Deep Learning and IoT based Air Quality Monitoring and Prediction System

Air pollution has emerged as a major concern of the current century. In recent times, fellow researchers have conducted numerous researches in the area of air quality monitoring. Still, air quality monitoring remains an open research area due to various challenges such as sophisticated topology design, privacy and security, power backup, large memory requirements and deployment of such systems at resource-constrained sites. The proposed research work is an attempt to address the issues of communication topology design, assessment of the Quality of Service (QoS) levels against accuracy, sensing throughput and power consumption optimization. In the undertaken work, the proposed IoT based Air Quality Monitoring system has been deployed at indoor and outdoor sites to measure air quality parameters such as PM10, PM2.5, carbon monoxide, temperature and humidity. The proposed system is also tested at variety of quality of service levels at the indoor and outdoor sites. The conducted experiments have also recorded accuracy in terms of reliable delivery of the messages under employed protocol.

Air pollution is one of the most critical environmental challenges affecting public health and economic sustainability. Continuous monitoring and accurate air quality prediction are essential for effective environmental management. This paper presents SmartAQI, an intelligent air quality monitoring and prediction system that integrates environmental data analytics with machine learning techniques. The proposed system utilizes historical air pollution datasets, India district-level geographic information, and real-time meteorological data obtained through the OpenWeather API to analyze air quality conditions across different regions of India. Major pollutants, including PM2.5, PM10, NO₂, SO₂, CO, and O₃, are processed to compute the Air Quality Index (AQI) according to the guidelines established by the Central Pollution Control Board. To improve prediction capability, multiple machine learning models such as Linear Regression, Random Forest, and Time Series forecasting are implemented and evaluated. The system further provides an interactive visualization dashboard that displays live AQI values, pollutant concentration levels, predicted AQI values, and geographic air quality distribution through charts and maps. Results demonstrate that integrating environmental data with machine learning models enables reliable AQI prediction and effective spatial analysis of pollution trends. The SmartAQI framework offers a practical solution for environmental monitoring and can support researchers, policymakers, and the public in understanding and managing air quality conditions more effectively, which is reliable

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.

Recently the intensity and magnitude of air pollutant concentration has grown up rapidly in the troposphere. The air pollution is primarily associated with automobiles and industrial sources Hyderabad, capital of Telangana, is a center of southern part of India for both industrial and commercial activity. It is one of the most populous urban areas with approximately 6.8 million inhabitants and over 73,000 small, medium and major industrial establishments sharing the greater city.Air pollution in India is monitored by the Central Pollution Control Board (CPCB) together with the State Pollution Control Boards (SPCBs) and the National Environmental Engineering Research Institute (NEERI) in Nagpur. The National Air Quality Monitoring Programme (NAMP) was started in 1984 with 7 sensor stations, 248 towns and cities have the air quality network of 591 Air Quality Monitoring Stations upto 2015, it is reported that in India 2022 added 180 manual air quality monitoring stations, increasing their number to 883 to achieve the target of 1,500 by 2024. For our study due to practical difficulties to collect, analysis the air quality, pollutants data has been collected from CPCB.The dataset contains City, Date, PM2.5, PM10, NO, NO2, NOx, NH3, CO, SO2, O3, Benzene, Toulene, Xylene, Air Quality Index (AQI). Hyderabad was divided into 6 zones, air quality monitoring sensors is located at 14 places in and around six zones. For our study we selected 2 stations Newmalakpet and Sanathnagar based on heavy traffic area to analyse the maximum concentration of pollutants such as PM2.5, PM10, NO2, NO3, SO2, CO, for the period of three months ( Dec 2022,Jan, Feb 2023).It was observed at site 1 to site 52PM2.5,range 120 to 249 µg/m3 is very poor as per AQI, PM10 range 101.2 to 171 µg/m3 is moderately polluted as per AQI, NO2 range 7.46 to 32.9 µg/m3 is good as per AQI, NH3 range3.06 to 5.44 is good as per AQI, SO2 is 12.97 to 8.53 µg/m3 is good ,CO 61.83 to 71.9 is severe as per AQI, continuous air quality monitoring is necessary to protect environment and human health

