http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Prima Riza Kadavi (검색결과 5 건)
- 무료
- 기관 내 무료
- 유료
-
Prima Riza Kadavi,이창욱 한국지질과학협의회 2018 Geosciences Journal Vol.22 No.4
Land cover (LC) mapping is an important research topic with many applications in remote sensing. Especially, for volcanic areas where direct field access is difficult, remote sensing data are needed to map LC. Volcanic areas are attractive targets for LC mapping because any spread of volcanic eruptions must be monitored. When creating LC maps, it is important to minimize errors because such errors compromise analyses using these maps. Here, we analyzed multispectral data from Mount Kanaga, Mount Fourpeaked, Mount Pavlof, and Mount Augustine using two different classifiers, an artificial neural network (ANN) and a support vector machine (SVM). To this end, we employed Landsat 8 imagery, which features four LC classes: outcrops (pyroclastic deposits, volcanic rock, sand, etc.), vegetation, water bodies, and snow. We found that the SVM was more accurate than the ANN. For Mount Kanaga, the SVM afforded the best classification accuracy (98.08%), 9.14% better than the ANN (88.94%); for the other volcanoes, the accuracy of the two methods did not differ significantly. Overall, both classifiers accurately distinguished products of volcanic eruption (outcrops) from other LC. Thus, both the ANN and SVM can be used for LC classification.
-
-
Azam Kadirhodjaev,Prima Riza Kadavi,이창욱,이사로 한국지질과학협의회 2018 Geosciences Journal Vol.22 No.6
This paper uses a probability-based approach to study the spatial relationships between landslides and their causative factors in the Mingchukur area, Bostanlik districts of Tashkent, Uzbekistan. The approach is based on digital databases and incorporates methods including probability analysis, spatial pattern analysis, and interactive mapping. First, an object-oriented conceptual model for describing landslide events is proposed, and a combined database of landslides and environmental factors is constructed by integrating various databases within a unifying conceptual framework. The frequency ratio probability model and landslide occurrence data are linked for interactive, spatial evaluation of the relationships between landslides and their causative factors. In total, 15 factors were analyzed, divided into topography, hydrology, and geology categories. All analyzed factors were also divided into numerical and categorical types. Numerical factors are continuous and were evaluated according to their R2 values. A landslide susceptibility map was constructed based on conditioning factors and landslide occurrence data using the frequency ratio model. Finally, the map was validated and the accuracy showed the satisfactory value of 83.3%.
-
-
확률론적 모델을 이용한 산사태 취약성 지도 분석: 한국 사천면과 주문진읍을 중심으로
박성재 ( Sung-jae Park ),( Prima Riza Kadavi ),이창욱 ( Chang-wook Lee ) 대한원격탐사학회 2018 大韓遠隔探査學會誌 Vol.34 No.5
이 연구의 목적은 확률모델의 2가지 방법인 Frequency Ratio(FR), Evidential Belief Functions(EBF) 모델을 사용하여 산사태 취약성을 작성하고 강릉시 사천면과 주문진읍에서의 결과 비교를 통해 각 지역에 적합한 모델을 선정하는 것이다. 사천면에서 762개, 주문진읍에서 548개의 산사태 위치를 항공 사진의 해석을 기반으로 작성되었다. 각각의 산사태 지점 중 절반을 모델링을 위해 무작위로 선택하였고 남은 산사태 지점은 검증 목적으로 사용하였다. 지형 요소, 수문 요소, 산림입지토양도(1:5,000), 임상도(1:5,000), 지질도(1:25,000)와 같은 5가지 범주로 분류된 20가지의 산사태 유발 요소가 연구에서 산사태 취약성 작성을 위해 고려되었다. 산사태 발생과 산사태 유발 요소 사이의 관계는 FR, EBF 모델을 사용하여 분석되었다. 그 후, 2 가지 모델을 AUC(curve under area) 방법을 사용하여 검증하였다. 검증 결과에 따르면 주문진읍에서 FR모델(AUC = 81.2%)이 EBF 모델(AUC = 78.9%)에 비해 정확도가 높았다. 사천면 지역에서는 EBF 모델(AUC = 83.6%)이 FR모델(AUC =81.6%)보다 정확도가 높게 나타났다. 검증 결과 FR 모델과 EBF 모델은 정확도 80% 내외로 높은 정확도를 가지고 있음을 나타낸다. The purpose of this study is to create landslide vulnerability using frequency ratio (FR) and evidential belief functions (EBF) model which are two methods of probability model and to select appropriate model for each region through comparison of results in Sacheon-myeon and Jumunjin-eup of Gangneung. 762 locations in Sacheon-myeon and 548 landscapes in Jeonju-eup were constructed based on the interpretation of aerial photographs. Half of each landslide point was randomly selected for modeling and remaining landslides were used for verification purposes. Twenty landslide-inducing factors classified into five categories such as topographic elements, hydrological elements, soil maps (1:5,000), forest maps (1:5,000), and geological maps (1:25,000) were considered for the preparation of landslide vulnerability in the study. The relationship between landslide occurrence and landslide inducing factors was analyzed using FR and EBF models. The two models were then verified using the AUC (curve under area) method. According to the results of verification, the FR model (AUC = 81.2%) was more accurate than the EBF model (AUC = 78.9%) at Jeonjun-eup. In the Sacheon-myeon, the EBF model (AUC = 83.6%) was more accurate than the FR model (AUC = 81.6%). Verification results show that FR model and EBF model have high accuracy with accuracy of around 80%.
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
