GIS-Based Soft Computing Models for Landslide Susceptibility Mapping: A Case Study of Pithoragarh District, Uttarakhand State, India

Tran, Tu Anh; Dam, Nguyen Duc; Jalal, Fazal E.; Al‐Ansari, Nadhir; Ho, Lanh Si; Phong, Tran Van; Iqbal, Mudassir; Le, Hiep Van; Nguyen, Hanh Bich Thi; Prakash, Indra; Pham, Binh Thai

doi:10.1155/2021/9914650

Cited by 23 publications

(13 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that the random subspace-based extra tree (RSS-ET) model outperforms the random subspace-based (RSS-REPT) and reduced error pruning tree (REPT) models regardless of the performance index is used. Moreover, the prediction accuracy of the random subspace-based extra tree (RSS-ET) model (R 2 = 0.968) developed in this research is higher than the prediction accuracy of the soft computing models currently reported in the literature [49,[104][105][106][107].…”

Section: Comparison Of Developed Modelsmentioning

confidence: 56%

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

et al. 2021

Self Cite

View full text Add to dashboard Cite

The California Bearing Ratio (CBR) is an important index for evaluating the bearing capacity of pavement subgrade materials. In this research, random subspace optimization-based hybrid computing models were trained and developed for the prediction of the CBR of soil. Three models were developed, namely reduced error pruning trees (REPTs), random subsurface-based REPT (RSS-REPT), and RSS-based extra tree (RSS-ET). An experimental database was compiled from a total of 214 soil samples, which were classified according to AASHTO M 145, and included 26 samples of A-2-6 (clayey gravel and sand soil), 3 samples of A-4 (silty soil), 89 samples of A-6 (clayey soil), and 96 samples of A-7-6 (clayey soil). All CBR tests were performed in soaked conditions. The input parameters of the models included the particle size distribution, gravel content (G), coarse sand content (CS), fine sand content (FS), silt clay content (SC), organic content (O), liquid limit (LL), plastic limit (PL), plasticity index (PI), optimum moisture content (OMC), and maximum dry density (MDD). The accuracy of the developed models was assessed using numerous performance indexes, such as the coefficient of determination, relative error, MAE, and RMSE. The results show that the highest prediction accuracy was obtained using the RSS-based extra tree optimization technique.

show abstract

Section: Comparison Of Developed Modelsmentioning

confidence: 56%

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The paradigm shift in regression models using machine learning significantly contributes to solving engineering problems [ 67 , 68 , 69 , 70 , 71 ]. The current study investigated the effect of changing dosages of NGPs on the mechanical characteristics of concrete.…”

Section: Discussionmentioning

confidence: 99%

Performance Evaluation of Cementitious Composites Incorporating Nano Graphite Platelets as Additive Carbon Material

et al. 2021

Self Cite

View full text Add to dashboard Cite

Nano graphite platelets (NGPs) belong to the carbon family and have a huge impact on the construction industry. NGPs are used as multi-functional fillers and have the potential to develop reinforcing within cementitious composites. In this paper, NGPs were incorporated in cementitious composites to investigate the effects of NGPs on the fresh, mechanical, durability, and microstructural properties of concrete. Five mixes were prepared with intrusion of NGPs (0%, 0.5%, 1.5%, 3%, and 5% by weight of cement). The properties studied involved workability, air content, hardened density, compressive strength, tensile strength, flexural strength, sorptivity, ultrasonic pulse velocity (UPV), water absorption, and external sulfate attack. The workability and percent air content decrease by 22.5% and 33.8%, respectively, for concrete with 5% NGPs compared to the control mix. The specimens containing 5% of NGPs revealed the hardened density, compressive, tensile, and flexural strength to increase by 11.4%, 38.5%, 31.6%, and 44.34%, respectively, compared to the control mix. The results revealed that the incorporation of 5%NGPs in cementitious composites reduces the sorptivity and water absorption by 32.2% and 73.9%, respectively, whereas, it increases the UPV value by 7.5% compared to the control mix. Furthermore, the incorporation of NGPs provided better resistance against external sulfate attacks. SEM–EDX spectroscopy was carried out to investigate its microstructural analysis.

show abstract

“…With the advancement in artificial intelligence (AI), wide variety of civil engineering problems are solved using AI [38][39][40][41][42][43][44][45]. AI models shall be developed that can product the mechanical and durability properties of rubberized concrete.…”

Section: Discussionmentioning

confidence: 99%

Experimental Investigation of the Stress–Strain Behavior and Strength Characterization of Rubberized Reinforced Concrete

et al. 2022

Self Cite

View full text Add to dashboard Cite

Due to the rapid increase in population, the use of automobile vehicles increases day by day, which causes a considerable increase in the waste tires produced worldwide. Research studies are in progress to utilize scrap tires and waste rubber material in several fields to cater the pollution problems in a sustainable and environmentally friendly manner. In this research, the shredded waste tires were used in concrete to replace fine aggregates in different percentages. The fine aggregates in the rubberized concrete were replaced 10%, 15%, and 20% by rubber. The stress–strain behavior of the concrete models is then determined and compared with the already established analytical models, i.e., Modified Kent and Park Model, Mander’s model, and Razvi and Saatcioglu Model. A total of 12 standard concrete cylinders and 18 models of each type of concrete, i.e., normal concrete, reinforced rubberized concrete with 10%, 15%, and 20% addition of rubber, were fabricated. Specimens fabricated in each replacement of rubber were laterally confined, employing 3 in (76 mm) and 6 in (152 mm) c/c tie spacing. The model and cylinders were subjected to uni-axial compression tests using Universal Testing Machine (UTM). The drop in compressive strength, stress–strain constitutive law, strain limits, and overall behavior of the rubberized reinforced concrete were explored experimentally. The results were then compared with the analytical results of the established models. The research can help explore the possible future for the use of rubberized concrete for the potential application as a structural material.

show abstract

GIS-Based Soft Computing Models for Landslide Susceptibility Mapping: A Case Study of Pithoragarh District, Uttarakhand State, India

Cited by 23 publications

References 93 publications

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

On Random Subspace Optimization-Based Hybrid Computing Models Predicting the California Bearing Ratio of Soils

Performance Evaluation of Cementitious Composites Incorporating Nano Graphite Platelets as Additive Carbon Material

Experimental Investigation of the Stress–Strain Behavior and Strength Characterization of Rubberized Reinforced Concrete

Contact Info

Product

Resources

About