Air Pollution Detection Research Articles

AHP Algorithm for Indoor Air Pollution Detection and Evaluation System Design

AHP Algorithm for Indoor Air Pollution Detection and Evaluation System Design

An enhanced loss function in deep learning model to predict PM2.5 in India

Fine particulate matter (PM2.5) is one of the major air pollutants and is an important parameter for measuring air quality levels. High concentrations of PM2.5 show its impact on human health, the environment, and climate change. An accurate prediction of fine particulate matter (PM2.5) is significant to air pollution detection, environmental management, human health, and social development. The primary approach is to boost the forecast performance by reducing the error in the deep learning model. So, there is a need to propose an enhanced loss function (ELF) to decrease the error and improve the accurate prediction of daily PM2.5 concentrations. This paper proposes the ELF in CTLSTM (Chi-Square test Long Short Term Memory) to improve the PM2.5 forecast. The ELF in the CTLSTM model gives more accurate results than the standard forecast models and other state-of-the-art deep learning techniques. The proposed ELFCTLSTM reduces the prediction error of by a maximum of 10 to 25 percent than the state-of-the-art deep learning models.

Air Pollution Detection and Control System Using ML Techniques

In present times, air pollution is increasing day by day, depriving the health of many people due to the various toxic components in air. So, it is necessary to monitor and detect the levels of pollution in various areas and try to control it by taking precautionary actions. Air pollution detection and control system is all about detecting the level of pollution in a particular area based on the amount of polluting components and proposing the measures to control the pollution. Analysis is made on the regions of Visakhapatnam city in Andhra Pradesh, India and grouped based on their pollution and displayed along with each component level, reasons for the pollution depending on each component and measures that can be followed. Apart from this, we also display list of top 10 regions with the highest values for each component which can be used to identify the harmful regions based on the toxic components.

Detection of Air Pollution in Urban Areas Using Monitoring Images

Air quality monitoring in polluted environments is of great significance to human health. Traditional methods use various pieces of meteorological equipment, which have limited applications in complex terrains and high costs. In this paper, a novel idea is put forward to solve the problem of air pollution monitoring in urban areas. We investigate whether air quality can be assessed visually by examining the haziness of photos from a far distance. Specifically, the correlation between the air quality indexes, such as the AQI, PM2.5, and PM10, of real outdoor scenarios and the haziness level evaluation scores of the monitoring images is calculated. The results show that the objective indicators can indeed reflect the level of air pollution, and the degree of correlation is invariant to the image size. To apply this new observation to a practical system, a novel method called fastDBCP (fast dark and bright channel prior) is developed. Based on a down-sampling strategy, a ratio is calculated between the dark and bright channel prior information in scaled images and adopted as the visual index of air pollution. Our experimental results show that the proposed metric not only demonstrates advantages in terms of its correlation degree and computational speed, but also shows a high level of classification accuracy compared to that of competing metrics.

A short review on Smart Air Pollution and Temperature Detection System

A short review on Smart Air Pollution and Temperature Detection System

An Internet of Things Based Air Pollution Detection Device for Mitigating Climate Changes

An Internet of Things Based Air Pollution Detection Device for Mitigating Climate Changes

Characterization of water-insoluble particulate matters in sequential rain samples collected by a novel automatic sampler in Antalya, Turkey

Three rainfall events were sampled sequentially in Antalya, Turkey on November 19 and December 04,13, 2020 by using an automatic rain sample collection device that was developed and validated by our group. Water-insoluble particulate matters (PMs) were characterized by using a scanning electron microscopy-energy dispersive X-ray fluorescence (SEM-EDS) and the particle size distributions in the rain sequences were determined by using particle size analyzer directly, without any sample pretreatment In order to determine the transport regions of the sampled rain events, back trajectory calculations were made using the HYSPLIT modeling program. In studies on the detection of air pollution in aerosol samples, the particles (PMs) are collected on the filter and examined. This method can cause many particles to accumulate on the filter and make it difficult to characterize them by using semi-quantitative methods. The use of particle size analyzer and SEM device to characterize and detect particles in rainwater provides more successful results. This method can provide direct evidence for single particle analyses, and the determination of compositions and morphologies of atmospheric PMs. In this study, the water-soluble ionic compositions were determined by using ion chromatography. Inductively Coupled Plasma-Mass Spectrometer (ICP-MS) was used for water soluble and insoluble element concentrations. The pHs of all sequences changed from 6.88 to 7.84 The measured particle size distribution ranged from 0.073 to 1503.2 μm, 0.266–680.2 μm, and 0.406–530.7 μm, respectively for the 1st, 2nd, and 3rd series samples. Arithmetic mean and the standard deviation of the neutralization factors corresponding to calcium, potassium, ammonium, magnesium, and sodium ions were determined as 4.88 ± 7.03, 0.07 ± 0.11, 0.55 ± 0.29, 0.14 ± 0.09, 0.01 ± 0.04, respectively. The main aim of the study was to demonstrate the applicability of chemical compositions of water-insoluble PMs (from EDS) in source identification and the advantage of sequential sampling.

