Evaluation of traffic noise pollution using geographic information system and descriptive statistical method: a case study in Mashhad, Iran

Air quality prediction and control systems using machine learning and adaptive neuro-fuzzy inference system

Accurately predicting air quality concentrations is a challenging task due to the complex interactions of pollutants and their reliance on nonlinear processes. This study introduces an innovative approach in environmental engineering, employing artificial intelligence techniques to forecast air quality in Semnan, Iran. Comprehensive data on seven different pollutants was initially collected and analyzed. Then, several machine learning (ML) models were rigorously evaluated for their performance, and a detailed analysis was conducted. By incorporating these advanced technologies, the study aims to create a reliable framework for air quality prediction, with a particular focus on the case study in Iran. The results indicated that the adaptive neuro-fuzzy inference system (ANFIS) was the most effective method for predicting air quality across different seasons, showing high reliability across all datasets.

Assessment and mapping of noise pollution in recreation spaces using geostatistic method after COVID-19 lockdown in Turkey

Increased use of recreational areas after the lifting of COVID-19 pandemic restrictions has led to increased noise levels. This study aims to determine the level of noise pollution experienced in recreational areas with the increasing domestic and international tourism activities after the lifting of pandemic lockdowns, to produce spatial distribution maps of noise pollution, and to develop strategic planning suggestions for reducing noise pollution in line with the results obtained. Antalya-Konyaaltı Beach Recreation Area, the most important international tourism destination of Turkey, is determined as the study area. To determine the existing noise pollution, 31 measurement points were marked at 100 m intervals within the study area. Noise measurements were taken during the daytime (07:00-19:00), evening (19:00-23:00), and nighttime (23:00-07:00) on weekdays (Monday, Wednesday, Friday) and weekends (Sunday) over 2 months in the summer when the lockdown was lifted. In addition, the sound level at each measurement point was recorded for 15 min, while the number of vehicles passing through the area during the same period was determined. The database created as a result of measurements and observations was analyzed using statistical and geostatistical methods. After the analysis of the data, it was found that the co-kriging-stable model showed superior performance in noise mapping. Additionally, it was revealed that there is a high correlation between traffic density and noise intensity, with the highest equivalent noise level (Leq) on weekdays and weekend evenings due to traffic and user density. In conclusion, regions exposed to intense noise pollution were identified and strategic planning recommendations were developed to prevent/reduce noise sources in these identified regions.

Statistical and spatio-temporal analyses of noise pollution level and its health impact

Due to rapid urbanization and exponential growth in transportation; traffic noise has become a major area of concern. Noise not only disturbs our day-to-day life but also have severe adverse health effects over humans which further may lead to mortality. This paper focuses on the behavior of noise levels of Lucknow city over a decade and establishes its correlation with impact on human health in terms of annoyance and sleep disturbance. Apart from Leq, different noise parameters like L10, L50, L90, Traffic Noise Index (TNI), Noise Pollution Index (NPI), and Noise Climate (NC) have also been analyzed to understand the variation of noise. At all the locations, the noise level has been found exceeding their prescribed standards during day time and night time except at Amausi. Out of nine locations, TNI was found to be exceeding at three locations during day time and NPI exceeding at one location. However, during night time both values of TNI and NPL were observed within the limit at all the locations. From the noise map of the city during day time and night time, among all sampling locations, Charbagh has been found to be worst affected by noise pollution. A strong positive correlation has been observed among the total population, vehicular count, and day and night time noise data, which directly contribute to a higher percentage of sleep disturbance and annoyance among residents. Due to the increase in noise levels over a period of time, almost four times the population get affected by high annoyance and almost double the population get affected by sleep disturbance.

Evaluating the Performance of a Solar Distillation Technology in the Desalination of Brackish Waters

Desalination is set to become a major source of drinking water in several Middle Eastern countries over the coming decades. Solar distillation is a simple power-independent method of water desalination, which can be carried out in active or passive modes. This study is among the first attempts to investigate the possibility of desalinating brackish groundwater resources under the threat of saltwater intrusion in the southern areas of Razavi Khorasan province in Iran. For this purpose, a pilot solar distillation unit was constructed to analyze the effects of the unit orientation, depth of the water pool, atmospheric conditions, input salinity, and flow continuity on the solar distillation performance. The results showed that the unit exhibited the highest efficiency when it had a 3 cm deep water pool. It was oriented facing southward while operating a continuous flow for at least 3 days under sunny weather conditions. It was found that among the studied parameters, the unit orientation and pool depth had the greatest impact on the water production performance for this type of water desalination system. Conversely, the water production efficiency was not very sensitive to the input salinity level. Overall, the solar distillation technology was able to reduce the salinity by 99.7% and the hardness by 94.7%.