Evaluation of data preprocessing and feature selection process for prediction of hourly PM10 concentration using long short-term memory models.

Studies have confirmed that PM10, defined as respirable particles with diameters of 10 µm and smaller, has adverse effects on human health and the environment. Various estimation methods are employed to determine the PM10 concentration using historical data on controlling PM10 air pollution, early warning, and protecting public health and the environment. The present study analyses different Long Short-Term Memory (LSTM) models that can predict hourly PM10 concentration. In parallel, the study also investigates the effectiveness of the data preprocessing and feature selection (DPFS) process on the prediction accuracy of the LSTM models. For this purpose, three different LSTM models, namely Vanilla, Bi-Directional, and Stacked, were developed. Then, a comprehensive data preprocessing stage is used to eliminate missing and erroneous data and outliers from real-world raw data, and a feature selection process is applied to extract unnecessary features. The LSTM models consider three air quality parameters, including SO2, O3, and CO, and three meteorological factors, including relative humidity, wind direction, and wind speed. The prediction performances of the LSTM models are compared using the RMSE, MAE and R2 performance index according to whether DPFS is used in the models or not. As a result, when the DPFS process was applied, the proposed LSTM models achieved high prediction performance and can be used to predict hourly PM10 concentrations. Overall, the DPFS process significantly enhanced the developed LSTM models' prediction performance. Furthermore, the proposed model might be a useful tool for city administrators to make decisions and improve air quality management efforts.

Spatial distribution and source identification of persistent organic pollutants in the sediments of the Yesilirmak River and coastal area in the Black Sea.

Surface sediments from the Yesilirmak River and the near coastal area in the Black Sea were collected using sediment traps to assess the spatial distributions of persistent organic pollutants and find their potential sources. Analyses were carried out to determine the concentrations of the persistent organic pollutants of seventeen polychlorinated dibenzo-p-dioxins and dibenzofurans, sixteen polycyclic aromatic hydrocarbons, seven polychlorinated biphenyls, and eight organochlorine pesticides using high-resolution gas chromatography-mass spectrometry and gas chromatography-tandem mass spectrometry systems. Analysis showed that the three main components of persistent organic pollutants (polychlorinated dibenzo-p-dioxins and dibenzofurans, polycyclic aromatic hydrocarbons, and organochlorine pesticides) primary sources are industrial activities. In addition, the widespread occurrence of persistent organic pollutants in the watershed surface sediments taken from the Yesilirmak River basin showed that agricultural and urban areas are also diffuse persistent organic pollutants sources.

Physical disintegration of toilet papers in wastewater systems: experimental analysis and mathematical modeling.

Physical disintegration of representative toilet papers was investigated in this study to assess their disintegration potential in sewer systems. Characterization of toilet papers from different parts of the world indicated two main categories as premium and average quality. Physical disintegration experiments were conducted with representative products from each category according to standard protocols with improvements. The experimental results were simulated by mathematical model to estimate best-fit values of disintegration rate coefficients and fractional distribution ratios. Our results from mathematical modeling and experimental work show that premium products release more amounts of small fibers and disintegrate more slowly than average ones. Comparison of the toilet papers with the tampon applicators studied previously indicates that premium quality toilet papers present significant potential to persist in sewer pipes. Comparison of turbulence level in our experimental setup with those of partial flow conditions in sewer pipes indicates that drains and small sewer pipes are critical sections where disintegration of toilet papers will be limited. For improvement, requirements for minimum pipe slopes may be increased to sustain transport and disintegration of flushable products in small pipes. In parallel, toilet papers can be improved to disintegrate rapidly in sewer systems, while they meet consumer expectations.