Dispersion modelling is an effective tool to estimate traffic-related fine particulate matter (PM₂.₅) concentrations in near-road environments. However, many sources of uncertainty and variability are associated with the process of near-road dispersion modelling, which renders a single-number estimate of concentration a poor indicator of near-road air quality. In this study, we propose an integrated traffic-emission-dispersion modelling chain that incorporates several major sources of uncertainty. Our approach generates PM₂.₅ probability distributions capturing the uncertainty in emissions and meteorological conditions. Traffic PM₂.₅ emissions from 7 a.m. to 6 p.m. were estimated at 3400 ± 117 g. Modelled PM₂.₅ levels were validated against measurements along a major arterial road in Toronto, Canada. We observe large overlapping areas between modelled and measured PM₂.₅ distributions at all locations along the road, indicating a high likelihood that the model can reproduce measured concentrations. A policy scenario expressing the impact of reductions in truck emissions revealed that a 30% reduction in near-road PM₂.₅ concentrations can be achieved by upgrading close to 55% of the current trucks circulating along the corridor. A speed limit reduction of 10 km/h could lead to statistically significant increases in PM₂.₅ concentrations at twelve out of the eighteen locations.

This study investigates the influence of meteorology, land use, built environment, and traffic characteristics on near-road ultrafine particle (UFP) concentrations. To achieve this objective, minute-level UFP concentrations were measured at various locations along a major arterial road in the Greater Toronto Area (GTA) between February and May 2019. Each location was visited five times, at least once in the morning, mid-day, and afternoon. Each visit lasted for 30 min, resulting in 2.5 h of minute-level data collected at each location. Local traffic information, including vehicle class and turning movements, were processed using computer vision techniques. The number of fast-food restaurants, cafes, trees, traffic signals, and building footprint, were found to have positive impacts on the mean UFP, while distance to the closest major road was negatively associated with UFP. We employed the Extreme Gradient Boosting (XGBoost) method to develop prediction models for UFP concentrations. The Shapley additive explanation (SHAP) measures were used to capture the influence of each feature on model output. The model results demonstrated that minute-level counts of local traffic from different directions had significant impacts on near-road UFP concentrations, model performance was robust under random cross-validation as coefficients of determination (R²) ranged from 0.63 to 0.69, but it revealed weaknesses when data at specific locations were eliminated from the training dataset. This result indicates that proper cross-validation techniques should be developed to better evaluate machine learning models for air quality predictions.

Massive Sargassum stranding events affect erratically numerous countries from the Gulf of Guinea to the Gulf of Mexico. Forecasting transport and stranding of Sargassum aggregates require progress in detection and drift modelling. Here we evaluate the role of currents and wind, i.e. windage, on Sargassum drift. Sargassum drift is computed from automatic tracking using MODIS 1 km Sargassum detection dataset, and compared to reference surface current and wind estimates from collocated drifters and altimetric products. First, we confirm the strong total wind effect of ≈3 % (≈2 % of pure windage), but also show the existence of a deflection angle of ≈10° between Sargassum drift and wind directions. Second, our results suggest reducing the role of currents on drift to 80 % of its velocity, likely because of Sargassum resistance to flow. These results should significantly improve our understanding of the drivers of Sargassum dynamics and the forecast of stranding events.

Municipal solid waste (MSW) management currently requires critical attention in ensuring the best principles of socio-economic attributes such as environmental protection, economic sustainability, and mitigation of human health problems. Numerous surveys on the waste management system reveal that approximately 90% of the MSW systems are improperly disposing the wastages in open dumps and landfills. Classifying the wastages into biodegradable and non-biodegradable helps converting them into usable energy and disposing properly. The advancements of effective computational approaches like artificial intelligence and image processing provide wide range of solutions for the present problem identified in MSW management. The computational approaches can be programmed to classify wastes that help to convert them into usable energy. Existing methods of waste classification in MSW remain unresolved due to poor accuracy and higher error rate. This paper presents an experimented effective computer vision–based MSW management solution with the help of the Internet of Things (IoT), and machine learning (ML) techniques namely regression, classification, clustering, and correlation rules for the perception of solid waste images. A ground-up built convolutional neural network (CNN) and CNN by the inception of ResNet V2 models trained through transfer learning for image classification. ResNet V2 supports training large datasets in deep neural networks to achieve improved accuracy and reduced error rate in identity mapping. In addition, batch normalization and mixed hybrid pooling techniques are incorporated in CNN to improve stability and yield state of art performance. The proposed model identifies the type of waste and classifies them as biodegradable or non-biodegradable to collect in respective waste bins precisely. Furthermore, observation of performance metrics, accuracy, and loss ensures the effective functions of the proposed model compared to other existing models. The proposed ResNet-based CNN performs waste classification with 19.08% higher accuracy and 34.97% lower loss than the performance metrics of other existing models.

