Swelling Potential of Kansas Soils: Modeling and Validation Using Artificial Neural Network Reliability Approach

Abstract

Determination of the swell potential of a troublesome soil can only be made possible through the use of systematic methods for identifying, testing, and evaluating that potential. For proper evaluation of the severity of swelling for such soils, an accurate soil swell potential assessment method is warranted. To address this key issue, a two-phase research study was performed to develop combined artificial neural network and reliability-based soil swell prediction models. In Phase 1, a reasonable-sized database representing 514 swell soil tests retrieved from over 51 different projects in Kansas was used to develop both neural network–based (NNB) and statistical-based (SB) swell potential prediction models. Direct comparison of results obtained showed that NNB models provide significant improvements in prediction accuracy over their SB counterparts. In the second phase, predictions obtained using the developed NNB models along with the available experimental database were used to produce reliability (probability) factor matrices, which are used to assign a specific confidence level to predictions obtained via NNB models in order to classify the soil under consideration as a swelling or nonswelling type.

Get full access to this article

View all access options for this article.

References

Coduto

D. P.

Foundation Design: Principles and Practices. Prentice-Hall, Englewood Cliffs, N.J., 1994.

Jones

D. E.

, and Jones

K. A.

. Treating Expansive Soils. Civil Engineering, ASCE, Vol. 57, No. 8, 1987.

Seed

H. B.

, Woodward

R. J.

, and Lundgren

. Prediction of Swelling Potential for Compacted Clays. Journal of the Soil Mechanics and Foundations Division, ASCE, Vol. 88, No. SM3, 1962, pp. 53–89.

Gisi

A. J.

, and Bandy

S. S.

. Swell Prediction of Natural Soils in Kansas. Memorandum. Kansas Department of Transportation, 1980.

Najjar

Y. M.

, and Basheer

I. A.

. Modeling of Soil Swelling via Regression and Neural Network Approaches: Final Report. Report KS 98-1. Kansas Department of Transportation, 1998.

Najjar

Y. M.

, Basheer

I. A.

, and McReynolds

R. L.

. Neuronet-Based Approach to Modeling the Durability of Aggregate in Concrete Pavement Construction. In Transportation Research Record 1582, TRB, National Research Council, Washington, D.C., 1997, pp. 29–33.

Najjar

Y. M.

, Basheer

I. A.

, and Naouss

W. A.

. On the Identification of Compaction Characteristics by Neuronets. Journal of Computers and Geotechnics, Vol. 18, No. 3, 1996, pp. 167–187.

Najjar

Y. M.

, Basheer

I. A.

, and McReynolds

L. R.

. Neural Modeling of Kansas Soil Swelling. In Transportation Research Record 1526, TRB, National Research Council, Washington, D.C., 1996, pp. 14–19.

Najjar

Y. M.

, and Basheer

I. A.

. Utilizing Computational Neural Networks for Evaluating the Permeability of Compacted Clay Liners. Geotechnical and Geological Engineering, Vol. 14, No. 3, 1996, pp. 193–212.

10.

Basheer

I. A.

, Reddi

L. N.

, and Najjar

Y. M.

. Site Characterization by Neuronets: An Application to the Landfill Siting Problem. Ground Water, Vol. 34, No. 4, 1996, pp. 610–617.

11.

Najjar

Y. M.

, and Basheer

I. A.

. A Neural Network Approach for Site Characterization and Uncertainty Prediction. In Geotechnical Special Publication 58 ( Shackelford

C.D.

et al., eds.), ASCE, New York, 1996, Vol. 1, pp. 134–148.

12.

Basheer

, and Najjar

. Modeling Cyclic Constitutive Behavior by Neural Networks: Theoretical and Real Data. Proc., 12th ASCE Specialty Conference on Engineering Mechanics (CD-ROM), La Jolla, Calif., May 17–20, 1998, pp. 952–955.

13.

Ali

H. E.

, and Najjar

Y. M.

. Neuronet-Based Approach for Assessing Liquefaction Potential of Soils. In Transportation Research Record 1633, TRB, National Research Council, Washington, D.C., 1998, pp. 3–8.