set of digital solutions for the environmental air pollution challenges including (1) custom-designed low-cost air quality monitors that are premised on IoT technology (2) a methodology for deploying a high-resolution and citizen-driven air quality monitoring (3) AI-powered digital tools for air quality information modelling and analysis for citizens and city leaders, and (4) a framework for engagement for citizens and leaders. The AirQo project has been deployed and scaled out in cities in Eastern, Western, and Central African countries. The societal impacts resulting from the implementation of the AirQo research project include policy and regulations, education and awareness, and research around air quality issues.

SQCS: A sustainable quality control system for spatial crowdsourcing via three-party evolutionary game: Theory and practice

Quality control of sensing data poses a fundamental challenge in Spatial Crowdsourcing (SC) applications, and various incentive mechanisms have been proposed to effectively motivate workers. However, real-world SC systems involve multiple stakeholders, namely workers, platforms, and requesters, who exhibit bounded rationality. Moreover, prior research has often neglected the practical aspect of platforms needing to verify sensing data against ground truth information, which incurs a cost. Therefore, platforms face the constraint of verification cost and must judiciously select the verification rate. In this paper, a Sustainable Quality Control System (SQCS) is proposed, which employs a three-party evolutionary game to model the dynamic interaction among workers, platforms, and requesters in practical SC scenarios. Based on this dynamic model: (1) In theory, we derive the minimum verification rate required for effective worker monitoring and the maximum verification cost that platforms can sustainably bear via the analysis of evolutionary stable strategies. These findings serve as guidelines for achieving sustainable quality control within the SQCS framework; (2) In practice, we apply the SQCS framework to the SC scenario of urban air pollution monitoring. The optimal quality control strategy that maximizes overall social benefits is analyzed via numerical methods. Extensive experimental validation is conducted to demonstrate the effectiveness of the proposed theory and practical approach. These findings provide valuable insights for the sustainable development of SC systems.

Expansion of Roadside Air Pollution Monitoring Network in Seoul using Learning-based Optimization Method

Objectives : In this study, a learning-based optimization method is proposed and implemented for determining new monitoring sites when expanding the roadside air pollution monitoring network. Utilizing the bigdata available in Seoul, this decision-making tool is developed that takes into account the objectives of selecting new monitoring sites and incorporates social, economic, and environmental characteristics. The optimized results can suggest potential locations for new roadside air pollution monitoring sites. Additionally, the capability of this tool to facilitate objective decision-making processes is evaluated by determining the influence range providing reliable air pollution information with the addition of the new monitoring sites.Methods : The proposed learning-based optimization algorithm is a new approach for selecting the new optimal monitoring sites by comprehensively considering social, economic, and environmental factors aligned with the installation purpose of the monitoring system in Seoul. The algorithm starts with genetic algorithms to select candidate locations for new monitoring sites that maximize the influence area of the expanded monitoring network compared to the existing monitoring network, capture a high overall level of air pollution, and do not overlap with the existing monitoring network. After that, PROMETHEE method is applied to evaluate the solutions generated by the genetic algorithm and choose the final solution that best fits six evaluation factors (Information entropy, number of new monitoring sites, distance from point sources, wind speed, traffic volume, and population) to be considered when installing new monitoring sites.Results and Discussion : The learning-based optimization algorithm selects 10 potential new monitoring sites adding to the existing roadside air pollution monitoring network having 15 monitoring sites. The explainable spatiotemporal range of the air pollution information that can be expected after the installation of the new monitoring sites is quantified to cover 84.33% of Seoul, reducing the uncertainty of the air pollution information of existing monitoring network by 26.15%. The final solution, selected from several solutions, can get new optimal roadside air pollution monitoring sites reflecting the regional characteristics of Seoul and the installation purpose of the monitoring system by having a small number of newly established monitoring locations, being close to air pollution emissions facilities, and having a high population and traffic volume.Conclusion : The proposed learning-based optimization method, using relevant variables for the installation purpose of the monitoring system, can derive the objective solution for deciding new monitoring locations of the roadside air pollution monitoring network, considering additional social factors as opposed to urban air pollution monitoring network. The final solution obtained through the optimization algorithm has great potential for future use, as it can guide to determine practical and feasible new monitoring sites with additional on-site verification. Furthermore, this optimized approach can be applied widely during the decision-making process for the expansion of other environmental monitoring networks.