Whether by habit or necessity, people tend to spend most of their time indoors. Built-up Carbon dioxide (CO2) can lead to a series of negative health effects such as nausea, headache, fatigue, and so on. Thus, indoor air quality must be monitored for a variety of health reasons. Various air quality monitoring systems are available on the market. However, since they are expensive and difficult to obtain, they are not commonly employed by the general population. With the advent of the Internet of Things (IoT), the Indoor Air Quality (IAQ) monitoring system has been simplified, and a number of studies have been conducted in order to monitor the IAQ using IoT. In this paper, we propose an improved IoT-based, low-cost IAQ monitoring system using Artificial Intelligence (AI) to provide recommendations. In our proposed system, the IoT sensors transmit data via Message Queuing Telemetry Transport (MQTT) protocol which can be visualised in real time on a user-friendly dashboard. Furthermore, the AI technique referred to as Long Short-Term Memory (LSTM) is applied to the collected CO2 data for the purpose of predicting future CO2 concentrations. Based on the predicted CO2 concentration, our system can compute CO2 steady state in advance with an error margin of 5.5%.

In recent years, urban air quality monitoring is increasingly important. To monitor air quality in urban areas, wireless sensor networks (WSNs) might be a great tool, because they can automatically collect air-quality data. WSNs are able to provide data with spatiotemporal continuity, so researchers can analyze the data in detail. This paper proposes a self-sustainable air quality monitoring system based on the WSN technology to collect air quality parameters in an urban area. The proposed system uses carbon monoxide (CO) and particulate matter (PM) sensors to monitor CO and PM, and the readings from the two sensors are viewed as air quality indices. The proposed system combines a solar cell and a lead-acid battery as its power supply devices, so the system has the long-tern monitoring capability.

Arduino-Based Real Time Air Quality and Pollution Monitoring System

In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo's derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

Now-a-days the amount air pollution in atmosphere is rapidly increasing due to the vehicles, industries and urbanization. due to increase of air pollution human life may effect. IOT based air quality monitoring system using MQ135 and arduino is used to Display the air quality over an internet server the use of net and it will alarm when the air satisfactory goes underneath a certain degree, whilst there is enough amount of the dangerous gases that are found in atmosphere are s02, co2, smoke, benze steam, alcohol and nh3. the air nice is proven in ppm on the liquid crystal display and at the website so the air satisfactory may be monitored quickly. Here we are going to use mq135 gas sensor to monitor the air quality it will measure the harmful gases that are present in air.in which air quality can be measured from anywhere using mobile or computer.

