A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization

Design and Enhancement of a Fog-Enabled Air Quality Monitoring and Prediction System: An Optimized Lightweight Deep Learning Model for a Smart Fog Environmental Gateway

Effective air quality monitoring and forecasting are essential for safeguarding public health, protecting the environment, and promoting sustainable development in smart cities. Conventional systems are cloud-based, incur high costs, lack accurate Deep Learning (DL)models for multi-step forecasting, and fail to optimize DL models for fog nodes. To address these challenges, this paper proposes a Fog-enabled Air Quality Monitoring and Prediction (FAQMP) system by integrating the Internet of Things (IoT), Fog Computing (FC), Low-Power Wide-Area Networks (LPWANs), and Deep Learning (DL) for improved accuracy and efficiency in monitoring and forecasting air quality levels. The three-layered FAQMP system includes a low-cost Air Quality Monitoring (AQM) node transmitting data via LoRa to the Fog Computing layer and then the cloud layer for complex processing. The Smart Fog Environmental Gateway (SFEG) in the FC layer introduces efficient Fog Intelligence by employing an optimized lightweight DL-based Sequence-to-Sequence (Seq2Seq) Gated Recurrent Unit (GRU) attention model, enabling real-time processing, accurate forecasting, and timely warnings of dangerous AQI levels while optimizing fog resource usage. Initially, the Seq2Seq GRU Attention model, validated for multi-step forecasting, outperformed the state-of-the-art DL methods with an average RMSE of 5.5576, MAE of 3.4975, MAPE of 19.1991%, R2 of 0.6926, and Theil's U1 of 0.1325. This model is then made lightweight and optimized using post-training quantization (PTQ), specifically dynamic range quantization, which reduced the model size to less than a quarter of the original, improved execution time by 81.53% while maintaining forecast accuracy. This optimization enables efficient deployment on resource-constrained fog nodes like SFEG by balancing performance and computational efficiency, thereby enhancing the effectiveness of the FAQMP system through efficient Fog Intelligence. The FAQMP system, supported by the EnviroWeb application, provides real-time AQI updates, forecasts, and alerts, aiding the government in proactively addressing pollution concerns, maintaining air quality standards, and fostering a healthier and more sustainable environment.

Applications of remote sensing vis-à-vis machine learning in air quality monitoring and modelling: a review

Environmental contamination especially air pollution is an exponentially growing menace requiring immediate attention, as it lingers on with the associated risks of health, economic and ecological crisis. The special focus of this study is on the advances in Air Quality (AQ) monitoring using modern sensors, integrated monitoring systems, remote sensing and the usage of Machine Learning (ML), Deep Learning (DL) algorithms, artificial neural networks, recent computational techniques, hybridizing techniques and different platforms available for AQ modelling. The modern world is data-driven, where critical decisions are taken based on the available and accessible data. Today's data analytics is a consequence of the information explosion we have reached. The current research also tends to re-evaluate its scope with data analytics. The emergence of artificial intelligence and machine learning in the research scenario has radically changed the methodologies and approaches of modern research. The aim of this review is to assess the impact of data analytics such as ML/DL frameworks, data integration techniques, advanced statistical modelling, cloud computing platforms and constantly improving optimization algorithms on AQ research. The usage of remote sensing in AQ monitoring along with providing enormous datasets is constantly filling the spatial gaps of ground stations, as the long-term air pollutant dynamics is best captured by the panoramic view of satellites. Remote sensing coupled with the techniques of ML/DL has the most impact in shaping the modern trends in AQ research. Current standing of research in this field, emerging trends and future scope are also discussed.

ACBiGRU-DAO: Attention Convolutional Bidirectional Gated Recurrent Unit-based Dynamic Arithmetic Optimization for Air Quality Prediction