Digital eye strain (DES) is a growing occupational and public health problem and one of the most frequent reasons for seeking medical care. The objectives of this study are to identify the prevalence and to study some associated personal, ergonomic, and environmental factors of DES among information technology (IT) professionals at Tanta University, Egypt. An interview questionnaire was used to collect data related to socio-demographic, job, ergonomic and environmental characteristics. Computer vision syndrome questionnaire (CVS-Q) was used for the assessment of DES. It was used to measure ocular and visual symptoms related to computer use. CVS-Q includes 16 symptoms that are scored using two rating scales, one for frequency and the other for intensity. A total of 108 IT professionals were included. Prevalence of DES was 82.41%. The most common symptoms were headache (81.5%), burning of the eye (75.9%), and blurred vision (70.4%). Significant predictors of DES were female gender (OR = 2.845), age ≥ 35 years (OR = 1.112), daily computer use more than 6 h (OR = 1.351), duration of work more than 10 years (OR = 1.793), wearing corrective glasses (OR = 5.009), distance from the monitor less than 20 in. (OR = 4.389), not using antiglare screen (OR = 0.214), no brightness adjustment of screen (OR = 0.015), not taking break time during computer work (OR = 0.007), exposure to air pollution (OR = 5.667), use of the air conditioner (OR = 23.021), and exposure to windy environments (OR = 3.588). Prevalence of DES was found to be high among IT professionals. Significant predictors of DES were female gender, older age, wearing eyeglasses, long duration of computer use, unadjusted ergonomic workstation, and dry environment. DES is a problem that can be prevented by increasing knowledge and awareness about DES by providing computer users with eye health education, periodic training on a proper ergonomic computer workstation, and adjustment of the suitable comfortable workplace environment.

Recently, analytical procedures based on computer vision related to the colorimetric analysis of digital images have been described in the scientific literature. In this sense, a novel analytical approach is presented based on digital image colorimetry for nickel determination. The method consists in the development of a system with solid-phase extraction, consisting basically of an extraction chamber filled with polystyrene divinylbenzene sorbent impregnated with the complexing reagent 1-(2-thiazolylazo)-p-cresol (TAC) and a portable microscope multifunction, used for image acquisition. The image of the sorbent after extraction of Ni is obtained. This image is related to the concentration of the elements. The variables (pH, flow, and sample volume) were evaluated using a full factorial design 2³ for the screening and a Doehlert matrix to establish the significant variables’ optimal levels. The enrichment factor and limit of detection were 148 and 0.8 μg L⁻¹, respectively. The method was applied to the determination of nickel in river water, coffee, and cigarette samples.

As the whole world is witnessing what novel coronavirus (COVID-19) can do to the mankind, it presents several unique features also. In the absence of specific vaccine for COVID-19, it is essential to detect the disease at an early stage and isolate an infected patient. Till today there is a global shortage of testing labs and testing kits for COVID-19. This paper discusses about the role of machine learning techniques for getting important insights like whether lung computed tomography (CT) scan should be the first screening/alternative test for real-time reverse transcriptase-polymerase chain reaction (RT-PCR), is COVID-19 pneumonia different from other viral pneumonia and if yes how to distinguish it using lung CT scan images from the carefully selected data of lung CT scan COVID-19-infected patients from the hospitals of Italy, China, Moscow and India? For training and testing the proposed system, custom vision software of Microsoft azure based on machine learning techniques is used. An overall accuracy of almost 91% is achieved for COVID-19 classification using the proposed methodology.