Effect of Measurement System Configuration and Operating Conditions on 2D Material-Based Gas Sensor Sensitivity.

Gas sensors applied in real-time detection of toxic gas leakage, air pollution, and respiration patterns require a reliable test platform to evaluate their characteristics, such as sensitivity and detection limits. However, securing reliable characteristics of a gas sensor is difficult, owing to the structural difference between the gas sensor measurement platform and the difference in measurement methods. This study investigates the effect of measurement conditions and system configurations on the sensitivity of two-dimensional (2D) material-based gas sensors. Herein, we developed a testbed to evaluate the response characteristics of MoS2-based gas sensors under a NO2 gas flow, which allows variations in their system configurations. Additionally, we demonstrated that the distance between the gas inlet and the sensor and gas inlet orientation influences the sensor performance. As the distance to the 2D gas sensor surface decreased from 4 to 2 mm, the sensitivity of the sensor improved to 9.20%. Furthermore, when the gas inlet orientation was perpendicular to the gas sensor surface, the sensitivity of the sensor was the maximum (4.29%). To attain the optimum operating conditions of the MoS2-based gas sensor, the effects of measurement conditions, such as gas concentration and temperature, on the sensitivity of the gas sensor were investigated.

Machine Learning-Based IOT Air Quality and Pollution Detection

In India, gas leakage from the different factories harmful to human surveying in the last fifty years is very low. However, there is a lack of prior detection of the chemical gases detection system in the situation raised. So, In this regard, there is a gap identification of chemical gases intensity detection needed. In this work, the main objective is to identify chemical gases intensity and maintain the stream data in the database from different locations. To fill this gap, that is identifying the high-intensity chemical gases from the chemical gas disaster areas. The first step needs to identify the different chemical gases and natural gas compositions. In this regard in this work for design internet-based gases in the air system. So, the sensors MQ2(Ethanol i-Butane Methane Alcohol Gas Sensor Sensor), MQ3(Sensitivity Alcohol Detector), MQ4 (Methane and Natural Gas (CNG)), MQ-5 ( LPG GAS SENSOR), MQ-7 (CO Gas Sensor Module Test Carbon Monoxide Detector), MQ-8 (hydrogen Gas Sensor), MQ-9 (carbon monoxide), MQ-135 Sensor(Air Quality Sensor Hazardous Gas Detector) and DHT11 Digital Temperature Humidity Sensors. These sensors are interfacing with the micro-control STM 32 board. It is also called one Pollution identification terminal by using it to pull the sensor stream data from location to centralized data. This stream data transportation is a service to pull the data. For this Data pulling, design an algorithm store into a cloud database. In this research work, design the electronic terminal with a wifi circuit using IoT technologies.Moreover, getting these attributes as data. Data need to apply the preprocessing techniques and extracted feature techniques also. This paper discusses mainly designing the terminal for pollution attributes , cleaning the data, and applying the Machine Learning based Feature extraction techniques.

Pyridinic Dominance N-Doped Graphene: A Potential Material for SO2 Gas Detection.

The sensors based on graphene have shown great promise in the detection of toxic air pollutants that are detrimental to nature and create risks to human health. Many recent experimental and computational efforts have been dedicated to sensor concepts incorporating pure graphene, graphene oxide, and doped graphene. Herein, a combination of spin-polarized density functional theory (DFT) with van der Waals correction and ab initio molecular dynamics (AIMD) approaches are utilized to assess the gas sensing potential of pyridinic dominance N-doped graphene (PNG) toward SO2 detection. The potential of PNG systems as SO2 sensing can be explored through an in-depth analysis of adsorption energies, electronic parameters, charge transfer, selectivity, and thermal stability. It is further demonstrated that external strains and the modulation of external electric fields are two effective ways to modify the adsorption strength. In light of these findings, our studies suggest that PNG monolayers have the potential to be an essential substrate for the detection of SO2.