Over the past decades, air pollution has turned out to be a major cause of environmental degradation and health effects, particularly in developing countries like India. Various measures are taken by scholars and governments to control or mitigate air pollution. The air quality prediction model triggers an alarm when the quality of air changes to hazardous or when the pollutant concentration surpasses the defined limit. Accurate air quality assessment becomes an indispensable step in many urban and industrial areas to monitor and preserve the quality of air. To accomplish this goal, this paper proposes a novel Attention Convolutional Bidirectional Gated Recurrent Unit based Dynamic Arithmetic Optimization (ACBiGRU-DAO) approach. The Attention Convolutional Bidirectional Gated Recurrent Unit (ACBiGRU) model is determined in which the fine-tuning parameters are used to enhance the proposed method by Dynamic Arithmetic Optimization (DAO) algorithm. The air quality data of India was acquired from the Kaggle website. From the dataset, the most-influencing features such as Air Quality Index (AQI), particulate matter namely PM2.5 and PM10, carbon monoxide (CO) concentration, nitrogen dioxide (NO2) concentration, sulfur dioxide (SO2) concentration, and ozone (O3) concentration are taken as input data. Initially, they are preprocessed through two different pipelines namely imputation of missing values and data transformation. Finally, the proposed ACBiGRU-DAO approach predicts air quality and classifies based on their severities into six AQI stages. The efficiency of the proposed ACBiGRU-DAO approach is examined using diverse evaluation indicators namely Accuracy, Maximum Prediction Error (MPE), Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Correlation Coefficient (CC). The simulation result inherits that the proposed ACBiGRU-DAO approach achieves a greater percentage of accuracy of about 95.34% than other compared methods.

Machine learning-based Decision Tree J48 with grey wolf optimizer for environmental pollution control

ABSTRACTDue to industrialization, activities of human and urbanization, environment is getting polluted. Air pollution has become a main issue in the metropolitan areas of the world. To protect people from diseases, monitoring air quality plays an important thing. This air pollutant may lead to many health issues like respiratory and cardiac problems. The major air pollutants are NO, C₆H₆, CO, etc. Many research works have been done in predicting air pollution-based health issues, predicting air pollution levels, monitoring and controlling the polluted levels. But they are not efficient, cost of maintenance is high and insufficient tool for monitoring it. To overcome these issues, this paper implements hybrid algorithm of Decision Tree J48 and Grey Wolf Optimizer (DT-GWO). This DT-GWO is a better model to addresses the predicting of Air Quality Index (AQI), which minimizes the error rate, accurately and effectively predicting the air quality. The AQI values are categorised as good, moderate, unhealthy, very unhealthy and hazardous. The dataset used in this work is collected from Kaggle website which contains air pollutants details with air quality index values. Accuracy obtained for decision Tree J48 is 93.72%, grey wolf optimizer is 96.83% and our proposed work DT-GWO is 99.78%.

Smart Air Quality Monitoring IoT-Based Infrastructure for Industrial Environments

Deficient air quality in industrial environments creates a number of problems that affect both the staff and the ecosystems of a particular area. To address this, periodic measurements must be taken to monitor the pollutant substances discharged into the atmosphere. However, the deployed system should also be adapted to the specific requirements of the industry. This paper presents a complete air quality monitoring infrastructure based on the IoT paradigm that is fully integrable into current industrial systems. It includes the development of two highly precise compact devices to facilitate real-time monitoring of particulate matter concentrations and polluting gases in the air. These devices are able to collect other information of interest, such as the temperature and humidity of the environment or the Global Positioning System (GPS) location of the device. Furthermore, machine learning techniques have been applied to the Big Data collected by this system. The results identify that the Gaussian Process Regression is the technique with the highest accuracy among the air quality data sets gathered by the devices. This provides our solution with, for instance, the intelligence to predict when safety levels might be surpassed.

Machine Learning for Determining Interactions between Air Pollutants and Environmental Parameters in Three Cities of Iran

Air pollution, as one of the most significant environmental challenges, has adversely affected the global economy, human health, and ecosystems. Consequently, comprehensive research is being conducted to provide solutions to air quality management. Recently, it has been demonstrated that environmental parameters, including temperature, relative humidity, wind speed, air pressure, and vegetation, interact with air pollutants, such as particulate matter (PM), NO2, SO2, O3, and CO, contributing to frameworks for forecasting air quality. The objective of the present study is to explore these interactions in three Iranian metropolises of Tehran, Tabriz, and Shiraz from 2015 to 2019 and develop a machine learning-based model to predict daily air pollution. Three distinct assessment criteria were used to assess the proposed XGBoost model, including R squared (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). Preliminary results showed that although air pollutants were significantly associated with meteorological factors and vegetation, the formulated model had low accuracy in predicting (R2PM2.5 = 0.36, R2PM10 = 0.27, R2NO2 = 0.46, R2SO2 = 0.41, R2O3 = 0.52, and R2CO = 0.38). Accordingly, future studies should consider more variables, including emission data from manufactories and traffic, as well as sunlight and wind direction. It is also suggested that strategies be applied to minimize the lack of observational data by considering second-and third-order interactions between parameters, increasing the number of simultaneous air pollution and meteorological monitoring stations, as well as hybrid machine learning models based on proximal and satellite data.

