A BOHB-optimized stacking ensemble approach for predicting the coefficient of compressibility and quantifying uncertainty of guilin lateritic clays

Tongtong Wang, Hanying Bai, Jinghe Li · 2026

Read A BOHB-optimized stacking ensemble approach for predicting the coefficient of compressibility and quantifying uncertainty of guilin lateritic clays by Tongtong Wang, Hanying Bai, Jinghe Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13451917.txt.

Description

Tongtong Wang, Hanying Bai, and Jinghe Li build in 2026 a stacked learning model that guesses how much a red clay soil will squash under load. That squash rate drives how much buildings settle, yet lab tests take a week or more and disturb the soil. The team trained on 454 data sets from Guilin, China, using plain soil measures such as water content.

A tuned stack of three boost models with a linear top beat each single model, with a test score near the top of the scale. Two inputs, a wetness index and water content, carried near all the weight, and their joint rise drove high squash. Map-style checks and repeat random runs held firm, with most doubt bands narrow.

Catalog record

CREATORTongtong Wang, Hanying Bai, Jinghe Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE88 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13451917

Browse the full library · About the Tower of Babel