Real-time Pollution Research Articles

Development of Multi-Item Air Quality Monitoring System Based on Real-Time Data

Many air pollutants are inhaled by human breathing, increasing the prevalence of respiratory disease and even mortality. With the recent COVID-19 issue, the number of air pollutants affecting humans is demands further investigation. However, there are not many adequate air measuring devices that can cover a variety of air pollutants. In this study, the developed air measurement system is able to measure sixteen air pollutants (PM10, PM2.5, PM4.0, PM1.0, CO2, CH4, temperature, humidity, VOCs, O2, H2S, NH3, SO2, CO, O3, NO2) in real time. The developed ‘multi-item air quality monitoring system’ can measure sixteen air pollutants in real time and transmit them to the server and the smartphone application at the same time. It was developed to reduce air pollutant damage to humans by emergency alerts using the smartphone application. The development system is composed of hardware development (measurement device) and software development (smartphone application, server). To verify the reliability of the developed equipment, a comparative test, temperature–humidity accuracy test, and operating temperature test were conducted. In the comparative test, difference ratios of ±5% for PM10, ±6% for PM2.5, ±4% for O3, ±5% for NO2, ±7% for CO, and ±7% for SO2 were found compared to the professional measuring devices. The temperature and humidity accuracy test result showed high reliability at ±1% and humidity ± 2%. The result of the operating temperature test showed that there was no problem in normal operation, However, further tests including the long-term comparative test and the closed chamber test will be carried out for all sensors. Additional work including a long-term test for more clear reliability of the device and closed chamber accuracy test for all 16-item sensors, data acquisition rate, and data transmit rate are in progress for commercializing the device.

Non-intrusive, real-time deep learning-based pollution analysis applied to open-channels

Non-intrusive, real-time deep learning-based pollution analysis applied to open-channels

Analytics in Extracting Intelligence from IoT-Based Sensors in Transportation, Healthcare and Natural Gas Detection

Networking of sensors and the development of sensor systems have become routine technological endeavors. The advent of Internet-of-Things (IoT) technologies has enabled an expanding matrix of applications for integration of specialized sensor systems. The focus on innovation is now on driving costs down, while increasing performance. Additive manufacturing techniques and topological improvements are key drivers of innovation for sensors.As sensors and sensor systems transform their capabilities from (strictly) data generation and gathering, the focus now shifts on how to increase the utility of the sensor and sensor system.SensorComm defines the utility of a sensor as its ability to provide intelligence. Intelligence comes from the collection of data. Through data-analytics, information can be extracted. The final step of interpreting the information is through the generation of intelligence. Off-the-shelf tools are available that include machine learning, artificial intelligence, and even toolboxes in platforms like MATLAB, all of which have changed the way we obtain information. The next step is obtaining the intelligence.SensorComm has applied this methodology of intelligence extraction in three areas: 1) transportation 2) healthcare and now 3) natural gas monitoring/detection.In transportation, we will describe how intelligence is obtained from SensorComm’s IoT-based mobile pollution monitoring system. Installed at the tailpipe, Wi-NOx™ captures the real-time pollution footprint of vehicles. The system extracts, analyzes and transforms NOx emissions data into real-time information providing transportation managers with business intelligence that leads to operational efficiencies and measurable savings. Wi-NOx™ is the cornerstone of a global pollution mitigation strategy that enables fuel savings, emissions reduction, vehicle optimization and extended asset life (to responsibly delay significant infrastructure investments like electrification).The Wi-NOx™ system was developed to monitor emissions from vehicles. Recently, we have modified it to remotely monitor patients in healthcare applications, and now, to monitor natural gas for oil & gas applications.In healthcare, Sensorcomm has developed a wrist-worn temperature monitoring system for COVID-19 detection using the Data-Centric Care™ model. Data-Centric Care™ focuses on data to provide the necessary intelligence to correctly assess the situation. The system uses (near) continuous temperature monitoring of individuals to identify at-risk persons who may or may not be symptomatic (for COVID-19 and beyond). The system uses a smart wearable device (wrist-worn) that monitors temperature as a trigger for second-tier screening from which a corresponding response is implemented (e.g. return to daily activity, isolate, elevated care). The continuous monitoring allows for the development of individualized thresholds (average temperature and fever threshold) rather than using population thresholds. The system identifies at-risk individuals (people with anomalies in their daily temperature profiles) for additional screening, prior to entering a facility.The most recent development at SensorComm is the partnership with the Center for Micro-Engineered Materials at the University of New Mexico, who is developing mixed-potential methane sensors using additive manufacturing. Mitigating environmental effects and financial costs of methane leaks requires a robust, widely deployable, low-cost sensing technology to provide continuous monitoring of natural gas infrastructure. Since methane emissions originate from multiple sources (agricultural or wetlands sites), sensors need to distinguish between natural gas or one of these other sources. Strategies for gathering the data, extracting the information and providing intelligence will be discussed.This talk will discuss the different techniques utilized in the data analytics and will provide key examples of how intelligence is extracted in the various applications.This material is based upon work supported by the U.S. Department of Energy, National Energy Technology Office program under Award Number DE-FOA-0031864, and partially by the National Science Foundation under Grant No. 1632498. Figure 1