Intelligent Forecasting of Air Quality and Pollution Prediction Using Machine Learning

Air pollution consists of harmful gases and fine Particulate Matter (PM2.5) which affect the quality of air. This has not only become the key issues in scientific research but also turned to be an important social issues of the public’s life. Therefore, many experts and scholars at different R&Ds, universities, and abroad are involved in lot of research on PM2.5 pollutant predictions. In this scenario, the authors proposed various machine learning models such as linear regression, random forest, KNN, ridge and lasso, XGBoost, and AdaBoost models to predict PM2.5 pollutants in polluted cities. This experiment is carried out using Jupyter Notebook in Python 3.7.3. From the results with respect to MAE, MAPE, and RMSE metrics, among the models, XGBoost, AdaBoost, random forest, and KNN models (8.27, 0.40, and 13.85; 9.23, 0.45, and 10.59; 39.84, 1.94, and 54.59; and 49.13, 2.40, and 69.92, respectively) are observed to be more reliable models. The PM2.5 pollutant concentration (PClow-PChigh) range observed for these models is 0-18.583 μg/m3, 18.583-25.023 μg/m3, 25.023-28.234μg/m3, and 28.234-49.032 μg/m3, respectively, so these models can both predict the PM2.5 pollutant and can forecast the air quality levels in a better way. On comparison between various existing models and proposed models, it was observed that the proposed models can predict the PM2.5 pollutant with a better performance with a reduced error rate than the existing models.

Air pollution prediction with machine learning: a case study of Indian cities

The survival of mankind cannot be imagined without air. Consistent developments in almost all realms of modern human society affected the health of the air adversely. Daily industrial, transport, and domestic activities are stirring hazardous pollutants in our environment. Monitoring and predicting air quality have become essentially important in this era, especially in developing countries like India. In contrast to the traditional methods, the prediction technologies based on machine learning techniques are proved to be the most efficient tools to study such modern hazards. The present work investigates six years of air pollution data from 23 Indian cities for air quality analysis and prediction. The dataset is well preprocessed and key features are selected through the correlation analysis. An exploratory data analysis is exercised to develop insights into various hidden patterns in the dataset and pollutants directly affecting the air quality index are identified. A significant fall in almost all pollutants is observed in the pandemic year, 2020. The data imbalance problem is solved with a resampling technique and five machine learning models are employed to predict air quality. The results of these models are compared with the standard metrics. The Gaussian Naive Bayes model achieves the highest accuracy while the Support Vector Machine model exhibits the lowest accuracy. The performances of these models are evaluated and compared through established performance parameters. The XGBoost model performed the best among the other models and gets the highest linearity between the predicted and actual data.

Data-Driven Framework for Understanding and Predicting Air Quality in Urban Areas

Monitoring, predicting, and controlling the air quality in urban areas is one of the effective solutions for tackling the climate change problem. Leveraging the availability of big data in different domains like pollutant concentration, urban traffic, aerial imagery of terrains and vegetation, and weather conditions can aid in understanding the interactions between these factors and building a reliable air quality prediction model. This research proposes a novel cost-effective and efficient air quality modeling framework including all these factors employing state-of-the-art artificial intelligence techniques. The framework also includes a novel deep learning-based vegetation detection system using aerial images. The pilot study conducted in the UK city of Cambridge using the proposed framework investigates various predictive models ranging from statistical to machine learning and deep recurrent neural network models. This framework opens up possibilities of broadening air quality modeling and prediction to other domains like vegetation or green space planning or green traffic routing for sustainable urban cities. The research is mainly focused on extracting strong pieces of evidence which could be useful in proposing better policies around climate change.

Stacked ResNet-LSTM and CORAL model for multi-site air quality prediction

As the global economy is booming, and the industrialization and urbanization are being expedited, particulate matter 2.5 (PM2.5) turns out to be a major air pollutant jeopardizing public health. Numerous researchers are committed to employing various methods to address the problem of the nonlinear correlation between PM2.5 concentration and several factors to achieve more effective forecasting. However, a considerable space remains for the improvement of forecasting accuracy, and the problem of missing air pollution data on certain target areas also needs to be solved. Our research work is divided into two parts. First, this study presents a novel stacked ResNet-LSTM model to enhance prediction accuracy for PM2.5 concentration level forecast. As revealed from the experimental results, the proposed model outperforms other models such as boosting algorithms or general recurrent neural networks, and the advantage of feature extraction through residual network (ResNet) combined with a model stacking strategy is shown. Second, to solve the problem of insufficient air quality and meteorological data on some research areas, this study proposes the use of a correlation alignment (CORAL) method to carry out a prediction on the target area by aligning the second-order statistics between source area and target area. As indicated from the results, this model exhibits a considerable accuracy even in the absence of historical PM2.5 data in the target forecast area.

