scholarly journals Atterberg Limits Prediction Comparing SVM with ANFIS Model

2017 ◽  
Vol 2 (1) ◽  
pp. 20
Author(s):  
Mohammad Murtaza Sherzoy
Keyword(s):  
Grain Size ◽  
Size Distribution ◽  
Grain Size Distribution ◽  
Liquid Limit ◽  
Plasticity Index ◽  
Atterberg Limits ◽  
Support Vector ◽  
Plastic Limit ◽  
Anfis Model ◽  
Svm Model

Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy inference Systems (ANFIS) both analytical methods are used to predict the values of Atterberg limits, such as the liquid limit, plastic limit and plasticity index. The main objective of this study is to make a comparison between both forecasts (SVM & ANFIS) methods. All data of 54 soil samples are used and taken from the area of Peninsular Malaysian and tested for different parameters containing liquid limit, plastic limit, plasticity index and grain size distribution and were. The input parameter used in for this case are the fraction of grain size distribution which are the percentage of silt, clay and sand. The actual and predicted values of Atterberg limit which obtained from the SVM and ANFIS models are compared by using the correlation coefficient R2 and root mean squared error (RMSE) value.  The outcome of the study show that the ANFIS model shows higher accuracy than SVM model for the liquid limit (R2 = 0.987), plastic limit (R2 = 0.949) and plastic index (R2 = 0966). RMSE value that obtained for both methods have shown that the ANFIS model has represent the best performance than SVM model to predict the Atterberg Limits as a whole.

scholarly journals Prediction of Shear Strength of Soil Using Direct Shear Test and Support Vector Machine Model

2020 ◽  
Vol 14 (1) ◽  
pp. 41-50 ◽  
Author(s):  
Hai-Bang Ly ◽  
Binh Thai Pham
Keyword(s):  
Support Vector Machine ◽  
Shear Strength ◽  
Moisture Content ◽  
Mean Squared Error ◽  
Learning Algorithm ◽  
Liquid Limit ◽  
Support Vector ◽  
Plastic Limit ◽  
Svm Model ◽  
Soil Shear Strength

Background: Shear strength of soil, the magnitude of shear stress that a soil can maintain, is an important factor in geotechnical engineering. Objective: The main objective of this study is dedicated to the development of a machine learning algorithm, namely Support Vector Machine (SVM) to predict the shear strength of soil based on 6 input variables such as clay content, moisture content, specific gravity, void ratio, liquid limit and plastic limit. Methods: An important number of experimental measurements, including more than 500 samples was gathered from the Long Phu 1 power plant project’s technical reports. The accuracy of the proposed SVM was evaluated using statistical indicators such as the coefficient of correlation (R), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) over a number of 200 simulations taking into account the random sampling effect. Finally, the most accurate SVM model was used to interpret the prediction results due to Partial Dependence Plots (PDP). Results: Validation results showed that SVM model performed well for prediction of soil shear strength (R = 0.9 to 0.95), and the moisture content, liquid limit and plastic limit were found as the three most affecting features to the prediction of soil shear strength. Conclusion: This study might help in quick and accurate prediction of soil shear strength for practical purposes in civil engineering.

A Study of Adobes Made with No Usual Soils Concerning Grain Size Distribution Test

2017 ◽  
Vol 864 ◽  
pp. 346-350
Author(s):  
M.A.P. Rezende ◽  
R.C. Alves ◽  
E.V.M. Carrasco ◽  
J.N.R. Mantilla ◽  
M.A. Smits ◽  
...  
Keyword(s):  
Grain Size ◽  
Size Distribution ◽  
Grain Size Distribution ◽  
Clay Mineral ◽  
Building Material ◽  
Atterberg Limits ◽  
Soil Behavior ◽  
Mineral Structure

This article presents and discusses an adobe production with shows a clay/silt/sand proportion that is completely different from that recommended by most authors and construction associations. The main objective was to improve comprehension of earth behaviors as building material by studying these two atypical cases of adobe production. The soil was analyzed by different tests as the grain size distribution test and Atterberg limits. Adobe resistance was tested using a methodology proposed by Proterra network which was created by a group of researchers from different Iberian American laboratories. This methodology was used in Ph.D. thesis, too. The results show a soil with 1% clay and 65.1 silte and an average of resistance of 2.11 MPa for the adobes. These results show the importance of the clay mineral structure and the complexity of the soil behavior, indicating the need for additional studies.

scholarly journals Moisture retention and plasticity of highly calcareous soils in Egypt.

