The Application of Artificial Neural Networks to Landslide Susceptibility Mapping at Janghung, Korea   总被引：13，自引：0，他引：13  

Saro Lee  Joo-Hyung Ryu  Moung-Jin Lee  Joong-Sun Won 《Mathematical Geology》2006,38(2):199-220

The purpose of this study was to develop techniques for landslide susceptibility using artificial neural networks and then to apply these to the selected study area at Janghung in Korea. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use. Thirteen landslide-related factors were extracted from the spatial database. These factors were then used with an artificial neural network to analyze landslide susceptibility. Each factor's weight was determined by the back-propagation training method. Five different training sets were applied to analyze and verify the effect of training. Then the landslide susceptibility indices were calculated using the back-propagation weights, and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. Landslide locations were used to verify results of the landslide susceptibility maps and to compare them. The artificial neural network proved to be an effective tool for analyzing landslide susceptibility.  相似文献   

A study of igneous rocks related to Zn–Pb mineralization in the Shinyemi and Gagok deposits of the Taebaeksan Basin,South Korea     

Jieun Seo  Seon‐Gyu Choi  Minho Koo  Chang Whan Oh  In&#x;Chang Ryu  Gilljae Lee 《Resource Geology》2020,70(3):215-232

The Shinyemi and Gagok deposits, located in the Taebaeksan Basin, South Korea, display Zn–Pb mineralization along a contact between Cretaceous granitoids and Cambrian–Ordovician carbonates of the Joseon Supergroup. The Shinyemi mine is one of the largest polymetallic skarn‐type magnetite deposits in South Korea and comprises Fe and Fe–Mo–Zn skarns, and Zn–Cu–Pb replacement deposits. Both deposits yield similar Cretaceous mineralization ages, and granitoids associated with the two deposits displaying similar mineral textures and compositions, are highly evolved, and were emplaced at a shallow depth. They are classified as calc‐alkaline, I‐type granites (magnetite series) and were formed in a volcanic arc. Compositional variation is less in the Shinyemi granites and aplites (e.g., SiO₂ = 74.4–76.6 wt% and 74.4–75.1 wt%, respectively) than in the Gagok granites and aplites (e.g., SiO₂ = 65.6–68.0 wt% and 74.9–76.5 wt%, respectively). Furthermore, SiO₂ vs K/Rb and SiO₂ vs Rb/Sr diagrams indicate that the Shinyemi granitoids are more evolved than the Gagok granitoids. Shinyemi granitoids had been already differentiated highly in deep depth and then intruded into shallow depth, so both granite and aplite show the highly evolved similar chemical compositions. Whereas, less differentiated Gagok granitoids were separated into two phases in the last stage at shallow depth, so granite and aplite show different compositions. The amounts of granites and aplite are similar in the Shinyemi deposit, whereas the aplite appears in an amount less than the granite in the Gagok deposit. For this reason, the Shinyemi granitoids caused not only Fe enrichment during formation of the dolomite‐hosted magnesian skarn but also was associated with Mo mineralization in the Shinyemi deposit. Zn mineralization of the Gagok deposit was mainly caused by granite rather than aplite. Our data suggest that the variation in mineralization displayed by the two deposits resulted from differences in the compositions of their associated igneous intrusions.  相似文献