Air Pollution Monitoring based Fuzzy Controller with Embedded System

Air pollution has a wide and great influence on the concentration of constituents of the atmosphere, which leads to many effects such as acid rains and global warming. In order to avoid such unwanted adverse imbalances in the nature, designing an air pollution monitoring system (APMS) is very important. This paper discussed the development of an effective solution for monitoring the air pollution by making an Arduino-Based Air Pollution Monitoring System (APMS). Carbon monoxide and Carbon Dioxide concentration levels in air were measured and monitored using MQ4 and MQ7 gas sensors and Arduino atmega microcontroller. These sensors can detect many harmful gases and can be used for measuring their amount very accurately. The concentrations of CO and CO2 in particle per million (PPM) will be monitored and displayed on the LCD very easily. Based on these measurements the pollution level could be monitored, determined, and displayed. The experiments were carried out using the developed wireless APMS under various physical conditions. The results showed that the designed system collects reliable and reasonable real time pollution data. Three hour sampling time was executed in each location. One of the logical functions that are widely used is fuzzy logic. A fuzzy logic artificial intelligence for gas sensors is used which clarifies the presence as well as the concentration of CO and CO2 efficiently. Fuzzy logic will gives the decision about whether the air is polluted or unpolluted. This logic function we can process some existing data into a form of output which can be in the form of a status or state of action that will be performed by a tool. This proposed system will contribute in the construction of an APMS in the outdoor or even in the indoor environment.

The U.S. EPA wildland fire sensor challenge: Performance and evaluation of solver submitted multi-pollutant sensor systems

Wildland fires can emit substantial amounts of air pollution that may pose a risk to those in proximity (e.g., first responders, nearby residents) as well as downwind populations. Quickly deploying air pollution measurement capabilities in response to incidents has been limited to date by the cost, complexity of implementation, and measurement accuracy. Emerging technologies including miniaturized direct-reading sensors, compact microprocessors, and wireless data communications provide new opportunities to detect air pollution in real time. The U.S. Environmental Protection Agency (EPA) partnered with other U.S. federal agencies (CDC, NASA, NPS, NOAA, USFS) to sponsor the Wildland Fire Sensor Challenge. EPA and partnering organizations share the desire to advance wildland fire air measurement technology to be easier to deploy, suitable to use for high concentration events, and durable to withstand difficult field conditions, with the ability to report high time resolution data continuously and wirelessly. The Wildland Fire Sensor Challenge encouraged innovation worldwide to develop sensor prototypes capable of measuring fine particulate matter (PM2.5), carbon monoxide (CO), carbon dioxide (CO2), and ozone (O3) during wildfire episodes. The importance of using federal reference method (FRM) versus federal equivalent method (FEM) instruments to evaluate performance in biomass smoke is discussed. Ten solvers from three countries submitted sensor systems for evaluation as part of the challenge. The sensor evaluation results including sensor accuracy, precision, linearity, and operability are presented and discussed, and three challenge winners are announced. Raw solver submitted PM2.5 sensor accuracies of the winners ranged from ~22 to 32%, while smoke specific EPA regression calibrations improved the accuracies to ~75–83% demonstrating the potential of these systems in providing reasonable accuracies over conditions that are typical during wildland fire events.

