Estimating the Unit Weight of Local Organic Soils from Laboratory Tests Using Artificial Neural Networks

Abstract

The estimation of the unit weight of soil is carried out using laboratory methods; however, it requires high-quality research material in the form of samples with undisturbed structures, the acquisition of which, especially in the case of organic soils, is extremely difficult, time-consuming and expensive. This paper presents a proposal to use artificial neural networks to estimate the unit weight of local organic soils as leading parameters in the process of checking the load capacity of subsoil, under a direct foundation in drained conditions, in accordance with current standards guidelines. The initial recognition of the subsoil, and the locating of organic soils at the Theological and Pastoral Institute in Rzeszow, was carried out using a mechanical cone penetration test (CPTM), using various interpretation criteria, and then, material for laboratory tests was obtained. The analysis of the usefulness of the artificial intelligence method, in this case, was based on data from laboratory tests. Standard multi-layer backpropagation networks were used to predict the soil unit weight based on two leading variables: the organic content LOIT and the natural water content w. The applied neural model provided reliable prediction results, comparable to the standard regression methods.

Determination of Relative Density and Degree of Saturation in Mineral Soils Based on In Situ Tests

“…Using the proposed dependencies to determine the relative density (D r ) in the case of fine-grained soils, the compaction index I s can also be determined as follows using and modifying the formula developed by Pisarczyk (1975Pisarczyk ( , 2015 [24][25][26] and the dependencies proposed herein:…”

“…-When examining the dependence of salinity on time, the amount of salinity decreases with soil drying but increases with the addition of water. modifying the formula developed by Pisarczyk (1975Pisarczyk ( , 2015 [ [24][25][26] and the dependencies proposed herein:…”

“…-When analyzing the dependence of temperature on time, daily temperature fluctuations may be noticed; the lowest was 20.4 °C, while the highest was 25.1 °C. modifying the formula developed by Pisarczyk (1975Pisarczyk ( , 2015 [ [24][25][26] and the dependencies proposed herein:…”

Estimation of standard penetration test value on cohesive soil using artificial neural network without data normalization

“…In the geotechnical field, there have been many studies using the capabilities of this ANN. Related researches such as soil composition [2], soil classification [3], soil compaction [4], bearing capacity [5], unit weight [6], shallow foundation bearing capacity [7]- [9], estimated settlement in shallow foundations [10]- [12], preconsolidation stress [13], electrical resistivity of soil [14], deformation of geogrid-reinforced soil structures [15], tunnel boring machine performance [16], estimating cohesion of limestone samples [17] and many other related studies.…”

Prediction of SPT value based on CPT data and soil properties using ANN with and without normalization

“…Several related studies such as predictions on foundation problems, that is prediction settlement of shallow foundation [7], axial capacity of pile foundation [8], pile drivability [9], pile bearing capacity [10], shaft and tip resistance concrete piles [11]. ANN has also been widely used to predict several physical and mechanical properties of soil such as prediction of soil classification [12], compaction [13], soil deformation [14], Compression coefficient value [15], compression index and compression ratio [16], bearing capacity [17], unit weight [18], compressive strength [19][20], recompression index [21], elastic settlement [22], soil layers [23], clay sensitivity [24], and electrical resistivity of soil [25]. In soil improvement, ANN has also been widely used such as slope stability [26][27] and soil stabilization [28].…”