• Analytical Science and Technology
• /
• v.20 no.5
• /
• pp.383-392
• /
• 2007

The water soluble components were analyzed in the $PM_{2.5}$ fine particles collected at the 1100 site of Mt. Halla for the spring seasons between 1998 and 2004. The $PM_{2.5}$ mass concentrations were within $13.4{\pm}9.6{\sim}21.7{\pm}20.0{\mu}g/m^3$, and the concentrations of ionic components were in the order of nss-$SO{_4}^{2-}$ > $NH{_4}{^+}$ > $NO{_3}{^-}$ > $Ca^{2+}$ > $K^+$ > $Na^+$ > $Cl^-$ > $Mg^{2+}$, in which the concentration of nss-$SO{_4}^{2-}$($3.41{\pm}2.42{\mu}g/m^3$) was the highest. The concentrations of $NH{_4}{^+}$, $SO{_4}^{2-}$, and $NO{_3}{^-}$, the secondary pollutants, were respectively 0.60~1.50, 2.86~4.42, and $0.24{\sim}1.57{\mu}g/m^3$, which had occupied 88 % of the total ionic components, on the other hand, the concentrations of marine species were less than 5 %. The nss-$SO{_4}^{2-}$ showed the high correlation with $NH{_4}{^+}$, $K^+$, so that $NH{_4}{^+}$ and nss-$SO{_4}^{2-}$ might exist in the form of $(NH_4)_3H(SO_4)_2$ and $(NH_4)_2SO_4$ in fine particles. From the backward trajectory analysis, in case of high concentrations of $NH{_4}{^+}$ and nss-$SO{_4}^{2-}$ simultaneously, the air masses were originated and stagnated at the east region of China for a while, then moved into the atmosphere of Jeju. However, in case of $NO{_3}{^-}$ and nss-$Ca^{2+}$, the air masses originated at China and Siberia were moved into Jeju via the eastern China.

• Journal of Wetlands Research
• /
• v.25 no.4
• /
• pp.306-314
• /
• 2023

Stream sediments are an important component of water quality management because they are receptors of various pollutants such as heavy metals and organic matters emitted from upland sources and can be secondary pollution sources, adversely affecting water environment. To effectively manage the stream sediments, identification of primary sources of sediment contamination and source-associated control strategies will be required. We evaluated the performance of machine learning models in identifying primary sources of sediment contamination based on the physico-chemical properties of stream sediments. A total of 356 stream sediment data sets of 18 quality parameters including 10 heavy metal species(Cd, Cu, Pb, Ni, As, Zn, Cr, Hg, Li, and Al), 3 soil parameters(clay, silt, and sand fractions), and 5 water quality parameters(water content, loss on ignition, total organic carbon, total nitrogen, and total phosphorous) were collected near abandoned metal mines and industrial complexes across the four major river basins in Korea. Two machine learning algorithms, linear discriminant analysis (LDA) and support vector machine (SVM) classifiers were used to classify the sediments into four cases of different combinations of the sampling period and locations (i.e., mine in dry season, mine in wet season, industrial complex in dry season, and　industrial complex in wet season). Both models showed good performance in the classification, with SVM outperformed LDA; the accuracy values of LDA and SVM were 79.5% and 88.1%, respectively. An SVM ensemble model was used for multi-label classification of the multiple contamination sources inlcuding landuses in the upland areas within 1 km radius from the sampling sites. The results showed that the multi-label classifier was comparable performance with sinlgle-label SVM in classifying mines and industrial complexes, but was less accurate in classifying dominant land uses (50~60%). The poor performance of the multi-label SVM is likely due to the overfitting caused by small data sets compared to the complexity of the model. A larger data set might increase the performance of the machine learning models in identifying contamination sources.