Machine learning based soft sensor model for BOD estimation using intelligence at edge

Real-time water quality monitoring is a complex system as it involves many quality parameters to be monitored, the nature of these parameters, and non-linear interdependence between themselves. Intelligent algorithms crucial in building intelligent systems are good candidates for building a reliable and convenient monitoring system. To analyze water quality, we need to understand, model, and monitor the water pollution in real time using different online water quality sensors through an Internet of things framework. However, many water quality parameters cannot be easily measured online due to several reasons such as high-cost sensors, low sampling rate, multiple processing stages by few heterogeneous sensors, the requirement of frequent cleaning and calibration, and spatial and application dependency among different water bodies. A soft sensor is an efficient and convenient alternative approach for water quality monitoring. In this paper, we propose a machine learning-based soft sensor model to estimate biological oxygen demand (BOD), a time-consuming and challenging process to measure. We also propose a system architecture for implementing the soft sensor both on the cloud and edge layers, so that the edge device can make adaptive decisions in real time by monitoring the quality of water. A comparative study between the computational performance of edge and cloud nodes in terms of prediction accuracy, learning time, and decision time for different machine learning (ML) algorithms is also presented. This paper establishes that BOD soft sensors are efficient, less costly, and reasonably accurate with an example of a real-life application. Here, the IBK ML technique proves to be the most efficient in predicting BOD. The experimental setup uses 100 test readings of STP water samples to evaluate the performance of the IBK technique, and the statistical measures are reported as correlation coefficient = 0.9273, MAE = 0.082, RMSE = 0.1994, RAE = 17.20%, RRSE = 37.62%, and edge response time = 0.15 s only.

Recording gear-type pump acoustic signals for assessing the hydraulic oil impurity level in a hydraulic excavator transmission

Mechanization and development of mining machines increase the importance of maintenance quality of working bodies and the machines themselves. This requires implementing improvements in technical maintenance processes. Improving technical maintenance implies the implementation of condition monitored maintenance that also allows real-time monitoring of the technical status. As hydraulic oil pollution is one of the major causes of breakdowns, it is recommended to implement oil pollution monitoring methods that will allow estimating the real-time oil pollution level. Today, sampling is the most widespread method of pollution level control. This method is time-consuming and that is why there are many attempts to devise new methods of monitoring the real-time oil pollution level. One of such methods includes recording of the acoustic-emission signal. In this work, we suggested that increase in transmission oil pollution level leads to increase in acoustic-emission signal in 20-300 kHz range. This increase in the acoustic level will indicate the pollution of oil with solid particles and alert the maintenance crew of the necessity of replacing the oil. This method allows real-time monitoring the hydraulic oil condition not associated with high labor, time, or economic costs.

Environmental policy of Novokuznetsk in the context of modern requirements for metallurgical industry development

Analysis of air pollution by pollutants, sources of pollution, types of economic activity, and administrative areas in the city of Novokuznetsk over 5 years was carried out. The largest share in the city air emissions is accounted for: CO – 61.8 %; SO2 – 17.4 %; solids – 11.3 %; NO2 – 5.9 %; CH4 – 1.8 %. Dynamics of gross emissions by years is shown. Planned implementation of the approved measures of the national project Ecology will make it possible to reduce air pollution in the city by more than 20 % by 2024, which corresponds to the federal project Clean Air. According to planes of the city industrial enterprises, environmental programs have been prepared, with monitoring by environmental specialists from the city administration and public control. Various measures were taken: automatic stationary posts were put into operation to monitor air pollution in real time; mobile laboratory was acquired to measure urban air. To improve waste management in the city, separate collection projects were implemented. Environmental assets exist and develop in the city, which ideas and projects find common understanding and form ecological attitude of the urban community. Trends in gross emissions of pollutants into the atmosphere of Novokuznetsk are shown for the period of 2014 – 2018; refinements and explanations of the observed trends are given.

Ecological monitoring system of the atmosphere

The research is targeted at the development and testing of a hardware-software system for environmental monitoring of atmospheric air in real time. The relevance of creating the system is substantiated in the article where it is shown that one cannot obtain operational data on the degree of atmospheric air pollution using available means, although this information is important for the population of large cities and industrial centers. The results of the creation and use of the automated system for monitoring atmospheric air using the modeling of transfer of pollutants are presented. The system was based on a hardwaresoftware complex consisting of a microcomputer, pollution sensors, a wireless communication module, and an unmanned aerial vehicle. Real-time pollution indicators are processed in order to build up-to-date maps, including to provide the opportunity to choose the optimal route taking into account the adverse effects of pollution. The developed mobile application provides the opportunity for the end user to receive information on-line and make forecasts based on the data on wind strength and direction in the short and medium term. The OND-86 methodology, which is mandatory in the Republic of Belarus, was chosen as the main model for the transfer of pollutants in the air. Information about the strength and direction of the wind for building forecasts is taken from open Internet sources of weather data. Using real data on the mass of emissions, a map of the planned concentration is constructed, which is scattered in proportion to the distance from the source of the emission, taking into account the strength and direction of the wind. The forecast obtained in this way can be used to select the optimal route, optimize traffic flows and organize actions in emergency situations associated with leakage and emissions of harmful substances.