Geospatial complex event processing in smart city applications

The extensive deployment of the Internet of things (IoT) devices in urban areas enables smart city systems (e.g., urban traffic detection and air pollution monitoring) to use these devices to discover the affected regions by various events, particularly complex ones. A complex event is inferred from patterns of different individual primitive events according to their spatio-temporal information. Complex event processing (CEP) systems facilitate applications to define their reasoning rules based on event processing languages (EPL), similar to SQL. However, current languages and CEP engines do not efficiently support spatial data characteristics. Geospatial CEP is challenging since applications have diverse definitions for complex events (e.g., air quality index), IoT devices have heterogeneous specifications/capabilities, and complex events may happen concurrently. This paper proposes the Geo-Tesla language that enables smart city applications to define spatial attributes in complex event definitions and reasoning rules. Then, we devise the GeoT-Rex CEP engine that implements geospatial operations that compiles Geo-Tesla language and processes the spatial data. The integration of Geo-Tesla and GeoT-Rex enables applications to process complex events with spatial characteristics in their reasoning rules and identify boundaries of the detected complex event (event footprint). The evaluation results from the proof of concept implementation show that our proposed solution outperforms in identifying the footprint of complex events up to 44% in the largest network size. They also show that the detection percentage in the concurrent appearance of complex events is 40% more on average than a close state-of-the-art baseline.

Environmental Justice and the Use of Artificial Intelligence in Urban Air Pollution Monitoring

The main aims of urban air pollution monitoring are to optimize the interaction between humanity and nature, to combine and integrate environmental databases, and to develop sustainable approaches to the production and the organization of the urban environment. One of the main applications of urban air pollution monitoring is for exposure assessment and public health studies. Artificial intelligence (AI) and machine learning (ML) approaches can be used to build air pollution models to predict pollutant concentrations and assess environmental and health risks. Air pollution data can be uploaded into AI/ML models to estimate different exposure levels within different communities. The correlation between exposure estimates and public health surveys is important for assessing health risks. These aspects are critical when it concerns environmental injustice. Computational approaches should efficiently manage, visualize, and integrate large datasets. Effective data integration and management are a key to the successful application of computational intelligence approaches in ecology. In this paper, we consider some of these constraints and discuss possible ways to overcome current problems and environmental injustice. The most successful global approach is the development of the smart city; however, such an approach can only increase environmental injustice as not all the regions have access to AI/ML technologies. It is challenging to develop successful regional projects for the analysis of environmental data in the current complicated operating conditions, as well as taking into account the time, computing power, and constraints in the context of environmental injustice.

Missing Data Imputation in the Internet of Things Sensor Networks

The Internet of Things (IoT) has had a tremendous impact on the evolution and adoption of information and communication technology. In the modern world, data are generated by individuals and collected automatically by physical objects that are fitted with electronics, sensors, and network connectivity. IoT sensor networks have become integral aspects of environmental monitoring systems. However, data collected from IoT sensor devices are usually incomplete due to various reasons such as sensor failures, drifts, network faults and various other operational issues. The presence of incomplete or missing values can substantially affect the calibration of on-field environmental sensors. The aim of this study is to identify efficient missing data imputation techniques that will ensure accurate calibration of sensors. To achieve this, we propose an efficient and robust imputation technique based on k-means clustering that is capable of selecting the best imputation technique for missing data imputation. We then evaluate the accuracy of our proposed technique against other techniques and test their effect on various calibration processes for data collected from on-field low-cost environmental sensors in urban air pollution monitoring stations. To test the efficiency of the imputation techniques, we simulated missing data rates at 10–40% and also considered missing values occurring over consecutive periods of time (1 day, 1 week and 1 month). Overall, our proposed BFMVI model recorded the best imputation accuracy (0.011758 RMSE for 10% missing data and 0.169418 RMSE at 40% missing data) compared to the other techniques (kNearest-Neighbour (kNN), Regression Imputation (RI), Expectation Maximization (EM) and MissForest techniques) when evaluated using different performance indicators. Moreover, the results show a trade-off between imputation accuracy and computational complexity with benchmark techniques showing a low computational complexity at the expense of accuracy when compared with our proposed technique.

