gully erosion constitutes a major problem in natural resources management and soil conservation, which causes severe land degradation in arid and semi-arid areas. therefore, determination of gully prone area and identification of gully conditioning factors can help to managers and decision makers to reduce the hazard of gully erosion. the aim of this study is to predictthe gully erosion suscept...

A combination of subsurface borehole imaging data and drilling logs were used to characterize the fractures and lithology in 40 bedrock wells at the fractured-rock research site in the Mirror Lake area in Grafton County, New Hampshire. The purpose of the research was to determine whether subsurface lithology and fractures have an effect on the hydraulic conductivity of the crystalline-rock aqui...

Machine-learning algorithms have been used by geoscientists to infer geologic and physical properties from hydrocarbon exploration development wells for more than 40 years. These techniques historically utilize digital well-log information, which, like any remotely sensed measurement, resolution limitations. Core is the only subsurface data that true scale heterogeneity. However, core descripti...

A Bayesian model coupled with a fuzzy neural network (BFNN) is developed to alleviate the difficulty of using geophysical data in lithology estimation when cross correlation between lithology and geophysical attributes is nonlinear. The prior estimate is inferred from borehole lithology measurements using indicator kriging based on spatial correlation, and the posterior estimate is obtained fro...

Lithology identification is an essential fact for delineating uranium-bearing sandstone bodies. A new method provided to delineate bodies by a lithological automatic classification model using machine learning techniques, which could also improve the efficiency of borehole core logging. In this contribution, BP neural network lithology was established optimized gradient descent algorithm based ...