Impacts of Modifiable Factors on Ambient Air Pollution: A Case Study of COVID-19 Shutdowns.

COVID-19-related closures offered a novel opportunity to observe and quantify the impact of activity levels of modifiable factors on ambient air pollution in real time. We use data from a network of low-cost Real-time Affordable Multi-Pollutant (RAMP) sensor packages deployed throughout Pittsburgh, Pennsylvania, along with data from Environmental Protection Agency regulatory monitors. The RAMP locations were divided into four site groups based on land use. Concentrations of PM2.5, CO, and NO2 following the COVID-related closures at each site group were compared to measurements from “business-as-usual” periods. Overall, PM2.5 concentrations decreased across the domain by ∼3 μg/m3. The morning rush-hour-induced CO and NO2 concentrations at the high-traffic sites were both reduced by ∼50%, which is consistent with observed reductions in commuter traffic (∼50%). The morning rush-hour PM2.5 enhancement from traffic emissions was reduced nearly 100%, from 1.4 to ∼0 μg/m3 across all site groups. There was no significant change in the industry-related intraday variability of CO and PM2.5 at the industrial sites following the COVID-related closures. If PM2.5 National Ambient Air Quality Standards (NAAQS) are tightened, this natural experiment sheds light on the extent to which reductions in traffic-related emissions can aid in meeting more stringent regulations.

Ultra-sensitive SERS detection, rapid selective adsorption and degradation of cationic dyes on multifunctional magnetic metal-organic framework-based composite

In-situ and real-time ultra-sensitive monitoring for the degradation process of environmental pollutants is always an important issue of concern to many people. Herein, a multifunctional magnetic metal-organic framework (MOF)-based composite has been successfully constructed and applied in monitoring the disposal of cationic dyes. Owing to its particular MOFs shell and internal gold particles, the composite can be used as an efficient SERS substrate to ultra-sensitively detect the cationic dyes. Furthermore, the prepared MOF-based composite is also a peroxidase-like nanozyme, which can catalytically degrade the adsorbed cationic dyes. Additionally, the magnetic core in the MOF-based composite offers a good magnetic separation capacity, which makes a facile and rapid separation of the catalyst from the reacted solution for recyclability. This work has provided a new way to monitor the catalytic degradation process by SERS technique in the co-existence of catalyst and dye molecules in the reaction system, which can effectively eliminate the absorption of the catalyst compared with the UV–vis technique, showing promising applications in in-situ and real-time pollution disposal monitoring.

Perfluorooctane sulfonate enhances mRNA expression of PPARγ and ap2 in human mesenchymal stem cells monitored by long-retained intracellular nanosensor

Perfluorooctane sulfonate (PFOS) has been widely used as a surface coating for household products. It still exists in living environments despite being restricted, due to its bioaccumulation and long half-life. Studies have shown that PFOS has the ability to induce adipogenic differentiation of human cells. Human mesenchymal stem cells (hMSCs) distributed within the adipose tissue might be a potential target of accumulated PFOS. However, traditional end-point toxicity assays failed to examine the subtle changes of cellular function exposed to low-dose persistent organic pollutants in real time. In the present work, highly sensitive and long-retained (more than 30 days) fluorescence based polymeric nanosensors were developed and employed for real-time assessment of cellular functions. hMSCs were engineered with sensor molecules encapsulated poly (lactic-co-glycolic acid) (PLGA) particles. Once internalized by hMSCs, PLGA particles continuously release and replenish sensor molecules to cytoplasm, resulting in prolonged fluorescence signal against photo bleaching and dilution by exocytosis. With this method, the dynamic changes of viability, ROS induction, and adipogenic differentiation related mRNA expression of hMSCs were monitored. PFOS with the concentration as low as 0.1 μM can induce cellular ROS and enhance the PPARγ and ap2 mRNA expression, suggesting the effect on promoting adipogenic differentiation of hMSCs.

