scholarly journals Prediction of PM2.5 concentrations in Malaysia using machine learning techniques: a review

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 1279
Author(s):  
Naveen Palanichamy ◽  
Su-Cheng Haw ◽  
Subramanian S ◽  
Kuhaneswaran Govindasamy ◽  
Rishanti Murugan
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Fine Particles ◽  
Smart Cities ◽  
Control Strategies ◽  
Air Pollutant ◽  
Machine Learning Techniques ◽  
Motor Vehicles ◽  
Pollutant Concentrations ◽  
Haze Pollution

Particulate matter (PM), an air pollutant that is detrimental to breathing, is either emitted or formed ambiently. The exposure of respiratory system towards PM2.5, the fine particles of 2.5 micrometres diameter, causes complication for health. Thus, developing pollution control strategies requires the prediction of PM2.5 concentrations. Advancement of technology and computer science knowledge, machine learning (ML) algorithms are used for highly accurate prediction of air pollutant concentrations. Recently, air quality in Smart Cities of Malaysia has been getting worse due to industrialization, emissions from private motor vehicles, and transboundary haze pollution. Therefore, the forecasting of PM2.5 emissions to ensure they are within the statutory limits becomes necessary. Several machine learning methods have been implemented in existing research to predict air pollution concentrations in comparison to PM2.5. However, very few studies have used ML techniques to predict air quality in Malaysia when compared with global studies. Hence, to create awareness on the ML techniques and promote further research in this area, this study reviews and highlights most of the existing ML techniques for the prediction of PM2.5.

scholarly journals Comparative Analysis of Machine Learning Techniques for Predicting Air Quality in Smart Cities

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 128325-128338 ◽  
Author(s):  
Saba Ameer ◽  
Munam Ali Shah ◽  
Abid Khan ◽  
Houbing Song ◽  
Carsten Maple ◽  
...  
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Air Quality ◽  
Smart Cities ◽  
Machine Learning Techniques ◽  
Learning Techniques

Source apportionment of PM2.5 at two receptor sites in Brisbane, Australia

2011 ◽  
Vol 8 (6) ◽  
pp. 569 ◽  
Author(s):  
Adrian J. Friend ◽  
Godwin A. Ayoko ◽  
Eduard Stelcer ◽  
David Cohen
Keyword(s):  
Air Quality ◽  
Fine Particles ◽  
Function Analysis ◽  
Control Strategies ◽  
Motor Vehicles ◽  
The South ◽  
Receptor Sites ◽  
Reduction Strategies ◽  
Study Sites ◽  
Conditional Probability Function

Environmental contextFine particles affect air quality locally, regionally and globally. Determining the sources of fine particle is therefore critical for developing strategies to reduce their adverse effects. Advanced data analysis techniques were used to determine the sources of fine particles at two sites, providing information for future pollution reduction strategies not only at the study sites but in other areas of the world as well. AbstractIn this study, samples of particulate matter with aerodynamic diameter less than 2.5 µm (PM2.5) collected at two sites in the south-east Queensland region, a suburban (Rocklea) and a roadside site (South Brisbane), were analysed for H, Na, Al, Si, P, S, Cl, K, Ca, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Br, Pb and black carbon (BC). Samples were collected during 2007–10 at the Rocklea site and 2009–10 at the South Brisbane site. The receptor model Positive Matrix Factorisation was used to analyse the samples. The sources identified included secondary sulfate, motor vehicles, soil, sea salt and biomass burning. Conditional probability function analysis was used to determine the most likely directions of the sources. Future air quality control strategies may focus on the particular sources identified in the analysis.

scholarly journals Evolution of Gaseous and Particulate Pollutants in the Air: What Changed after Five Lockdown Weeks at a Southwest Atlantic European Region (Northwest of Spain) Due to the SARS-CoV-2 Pandemic?