Estimation of Aerosol Optical Depth at 30 m Resolution Using Landsat Imagery and Machine Learning

Current remote sensing-based aerosol optical depth (AOD) products have coarse spatial resolutions, which are useful for studies at continental and global scales, but unsatisfactory for local scale applications, such as urban air pollution monitoring. In this study, we investigated the possibility of using Landsat imagery to develop high-resolution AOD estimations at 30 m based on machine learning algorithms. We assessed the performance of six machine learning algorithms, including Extreme Gradient Boosting, Random Forest, Cascade Random Forest, Gradient Boosted Decision Trees, Extremely Randomized Trees, and Multiple Linear Regression. To obtain accurate AOD estimations, we used prior knowledge from multiple sources as inputs to the machine learning models, including the Global Land Surface Satellite (GLASS) albedo, the 1-km AOD product from MODIS data using the Multi-Angle Implementation of Atmospheric Correction (MAIAC) algorithm, and meteorological and surface elevation data. A total of 13,624 AOD measurements from Aerosol Robotic Network (AERONET) sites were used for model training and validation. We found that all six algorithms exhibited good performance, with R2 values ranging from 0.73 to 0.78 and AOD root-mean-square errors (RMSE) ranging from 0.089 to 0.098. The extremely randomized trees algorithm, however, demonstrated marginally superior performance as compared to the other algorithms; hence, it was used to produce AOD estimates at a 30 m resolution for one Landsat scene coving Beijing in 2013–2019. Through a comparison with overlapping AERONET observations, a high level of accuracy was achieved, with an R2 = 0.889 and an RMSE = 0.156. Our method can be potentially used to generate a global high-resolution AOD dataset based on Landsat imagery.

Air Pollution Modelling by Machine Learning Methods

Precise environmental modelling of pollutants distributions represents a key factor for addresing the issue of urban air pollution. Nowadays, urban air pollution monitoring is primarily carried out by employing sparse networks of spatially distributed fixed stations. The work in this paper aims at improving the situation by utilizing machine learning models to process the outputs of multi-sensor devices that are small, cheap, albeit less reliable, thus a massive urban deployment of those devices is possible. The main contribution of the paper is the design of a mathematical model providing sensor fusion to extract the information and transform it into the desired pollutant concentrations. Multi-sensor outputs are used as input information for a particular machine learning model trained to produce the CO, NO2, and NOx concentration estimates. Several state-of-the-art machine learning methods, including original algorithms proposed by the authors, are utilized in this study: kernel methods, regularization networks, regularization networks with composite kernels, and deep neural networks. All methods are augmented with a proper hyper-parameter search to achieve the optimal performance for each model. All the methods considered achieved vital results, deep neural networks exhibited the best generalization ability, and regularization networks with product kernels achieved the best fitting of the training set.

Crowdsourcing without Data Bias: Building a Quality Assurance System for Air Pollution Symptom Mapping

Crowdsourcing is one of the spatial data sources, but due to its unstructured form, the quality of noisy crowd judgments is a challenge. In this study, we address the problem of detecting and removing crowdsourced data bias as a prerequisite for better-quality open-data output. This study aims to find the most robust data quality assurance system (QAs). To achieve this goal, we design logic-based QAs variants and test them on the air quality crowdsourcing database. By extending the paradigm of urban air pollution monitoring from particulate matter concentration levels to air-quality-related health symptom load, the study also builds a new perspective for citizen science (CS) air quality monitoring. The method includes the geospatial web (GeoWeb) platform as well as a QAs based on conditional statements. A four-month crowdsourcing campaign resulted in 1823 outdoor reports, with a rejection rate of up to 28%, depending on the applied. The focus of this study was not on digital sensors’ validation but on eliminating logically inconsistent surveys and technologically incorrect objects. As the QAs effectiveness may depend on the location and society structure, that opens up new cross-border opportunities for replication of the research in other geographical conditions.

Fine-Grained Air Pollution Inference with Mobile Sensing Systems

Air pollution is a global health threat. Except static official air quality stations, mobile sensing systems are deployed for urban air pollution monitoring to achieve larger sensing coverage and greater sampling granularity. However, the data sparsity and irregularity also bring great challenges for pollution map recovery. To address these problems, we propose a deep autoencoder framework based inference algorithm. Under the framework, a partially observed pollution map formed by the irregular samples are input into the model, then an encoder and a decoder work together to recover the entire pollution map. Inside the decoder, we adopt a convolutional long short-term memory (ConvLSTM) model by revealing its physical interpretation with an atmospheric dispersion model, and further present a weather-related ConvLSTM to enable quasi real-time applications. To evaluate our algorithm, a half-year data collection was deployed with a real-world system on a coastal area including the Sino-Singapore Tianjin Eco-city in north China. With the resolution of 500 m x 500 m x 1 h, our offline method is proved to have high robustness against low sampling coverage and accidental sensor errors, obtaining 14.9% performance improvement over existing methods. Our quasi real-time model better captures the spatiotemporal dependencies in the pollution map with unevenly distributed samples than other real-time approaches, obtaining 4.2% error reduction.

MoreAir: A Low-Cost Urban Air Pollution Monitoring System.

