Classification of Soil Groups Using Weights-of-Evidence-Method and RBFLN-Neural Nets

Weights-of-Evidence (WofE) and Radial Basis Function Link Net (RBFLN) were applied to soil group mapping in eastern Finland. The data consisted of low altitude airborne geophysical measurements, Landsat 5 TM-satellite image, and digital elevation model (DEM) and slope information derived from it. Probability maps were constructed for each soil group one by one and combined into a prediction map of soil groups using maximum posterior probability (WofE) or pattern membership (RBFLN). Self-Organizing Map (SOM) and Sammon’s Mapping were applied for selecting the data sets for modeling and visualizing the data. The soil types belonging to each soil group used in the Arc-SDM modeling were defined by clusters revealed by the SOM and Sammon’s Mapping algorithms. The soil types with similar characters were collected in the same cluster. Numerical evaluation of the models’ performance was performed using the confusion matrix. The Ratio of Correct Classifications (RCC) for the best WofE model was 0.64 in the training area and 0.61 in the testing area. The RCC for the best RBFLN model was 0.62. Modeling of soil groups using Arc-SDM is time consuming because models need to be constructed for each soil group before combining them into a final prediction map. In this study a simple method was tested for combining the maps. In the future, more attention should be paid to combining the posterior probability models and also to selecting data sets used for modeling.     

Sub-ice geology inland of the Transantarctic Mountains in light of new aerogeophysical data

The Transantarctic Mountains are a major geologic boundary that bisects the Antarctic continent, separating the low-lying, tectonically active terrains of West Antarctica from the East Antarctic craton. A new comprehensive aerogeophysical data set, extending 1150 km from the Ross Sea into the interior of East Antarctica provides insights into the complex structure inland of the Transantarctic Mountains. Geophysical maps, compiled from 21 000 km of gravity, magnetic and subglacial topography data, outline the boundaries of several geologic and tectonic segments within the survey area. The coherent pattern in magnetic data and mesa topography suggests a subglacial extent of the Transantarctic Mountains 400–500 km inland the last exposed rock outcrops. We estimate the maximum thickness of a potential sediment infill in the Wilkes Subglacial Basin to be less than 1 km, based on gravity modeling and source depth estimates from magnetic data. The coherent nature of the potential field and topography data, together with the northwest–southeast trends, define the Adventure Subglacial Trench and the Resolution Subglacial Highlands as a tectonic unit. The crustal structure and the strong similarity of the observed gravity with fold-and-thrust belts suggest a compressional scenario for the origin of the Adventure Subglacial Trench and the Resolution Subglacial Highlands. The complexity and apparent structural control of the Wilkes Subglacial Basin raise the issue of what influence pre-existing structures may have played in the formation of the Transantarctic Mountains system. The previous hypothesis of a thermal boundary beneath the mountains is difficult to reconcile with our new gravity data. The apparent difficulties to match our new data with certain key aspects of previous models suggests that a reassessment of the existing uplift models is necessary. We have modeled the prominent gravity anomaly over the Transantarctic Mountains with thicker crust.