Embedded Generative Air Pollution Model with Variational Autoencoder and Environmental Factor Effect in Ulaanbaatar City

Air pollution is one of the most pressing modern-day issues in cities around the world. However, most cities have adopted air quality measurement devices that only measure the past pollution levels without paying attention to the influencing factors. To obtain preliminary pollution information with regard to environmental factors, we developed a variational autoencoder and feedforward neural network-based embedded generative model to examine the relationship between air quality and the effects of environmental factors. In the model, actual SO2, NO2, PM2.5, PM10, and CO measurements from 2016 to 2020 were used, which were assembled from 15 differently located ground monitoring stations in Ulaanbaatar city. A wide range of weather and fuel measurements were used as the data for the influencing factors, and were collected over the same period as the air pollution data were recorded. The prediction results concerned all measurement stations, and the results were visualized as a spatial–temporal distribution of pollution and the performance of individual stations. A cross-validated R2 was used to estimate the entire pollution distribution through the regions as SO2: 0.81, PM2.5: 0.76, PM10: 0.89, and CO: 0.83. Pearson’s chi-squared tests were used for assessing each measurement station, and the contingency tables represent a high correlation between the actual and model results. The model can be applied to perform specific analysis of the interdependencies between pollution and environmental factors, and the performance of the model improves with long-range data.

Pollution and Weather Reports: Using Machine Learning for Combating Pollution in Big Cities

Air pollution has become the most important issue concerning human evolution in the last century, as the levels of toxic gases and particles present in the air create health problems and affect the ecosystems of the planet. Scientists and environmental organizations have been looking for new ways to combat and control the air pollution, developing new solutions as technologies evolves. In the last decade, devices able to observe and maintain pollution levels have become more accessible and less expensive, and with the appearance of the Internet of Things (IoT), new approaches for combating pollution were born. The focus of the research presented in this paper was predicting behaviours regarding the air quality index using machine learning. Data were collected from one of the six atmospheric stations set in relevant areas of Bucharest, Romania, to validate our model. Several algorithms were proposed to study the evolution of temperature depending on the level of pollution and on several pollution factors. In the end, the results generated by the algorithms are presented considering the types of pollutants for two distinct periods. Prediction errors were highlighted by the RMSE (Root Mean Square Error) for each of the three machine learning algorithms used.

AQI time series prediction based on a hybrid data decomposition and echo state networks

A hybrid AQI time series prediction model is proposed based on EWT-SE-VMD secondary decomposition, ICA (imperialist competitive algorithm) feature selection, and ESN (echo state network) neural network. Firstly, EWT (empirical wavelet transform) and VMD (variational mode decomposition) are used to decompose the original AQI time series into several stable and reliable subseries. Then, the ICA is used to select features of the above subseries for the ESN prediction model. Finally, the optimized feature variables are put into the ESN deep network to establish a prediction model of each AQI subseries and obtain the future AQI index. According to the experimental results of the daily AQI series in Beijing, Tianjin, and Shijiazhuang, we find that (a) among all decomposition methods, the proposed secondary decomposition method (EWT-SE-VMD) performs best in processing data; (b) it is proved that the proposed hybrid model has broad application prospect and research value in the AQI prediction field.

Air quality management using genetic algorithm based heuristic fuzzy time series model

Purpose

The purpose of this paper is to provide a better method for quality management to maintain an essential level of quality in different fields like product quality, service quality, air quality, etc.

Design/methodology/approach

In this paper, a hybrid adaptive time-variant fuzzy time series (FTS) model with genetic algorithm (GA) has been applied to predict the air pollution index. Fuzzification of data is optimized by GAs. Heuristic value selection algorithm is used for selecting the window size. Two algorithms are proposed for forecasting. First algorithm is used in training phase to compute forecasted values according to the heuristic value selection algorithm. Thus, obtained sequence of heuristics is used for second algorithm in which forecasted values are selected with the help of defined rules.