MoreAir is a low-cost and agile urban air pollution monitoring system. This paper describes the methodology used in the development of this system along with some preliminary data analysis results. A key feature of MoreAir is its innovative sensor deployment strategy which is based on mobile and nomadic sensors as well as on medical data collected at a children’s hospital, used to identify urban areas of high prevalence of respiratory diseases. Another key feature is the use of machine learning to perform prediction. In this paper, Moroccan cities are taken as case studies. Using the agile deployment strategy of MoreAir, it is shown that in many Moroccan neighborhoods, road traffic has a smaller impact on the concentrations of particulate matters (PM) than other sources, such as public baths, public ovens, open-air street food vendors and thrift shops. A geographical information system has been developed to provide real-time information to the citizens about the air quality in different neighborhoods and thus raise awareness about urban pollution.

A Novel Interpolation-SVT Approach for Recovering Missing Low-Rank Air Quality Data

With increasing public demands for timely and accurate air pollution reporting, more air quality monitoring stations have been deployed by the governments in urban metropolises to increase the coverage of urban air pollution monitoring. However, due to systematic or accidental failures, some air pollution measurements obtained from these stations are found to have missing values, which will adversely affect the accuracy of any follow-up air pollution analyses and the quality of environmental decision-makings. In this study, the mathematical property of air quality measurements is investigated to recover the missing air pollution values. A new algorithm, which matches meteorology data with air pollution data from different locations, to reconstruct the data matrix and recover missing entries, is proposed. Next, a Low Rank Matrix Completion problem is used to reconstruct the missing values, by transforming the data recovery problem to a sub-gradient primal-dual problem, based on the duality theory, with Singular Value Thresholding (SVT) employed to develop sub-optimal solutions. Next, an Interpolation-SVT (ISVT) approach is adopted to handle the sparsity of observed measurements. Comprehensive case studies are conducted to evaluate the performance of the proposed methods. The simulation results have demonstrated that the proposed SVT and ISVT methods can effectively recover the missing air pollution data and outperform existing interpolation methods and data imputation techniques. The proposed study can improve air pollution estimation and prediction whenever the low-rank data types that are used as proxies for air pollution estimation contain a lot of missing values and require data recovery.

Urban air pollution monitoring using scanning Lidar

We have developed a scanning Lidar system in this work to detect urban air pollution changes in real time and locate the sources of urban air pollution. We first proposed an algorithm to retrieve atmospheric extinction coefficients, which we used to create Lidar maps. Using Lidar map of the average extinction coefficients, we identified the locations of the local maximum values, and hence, the positions of the urban air pollution sources. Experimental results indicate that this method is effective for urban air pollution monitoring.

Urban Air Pollution Monitoring System for Mapping Areas Based on Pollutant Level

This paper presents an explanation of the design of Carepol, an air pollution monitoring system in urban areas, using ISPU standard calculations (air pollution standards index of Indonesia) based on the internet] of thing’s (IoT). ISPU is a standard of air quality determination recognized by the government of the Republic of Indonesia through the Ministry of Environment. This IoT-based air pollution monitoring system is focused on measuring carbon monoxide (CO) levels as the highest pollutants in the world today, and analyzing and estimating the value of these pollutants in real-time and continuously. By using Carepol, society can actively engage in the control of urban air quality, and contribute to improving the environment and public health. For the government, Carepol can serve as a reference platform for proper policy-making in environmental issues, especially air pollution, and as well as the realization of Smart City for better life.

Smart Citizen Kit and Station: An open environmental monitoring system for citizen participation and scientific experimentation

Abstract In the past years, multiple research projects have explored the potential of low-cost environmental sensors for urban air pollution monitoring. However, each project has taken its own independent and in many cases, fully or partially closed approach. We present the Smart Citizen System, a flexible, easy-to-use and fully open-source environmental monitoring solution for particulate matter, carbon monoxide, nitrogen dioxide, noise levels, and many other indicators. The use of low-cost sensors in recent years has been generally approached in two different ways citizen science and educational activities, where the primary purpose is to engage citizens in the measurement process and raise awareness of environmental concerns; and a more sophisticated scientific approach, where the main aim is to study the potentiality of the low-cost sensing technologies. The Smart Citizen System balances modularity with integration to fulfil both needs by providing an extendable solution, with different ranges of sensors based on the same core components. With that aim, two solutions have been developed: the Smart Citizen Kit, intended for citizen science and awareness activities; and the Smart Citizen Station, designed to serve as a more complex and accurate set of air pollution sensors. The design is based on the principle of reproducibility, also integrating non-hardware components such as a dedicated storage platform and a sensor analysis framework. The core system bases its sensing capabilities in widely reviewed low-cost sensors and aims to provide a robust framework for environmental monitoring activities. By making everything open, from the hardware to the software platform or the sensor post-processing algorithms, we hope others might find it useful as a development platform allowing them to focus on their project particular needs instead of reinventing everything from the ground-up.

