GIS-based groundwater potential mapping using artificial neural network and support vector machine models: the case of Boryeong city in Korea     

Saro Lee  Hyung-Sup Jung 《国际地球制图》2018,33(8):847-861

Groundwater productivity-potential (GPP) was analysed using the data mining models of an artificial neural network (ANN) and a support vector machine (SVM) in Boryeong city, Korea. The groundwater-productivity data with specific capacity (SPC) is strongly related to hydrogeological factors, and hence the relation may allow for groundwater potential mapping from hydrogeological factors through the ANN and SVM models. A back-propagation algorithm was used for the ANN model while a polynomial kernel was adopted for the SVM model. For the validation of the GPP maps generated from the ANN and SVM models, the area-under-the-curve analysis was performed using the SPC values of well data. The accuracies achieved from the ANN and SVM models are about 83.57 and 80.83%, respectively. It proves that the ANN and SVM models will be highly conducive to developing useful groundwater resources.  相似文献   

Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran     

Phuong Thao Thi Ngo  Mahdi Panahi  Khabat Khosravi  Omid Ghorbanzadeh  Narges Kariminejad  Artemi Cerda  Saro Lee 《地学前缘(英文版)》2021,12(2):505-519

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.  相似文献   

Validation of an artificial neural network model for landslide susceptibility mapping   总被引：6，自引：3，他引：3  

Jaewon Choi  Hyun-Joo Oh  Joong-Sun Won  Saro Lee 《Environmental Earth Sciences》2010,60(3):473-483

The aim of this study was to validate an artificial neural network model at Youngin, Janghung, and Boeun, Korea, using the geographic information system (GIS). The factors that influence landslide occurrence, such as the slope, aspect, curvature, and geomorphology of topography, the type, material, drainage, and effective thickness of soil, the type, diameter, age, and density of forest, distance from lineament, and land cover were either calculated or extracted from the spatial database and Landsat TM satellite images. Landslide susceptibility was analyzed using the landslide occurrence factors provided by the artificial neural network model. The landslide susceptibility analysis results were validated and cross-validated using the landslide locations as study areas. For this purpose, weights for each study area were calculated by the artificial neural network model. Among the nine cases, the best accuracy (81.36%) was obtained in the case of the Boeun-based Janghung weight, whereas the Janghung-based Youngin weight showed the worst accuracy (71.72%).  相似文献   

Evidence from IRAS for a very young, partially formed dust band     

Ashley J. Espy  Stanley F. Dermott  Sumita Jayaraman 《Planetary and Space Science》2009,57(2):235-242

The relative proportions of asteroidal and cometary materials in the zodiacal cloud is an ongoing debate. The determination of the asteroidal component is constrained through the study of the Solar System dust bands (the fine-structure component superimposed on the broad background cloud), since they have been confidently linked to specific, young, asteroid families in the main belt. The disruptions that produce these families also result in the injection of dust into the cloud and thus hold the key to determining at least a minimum value for the asteroidal contribution to the zodiacal cloud. There are currently known to be at least three dust band pairs, one at approximately 9.35° associated with the Veritas family and two central band pairs near the ecliptic, one of which is associated with the Karin subcluster of the Koronis family. Through careful co-adding of almost all the pole-to-pole intensity scans in the mid-infrared wavebands of the Infrared Astronomical Satellite (IRAS) data set, we find strong evidence for a partial Solar System dust band, that is, a very young dust band in the process of formation, at approximately 17° latitude. We think this is a confirmation of the M/N partial band pair first suggested by Sykes [1988. IRAS observations of extended zodiacal structures. Astrophys. J. 334, L55-L58]. The new dust band appears at some but not all ecliptic longitudes, as expected for a young, partially formed dust band. We present preliminary modeling of the new, partial dust band which allows us to put constraints on the age of the disruption event, the inclination and node of the parent body at the time of disruption, and the quantity of dust injected into the zodiacal cloud.  相似文献   

Landslide susceptibility mapping on Panaon Island,Philippines using a geographic information system   总被引：6，自引：3，他引：3  

