A novel combined model based on echo state network - a case study of PM10 and PM2.5 prediction in China

Deep-learning architecture for PM2.5 concentration prediction: A review

Accurately predicting the concentration of fine particulate matter (PM2.5) is crucial for evaluating air pollution levels and public exposure. Recent advancements have seen a significant rise in using deep learning (DL) models for forecasting PM2.5 concentrations. Nonetheless, there is a lack of unified and standardized frameworks for assessing the performance of DL-based PM2.5 prediction models. Here we extensively reviewed those DL-based hybrid models for forecasting PM2.5 levels according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We examined the similarities and differences among various DL models in predicting PM2.5 by comparing their complexity and effectiveness. We categorized PM2.5 DL methodologies into seven types based on performance and application conditions, including four types of DL-based models and three types of hybrid learning models. Our research indicates that established deep learning architectures are commonly used and respected for their efficiency. However, many of these models often fall short in terms of innovation and interpretability. Conversely, models hybrid with traditional approaches, like deterministic and statistical models, exhibit high interpretability but compromise on accuracy and speed. Besides, hybrid DL models, representing the pinnacle of innovation among the studied models, encounter issues with interpretability. We introduce a novel three-dimensional evaluation framework, i.e., Dataset-Method-Experiment Standard (DMES) to unify and standardize the evaluation for PM2.5 predictions using DL models. This review provides a framework for future evaluations of DL-based models, which could inspire researchers to standardize DL model usage in PM2.5 prediction and improve the quality of related studies.

PM2.5 activated NLRP3 inflammasome and IL-1β release in MH-S cells by facilitating autophagy via activating Wnt5a

Particulate matter 2.5 (PM2.5)-induced pulmonary inflammation is an important issue worldwide. NLRP3 inflammasome activation has been found to be involved in pulmonary inflammation development. However, whether PM2.5 induces pulmonary inflammation by activating the NLRP3 inflammasome has not yet been fully elucidated. This study researched whether PM2.5 induces the NLRP3 inflammasomes activation to trigger pulmonary inflammation.

Mice and MH-S cells were exposed to PM2.5, BOX5, and Rapamycin. Hematoxylin and eosin staining was performed on the lung tissues of mice. M1 macrophage marker CD80 expression in the lung tissues of mice and LC3B expression in MH-S cells was detected by immunofluorescence. IL-1β level in the lavage fluid and MH-S cells were detected by enzyme-linked immunosorbent assay. Protein expression was detected by Western blot. Autophagy assay in MH-S cells was performed by LC3B-GFP punctae experiment.PM2.5 exposure induced the lung injury of mice and increased NLRP3, P62, Wnt5a, LC3BII/I, and CD80 expression and IL-1β release in the lung tissues. PM2.5 treatment increased NLRP3, pro-caspase-1, cleaved caspase-1, Pro-IL-1β, Pro-IL-18, P62, LC3BII/I, and Wnt5a expression, IL-1β release, and LC3B-GFP punctae in MH-S cells. However, BOX5 treatment counteracted this effect of PM2.5 on lung tissues of mice and MH-S cells. Rapamycin reversed the effect of BOX5 on PM2.5-induced lung tissues of mice and MH-S cells.PM2.5 activated the NLRP3 inflammasome and IL-1β release in MH-S cells by facilitating the autophagy via activating Wnt5a. The findings of this study provided a new clue for the treatment of pulmonary inflammation caused by PM2.5.

Enhanced removal of As(Ⅲ) and As(Ⅴ) from aqueous solution using ionic liquid-modified magnetic graphene oxide

In this study, ionic liquid (IL) 1-butyl-3-methylimidazolium hexafluorophosphate ([BMIM][PF₆])-modified magnetic graphene oxide (MGO-IL) was prepared for the first time, and was used to adsorb and remove arsenic (As(Ⅲ) and As(V)) ions from aqueous solution. MGO-IL was characterized by scanning electron microscopy, Fourier transform infrared spectroscopy, X-ray diffraction, thermogravimetric analysis, and magnetization curves. Effects of ionic liquid type, solution pH, initial arsenic concentration and contact time on the adsorption performance of MGO-IL for As(Ⅲ) and As(V) were studied. The experimental results showed that the adsorption equilibrium was achieved within 30 min, with maximum adsorption capacities of 160.65 mg g^-1 for As(Ⅲ) and 104.13 mg g^-1 for As(V), respectively, and MGO-IL could be rapidly isolated from solution by applying a magnetic field. MGO-IL was reused for 5 times, without marked decrease in its adsorption capacities. Moreover, common coexisting anions did not interfere with the absorption of As(Ⅲ) and As(V). Compared with MGO, the sorption quantities of MGO-IL for As(Ⅲ) and As(V) were greatly enhanced, and the equilibrium time was significantly reduced. Therefore, MGO-IL can potentially serve as an excellent adsorbent for the simultaneous separation and removal of As(Ⅲ) and As(V) from water.