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 (ksat) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based ksat estimation model is optimized based on map size and feature selection, then...

Full description

Saved in:
Bibliographic Details
Main Authors: Kyeongmo Koo, Hyunki Kim
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Soils and Foundations
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0038080625000356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426964481310720
author Kyeongmo Koo
Hyunki Kim
author_facet Kyeongmo Koo
Hyunki Kim
author_sort Kyeongmo Koo
collection DOAJ
description This study proposes an unsupervised Self-Organizing Map (SOM) approach to enhance saturated hydraulic conductivity (ksat) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based ksat 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 ksat, 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.
format Article
id doaj-art-7f60ba5be782456cba3fb0859140f8bf
institution Kabale University
issn 2524-1788
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Soils and Foundations
spelling doaj-art-7f60ba5be782456cba3fb0859140f8bf2025-08-20T03:29:10ZengElsevierSoils and Foundations2524-17882025-06-0165310160110.1016/j.sandf.2025.101601Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map methodKyeongmo Koo0Hyunki Kim1Dept. of Civil & Environmental Engineering, Kookmin University, South KoreaCorresponding author.; Dept. of Civil & Environmental Engineering, Kookmin University, South KoreaThis study proposes an unsupervised Self-Organizing Map (SOM) approach to enhance saturated hydraulic conductivity (ksat) estimation. Using the extensive FLSOIL database of 6,487 soil samples from Florida, the SOM-based ksat 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 ksat, 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.http://www.sciencedirect.com/science/article/pii/S0038080625000356Hydraulic ConductivitySelf-Organizing MapUnsupervised Machine LearningReliability
spellingShingle Kyeongmo Koo
Hyunki Kim
Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
Soils and Foundations
Hydraulic Conductivity
Self-Organizing Map
Unsupervised Machine Learning
Reliability
title Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
title_full Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
title_fullStr Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
title_full_unstemmed Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
title_short Stochastic estimation of soil hydraulic conductivity utilizing self-organizing map method
title_sort stochastic estimation of soil hydraulic conductivity utilizing self organizing map method
topic Hydraulic Conductivity
Self-Organizing Map
Unsupervised Machine Learning
Reliability
url http://www.sciencedirect.com/science/article/pii/S0038080625000356
work_keys_str_mv AT kyeongmokoo stochasticestimationofsoilhydraulicconductivityutilizingselforganizingmapmethod
AT hyunkikim stochasticestimationofsoilhydraulicconductivityutilizingselforganizingmapmethod