Atmosphere ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 562
Author(s):  
Jorge Moreda-Piñeiro ◽  
Joel Sánchez-Piñero ◽  
María Fernández-Amado ◽  
Paula Costa-Tomé ◽  
Nuria Gallego-Fernández ◽  
...  
Keyword(s):  
Air Quality ◽  
Road Traffic ◽  
Statistical Significance ◽  
Temporal Trends ◽  
Air Pollutant ◽  
Concentration Data ◽  
Southwest Atlantic ◽  
Pollutant Concentrations ◽  
Air Quality Monitoring Stations ◽  
Almost All

Due to the exponential growth of the SARS-CoV-2 pandemic in Spain (2020), the Spanish Government adopted lockdown measures as mitigating strategies to reduce the spread of the pandemic from 14 March. In this paper, we report the results of the change in air quality at two Atlantic Coastal European cities (Northwest Spain) during five lockdown weeks. The temporal evolution of gaseous (nitrogen oxides, comprising NOx, NO, and NO2; sulfur dioxide, SO2; carbon monoxide, CO; and ozone, O3) and particulate matter (PM10; PM2.5; and equivalent black carbon, eBC) pollutants were recorded before (7 February to 13 March 2020) and during the first five lockdown weeks (14 March to 20 April 2020) at seven air quality monitoring stations (urban background, traffic, and industrial) in the cities of A Coruña and Vigo. The influences of the backward trajectories and meteorological parameters on air pollutant concentrations were considered during the studied period. The temporal trends indicate that the concentrations of almost all species steadily decreased during the lockdown period with statistical significance, with respect to the pre-lockdown period. In this context, great reductions were observed for pollutants related mainly to fossil fuel combustion, road traffic, and shipping emissions (−38 to −78% for NO, −22 to −69% for NO2, −26 to −75% for NOx, −3 to −77% for SO2, −21% for CO, −25 to −49% for PM10, −10 to −38% for PM2.5, and −29 to −51% for eBC). Conversely, O3 concentrations increased from +5 to +16%. Finally, pollutant concentration data for 14 March to 20 April of 2020 were compared with those of the previous two years. The results show that the overall air pollutants levels were higher during 2018–2019 than during the lockdown period.

scholarly journals Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

Energies ◽  
2021 ◽  
Vol 14 (16) ◽  
pp. 4776
Author(s):  
Seyed Mahdi Miraftabzadeh ◽  
Michela Longo ◽  
Federica Foiadelli ◽  
Marco Pasetti ◽  
Raul Igual
Keyword(s):  
Machine Learning ◽  
Power Systems ◽  
Smart Grids ◽  
State Of The Art ◽  
Smart Cities ◽  
Power Grids ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
New Research ◽  
Traditional Approaches

The recent advances in computing technologies and the increasing availability of large amounts of data in smart grids and smart cities are generating new research opportunities in the application of Machine Learning (ML) for improving the observability and efficiency of modern power grids. However, as the number and diversity of ML techniques increase, questions arise about their performance and applicability, and on the most suitable ML method depending on the specific application. Trying to answer these questions, this manuscript presents a systematic review of the state-of-the-art studies implementing ML techniques in the context of power systems, with a specific focus on the analysis of power flows, power quality, photovoltaic systems, intelligent transportation, and load forecasting. The survey investigates, for each of the selected topics, the most recent and promising ML techniques proposed by the literature, by highlighting their main characteristics and relevant results. The review revealed that, when compared to traditional approaches, ML algorithms can handle massive quantities of data with high dimensionality, by allowing the identification of hidden characteristics of (even) complex systems. In particular, even though very different techniques can be used for each application, hybrid models generally show better performances when compared to single ML-based models.

Machine learning techniques based on security management in smart cities using robots

Work ◽  
2021 ◽  
pp. 1-12
Author(s):  
Zhang Mengqi ◽  
Wang Xi ◽  
V.E. Sathishkumar ◽  
V. Sivakumar
Keyword(s):  
Machine Learning ◽  
Information And Communication Technologies ◽  
Smart City ◽  
Smart Cities ◽  
Security Management ◽  
Machine Learning Techniques ◽  
Quality Of Services ◽  
Learning Techniques ◽  
Learning Concept

BACKGROUND: Nowadays, the growth of smart cities is enhanced gradually, which collects a lot of information and communication technologies that are used to maximize the quality of services. Even though the intelligent city concept provides a lot of valuable services, security management is still one of the major issues due to shared threats and activities. For overcoming the above problems, smart cities’ security factors should be analyzed continuously to eliminate the unwanted activities that used to enhance the quality of the services. OBJECTIVES: To address the discussed problem, active machine learning techniques are used to predict the quality of services in the smart city manages security-related issues. In this work, a deep reinforcement learning concept is used to learn the features of smart cities; the learning concept understands the entire activities of the smart city. During this energetic city, information is gathered with the help of security robots called cobalt robots. The smart cities related to new incoming features are examined through the use of a modular neural network. RESULTS: The system successfully predicts the unwanted activity in intelligent cities by dividing the collected data into a smaller subset, which reduces the complexity and improves the overall security management process. The efficiency of the system is evaluated using experimental analysis. CONCLUSION: This exploratory study is conducted on the 200 obstacles are placed in the smart city, and the introduced DRL with MDNN approach attains maximum results on security maintains.

