Soil types mapping and the spatial variation of soil classes are essential concerns in both geotechnical and geoenvironmental engineering. Because conventional soil mapping systems are time-consuming and costly, alternative quick and cheap but accurate methods need to be developed. In this paper, a new optimized multi-output generalized feed forward neural network (GFNN) structure using 58 piezocone penetration test points (CPTu) for producing a digital soil types map in the southwest of Sweden is developed. The introduced GFNN architecture is supported by a generalized shunting neuron (GSN) model computing unit to increase the capability of nonlinear boundaries of classified patterns. The comparison conducted between known soil type classification charts, CPTu interpreting procedures, and the outcomes of the GFNN model indicates acceptable accuracy in estimating complex soil types. The results show that the predictability of the GFNN system offers a valuable tool for the purpose of soil type pattern classifications and providing soil profiles.

No abstract

No abstract

Iran is an active seismic region and frequent earthquakes and because of the active faults, often leads to severe casualties caused by structural destruction. Earthquake damage is commonly controlled by three interacting factors, source and path characteristics, local geological and geotechnical conditions and type of the structures. Obviously, all of this would require analysis and presentation of a large amount of geological, seismological and geotechnical data. In this paper, nonlinear geotechnical seismic hazard analysis considering the local site effects was executed and the soil liquefaction potential analysis has been evaluated for the Nemat Abad earth dam in Hamedan province of Iran because of its important socioeconomic interest and its location. Liquefaction susceptibility mapping is carried out using a decisional flow chart for evaluation of earthquake-induced effects, based on available data such as geological, groundwater depth, seismotectonic, sedimentary features, in situ, field and laboratory geotechnical parameters. A series model tests were conducted and then on base of the achieved data the idealized soil profile constructed. A C # GUI computer code "NLGSS_Shahri" was Generate, developed and then employed to evaluate the variation of shear modulus and damping ratio with shear strain amplitude to assess their effects on site response. To verify and validate the methodology, the obtained results of the generated code were compared to several known applicable procedures. It showed that computed output of this code has good and suitable agreement with other known applicable procedures.

No abstract