ICT

Recent years have witnessed a growing interest in urban air pollution monitoring, where hundreds of low-cost air quality sensors are deployed city-wide. To guarantee data accuracy and consistency, these sensors need periodic calibration after deployment. Since access to ground truth references is often limited in large-scale deployments, it is difficult to conduct city-wide post-deployment sensor calibration. In this work we propose In-field Calibration Transfer (ICT), a calibration scheme that transfers the calibration parameters of source sensors (with access to references) to target sensors (without access to references). On observing that (i) the distributions of ground truth in both source and target locations are similar and (ii) the transformation is approximately linear, ICT derives the transformation based on the similarity of distributions with a novel optimization formulation. The performance of ICT is further improved by exploiting spatial prediction of air quality levels and multi-source fusion. Experiments show that ICT is able to calibrate the target sensors as if they had direct access to the references.

Air pollution monitoring with secure low-cost Vehicular Sensor Networks

Counteracting the effects of air quality degradation is one of the main challenges in large cities today. To achieve such a goal, the first step is to control the emissions of various pollutant gases which in turn requires their concentrations to be measured such that proper methods can be applied. In this work we present a low cost urban air pollution monitoring system which we developed as proof-of-concept in Timisoara, Romania. The proposed solution is a Vehicular Sensor Network (VSN), with affordable midclass sensor nodes being installed on moving vehicles, ideally on the public transportation busses. The system measures temperature, humidity, the concentration of CO2 and dust, along with Volatile Organic Compounds (VOC). The aim of collecting weather data is to build correlations between air pollution levels and different weather conditions. In addition to technical constraints for measuring air quality, one of the challenges that we address is to implement secure transmissions between the devices. This raises several difficulties on microcontrollers that we use due to their low memory and computational resources. To answer both privacy and security issues, the proposed data transmission protocol of the measuring system, builds upon a modified version of the Station to Station (STS) protocol which allows secure tunnelling in an anonymous manner.

A Mobile Air Pollution Monitoring Data Set

Air pollution was observed in Hamilton, Ontario, Canada using monitors installed in a mobile platform from November 2005 up to November 2016. The dataset is an aggregation of several project specific monitoring days, which attempted to quantify air pollution spatial variation under varying conditions or in specific regions. Pollutants observed included carbon monoxide, nitric oxide, nitrogen dioxide, total nitrogen oxides, ground-level ozone, particulate matter concentrations for size cuts of 10 µm, 2.5 µm and 1 µm, and sulfur dioxide. Observations were collected over 114 days, which occurred in varying seasons and months. During sampling, the mobile platform travelled at an average speed of 27 km/h. The samples were collected as one-minute integrated samples and are prepared as line-segments, which include an offset for instrument response time. Sampling occurred on major freeways, highways, arterial and residential roads. This dataset is shared in hopes of supporting research on how to best utilize air pollution observations obtained with mobile air pollution platforms, which is a growing technique in the field of urban air pollution monitoring. We conclude with limitations in the data capture technique and recommendations for future mobile monitoring studies.

A Review on Urban Air Pollution Monitoring System with Forecasting Model

A Review on Urban Air Pollution Monitoring System with Forecasting Model

A Review of Urban Air Pollution Monitoring and Exposure Assessment Methods

The impact of urban air pollution on the environments and human health has drawn increasing concerns from researchers, policymakers and citizens. To reduce the negative health impact, it is of great importance to measure the air pollution at high spatial resolution in a timely manner. Traditionally, air pollution is measured using dedicated instruments at fixed monitoring stations, which are placed sparsely in urban areas. With the development of low-cost micro-scale sensing technology in the last decade, portable sensing devices installed on mobile campaigns have been increasingly used for air pollution monitoring, especially for traffic-related pollution monitoring. In the past, some reviews have been done about air pollution exposure models using monitoring data obtained from fixed stations, but no review about mobile sensing for air pollution has been undertaken. This article is a comprehensive review of the recent development in air pollution monitoring, including both the pollution data acquisition and the pollution assessment methods. Unlike the existing reviews on air pollution assessment, this paper not only introduces the models that researchers applied on the data collected from stationary stations, but also presents the efforts of applying these models on the mobile sensing data and discusses the future research of fusing the stationary and mobile sensing data.