1976 ◽  
Vol 24 (1) ◽  
pp. 43-57
Author(s):  
W.P. Stakman ◽  
B.G. Bishay
Keyword(s):  
Particle Size ◽  
Particle Size Distribution ◽  
Size Distribution ◽  
Sandy Loam ◽  
Calcareous Soils ◽  
Liquid Limit ◽  
Plasticity Index ◽  
Plastic Limit ◽  
Moisture Retention ◽  
Unsaturated Condition

Particle size distribution, moisture retention curves and consistency limits were determined for six soils from northwestern Egypt. The soils contained 25-61% CaCO3 and attapulgite was the major clay mineral. In the clay and clay loam soils the CaCO3 was predominantly in the silt and clay fractions, in the sandy loam it was regularly distributed over the clay, silt and sand fractions and in the loamy sand it was mainly in the sand fraction. Decalcification shifted the particle size distribution to a coarser texture class and increased porosity and moisture content. Liquid limit and plasticity index increased with increasing clay and CaCO3 contents up to 40% clay and 35% CaCO3. The plastic limit stayed rather constant at increasing clay and CaCO3 contents. The liquid limit corresponded with suctions of pF 1.3-1.9 within the flex range from the saturated to the unsaturated condition of the pF curves. The plastic limit and the plasticity index corresponded with pF 2.1-3.0 and 2.6-3.8, respectively. (Abstract retrieved from CAB Abstracts by CABI’s permission)

Machine learning-based grain size mapping from satellite images 

2021 ◽  
Author(s):  
Giulia Marchetti ◽  
Simone Bizzi ◽  
Barbara Belletti ◽  
Barbara Lastoria ◽  
Stefano Mariani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Grain Size ◽  
Size Distribution ◽  
Grain Size Distribution ◽  
Satellite Images ◽  
Support Vector ◽  
Mapping Procedure ◽  
Bed Sediments ◽  
Size Classes ◽  
Sentinel 2

<p>A comprehensive understanding of river dynamics requires the quantitative knowledge of the grain size distribution of bed sediments and its variation across multiple temporal and spatial scales. Several techniques are already available for grain size assessment based on field and remotely sensed data. However, the existing methods permit to cover small areas and short time scale, thus the operational measurement of grain size distribution of river bed sediments at the catchment scale remains an open problem. A solution could be the use of satellite images but very limited investigations have been carried out so far on the use of satellite-based sub-pixel mapping of river characteristics relevant to ecohydraulic processes.</p><p>In this study, we propose a new approach to retrieve sub-pixel scale grain size classes information from Sentinel 2 imagery building upon a new image-based grain size mapping procedure. Four Italian gravel-bed rivers featuring different morphology were selected to conduct UAV acquisitions and extract ground truth grain size data from the near-ground images, by photo-sieving techniques. We generated grain size maps at the resolution of 2 cm on river bars in each study site by exploiting image texture measurements, and subsequently resampled and co-registered the grain size maps with Sentinel 2 data resolution.</p><p>Relationships between the grain sizes measured and the reflectance values in Sentinel 2 imagery - available in 11 bands super resolved at 10 m resolution – were analyzed. Based on these, our first results show statistically significant predictive models (cross validation results: MAE of 3.38 ± 13.4 mm and R<sup>2</sup>=0.48) by using a machine learning framework (Support Vector Machine) to retrieve grain size classes from reflectance data.</p><p>Our proposed approach based on freely available satellite data calibrated by low-cost automated drone technology can provide reasonably accurate estimates of surface grain size for bar sediments in medium to large river channels, over lengths of hundreds of kilometers. Moreover, the proposed methodology is easily replicable to other natural environments where an extensive grain size distribution assessment is crucial to understand geomorphic processes, thus providing a new technique for collecting such precious data and support studies of landscape evolution.</p>

scholarly journals Prediction of Shear Strength of Soil Using Direct Shear Test and Support Vector Machine Model