Hyun-Joo Oh  Saro Lee 《Environmental Earth Sciences》2011,62(5):935-951

For landslide susceptibility mapping, this study applied, verified and compared the Bayesian probability model, the weights-of-evidence to Panaon Island, Philippines, using a geographic information system. Landslide locations were identified in the study area from the interpretation of aerial photographs and field surveys, and a spatial database was extracted from SRTM (Shuttle Radar Topographic Mission) DEM (Digital Elevation Model) imagery, aerial photograph, topographic map, and geological map. The factors that influence landslide occurrence, such as slope, aspect, curvature, topographic wetness index and stream power index of topography, were calculated from SRTM imagery. Distance from drainage was extracted from topographic database. Lithology and distance from fault were extracted and calculated from geological database. Terrain mapping unit was classified from aerial photographs. The spatial association between the factors and the landslides was calculated as the contrast values, W ⁺ and W ⁻ using the weights-of-evidence model. Tests of conditional independence were performed for the selection of the factors, allowing the large number of combinations of factors to be analyzed. For each factor rating, the contrast values, W ⁺ and W ⁻ were overlaid for landslide susceptibility mapping. The results of the analysis showed that contrast rating (78.60%) for each factor’s multiclass had better accuracy of 5.90% than combinations of factor assigned to binary class with W ⁺ and W ⁻ (72.70%).  相似文献   

Spatial prediction of urban landslide susceptibility based on topographic factors using boosted trees     

Sunmin Lee  Moung-Jin Lee  Saro Lee 《Environmental Earth Sciences》2018,77(18):656

As global warming accelerates, abnormal weather events are occurring more frequently. In the twenty-first century in particular, hydrological disruption has increased as water flows have changed globally, causing the strength and frequency of hydrological disasters to increase. The damage caused by such disasters in urban areas can be extreme, and the creation of landslide susceptibility maps to predict and analyze the extent of future damage is an urgent necessity. Therefore, in this study, probabilistic and data mining approaches were utilized to identify landslide-susceptible areas using aerial photographs and geographic information systems. Areas where landslides have occurred were located through interpretation of aerial photographs and field survey data. In addition, topographic maps generated from aerial photographs were used to determine the values of topographic factors. A frequency ratio (FR) model was utilized to examine the influences of topographic, soil and vegetation factors on the occurrence of landslides. A total of 23 variables that affect landslide frequency were selected through FR analysis, and a spatial database was constructed. Finally, a boosted tree model was applied to determine the correlations between various factors and landslide occurrence. Correlations among related input variables were calculated as predictor importance values, and sensitivity analysis was performed to quantitatively analyze the impact of each variable. The boosted tree model showed validation accuracies of 77.68 and 78.70% for the classification and regression algorithms using receiver operating characteristic curve, respectively. Reliable accuracy can provide a scientific basis to urban municipalities for policy recommendations in the management of urban landslides.  相似文献   

Groundwater resources development in hard rock terrain - an approach using remote sensing and GIS techniques     

Jagannathan Krishnamurthy  Arul Mani  Venkatakrishnan Jayaraman  M Manivel 《International Journal of Applied Earth Observation and Geoinformation》2000,2(3-4)

To demonstrate the capabilities of remote sensing and Geographic Information System (GIS) techniques for groundwater resources development in hard rock terrains, specifically for the demarcation of suitable sites for artificial recharge of groundwater aquifers, a study was carried out in the Kallar Basin, which is located in parts of the Salem and Tiruchirapalli districts, Tamil Nadu, India. Thematic maps defining lithology, lineaments, landforms, landuse, drainage density, thickness of weathered zone, thickness of fractured zone, hydrological soils, and well yield were prepared from data collected by the Indian Remote Sensing Satellite (IRS) -1C and by conventional methods. All the thematic layers were integrated using a GIS-based model developed specifically for this purpose, enabling a map showing artificial recharge zones to be generated. The exact type of artificial recharge structure, eg, check dam, nallabund, gully plugging and percolation pond, suitable for replenishing groundwater was identified by superposing a drainage network map over an artificial recharge zones map. The GIS-based demarcation of artificial zones developed in the study was based on logical conditions and reasoning, so that the same techniques (with appropriate modifications) could be adopted elsewhere, especially in hard rock terrain, where the occurrence of groundwater is restricted and subject to greater complexity.  相似文献   

Study of Ozone and NO2 over Gadanki – a rural site in South India     

K. Renuka  Harish Gadhavi  A. Jayaraman  Shyam Lal  M. Naja  S. V. Bhaskara Rao 《Journal of Atmospheric Chemistry》2014,71(2):95-112

