基于自组织图法的土壤导电性随机估计

IF 3.3 2区工程技术 Q2 ENGINEERING, GEOLOGICAL

Soils and Foundations Pub Date : 2025-05-21 DOI:10.1016/j.sandf.2025.101601

Kyeongmo Koo, Hyunki Kim

{"title":"基于自组织图法的土壤导电性随机估计","authors":"Kyeongmo Koo, Hyunki Kim","doi":"10.1016/j.sandf.2025.101601","DOIUrl":null,"url":null,"abstract":"<div><div>This study proposes an unsupervised Self-Organizing Map (SOM) approach to enhance saturated hydraulic conductivity (<em>k<sub>sat</sub></em>) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based <em>k<sub>sat</sub></em> estimation model is optimized based on map size and feature selection, then compared with seven empirical equations and three supervised machine learning models. Unlike the other methods, the SOM-based approach provides a probabilistic distribution of <em>k<sub>sat</sub></em>, enabling reliability-based design-value determination. Moreover, refining input features particularly by including specific surface area and Kozeny–Carman derived formulas improves accuracy and mitigates bias by the model features, especially in fine-grained soils.</div></div>","PeriodicalId":21857,"journal":{"name":"Soils and Foundations","volume":"65 3","pages":"Article 101601"},"PeriodicalIF":3.3000,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method\",\"authors\":\"Kyeongmo Koo, Hyunki Kim\",\"doi\":\"10.1016/j.sandf.2025.101601\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This study proposes an unsupervised Self-Organizing Map (SOM) approach to enhance saturated hydraulic conductivity (<em>k<sub>sat</sub></em>) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based <em>k<sub>sat</sub></em> estimation model is optimized based on map size and feature selection, then compared with seven empirical equations and three supervised machine learning models. Unlike the other methods, the SOM-based approach provides a probabilistic distribution of <em>k<sub>sat</sub></em>, enabling reliability-based design-value determination. Moreover, refining input features particularly by including specific surface area and Kozeny–Carman derived formulas improves accuracy and mitigates bias by the model features, especially in fine-grained soils.</div></div>\",\"PeriodicalId\":21857,\"journal\":{\"name\":\"Soils and Foundations\",\"volume\":\"65 3\",\"pages\":\"Article 101601\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2025-05-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Soils and Foundations\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0038080625000356\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, GEOLOGICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Soils and Foundations","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0038080625000356","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}

引用次数: 0

摘要

本研究提出一种无监督自组织图（SOM）方法来提高饱和水力导电性（ksat）的估计。利用佛罗里达州FLSOIL数据库中6,487个土壤样本，基于地图大小和特征选择对基于som的ksat估计模型进行了优化，并与7个经验方程和3个监督机器学习模型进行了比较。与其他方法不同，基于som的方法提供了ksat的概率分布，从而实现了基于可靠性的设计值确定。此外，细化输入特征，特别是包括比表面积和Kozeny-Carman推导公式，提高了准确性，减轻了模型特征的偏差，特别是在细粒土壤中。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method

This study proposes an unsupervised Self-Organizing Map (SOM) approach to enhance saturated hydraulic conductivity (k_sat) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based k_sat estimation model is optimized based on map size and feature selection, then compared with seven empirical equations and three supervised machine learning models. Unlike the other methods, the SOM-based approach provides a probabilistic distribution of k_sat, enabling reliability-based design-value determination. Moreover, refining input features particularly by including specific surface area and Kozeny–Carman derived formulas improves accuracy and mitigates bias by the model features, especially in fine-grained soils.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Soils and Foundations 工程技术-地球科学综合

CiteScore

6.40

自引率

8.10%

发文量

审稿时长

5 months

期刊介绍： Soils and Foundations is one of the leading journals in the field of soil mechanics and geotechnical engineering. It is the official journal of the Japanese Geotechnical Society (JGS)., The journal publishes a variety of original research paper, technical reports, technical notes, as well as the state-of-the-art reports upon invitation by the Editor, in the fields of soil and rock mechanics, geotechnical engineering, and environmental geotechnics. Since the publication of Volume 1, No.1 issue in June 1960, Soils and Foundations will celebrate the 60th anniversary in the year of 2020. Soils and Foundations welcomes theoretical as well as practical work associated with the aforementioned field(s). Case studies that describe the original and interdisciplinary work applicable to geotechnical engineering are particularly encouraged. Discussions to each of the published articles are also welcomed in order to provide an avenue in which opinions of peers may be fed back or exchanged. In providing latest expertise on a specific topic, one issue out of six per year on average was allocated to include selected papers from the International Symposia which were held in Japan as well as overseas.