2020 ◽  
Vol 14 (1) ◽  
pp. 268-277 ◽  
Author(s):  
Hai-Bang Ly ◽  
Binh Thai Pham
Keyword(s):  
Support Vector Machine ◽  
Shear Strength ◽  
Moisture Content ◽  
Mean Squared Error ◽  
Learning Algorithm ◽  
Liquid Limit ◽  
Support Vector ◽  
Plastic Limit ◽  
Svm Model ◽  
Soil Shear Strength

Background: Shear strength of soil, the magnitude of shear stress that a soil can maintain, is an important factor in geotechnical engineering. Objective: The main objective of this study is dedicated to the development of a machine learning algorithm, namely Support Vector Machine (SVM) to predict the shear strength of soil based on 6 input variables such as clay content, moisture content, specific gravity, void ratio, liquid limit and plastic limit. Methods: An important number of experimental measurements, including more than 500 samples was gathered from the Long Phu 1 power plant project’s technical reports. The accuracy of the proposed SVM was evaluated using statistical indicators such as the coefficient of correlation (R), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) over a number of 200 simulations taking into account the random sampling effect. Finally, the most accurate SVM model was used to interpret the prediction results due to Partial Dependence Plots (PDP). Results: Validation results showed that SVM model performed well for prediction of soil shear strength (R = 0.9 to 0.95), and the moisture content, liquid limit and plastic limit were found as the three most affecting features to the prediction of soil shear strength. Conclusion: This study might help in quick and accurate prediction of soil shear strength for practical purposes in civil engineering.

Correlations between P-wave velocity and Atterberg limits of cohesive soils

2005 ◽  
Vol 42 (2) ◽  
pp. 673-677 ◽  
Author(s):  
Mustafa Fener ◽  
Sair Kahraman ◽  
Yakup Bay ◽  
Osman Gunaydin
Keyword(s):  
Wave Velocity ◽  
Soil Type ◽  
Liquid Limit ◽  
P Wave ◽  
Plasticity Index ◽  
Atterberg Limits ◽  
Cohesive Soils ◽  
Plastic Limit ◽  
Velocity Measurements ◽  
P Wave Velocity

Undisturbed and disturbed samples of cohesive soils were collected from eight different locations to investigate the possibility of estimating the Atterberg limits of cohesive soils from P-wave velocity measurements. Each soil type was classified according to the Unified Soil Classification System, and then Atterberg limits of soils were determined and P-wave velocity measurements carried out on the undisturbed samples of each soil type. P-wave velocity values were correlated with the corresponding values of Atterberg limits. It was found that liquid limit, plastic limit, and plasticity index exhibit good correlations with P-wave velocity. The relations follow a logarithmic function. Liquid limit, plastic limit, and plasticity index decrease with an increase in P-wave velocity. In addition, liquid limit, plastic limit, and plasticity index exhibit very good correlations with the ratio of P-wave velocity to water content. Liquid limit, plastic limit, and plasticity index decrease logarithmically with an increase in the ratio of P-wave velocity to water content. It can be concluded that the Atterberg limits of cohesive soils can be predicted from P-wave velocity measurements for preliminary investigations. The developed equations have some limitations and further study is required in this area.Key words: Atterberg limits, cohesive soils, P-wave velocity, regression analysis.

Sign in / Sign up

Export Citation Format

Share Document