Mining and analysis of multiple association rules between the Xining loess collapsibility and physical parameters

Abstract

Collapsibility determination in loess area is expensive, and it also requires a large amount of experimentation. This paper aims to find the association rules between physical parameters and collapsibility of the loess in Xining through the method of data mining, so to help researchers predict the collapsibility of loess. Related physical parameters of loess collapsibility, collected from 1039 samples, involve 13 potential influence factors. According to Grey Relational Analysis, the key influence factors that lead to collapsing are identified from these potential influence factors. Subsequently, take the key influence factors, δs (coefficient of collapsibility) and δzs (coefficient of collapsibility under overburden pressure) as input items, and use the Apriori algorithm to find multiple association rules between them. Then, through analysing the results of association rules between these key influence factors and collapsibility, the evaluation criteria for collapsibility in this area is proposed, which can be used to simplify the workload of determining collapsibility. Finally, based on these research results, recommendations for projects construction were made to ensure the safety of construction in the area.

Water Sensitivity and Structural Properties of Loess

“…When K 0 < 0.4, the collapsibility coefficient measured using the triaxial method is generally more significant than the confining-compression test. Conversely, when K 0 ≥ 0.4, the collapsibility coefficient measured using the triaxial method is generally smaller than the confining-compression test [42]. This experiment also proves this viewpoint.…”

Collapsible characteristics and prediction model of remodeled loess

“…There is a correlation between the collapsibility of loess and its dry density (Chen et al 2019), water content (Xing et al 2019;Wang et al 2021), salt content (Xu et al 2020), stress state (Munoz et al 2011;, and stress path (Jia et al 2019). The analysis of a large number of sample data confirmed the correlation rules between the collapsible deformation and various physical parameters (Li et al 2021), in which the saturation, density and porosity ratio were the main influencing factors.…”

“…Statistics (Zhang et al 2022), data mining (Li et al 2021), and machine learning (Sahand et al 2023) were also utilized to analyze the relationship between loess collapsible deformation and various factors, and to develop prediction models for loess collapsibility coefficient, which were important for understanding and predicting loess collapsible behaviors. Most existing prediction models (Li et al 2023;Hosseinpour-Zarnaq et al 2023;Anton Konurin Natural Hazards et al 2023) require extensive sample data for support.…”

Early detection of potential landslides along high‐speed railway lines: A pressing issue

“…Furthermore, the region is characterized by active tectonic movements and poor structural stability of slope rock-soil mass, which present additional internal conditions for landslides (An et al, 2021). The climate is plateau continental, with an average annual temperature of 7.6 C and an average annual precipitation of about 380 mm, which falls mainly from June to September (Li et al, 2021). However, influenced by weather originating in the Pacific Subtropics, August 2022 experienced frequent rainstorms and a significant increase in precipitation (Wang et al, 2023).…”