Findings

The proposed model is able to predict AQI more accurately when an appropriate heuristic value is chosen for the FTS model. It is tested and evaluated on real time air pollution data of two popular tourism cities of India. In the experimental results, it is observed that the proposed model performs better than the existing models.

Practical implications

The management and prediction of air quality have become essential in our day-to-day life because air quality affects not only the health of human beings but also the health of monuments. This research predicts the air quality index (AQI) of a place.

Originality/value

The proposed method is an improved version of the adaptive time-variant FTS model. Further, a nature-inspired algorithm has been integrated for the selection and optimization of fuzzy intervals.

Low-Cost Air Quality Sensing towards Smart Homes

The evolution of low-cost sensors (LCSs) has made the spatio-temporal mapping of indoor air quality (IAQ) possible in real-time but the availability of a diverse set of LCSs make their selection challenging. Converting individual sensors into a sensing network requires the knowledge of diverse research disciplines, which we aim to bring together by making IAQ an advanced feature of smart homes. The aim of this review is to discuss the advanced home automation technologies for the monitoring and control of IAQ through networked air pollution LCSs. The key steps that can allow transforming conventional homes into smart homes are sensor selection, deployment strategies, data processing, and development of predictive models. A detailed synthesis of air pollution LCSs allowed us to summarise their advantages and drawbacks for spatio-temporal mapping of IAQ. We concluded that the performance evaluation of LCSs under controlled laboratory conditions prior to deployment is recommended for quality assurance/control (QA/QC), however, routine calibration or implementing statistical techniques during operational times, especially during long-term monitoring, is required for a network of sensors. The deployment height of sensors could vary purposefully as per location and exposure height of the occupants inside home environments for a spatio-temporal mapping. Appropriate data processing tools are needed to handle a huge amount of multivariate data to automate pre-/post-processing tasks, leading to more scalable, reliable and adaptable solutions. The review also showed the potential of using machine learning technique for predicting spatio-temporal IAQ in LCS networked-systems.

Features Exploration from Datasets Vision in Air Quality Prediction Domain

Air pollution and its consequences are negatively impacting on the world population and the environment, which converts the monitoring and forecasting air quality techniques as essential tools to combat this problem. To predict air quality with maximum accuracy, along with the implemented models and the quantity of the data, it is crucial also to consider the dataset types. This study selected a set of research works in the field of air quality prediction and is concentrated on the exploration of the datasets utilised in them. The most significant findings of this research work are: (1) meteorological datasets were used in 94.6% of the papers leaving behind the rest of the datasets with a big difference, which is complemented with others, such as temporal data, spatial data, and so on; (2) the usage of various datasets combinations has been commenced since 2009; and (3) the utilisation of open data have been started since 2012, 32.3% of the studies used open data, and 63.4% of the studies did not provide the data.

An overview of methods of fine and ultrafine particle collection for physicochemical characterisation and toxicity assessments

Particulate matter (PM) is a crucial health risk factor for respiratory and cardiovascular diseases. The smaller size fractions, ≤2.5 μm (PM_2.5; fine particles) and ≤0.1 μm (PM_0.1; ultrafine particles), show the highest bioactivity but acquiring sufficient mass for in vitro and in vivo toxicological studies is challenging. We review the suitability of available instrumentation to collect the PM mass required for these assessments. Five different microenvironments representing the diverse exposure conditions in urban environments are considered in order to establish the typical PM concentrations present. The highest concentrations of PM_2.5 and PM_0.1 were found near traffic (i.e. roadsides and traffic intersections), followed by indoor environments, parks and behind roadside vegetation. We identify key factors to consider when selecting sampling instrumentation. These include PM concentration on-site (low concentrations increase sampling time), nature of sampling sites (e.g. indoors; noise and space will be an issue), equipment handling and power supply. Physicochemical characterisation requires micro- to milli-gram quantities of PM and it may increase according to the processing methods (e.g. digestion or sonication). Toxicological assessments of PM involve numerous mechanisms (e.g. inflammatory processes and oxidative stress) requiring significant amounts of PM to obtain accurate results. Optimising air sampling techniques are therefore important for the appropriate collection medium/filter which have innate physical properties and the potential to interact with samples. An evaluation of methods and instrumentation used for airborne virus collection concludes that samplers operating cyclone sampling techniques (using centrifugal forces) are effective in collecting airborne viruses. We highlight that predictive modelling can help to identify pollution hotspots in an urban environment for the efficient collection of PM mass. This review provides guidance to prepare and plan efficient sampling campaigns to collect sufficient PM mass for various purposes in a reasonable timeframe.

