High performance prediction of soil compaction parameters using multi expression programming

Wang, Hanlin; Yin, Zhen‐Yu

doi:10.1016/j.enggeo.2020.105758

Cited by 109 publications

(44 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mean and standard deviation for MoPesm and laboratory tests were similar. MoPesm predictions had a MAPE of 2,57%, a RMSE of 0,585, a R of 0,873, and a R 2 of 0,763, a very acceptable performance according to Wang and Yin (2020), to whom a high R 2 and low MAPE and RMSE indicate that a model has a higher precision, and to Karimpour-Fard et al (2019), who considered a R 2 above 0,70 as acceptable, labeling such model as "strong".…”

Section: Resultsmentioning

confidence: 99%

“…The results showed that the variation between experimental and predicted data was within a confidence interval of ± 2,5% for γ d, max and ± 9,5% for OMC. Wang and Yin (2020) developed a model using multi expression programming (MEP), a method of genetic programming, and data comprising a wide range of soil types from previously published studies. Their model was considered reliable (R 2 >0,85), even for high-plasticity and coarse-grained soils, which did not figure among the soil types analyzed in previous studies; and, although their results were extremely favorable, the required high-end computational tools somewhat lost track of the simplicity present in other models, which yielded as fair predictions and could make a difference in the face of time constraints and the unavailability of a more complex software apparatus.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Empirical Models to Predict Compaction Parameters for Soils in the State of Ceará, Northeastern Brazil

et al. 2021

View full text Add to dashboard Cite

This work developed prediction models for maximum dry unit weight (γd,max) and optimum moisture content (OMC) for compacted soils in Ceará, Brazil, ba M Winnie the Pooh sed on index and physical properties. The methodology included data from soils used in the construction of 15 dams in Ceará, with available information regarding laboratory tests of interest. Correlations were developed using non-linear regression, from 169 laboratory results (83 for training and 86 for validating the models), which presented a R2 of 0,763 for MoPesm (prediction model for γd,max) and 0,761 for MoTuo (model for OMC). A posteriori, the same physical indexes used to train and validate MoPesm and MoTuo were used as inputs of other prediction models available in the literature, whose outputs differed considerably from laboratory results for the evaluated soils. MoPesm and MoTuo were able to satisfactorily predict compaction parameters, with outputs close to those obtained in the laboratory for tested soil samples. Their performance justifies their use for predicting compaction parameters in geotechnical structures that use compacted soils when there are financial restraints, short timeframes, or unavailability of test equipment, particularly in early design stages and preliminary studies, before appropriate soil sampling and field investigation can be conducted, thus saving substantial time and financial resources.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Empirical Models to Predict Compaction Parameters for Soils in the State of Ceará, Northeastern Brazil

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As stated earlier, the MEP approach is among the most significant linear configurations of the genetic programming (GP) series since it has the ability to deliver simplistic mathematical formulae to forecast a particular prediction model [ 35 , 41 ]. Therefore, the formulization of the UCS kaolin and UCS BC soil was performed in the Multi-Expression Programming X (MEPX version 2021.08.28.0-beta) by incorporating experimental records, as shown in Table 3 .…”

Section: Methodsmentioning

confidence: 99%

“…In general, the governing parameters in MEP include subpopulation size and number, code length, function set, and crossover probability. Recently, this approach has gained greater applications in the geotechnical engineering field for addressing varied problems which include the prediction of compaction characteristics [ 34 , 35 ], compressive strengths [ 36 , 37 ], permeability and compressibility characteristics [ 38 ], deformation modulus [ 39 ], soil water characteristic curves, and peak ground acceleration [ 40 ]. However, attempts to generate models for the prediction of geotechnical characteristics of the contaminated soils are scarce.…”

Section: Introductionmentioning

confidence: 99%

Multi Expression Programming Model for Strength Prediction of Fly-Ash-Treated Alkali-Contaminated Soils

et al. 2022

View full text Add to dashboard Cite

Rapid industrialization is leading to the pollution of underground natural soil by alkali concentration which may cause problems for the existing expansive soil in the form of producing expanding lattices. This research investigates the effect of stabilizing alkali-contaminated soil by using fly ash. The influence of alkali concentration (2 N and 4 N) and curing period (up to 28 days) on the unconfined compressive strength (UCS) of fly ash (FA)-treated (10%, 15%, and 20%) alkali-contaminated kaolin and black cotton (BC) soils was investigated. The effect of incorporating different dosages of FA (10%, 15%, and 20%) on the UCSkaolin and UCSBC soils was also studied. Sufficient laboratory test data comprising 384 data points were collected, and multi expression programming (MEP) was used to create tree-based models for yielding simple prediction equations to compute the UCSkaolin and UCSBC soils. The experimental results reflected that alkali contamination resulted in reduced UCS (36% and 46%, respectively) for the kaolin and BC soil, whereas the addition of FA resulted in a linear rise in the UCS. The optimal dosage was found to be 20%, and the increase in UCS may be attributed to the alkali-induced pozzolanic reaction and subsequent gain of the UCS due to the formation of calcium-based hydration compounds (with FA addition). Furthermore, the developed models showed reliable performance in the training and validation stages in terms of regression slopes, R, MAE, RMSE, and RSE indices. Models were also validated using parametric and sensitivity analysis which yielded comparable variation while the contribution of each input was consistent with the available literature.

show abstract

“…But even so, the consistency parameter PL is a more important factor as well as the gradational one F c among the compaction parameters (MDD and OWC except for ODS) of soils. Recently, although Wang and Yin (2020) recommend highly the proposed equations of Nagaraj et al (2015) as the prediction models for MDD and OWC in the literature (see Seqs. 4 and 10 in Tables 2 and 3, respectively), judging from the results of this study with an extended range of index properties in Figs.…”

Section: Volcanic Cohesive Soilsmentioning

confidence: 99%

Improved dataset for establishing novel relationships between compaction characteristics and physical properties of soils

Shimobe

Karakan

Sezer

2021

Bull Eng Geol Environ

View full text Add to dashboard Cite

In the past, several studies were performed for assessment of compaction properties of different types of soils. A comprehensive evaluation of compaction parameters is essential for engineers working in practice. The main goals of compaction in landfills including highways and railways can be listed as reducing permeability and developing strength as well as enhancing the stability of soils. Literature includes various correlations proposed for establishing the link between the compaction properties of soils and Atterberg limits. Besides, many researchers performed laboratory studies to obtain correlations among soil index, strength, compression, and compaction characteristics of soils. In this study, in addition to authors' own data composed of compaction, strength, index, and consistency identifiers of sand-clay mixtures from three different types of sands (S1, S2, Q) and two types of clays (kaolinite and bentonite), a vast amount of data from past studies including tests on different types of soils around the world were also compiled. The global database was evaluated to propose novel correlative relationships among compaction characteristics, grain size distribution properties, and Atterberg limits. Proposed equations and relationships for estimation of compaction characteristics seem to be viable to use in practice.

show abstract

High performance prediction of soil compaction parameters using multi expression programming

Cited by 109 publications

References 77 publications

Empirical Models to Predict Compaction Parameters for Soils in the State of Ceará, Northeastern Brazil

Empirical Models to Predict Compaction Parameters for Soils in the State of Ceará, Northeastern Brazil

Multi Expression Programming Model for Strength Prediction of Fly-Ash-Treated Alkali-Contaminated Soils

Improved dataset for establishing novel relationships between compaction characteristics and physical properties of soils

Contact Info

Product

Resources

About