In recent days the emission of air pollutants in to the environment has grown very quickly. The air pollution is caused due to the smoke emitted by vehicles, industries and other sources. Hyderabad is the largest and capital city of Telangana. It occupies 650km2 on the Deccan Plateau along the banks of the Musiriver, in the northern part of south India. According to the 2011 Census of India, Hyderabad is the fourth-most populous city in India with a population of 6.9 million residents within the city limits, and has a population of 9.7 million residents in the metropolitan region, making it the sixth-most populous metropolitan area in India. With an output of US$74 billion, Hyderabad has the fifth-largest urban economy in India. In India air pollution is monitored by Central Pollution Control Board(CPCB) along with State Pollution Control Boards (SPCBs) and the National Environmental Engineering Research Institute (NEERI) in Nagpur. The National Air Quality Monitoring Programme (NAMP) was started in 1984 with seven sensor stations 248 towns and cities have the air quality network of 591 air quality monitoring stations upto 2015, it is reported that in India 2022 added 180 manual air quality monitoring stations, increasing the number to 883 to achieve the goal of 1500 by 2024. For our study because of some practical difficulties and analysis of the air quality. Air Pollutants has been collected from the CPCB. The dataset contains City, Date, Time, PM2.5,PM10, NO2, SO2, CO, O3, Benzene, Toulene, Xylene, Air Quality Index (AQI). Hyderabad was divided into six zones, air quality monitoring sensors are located at 14 places in and around six zones. For our study we selected one sensor that is Secunderabad, which covers the surrounding areas including Jawahar Nagar treatment plant. To analysis the maximum concentration of air pollutants such as PM2.5,PM10,SO2,NO2,CO,O3over the time period of three months (Jan to Mar 2023).Most physio-chemical properties, including as pH, EC, Alkalinity, Chlorides, Cu, Mn, Pb, and Cr, exceeded their acceptable limits at more than three sample sites, according to this study. The water sources were determined to be unsafe for drinking, agricultural, and irrigation uses due to elevated toxicity levels.It was observed that PM2.5,ranges 218 - 403µg/m3 is very poor causes respiratory illness, PM10 range 112 - 360µg/m3 is moderately polluted causes breathing discomfort ( Asthma, lungs), NO2 range 10 – 12ppm is satisfied causes minor breathing discomfort to sensitive people ,O3 range 20 – 35ppm is good causes minor effect, SO2 is 12 – 22ppm is satisfied causes minor breathing discomfort to sensitive people ,CO 109 – 119ppm is severe effects on healthy people and serious impact for those with existing diseases, so continuous air quality monitoring is necessary to protect environment and human health

Outdoor air pollution is a serious problem in many developing countries today. This study focuses on monitoring the dynamic changes of air quality effectively in large cities by analyzing the spatiotemporal trends in geo-targeted social media messages with comprehensive big data filtering procedures. We introduce a new social media analytic framework to (1) investigate the relationship between air pollution topics posted in Sina Weibo (Chinese Twitter) and the daily Air Quality Index (AQI) published by China’s Ministry of Environmental Protection; and (2) monitor the dynamics of air quality index by using social media messages. Correlation analysis was used to compare the connections between discussion trends in social media messages and the temporal changes in the AQI during 2012. We categorized relevant messages into three types, retweets, mobile app messages, and original individual messages finding that original individual messages had the highest correlation to the Air Quality Index. Based on this correlation analysis, individual messages were used to monitor the AQI in 2013. Our study indicates that the filtered social media messages are strongly correlated to the AQI and can be used to monitor the air quality dynamics to some extent.

Background: Emerging evidence suggests that air pollution is a significant but under recognized contributor to cardiovascular disease (CVD) mortality, even in middle age adults. This study evaluates the association between long term statewise air quality, as measured by median Air Quality Index (AQI) and cardiovascular mortality rates among adults aged 35–44 years across the United States over a 25-year period. Methods: We linked annual statewise median AQI data from EPA AQS (2000–2024) with CDC WONDER mortality records for non-infectious CVD in the 35–44 age group. States were ranked by mean AQI to define “Highest 10” and “Lowest 10” AQI cohorts. Mean annual cardiovascular crude death rates were compared between these groups using t-tests, and trends were visualized year-by-year. Correlation and linear regression analyses assessed the association between AQI and mortality across all state years as well. Results: States with the highest long-term AQI (poor air quality) had significantly higher mean cardiovascular mortality rates (mean 46.99 per 100,000) than states with the lowest AQI (good air quality) (mean 30.35 per 100,000; p = 0.01). Yearwise analysis showed a persistent gap in mortality rates with the highest AQI states consistently exhibiting greater CVD mortality across the study period. Linear regression confirmed a significant positive association between AQI and mortality (slope = 0.62, p < 0.001), although AQI alone explained only a modest portion of the variation (R 2 = 0.095). Conclusions: Higher long term air pollution exposure, as measured by AQI, is associated with increased cardiovascular mortality among U.S. adults aged 35–44 years. This relationship is robust at the extremes of air quality and persists over time. This highlights the need for public health policies to improve air quality as a means to reduce early onset CVD mortality. Further studies should explore mechanisms and policy interventions to mitigate this risk.