Determining factors affecting the perceived usability of air pollution detection mobile application “AirVisual” in Thailand: A structural equation model forest classifier approach

Air pollution has been evident worldwide. It presented numerous pieces of evidence that affect health-related adverse effects causing diseases and even death and the development of technology has helped monitor the exposure of people to air pollution. This research analyzed factors affecting the perceived usability of air pollution detection on the ‘AirVisual’ mobile application based on the integrated model of Protection Motivation Theory (PMT) and Unified Theory of Acceptance and Use of Technology (UTAUT2). A total of 416 participants voluntarily answered a self-administered survey consisting of adapted constructs covering factors such as Performance expectancy (PE), Effort expectancy (EE), Social influence (SI), Facilitating conditions (FC), Habit (HB), Perceived risk (PR), Perceived trust (PT), Intention to use (IU), and Perceived usability (PU). Structural Equation Modeling and Random Forest Classifier were utilized to determine factors affecting perceived usability of the ‘AirVisual’ mobile application. The results showed that PE, EE, SI, and FC were key factors leading to very high PU among users. Moreover, IU was seen to be the most significant factor affecting PU, followed by PT, PR, and HB. This study is one of the first studies that considered the evaluation of usability among health-related mobile applications covering air pollution. The results and the framework utilized in this model may be applied to evaluate other factors and applications related to health among people. Lastly, this study can also be extended to evaluate other mobile applications worldwide.

Does air quality improvement promote enterprise productivity increase? Based on the spatial spillover effect of 242 cities in China.

Air pollution not only harms people's health, but also impedes urban economic development. This study aims to analyze how air quality improvement affects enterprise productivity. And then from regional and time heterogeneities' aspects to investigate if the air quality improvement increase enterprise productivity. The data were obtained from China Industrial Enterprise Database and China Patent Database,and this study used Spatial Durbin Model to analyze how air quality improvement affects enterprise productivity. The results show that: (1) air quality improvement and its spatial spillover effect can significantly increase enterprise productivity in adjacent areas. (2) After 2010, the government implemented more stringent measures to prevent and control air pollution, which made the air quality improvement promote enterprise productivity increase more obviously. The air quality improvement in eastern and central regions was less obvious than in western regions. (3) Air quality improvement can increase enterprise productivity by improving enterprise innovation quality, ensuring the health of urban residents, and increasing the stock of urban human capital. Air quality improvement and its spatial spillover effect can significantly increase enterprise productivity in adjacent areas. So this study puts forward some policy enlightenment, such as establishing an air pollution detection system, using an intelligent network supervision platform, and implementing a coordinated defense and governance system.

A highly efficient room-temperature formaldehyde gas sensor based on a Ni-doped ZnO hierarchical porous structure decorated with NiS illuminated by UV light

Developing room-temperature formaldehyde gas sensors with superior response-ability is crucial for many applications including the detection of indoor air pollutants. Herein, we synthesized a series of Ni-doped ZnO (Ni-ZnO) hierarchical porous structures decorated with NiS (NiS/Ni-ZnO) composite materials by the simple hydrothermal method, and the room-temperature (25 ± 1 ℃) UV light-activated photoelectronic formaldehyde sensors based on the ZnO, Ni-ZnO and NiS/Ni-ZnO composites were presented and compared. The response value of 0.2% NiS/0.4% Ni-ZnO material reached 330% toward 10 ppm formaldehyde gas, which was nearly 2.5 times higher than that of pure ZnO, and the faster response/recovery time (39.4 s/40.7 s) was obtained using UV light at room temperature. XPS, SPV, TPV spectrum analysis, and density functional theory (DFT) calculation showed that 0.2% NiS/0.4% Ni-ZnO sensor's excellent sensing performance was due to the synergistic effect of Ni doping and NiS modification which improved the separation efficiency and accelerated the migration of charge carriers. Here, the relationship between the response time of photoelectric gas sensors and the behavior of photogenerated carriers is firstly discussed in detail, which provides new insight into the development of room-temperature photoelectric gas sensors with superior response-ability. • NiS/Ni-ZnO hierarchical porous structure has been fabricated using hydrothermal method. • NiS/Ni-ZnO sensor exhibits fast response and high responsivity to formaldehyde at room temperature. • Excellent gas sensing performance of NiS/Ni-ZnO sensor is explained from the dynamic behavior of photogenerated carriers. • The relationship between the response time of gas sensor and the behavior of carriers is firstly discussed in detail.