To what extent does the environmental magnetism technique acts as a way of assessing the uptake of atmospheric particles by plants?

2021 ◽  
Author(s):  
Sarah Letaïef ◽  
Pierre Camps ◽  
Thierry Poidras ◽  
Patrick Nicol ◽  
Delphine Bosch ◽  
...  
Keyword(s):  
Air Quality ◽  
Endemic Species ◽  
Fine Particles ◽  
Magnetic Measurements ◽  
Deposition Velocity ◽  
Environmental Magnetism ◽  
Air Pollutant ◽  
Atmospheric Pollutants ◽  
Area Index ◽  
The Impact

<p>Numerous studies have already shown the possibility of tracing the sources, the<br>compositions, and the concentration of atmospheric pollutants deposited on plant<br>leaves. In environmental geochemistry, inter-element and isotope ratios from<br>chemical element assays have been used for these purposes. Alternatively,<br>environmental magnetism represents a quick and inexpensive asset that is<br>increasingly used as a relative indicator for concentrations of air pollutant on bio<br>accumulator surfaces such as plants. However, a fundamental issue is still pending:<br>Do plants in urban areas represent a sink for fine particles that is sufficiently effective<br>to improve air quality? This is a very topical issue because some studies have shown<br>that the foliage can trap fine particles by different dry deposition processes, while<br>other studies based on CFD models indicate that plant hedges in cities can hinder<br>the atmospheric dispersion of pollutants and therefore increase pollution at the level of<br>emission sources such as traffic. To date, no consensus was made because several<br>factors not necessary well known must be taken into account, such as, PM<br>concentration and size, prevailing wind, surface structures, epicuticular wax, to<br>mention just a few examples. A first step toward the understanding of the impact of<br>urban greens on air quality is the precise determination of the deposition velocity (Vd)<br>parameter. This latter is specific for each species and it is most of the time<br>underestimated in modeling-based studies by taking standard values.<br>In that perspective, we built a wind tunnel (6 m long, 86 cm wide and 86 cm high) to<br>perform analogical experiments on different endemic species. All parameters are<br>controlled, i.e, the wind speed, the nature and the injection time of pollutants (Gasoline<br>or Diesel exhausts, brakes or tires dust, etc…). We can provide the PM concentrations<br>upwind and downwind of natural reconstituted hedges by two dustmeters (LOACs -<br>MétéoModem). Beforehand, parameters such as the hedge resistance (%) or the leaf<br>area index (LAI) have been estimated for each studied specie to allow comparability<br>between plants removal potential. The interest would ultimately combine PM<br>concentration measured by size bins from the LOACs with magnetic measurements<br>(ARM, IRM100mT, IRM300mT and SIRM) of plant leaves. The idea is to check whether it<br>would be possible to precisely determine in situ the dust removal rate by urban greens<br>with environmental magnetism measurements. Up to now, we have carried out on<br>different endemic species such as Elaeagnus x ebbingei leaves and Mediterranean<br>pine needles, the results of which will be presented.</p>

scholarly journals Does afforestation deteriorate haze pollution in Beijing–Tianjin–Hebei (BTH), China?

2018 ◽  
Author(s):  
Xin Long ◽  
Naifang Bei ◽  
Jiarui Wu ◽  
Xia Li ◽  
Tian Feng ◽  
...  
Keyword(s):  
Forest Cover ◽  
Fine Particles ◽  
Control Strategies ◽  
Surface Wind ◽  
Forecast Model ◽  
Surface Wind Speed ◽  
Satellite Measurements ◽  
Haze Pollution ◽  
The Impact

Abstract. Although aggressive emission control strategies have been implemented recently in the Beijing–Tianjin–Hebei area (BTH), China, pervasive and persistent haze still frequently engulfs the region during wintertime. Afforestation in BTH, primarily concentrated in the Taihang and Yanshan Mountains, has constituted one of the controversial factors exacerbating the haze pollution due to its slowdown of the surface wind speed. We report here an increasing trend of forest cover in BTH during 2001–2013 based on long-term satellite measurements and the impact of the afforestation on the fine particles (PM2.5) level. Simulations using the Weather Research and Forecast model with chemistry reveal that the afforestation in BTH since 2001 generally deteriorates the haze pollution in BTH to some degree, enhancing PM2.5 concentrations by up to 6 % on average. Complete afforestation or deforestation in the Taihang and Yanshan Mountains would increase or decrease the PM2.5 level within 15 % in BTH. Our model results also suggest that implementing a large ventilation corridor system would not be effective or beneficial to mitigate the haze pollution in Beijing.

