2022, Vol.31, No.2

Journal of Environmental Impact Assessment 2023 KCI Impact Factor : 0.51

pISSN : 1225-7184
https://journal.kci.go.kr/kseia

In this study, DNN-based models were learned using air quality determination data for 2017, 2019, and 2020 provided by the National Measurement Network (Air Korea), and this models evaluated using data from 2016 and 2018. Based on Pearson correlation coefficient 0.2, four items (SO2, CO, NO2, PM10) were initially modeled as independent variables. In order to improve the accuracy of prediction, monthly independent modeling was carried out. The error was calculated by RMSE (Root Mean Square Error) method, and the initial model of RMSE was 5.78, which was about 46% better than the national moving average model result (10.77). In addition, the performance improvement of the independent monthly model was observed in months other than November compared to the initial model. Therefore, this study confirms that DNN modeling was effective in predicting PM2.5 concentrations based on air pollutants concentrations, and that the learning performance of the model could be improved by selecting additional independent variables.

Busan, where the coastal ecosystem health is deteriorating due to high development pressure and intensity of use, needs ecosystem management that considers humans and the natural environment together for sustainable use and ecosystem preservation of the coastal areas. In this study, the InVEST model was applied to assess the habitat status of the coastal land and coastal sea to manage the ecosystem based on habitats. As a result of the assessment of the coastal land, the habitat quality of Gadeok-do, Igidae, and Sinseondae, Gijang-gun are high, and Seo-gu, Jung-gu, Dong-gu, and Suyeong-gu are low. In the case of the coastal sea, the habitat risk of the Nakdong river estuary is low, and some areas of Yeongdo-gu, Saha-gu, Gangseo-gu are high. Therefore, for the sustainable use and preservation of coastal ecosystems, it is necessary to prepare ecosystem-based management measures to improve damaged habitats and reduce threats. In addition, the impact on coastal seas should be fully considered when planning coastal land development. The results of the InVEST habitat quality model in coastal land show similar tendencies to the biotope and environmental conservation value assessment map. The results of the habitat risk assessment in the coastal sea are expected to be utilized to identify habitats in the coastal sea and management of threat factors.

Multilateral Development Banks (MDBs) have actively responded to global climate change, and developed and operated the Common Principles for Climate Finance Tracking. They estimate climate finance in a granular manner with a conservative view. In other words, the MDBs track their financing only for those elements or proportions of projects that directly contribute to or promote climate adaptation or mitigation. The MDBs have reported jointly on climate finance since the first edition in 2012, which reported for 2011 and up to the 10th edition in 2021, which reported for 2020. MDBs apply two difference methodologies for adaptation and mitigation. For adaptation, the methodology is based on a context and location specific approach and captures the amounts associated with activities directly linked to vulnerability to climate change. For mitigation, it is evaluated in accordance with a comprehensive list of activities that reduce greenhouse gas emissions. The result of climate risk assessment is one of the major due diligence items for MDBs alongside with that of environmental and social impact assessment. Under the circumstance that many countries endeavor to deal with climate change at project level, it is meaningful to understand how MDBs have addressed climate change issues in their project approval process. This would be a good reference to establish a methodology for responding to climate change and to expand scope of environmental and social impact assessment.