One of the most burning environmental issues of the contemporary urban and industrial areas has turned out to be air pollution which poses serious threats to human health, ecological balance, and overall sustainability. The traditional monitoring stations are very precise, but expensive, sparsely distributed geographically and cannot give high spatial temporal information. To overcome these constraints, the presented study suggests to simulate and design an Internet of Things (IoT)-based air quality monitoring system with the use of low-cost and smart sensors and use MATLAB/Simulink as the main development environment. The suggested framework will incorporate particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), carbon monoxide (CO), ozone (O3), and volatile organic compound (VOC) sensors. The nodes have a microcontroller unit (ESP32 or Raspberry Pi), wireless communication system (Wi-Fi, LoRa, or NB-IoT), and an energy management system powered by a solar to maintain sustainability. A variety of data pre-processing methods (calibration, temperature and humidity compensation, noise elimination with digital filters, and Kalman filtering) are performed at the edge level to improve measurement accuracy prior to transmission, followed by the simulation of the end-to-end system (data acquisition and transmission, cloud integration and visualization) with the help of MATLAB/Simulink. Moreover, more complex algorithms like sensor fusion and machine learning models (Artificial Neural Networks (ANNs) and Long Short-Term Memory (LSTM) networks) are used to enhance air quality index (AQI) prediction and allow making predictions in the short term on pollution. The system is evaluated by use of performance metrics like: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), correlation coefficient (R2), energy consumption and network latency to determine the anticipated outcome of this research; a scalable, cost-effective, and energy-efficient IoT network that will be able to offer reliable real-time air quality monitoring and forecasting. The solution is a part of the smart city plans, aids policy-making regarding the environment, and contributes to the increase of the public awareness of their health through providing them with the accessible and high-quality air quality data.

The continuous deterioration of air and water quality worldwide poses severe threats to human health, biodiversity, and environmental sustainability. Rapid urbanization, industrial activities, and increasing vehicular emissions have escalated pollution levels, especially in developing nations like India. Traditional centralized environmental monitoring systems are often inefficient due to high data transmission delays, network congestion, and limited scalability, making them inadequate for real-time monitoring and response. The integration of Edge Computing and Internet of Things (IoT) technologies provides an innovative framework to overcome these challenges. Edge devices enable local data processing near IoT sensors, minimizing latency, reducing bandwidth usage, and ensuring timely and efficient monitoring outcomes. This paper reviews the integration of Edge Computing and IoT for real-time air and water quality monitoring systems, highlighting their architecture, implementation strategies, benefits, challenges, and future directions.We present recent real-time data from major Indian cities showing Delhi’s Air Quality Index (AQI) at 245, significantly exceeding safe levels, and Kolkata’s Water Quality Index (WQI) at 50, indicating poor water conditions. The paper includes system architecture diagrams, comparative data tables, and graphical representations to provide a comprehensive understanding of these systems. Key challenges such as energy efficiency, device interoperability, data security, and scalability are analyzed, and solutions like federated learning and blockchain integration are explored. Future research opportunities in predictive environmental analytics and citizen-centric monitoring are identified. This review aims to assist researchers, environmental policymakers, and smart city developers in designing resilient, scalable, and real-time environmental monitoring systems leveraging edge–IoT synergies.

With increasing global warming and sudden climate change, air quality monitoring is one of the important issues need to be addressed globally in today's ecosystems. This paper examines the issues and challenges of designing and implementing an integrated sensing system for air quality monitoring. The system is aiming to detect the level of six gases, Ozone, Particulate Matter, Carbon Monoxide, Nitrogen Oxides, Sulfur Dioxide, and Carbon Dioxide, as suggested by the US Environmental Protection Agency (EPA), on a real-time basis and provide overall quality alert timely. Experiments are conducted to validate and support the development of an integrated sensing system for real-time air quality monitoring.