Cost-Sensitive Variable Selection for Multi-Class Imbalanced Datasets Using Bayesian Networks

Multi-class classification in imbalanced datasets is a challenging problem. In these cases, common validation metrics (such as accuracy or recall) are often not suitable. In many of these problems, often real-world problems related to health, some classification errors may be tolerated, whereas others are to be avoided completely. Therefore, a cost-sensitive variable selection procedure for building a Bayesian network classifier is proposed. In it, a flexible validation metric (cost/loss function) encoding the impact of the different classification errors is employed. Thus, the model is learned to optimize the a priori specified cost function. The proposed approach was applied to forecasting an air quality index using current levels of air pollutants and climatic variables from a highly imbalanced dataset. For this problem, the method yielded better results than other standard validation metrics in the less frequent class states. The possibility of fine-tuning the objective validation function can improve the prediction quality in imbalanced data or when asymmetric misclassification costs have to be considered.

Indoor air quality prediction using optimizers: A comparative study

Indoor air pollution (IAP) has become a serious concern for developing countries around the world. As human beings spend most of their time indoors, pollution exposure causes a significant impact on their health and well-being. Long term exposure to particulate matter (PM) leads to the risk of chronic health issues such as respiratory disease, lung cancer, cardiovascular disease. In India, around 200 million people use fuel for cooking and heating needs; out of which 0.4% use biogas; 0.1% electricity; 1.5% lignite, coal or charcoal; 2.9% kerosene; 8.9% cow dung cake; 28.6% liquified petroleum gas and 49% use firewood. Almost 70% of the Indian population lives in rural areas, and 80% of those households rely on biomass fuels for routine needs. With 1.3 million deaths per year, poor air quality is the second largest killer in India. Forecasting of indoor air quality (IAQ) can guide building occupants to take prompt actions for ventilation and management on useful time. This paper proposes prediction of IAQ using Keras optimizers and compares their prediction performance. The model is trained using real-time data collected from a cafeteria in the Chandigarh city using IoT sensor network. The main contribution of this paper is to provide a comparative study on the implementation of seven Keras Optimizers for IAQ prediction. The results show that SGD optimizer outperforms other optimizers to ensure adequate and reliable predictions with mean square error = 0.19, mean absolute error = 0.34, root mean square error = 0.43, R2 score = 0.999555, mean absolute percentage error = 1.21665%, and accuracy = 98.87%.

Mining and Analysis of Air Quality Data to Aid Climate Change

The data science and AI community has gathered around the world to support tackling the climate change problem in different domains. This research aims to work on the air quality through emissions and pollutant concentration data along with vegetation information. Authorities especially in urban cities like London have been very vigilant in monitoring these different aspects of air quality and reliable sources of big data are available in this domain. This study aims to mine and collate this information spread all over the place in different formats into usable knowledge base on which further data analysis and powerful Machine Learning approaches can be built to extract strong evidences useful in building better policies around climate change.

A picture tells a thousand…exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiology

BACKGROUND

Artificial intelligence (AI) is revolutionizing our world, with applications ranging from medicine to engineering.

OBJECTIVES

Here we discuss the promise, challenges, and probable data sources needed to apply AI in the fields of exposure science and environmental health. In particular, we focus on the use of deep convolutional neural networks to estimate environmental exposures using images and other complementary data sources such as cell phone mobility and social media information.

DISCUSSION

Characterizing the health impacts of multiple spatially-correlated exposures remains a challenge in environmental epidemiology. A shift toward integrated measures that simultaneously capture multiple aspects of the urban built environment could improve efficiency and provide important insights into how our collective environments influence population health. The widespread adoption of AI in exposure science is on the frontier. This will likely result in new ways of understanding environmental impacts on health and may allow for analyses to be efficiently scaled for broad coverage. Image-based convolutional neural networks may also offer a cost-effective means of estimating local environmental exposures in low and middle-income countries where monitoring and surveillance infrastructure is limited. However, suitable databases must first be assembled to train and evaluate these models and these novel approaches should be complemented with traditional exposure metrics.

CONCLUSIONS

The promise of deep learning in environmental health is great and will complement existing measurements for data-rich settings and could enhance the resolution and accuracy of estimates in data poor scenarios. Interdisciplinary partnerships will be needed to fully realize this potential.