To identify the unknown values of the parameters of Burger’s constitutive law, commonly used for the evaluation of the creep behavior of the soft soils, this paper demonstrates a procedure relying on the data obtained from multiple sensors, where each sensor is used to its best advantage. The geophysical, geotechnical, and unmanned aerial vehicle data are used for the development of a numerical model whose results feed into the custom-architecture neural network, which then provides information about on the complex relationships between the creep characteristics and soil displacements. By utilizing InSAR and GPS monitoring data, particle swarm algorithm identifies the most probable set of Burger’s creep parameters, eventually providing a reliable estimation of the long-term behavior of soft soils. The validation of methodology is conducted for the Oostmolendijk embankment in the Netherlands, constructed on the soft clay and peat layers. The validation results show that the application of the proposed methodology, which relies on multisensor data, can overcome the high cost and long duration issues of laboratory tests for the determination of the creep parameters and can provide reliable estimates of the long-term behavior of geotechnical structures constructed on soft soils@en

Knowledge of the fines content is necessary for all soil classification systems and an important factor in the evaluation of soil strength in liquefaction and seismic settlement analysis. This paper presents the application of cone penetration test, CPT data for estimating the soil fines content. The correlation can be used either as a first estimate of fines content (for example in the offshore environment) or to provide statistical information on the variation of fines content within a given area of interest (e.g. for a regional liquefaction study). The paper shows how field and laboratory test data were used with a neural network to correlate the CPT results and the fines content. Data from five site investigation locations across Northern Croatia were utilised. Verification of the approach is performed using field and lab test data from the Veliki vrh landslide.

@en

The 189.50 m long Bobova tunnel constructed in 2005 is located on the D404 state highway and passes under a part of the Vežica – Sušak town area in Rijeka. The overburden above the tunnel pipe is between 2 m to 18 m thick. The rock mass along the tunnel route is made up of karst deposits (transient carbonate breccia, dolomite and limestone interlinked with rudist limestones). Extensive geotechnical instrumentation was installed in the tunnel by researchers at the faculty of Civil Engineering at the University of Zagreb. This consisted of: measurements in the tunnel area from the ground surface using inclinometers for horizontal, and sliding micrometers for vertical soil displacements, measuring displacements around underground openings using sliding micrometers supplemented with scanning of the tunnel interior using laser scanners, and measuring the stress and deformations in elements of support complex by pressure cells and measuring anchors. Data collected during construction and in the twelve years in which the three-lane highway tunnel has been operational, presented in this paper reveal that deformations and stresses in Bobova tunnel have continued to increase with time. The possible role of the shotcrete lining, rock creep and rock-bolt corrosion in the ongoing deformations are discussed. The application of continuous monitoring data from instruments as inputs for numerical model training using a machine learning model, with the objective to improve the predictions of existing probabilistic failure models is considered. The ultimate aim of this work is to develop improved predictive maintenance plans.@en

Soil classification is a means of grouping soils into categories according to a shared set of properties or characteristics that will exhibit similar engineering behaviour under loading. Correctly classifying site conditions is an important, costly, and time-consuming process which needs to be carried out at every building site prior to the commencement of construction or the design of foundation systems. This paper presents a means of automating classification for fine-grained soils, using a feed-forward ANN (Artificial Neural Networks) and CPT (Cone Penetration Test) measurements. Thus representing a significant saving of both time and money streamlining the construction process. 216 pairs of laboratory results and CPT tests were gathered from five locations across Northern Croatia and were used to train, test, and validate the ANN models. The resultant Neural Networks were saved and were subjected to a further external verification using CPT data from the Veliki vrh landslide. A test site, which the model had not previously been exposed to. The neural network approach proved extremely adept at predicting both ESCS (European Soil Classification System) and USCS (Unified Soil Classification System) soil classifications, correctly classifying almost 90% of soils. While the soils that were incorrectly classified were only partially misclassified. The model was compared to a previously published model, which was compiled using accepted industry standard soil parameter correlations and was shown to be a substantial improvement, in terms of correlation coefficient, absolute average error, and the accuracy of soil classification according to both USCS and ESCS guidelines. The study confirms the functional link between CPT results, the percentage of fine particles FC, the liquid limit w_L and the plasticity index I_P. As the training database grows in size, the approach should make soil classification cheaper, faster and less labour intensive.

@en