Selective turn-on fluorescence detection of formaldehyde in the gas phase

Reliable detection of formaldehyde in gas phase still remains a challenge regarding either sensitivity or selectivity or both. In this study we report on a simple, unique sensor composite, which enables efficient detection of gaseous formaldehyde with both low limit of detection (LOD) and extremely high selectivity. The primary components of the sensor composite include a hydroxylamine sulfuric acid salt ((NH2OH)2·H2SO4) and a fluorescence turn-on probe, which both are coated within the porous matrix of a cellulose plate. The fluorescence probe is based on a perylene diimide (PDI) molecule modified with an aniline group, which is non-fluorescent in its pristine state due to the photoinduced intramolecular electron transfer. Upon interaction with formaldehyde, the hydroxylamine salt will be converted to the corresponding Schiff base through aldimine condensation, releasing the sulfuric acid. The acid released will protonate the aniline group on PDI, resulting in a quick fluorescence turn-on. By measuring the fluorescence increase we can detect formaldehyde both quantitatively and specifically. Under the optimized condition, the sensor demonstrated a LOD of 3.7 ppb, which is much lower than the air quality threshold set by WHO. The sensor was also proven highly selective towards formaldehyde, with negligible response towards other common chemicals. The work reported will not only provide a new sensor for formaldehyde, but moreover open a unique design pathway for sensor composite that combines reactive components with various fluorescence indicators so as to enable highly efficient detection of many other air pollutants and toxic chemicals.

Synergistic Effect of Atmospheric Boundary Layer and Regional Transport on Aggravating Air Pollution in the Twain-Hu Basin: A Case Study

The impact of structural variations in the atmospheric boundary layer (ABL) during the regional transport of air pollutants on its local pollution changes deserves attention. Based on multi-source ABL detection and numerical simulation of air pollutants over the Twain-Hu Basin (THB) during 4–6 January 2019, the mechanism of the rapid growth of atmospheric pollutant concentrations in Xianning by the synergistic effect of regional transport and ABL evolution is explored, and the main conclusions are obtained as follows. The vertically stratified atmosphere is noticeable at nighttime, and the heavy humidity of near-surface fog within the stable boundary layer (SBL) promoted the generation and cumulative growth of secondary PM2.5 components during the pollution formation stage. The horizontal transport characteristics of atmospheric pollutant concentration peak were observed in the residual layer (RL) of 500–600 m. At the pollution maintenance stage, the convective boundary layer (CBL) developed during the daytime, and northerly wind transported high-concentration pollutants from the north to the THB. Under the combined action of horizontal transport and turbulent mixing, the high-concentration atmospheric pollutants in the mixing layer (ML) from the ground to the 500 m height were mixed uniformly and maintained accumulation growth. The next day, the strong vertical turbulent mixing caused the downward transport of high-concentration pollutants in the RL during nighttime due to the development of the CBL again, resulting in a doubling of near-surface pollutant concentration in a short time. With the development of ABL turbulence, local pollution dissipated rapidly without the continuous input of pollutants from external regions. This study emphasizes the importance of multi-scale processes impact on pollution variation, that is, regional transport of atmospheric pollutants at the CBL development stage for the rapid growth of PM2.5 concentration in the ML.

