Atmospheric models today represent all significant aerosol components. Atmospheric aerosols play an important role in the air, globally through their action on the Earth's radiation balance and locally through their effects on health in heavily polluted areas, they vary considerably in their properties that affect the way they absorb and disperse radiation, and they can thus have a cooling or warming effect, they impact on the formation and life of clouds is one example. Among the main sectors of activity releasing emissions of PM10 (fine particles with a diameter of less than 10 µm) and a diameter of less than 2.5 µm (PM2.5) is the industrial sector, in particular the extraction industry of building materials. The aerosols emitted by this type of industry are composed mainly of a mixture of dust, sulphates, carbon black and nitrates, is clearly perceptible in many continental regions of the northern hemisphere. Improvements in in situ, satellite and surface measurements are needed. However, the mechanisms by which aerosols interact with the environment are extremely complex and still poorly understood. This study is based on satellite atmospheric models to have spatiotemporal variability of concentrations of fine particles smaller than 10 µm in diameter (PM10) and smaller than 2.5 µm in diameter (PM2.5) at the level of the western Rif part of Morocco, home to a large number of extraction quarries and thus offering a high-resolution particle capture system (PM10 and PM2.5).

Air quality is a vital concern globally, and Sri Lanka, according to WHO statistics, faces challenges in achieving optimal air quality levels. To address this, we introduced an innovative IoT-based Air Pollution Monitoring (APM) Box. This solution incorporates readily available Commercial Off-The-Shelf (COTS) sensors, specifically MQ-7 and MQ-131, for measuring concentrations of Carbon Monoxide (CO) and Ozone (O3) ,Arduino and "ThingSpeak" platform. Yet, those COTS sensors are not factory-calibrated. Therefore, we implemented machine learning algorithms, including linear regression and deep neural network models, to enhance the accuracy of CO and O3 concentration measurements from these non-calibrated sensors. Our findings indicate promising correlations when dealing with MQ-7 and MQ-131 measurements after removing outliers.

Air quality is a vital concern globally, and Sri Lanka, according to WHO statistics, faces challenges in achieving optimal air quality levels. To address this, we introduced an innovative IoT-based Air Pollution Monitoring (APM) Box. This solution incorporates readily available Commercial Off-The-Shelf (COTS) sensors, specifically MQ-7 and MQ-131, for measuring concentrations of Carbon Monoxide (CO) and Ozone (O3) ,Arduino and "ThingSpeak" platform. Yet, those COTS sensors are not factory-calibrated. Therefore, we implemented machine learning algorithms, including linear regression and deep neural network models, to enhance the accuracy of CO and O3 concentration measurements from these non-calibrated sensors. Our findings indicate promising correlations when dealing with MQ-7 and MQ-131 measurements after removing outliers.