We have studied long-term changes in tropospheric NO₂ over South India using ground-based observations, and GOME and OMI satellite data. We have found that unlike urban regions, the region between Eastern and Western Ghat mountain ranges experiences statistically significant decreasing trend. There are few ground-based observatories to verify satellite based trends for rural regions. However, using a past study and recent measurements we show a statistically significant decrease in NO_X and O₃ mixing ratio over a rural location (Gadanki; 13.48° N, 79.18° E) in South India. In the ground-based records of surface NO_X, the concentration during 2010–11 is found to be lower by 0.9 ppbv which is nearly 60 % of the values observed during 1994–95. Small but statistically significant decrease in noon-time peak ozone concentration is also observed. Noon-time peak ozone concentration has decreased from 34?±?13 ppbv during 1993–96 to 30?±?15 ppbv during 2010–11. NO_X mixing ratios are very low over Gadanki. In spite of low NO_X values (0.5 to 2 ppbv during 2010–11), ozone mixing ratios are not significantly low compared to many cities with high NO_X. The monthly mean ozone mixing ratio varies from 9 ppbv to 37 ppbv with high values during Spring and low values during late Summer. Using a box-model, we show that presence of VOCs is also very important in addition to NO_X in determining ozone levels in rural environment and to explain its seasonal cycle.  相似文献   

Combining landslide susceptibility maps obtained from frequency ratio,logistic regression,and artificial neural network models using ASTER images and GIS     

Jaewon Choi  Hyun-Joo Oh  Hong-Jin Lee  Changwook Lee  Saro Lee 《Engineering Geology》2012

Landslide-related factors were extracted from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images, and integrated techniques were developed, applied, and verified for the analysis of landslide susceptibility in Boun, Korea, using a geographic information system (GIS). Digital elevation model (DEM), lineament, normalized difference vegetation index (NDVI), and land-cover factors were extracted from the ASTER images for analysis. Slope, aspect, and curvature were calculated from a DEM topographic database. Using the constructed spatial database, the relationships between the detected landslide locations and six related factors were identified and quantified using frequency ratio (FR), logistic regression (LR), and artificial neural network (ANN) models. These relationships were used as factor ratings in an overlay analysis to create landslide susceptibility indices and maps. Three landslide susceptibility maps were then combined and applied as new input factors in the FR, LR, and ANN models to make improved susceptibility maps. All of the susceptibility maps were verified by comparison with known landslide locations not used for training the models. The combined landslide susceptibility maps created using three landslide-related input factors showed improved accuracy (87.00% in FR, 88.21% in LR, and 86.51% in ANN models) compared to the individual landslide susceptibility maps (84.34% in FR, 85.40% in LR, and 74.29% in ANN models) generated using the six factors from the ASTER images.  相似文献   

A GIS-based logistic regression model in rock-fall susceptibility mapping along a mountainous road: Salavat Abad case study, Kurdistan, Iran   总被引：1，自引：0，他引：1  

Ataollah Shirzadi  Lee Saro  Oh Hyun Joo  Kamran Chapi 《Natural Hazards》2012,64(2):1639-1656

This study describes the application of logistic regression to rock-fall susceptibility mapping along 11?km of a mountainous road on the Salavat Abad saddle, in southwest Kurdistan, Iran. To determine the factors influencing rock-falls, data layers of slope degree, slope aspect, slope curvature, elevation, distance to road, distance to fault, lithology, and land use were analyzed by logistic regression analysis. The results are shown as rock-fall susceptibility maps. A spatial database, which included 68 sites (34 rock-fall point cells with value of 1 and 34 no rock-fall point cells with value of 0) was developed and analyzed using a Geographic Information System, GIS. The results are shown as four classes of rock-fall susceptibility. In this study, distance to fault, lithology, slope curvature, slope degree, and distance to road were found to be the most important factors affecting rock-fall. It was concluded that about 76?% of the study area can be classified as having moderate and high susceptibility classes. Rock-fall point cells were used to verify results of the rock-fall susceptibility map using success curve rate and the area under the curve. The verification results showed that the area under the curve for rock-fall susceptibility map is 77.57?%. The results from this study demonstrated that the use of a logistic regression model within a GIS framework is useful and suitable for rock-fall susceptibility mapping. The rock-fall susceptibility map can be used to reduce susceptibility associated with rock-fall.  相似文献