IoT-based air pollution detection, monitoring and controlling system

Air pollution is one of the most concerning and alarming problems in the modern world, and it is increasing day by day due to a large number of industries and urbanization. When pollutants are released into the air from several sources, such as the combustion of fossil fuels, industrial emissions, agricultural sources, and so on, it is referred to as air pollution. It is acknowledged as a significant risk factor for noncommunicable diseases (NCDs) that include lung cancer, stroke, heart disease, and acute and chronic respiratory illnesses including asthma. An estimated seven million individuals die globally every year due to air pollution as the world health organization reported on their website. In this paper, we have proposed an Internet of Things (IoT) based air pollution detection, monitoring, and controlling system. The system detects the various air pollutants by combining the different sensors, helps users to monitor the received pollutants levels over LCD, user’s mobile app, and cloud server, and controls the air quality up to a certain level when pollutants levels cross the threshold limits. NodeMCU plays an important role to exchange the data or information between the proposed system devices. We have designed a prototype for demonstrating the proposed system performance. The prototype testing and result show’s that the proposed system works significantly well in terms of detection, monitoring, and controlling air pollution, especially proposed controllers exhibit impressive performance for maintaining the air quality.

Air Pollution Detection and Sports Club Environmental Responsibility Based on the RBF Neural Network.

With the rapid development of soft computing technology, various models and comprehensive analysis methods are emerging one after another, and new theories and research results continue to emerge, showing great strength and development potential in actual theoretical research and engineering applications. This paper analyzes the air pollution detection and environmental responsibility of sports clubs based on RBF neural networks, constructs the corresponding neural network algorithm, and simulates and analyzes the data. In the process of simulation design, we adjust the weight and threshold of the network according to the error performance of the network to realize the functions required by the system. Different models were used to predict the concentration of air pollutants in typical cities. At the same time, a meta-analysis method was used to conduct a preliminary discussion on the impact of air pollutants on the health of the Chinese population, and some research results were obtained. In the past years, Chinese sports clubs have also built a solid social environmental protection system around the related environmental protection responsibilities of sports clubs. The research on green environmental monitoring has improved people's awareness of environmental responsibility and provided technical support for the green development of sports clubs.

Optimizing Urban Air Pollution Detection Systems.

Air pollution has become a serious problem in all megacities. It is necessary to continuously monitor the state of the atmosphere, but pollution data received using fixed stations are not sufficient for an accurate assessment of the aerosol pollution level of the air. Mobility in measuring devices can significantly increase the spatiotemporal resolution of the received data. Unfortunately, the quality of readings from mobile, low-cost sensors is significantly inferior to stationary sensors. This makes it necessary to evaluate the various characteristics of monitoring systems depending on the properties of the mobile sensors used. This paper presents an approach in which the time of pollution detection is considered a random variable. To the best of our knowledge, we are the first to deduce the cumulative distribution function of the pollution detection time depending on the features of the monitoring system. The obtained distribution function makes it possible to optimize some characteristics of air pollution detection systems in a smart city.

Ensemble Machine Learning Model for Accurate Air Pollution Detection Using Commercial Gas Sensors.

This paper presents the results on developing an ensemble machine learning model to combine commercial gas sensors for accurate concentration detection. Commercial gas sensors have the low-cost advantage and become key components of IoT devices in atmospheric condition monitoring. However, their native coarse resolution and poor selectivity limit their performance. Thus, we adopted recurrent neural network (RNN) models to extract the time-series concentration data characteristics and improve the detection accuracy. Firstly, four types of RNN models, LSTM and GRU, Bi-LSTM, and Bi-GRU, were optimized to define the best-performance single weak models for CO, O3, and NO2 gases, respectively. Next, ensemble models which integrate multiple single weak models with a dynamic model were defined and trained. The testing results show that the ensemble models perform better than the single weak models. Further, a retraining procedure was proposed to make the ensemble model more flexible to adapt to environmental conditions. The significantly improved determination coefficients show that the retraining helps the ensemble models maintain long-term stable sensing performance in an atmospheric environment. The result can serve as an essential reference for the applications of IoT devices with commercial gas sensors in environment condition monitoring.

An Internet of Things-based Air Pollution Detection System

The Internet of Things (IoT)-based air pollution detection system using gas sensors is a system that is developed to detect air pollution using IoT technology. Air pollution is a condition where there is a mixture of harmful chemicals in the air we inhale that can cause damage to humans and the surroundings. The issue of polluted air nowadays has made people become more aware of the air quality they inhale. The system has been developed using MQ2 and MQ9 gas sensors to detect the air pollution level. The system involved two features in helping users read the air pollution level and notify the reading through a mobile app. Users also get notified of the reading through a pop-up notification. The mobile application development uses Android Studio, while Google Firebase is used as the database for the system. This IoT-based air pollution detection system is successfully developed and notified users about the air pollution reading to be more aware of their surroundings.