scholarly journals First steps in the development of a possible measurement method to estimate the radon concentration as an indicator of the indoor air quality

2014 ◽  
Vol 29 (suppl.) ◽  
pp. 52-58
Author(s):  
Franz Roessler ◽  
Jai Azzam ◽  
Volker Grimm ◽  
Hans Hingmann ◽  
Tina Orovwighose ◽  
...  
Keyword(s):  
Exchange Rate ◽  
Air Quality ◽  
Indoor Air Quality ◽  
Indoor Air ◽  
Primary Energy ◽  
Air Pollutant ◽  
Daily Routine ◽  
Air Exchange Rate ◽  
Pollutant Concentrations ◽  
Air Exchange

The energy conservation regulation provides upper limits for the annual primary energy requirements for new buildings and old building renovation. The actions required could accompany a reduction of the air exchange rate and cause a degradation of the indoor air quality. In addition to climate and building specific aspects, the air exchange rate is essentially affected by the residents. Present methods for the estimation of the indoor air quality can only be effected under test conditions, whereby the influence of the residents cannot be considered and so an estimation under daily routine cannot be ensured. In the context of this contribution first steps of a method are presented, that allows an estimation of the progression of the air exchange rate under favourable conditions by using radon as an indicator. Therefore mathematical connections are established that could be affirmed practically in an experimental set-up. So this method could provide a tool that allows the estimation of the progression of the air exchange rate and in a later step the estimation of a correlating progression of air pollutant concentrations without limitations of using the dwelling.

scholarly journals La surveillance de la qualité de l'air dans les Hauts-de-France

2021 ◽  
pp. 045
Author(s):  
Jimmy Leyes ◽  
Laure Roussel
Keyword(s):  
Air Quality ◽  
Air Pollutant ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Non Profit ◽  
The Public ◽  
Pollutant Concentrations ◽  
Ambient Concentrations ◽  
Air Pollutant Concentrations ◽  
Qualité De L’Air

La surveillance réglementaire de la qualité de l'air en France est confiée aux associations régionales agréées de surveillance de la qualité de l'air (Aasqa) telles qu'Atmo Hauts-de-France. Elles s'appuient sur une palette d'outils et leur expertise pour mesurer les polluants dans l'air de leur territoire, alerter les populations en cas d'épisode de pollution, répondre aux exigences réglementaires de surveillance définies au niveau européen, tout en prenant en compte les spécificités régionales. Cet article présente les différents outils utilisés par les Aasqa, et plus particulièrement Atmo Hauts-de-France, pour surveiller et estimer la qualité de l'air. L'association régionale opère ainsi un ensemble de stations de mesures fixes et mobiles pour suivre en continu les concentrations de polluants réglementés ou non sur son territoire, et dispose d'outils de modélisation pour évaluer et prévoir la qualité de l'air en tous points de la région. Cet article présente également certains des paramètres météorologiques qui influencent la qualité de l'air de la région Hauts-de-France, particulièrement concernée par les épisodes de pollution aux particules. Regulatory air quality monitoring in France is performed by government-approved non-profit organisations called AASQAs, one of which is Atmo Hauts-de-France. These organisations rely on decades of accumulated air quality expertise and use several techniques to measure air pollutant concentrations, inform the public when pollutant levels are unhealthy, and comply with E.U. air quality monitoring regulations. This paper gives an overview of the tools used by AASQAs, and more particularly by Atmo Hauts-de-France, to monitor and forecast air quality. The year-round continuous monitoring of air pollutant levels at fixed sites is supplemented by short-term measurements made with fully-equipped vehicles or trailers and by modelling tools that forecast air quality and estimate pollutant levels where there are no measurements. AASQAs study pollutants which ambient concentrations are regulated by European air quality standards as well as other pollutants which are not regulated in this way. This work also discusses some of the meteorological factors, that affect air quality in the region Hauts-de-France, which is heavily impacted by particulate matter pollution.

Sign in / Sign up

Export Citation Format

Share Document