Comparison and Optimization of Various Coated Ceramic Insulator Artificial Coastal Thermal Power Plant Pollution

In power system, the post-insulator is a critical apparatus which carries the conductor and also provides isolation between the conductors as well as ground. Besides, it offers mechanical support. However, extreme weather and pollution cause post-insulator flashover, which results in interruption of power supply and revenue loss. Therefore, post-insulator’s pollution flashover study is necessary. The pollution flashover voltage (FOV) is directly related to dominating metrological circumstance and how this pollution severity on the surface of insulator. Mostly, anti-pollution flashover coating is deliberated to be one of the most effective means to prevent and reduce pollution flashover. This paper investigates and compares the application of Epoxy Resin and Room Temperature Vulcanize (RTV) Silicone Rubber for enhancing the performance of ceramic outdoor (near coastal thermal plant area) insulator to defeat the effect of environmental pollution. At first, a real-time pollution performance has been carried out in controlled laboratory setup. It shows that the withstand ability of post-insulator has been 25% with Silicone Rubber coating. Subsequently, Artificial Neural Network (ANN) has been used to predict the FOV of post-insulator under wet and dry condition. It shows that critical FOV has enriched with anti-reflection coating rate. After that, post-insulator has been modeled by COMSOL multiphysics software, which is used for estimating field distribution on post-insulator. From the modeling, we found that anti-reflection coated post-insulator surface has low electrical stress than that of others.

A spatial-and-temporal-based method for rapid particle concentration estimations in an urban environment

The increasing construction of buildings and infrastructure in cities heavily influences pollutant dispersion and causes a spread of increased particle concentrations. Real-time data and information on local pollution levels are highly desired by residents, urban planners and policy-makers. Such information is scarce due to the high cost of real-time measurement. To fill the gap, the aim of this research is to develop a model that can rapidly estimate particulate pollution based on a data-driven artificial neural network modelling approach. The key influential factors such as background pollution level, weather conditions and urban morphology are embedded in the model in association with local emission sources of pollution relating to construction activities and traffic flows. The data for urban spatial-variables (building and road) and traffic information is processed with the aid of the Geographic Information System using self-developed Python scripts. The geographic dataset containing the required information for each grid is integrated with the artificial neural network model to perform forecasting of particle concentrations. The model has been verified with measurements from a case study with 20 sample locations in Chongqing, China, showing that the average relative error of particle concentration estimation compared to measurement is 17.56% for PM10 and 16.04% for PM2.5. A map of a time-specific spatial interpolation of particle concentrations which visualises real-time pollution is consequently produced based on the method. The newly proposed method is novel and holistic which integrates spatial and time information covering aspects of urban form, weather file, traffic, construction sites. The rigorously validated model has been transformed to a robust tool for a fast estimation of real-time particle concentration in an urban environment.

Real-Time Pollution Analysis and Location Based on Vehicle Particle Radar

This paper first studies the advantages and main observation methods of atmospheric particulate matter lidar in Regional large-scale measurement, and then discusses the measurement principle of lidar and two commonly used methods for inversion of aerosol extinction coefficient.Finally, the mobile observation system consisting of lidar-assisted vehicle particle monitor is used. Anping County is used as the research area.The lidar data of Anping County on September 15 to September 20, 2017 are obtained by means of the combination of navigation and fixed vertical monitoring.The results of fixed detection showes that foreign pollutants begin to be imported around 10 pm on the 15th, and the superimposed pollutants peakes around 2 pm on the 16th.The concentration of particulate matter gradually decreased after 2 pm on the 16th, which is in line with the trend of air quality rising first and then falling in accordance with the trend of the Ministry of Environmental Protection.According to the particle trajectory tracking map of the navigation area, the contaminant transport was analyzed Combined with the meteorological conditions at that time.

