Many countries worldwide have poor air quality due to the emission of particulate matter (i.e., PM₁₀ and PM_2.5), which has led to concerns about human health impacts in urban areas. In this study, we developed models to predict fine PM concentrations using long short-term memory (LSTM) and deep autoencoder (DAE) methods, and compared the model results in terms of root mean square error (RMSE). We applied the models to hourly air quality data from 25 stations in Seoul, South Korea, for the period from 1 January 2015, to 31 December 2018. Fine PM concentrations were predicted for the 10 days following this period, at an optimal learning rate of 0.01 for 100 epochs with batch sizes of 32 for LSTM model, and DAEs model performed best with batch size 64. The proposed models effectively predicted fine PM concentrations, with the LSTM model showing slightly better performance. With our forecasting model, it is possible to give reliable fine dust prediction information for the area where the user is located.

Both long- and short-term exposure to high concentrations of airborne particulate matter (PM) severely affect human health. Many countries now regulate PM concentrations. Early-warning systems based on PM concentration levels are urgently required to allow countermeasures to reduce harm and loss. Previous studies sought to establish accurate, efficient predictive models. Many machine-learning methods are used for air pollution forecasting. The long short-term memory and gated recurrent unit methods, typical deep-learning methods, reliably predict PM levels with some limitations. In this paper, the authors proposed novel hybrid models to combine the strength of two types of deep learning methods. Moreover, the authors compare hybrid deep-learning methods (convolutional neural network (CNN)—long short-term memory (LSTM) and CNN—gated recurrent unit (GRU)) with several stand-alone methods (LSTM, GRU) in terms of predicting PM concentrations in 39 stations in Seoul. Hourly air pollution data and meteorological data from January 2015 to December 2018 was used for these training models. The results of the experiment confirmed that the proposed prediction model could predict the PM concentrations for the next 7 days. Hybrid models outperformed single models in five areas selected randomly with the lowest root mean square error (RMSE) and mean absolute error (MAE) values for both PM₁₀ and PM_2.5. The error rate for PM₁₀ prediction in Gangnam with RMSE is 1.688, and MAE is 1.161. For hybrid models, the CNN–GRU better-predicted PM₁₀ for all stations selected, while the CNN–LSTM model performed better on predicting PM_2.5.

Urban parks are critical components of green infrastructure, supporting recreation and public health. This study investigates the association between urban park quality and health outcomes in 85 South Korean cities, utilizing a localized version of the ParkScore Index. The Korean ParkScore evaluates five dimensions: acreage, amenities, investment, accessibility, and equity. The health indicators include municipal-level rates of mental health disorders (anxiety, depression, insomnia, ADHD, and schizophrenia) and obesity. Pearson’s correlation analysis revealed significant negative associations between ParkScore rankings and mental health indicators, particularly depression and anxiety. Higher-quality, more accessible parks correlated with lower levels of psychological distress, emphasizing the public health benefits of urban green spaces. While the cross-sectional design limits causal inference, the results support the role of urban parks as essential infrastructure for mental well-being. The findings underscore the need for equitable and data-driven urban park policies in fostering health-supportive urban environments and highlight the importance of considering specific ParkScore dimensions in urban planning.

The purpose of this study is to suggest the optimum mix design with a high volume of GGBS (Ground Granulated Blast-furnace Slag) replacement and the procedure of the cryogenic test to consider mechanical and thermal properties, and durability performance. To decide the optimum mix design, four mix designs with high-volume of GGBS replacement were suggested, in terms of the slump and retention time. Based on the test results, with respect to the workability and compressive strength, the mixtures with 65% of GGBS (C40-2 and C40-4) were better than the mixtures with 50% and 60% of GGBS (C40-1 and C40-3). After selecting two mixtures, two types of cryogenic test methods were conducted under one-cycle cryogenic condition (Test A) and 50-cycles cryogenic condition (Test B). As a result, in Test A, the compressive strength and elastic modulus of the C40-2 and C40-4 mixtures tended to be decreased over time, because of the volume expansion of ice crystals contained in the capillary pores. In Test B, the mechanical properties of the C40-4 mixture were better than those of the C40-2 mixture, in terms of the reduction rate of compressive strength and elastic modulus. In the view of the heat of hydration, the semi-adiabatic test was conducted. In the results, the C40-4 mixture was better to control the thermal cracks. Thus, the C40-4 mixture would be more suitable for cryogenic concrete and this procedure could be helpful to decide the mixture of cryogenic concrete. In the future, the long-term performance of cryogenic concrete needs to be investigated.

The use of rubber crumbs provides a viable solution for alleviating the disposal problem of waste tires. In this study, rubberized sulfur concrete (RSC) was researched to investigate the optimal mixture proportion and to improve the mixing process in terms of compressive strength and durability performance. For the mixture of the RSC, sand, rubber particles, and micro-filler were adopted as aggregates and sulfur was used for the binding material. Moreover, two mixing processes were applied: the dry mixing process and the wet mixing process. Based on the test results, the increment of rubber particles in the mixture led to a decrease in the compressive strength for both the dry and wet mixing processes. To minimize the voids between the sand and rubber particles, the micro-filler was used at 5% of the total volume. The amount of sulfur varied slightly depending on the mixing process: 30% sulfur for the dry mixing process and 34% sulfur for the wet mixing process, respectively. Consequently, compared to the dry mixing process, the wet mixing process increased the bonding force between sulfur and rubber powder due to the simultaneous heating and combining. In toughness, the wet mixing process demonstrates a 40% higher energy absorption capability compared to the dry mixing process. For the durability performance of the RSC, the mixture with 20% rubber particles produced using the wet mixing process exhibited better corrosion and freeze–thaw resistance.