IoT Solution for Smart Cities’ Pollution Monitoring and the Security Challenges

Air pollution is a major factor in global heating and an increasing focus is centered on solving this problem. Urban communities take advantage of Information Technology (IT) and communications technologies in order to improve the control of environmental emissions and sound pollution. The aim is to mitigate health threatening risks and to raise awareness in relation to the effects of air pollution exposure. This paper investigates the key issues of a real-time pollution monitoring system, including the sensors, Internet of Things (IoT) communication protocols, and acquisition and transmission of data through communication channels, as well as data security and consistency. Security is a major focus in the proposed IoT solution. All other components of the system revolve around security. The bill of the materials and communications protocols necessary for the designing, development, and deployment of the IoT solution are part of this paper, as well as the security challenges. The paper’s proof of concept (PoC) addresses IoT security challenges within the communication channels between IoT gateways and the cloud infrastructure where data are transmitted to. The security implementations adhere to existing guidelines, best practices, and standards, ensuring a reliable and robust solution. In addition, the solution is able to interpret and analyze the collected data by using predictive analytics to create pollution maps. Those maps are used to implement real-time countermeasures, such as traffic diversion in a major city, to reduce concentrations of air pollutants by using existing data collected over a year. Once integrated with traffic management systems—cameras monitoring and traffic lights—this solution would reduce vehicle pollution by dynamically offering alternate routes or even enforcing re-routing when pollution thresholds are reached.

IoT based pollution monitoring and health correlation: a case study on smart city

We are living in a world which is connected to the internet, and as a result, a significant amount of data is being generated which can be processed using efficient methods for the technology development for the mankind. This paper focuses on the implementation of the HUT architecture for analyzing the IoT data, for the pollution control of a smart city. We propose our solution in a real-world smart city use case by obtaining the correlation between different types of gases responsible for pollution and further predicting the solutions for the prevention of pollution in real time.

Comparative emission study by real-time congestion monitoring for stable pollution policy on temporal and meso-spatial regions in Delhi

Rapid industrialization, urbanization, and motorization lead to hiking of air pollution in various mega cities including Delhi, India. Studies done to analyze pollution suggests that vehicle exhaust emissions are major contributor to the urban air quality along with many other comparable sources. Hence to check instantaneous pollution increment, government aims to reduce vehicle emission. Traditional policies are working at times for holding sudden increase but long-term effects are not seen which need meso-spatial and small temporal policy. For optimizing meso-spatial policies implementation, many intricacies related to moving and stationary sources in near real-time have to be monitored including vehicular emission, itself. Analyzing these moving source emissions on the meso-spatial level is challenging. Therefore, the present study is an attempt to first understand the need of meso-spatial and near real-time checking policy and then leveraging the usage of previous region specific pollutant survey reports to map real-time pollution monitoring parameters. For that, a real-time vehicle monitoring strategy is proposed to map city-wide traffic congestion and emission using crowd-source data of Google Maps. For comparative study of different meso-spatial regions real-time moving source pollutant parameter ‘μ’ is calculated using a factor ‘F’. Also, the different effects of congestion on vehicular emission in two different meso-spatial areas of Delhi is presented using comparative case study. Analysis of case study revealed that Anand Vihar area is more prone to vehicle emission variability in case of congestion fluctuation. Further the discussion of short temporal and spatial emission calculation, for weekly pollution evaluation is presented in the paper. This will be helpful to the authorities in formulating technological, institutional and traffic management policies.

Chemical Sensing in Real Time with Plants Using a Webcam.

It has been established that plants can smell and respond to chemicals in order to adapt to and survive in a changing chemical environment. Here we show that a plant responds to chemicals in air, and the response can be detected rapidly to allow tracking of air pollution in real time. We demonstrate this capability by detecting subtle color and shape changes in the leaves of mosses upon exposure to sulfur dioxide in air with a simple webcam and an imaging-processing algorithm. The leaves of mosses consist of a monolayer of cells, providing a large surface-to-volume ratio for highly sensitive chemical sensing. The plant sensor responds linearly to sulfur dioxide within a wide concentration range (0-180 ppm), and it can tolerate humidity variation (15-85% relative humidity) and chemical interference and regenerate itself. We envision that plants can help alert chemical exposure danger as a part of our living environment using low-cost CMOS imagers, and their chemical-sensing capabilities may be further improved with genetic engineering.

CEO Hubris and Firm Pollution: State and Market Contingencies in a Transitional Economy

This study focuses on CEO hubris and its effect on corporate unethical behaviour—pollution in particular, and in addition examines critical institutional contingencies [state ownership (SO), political connection (PC) and industrial competition] which may moderate this effect. With data from over-polluting listed firms based on the real-time pollution monitoring system in transitional China from 2015 to 2017, we find that CEO hubris is significantly positively related to firm pollution, and that the moderating role of SO is not significant, that PC positively moderates the hubris–pollution relationship and that industrial competition negatively moderates this relationship. These findings contribute to research on the upper echelon theory, institutional theory and the growing literature on emerging economies.