Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring

Laura Hernandez-Alpizar; Jose Andres Gomez-Mejia

doi:10.18845/tm.v39i5.8521

Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring

Laura Hernandez-Alpizar
, Jose Andres Gomez-Mejia

Research output: Contribution to journal › Article › peer-review

Original language	English
Pages (from-to)	276-284
Number of pages	9
Journal	Tecnologia En Marcha
Volume	39
DOIs	https://doi.org/10.18845/tm.v39i5.8521
State	Published - Feb 2026

Keywords

Random Forest
UV-Vis spectroscopy
XGBoost
Nitrate
Spectral interference
Water

Access to Document

10.18845/tm.v39i5.8521

Cite this

@article{d74ace142e7344ebb514e7fa20365459,

title = "Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring",

keywords = "Random Forest, UV-Vis spectroscopy, XGBoost, Nitrate, Spectral interference, Water",

author = "Laura Hernandez-Alpizar and Gomez-Mejia, \{Jose Andres\}",

year = "2026",

month = feb,

doi = "10.18845/tm.v39i5.8521",

language = "Ingl{\'e}s",

volume = "39",

pages = "276--284",

journal = "Tecnologia En Marcha",

issn = "0379-3982",

}

TY - JOUR

T1 - Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring

AU - Hernandez-Alpizar, Laura

AU - Gomez-Mejia, Jose Andres

PY - 2026/2

Y1 - 2026/2

KW - Random Forest

KW - UV-Vis spectroscopy

KW - XGBoost

KW - Nitrate

KW - Spectral interference

KW - Water

UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=tec-sibitec&SrcAuth=WosAPI&KeyUT=WOS:001712220000022&DestLinkType=FullRecord&DestApp=WOS_CPL

U2 - 10.18845/tm.v39i5.8521

DO - 10.18845/tm.v39i5.8521

M3 - Artículo

SN - 0379-3982

VL - 39

SP - 276

EP - 284

JO - Tecnologia En Marcha

JF - Tecnologia En Marcha

ER -

Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring

Keywords

Access to Document

Other files and links

Desarrollo de una plataforma tecnológica escalable y modular para el registro de variables físicas y químicas asociadas a la calidad y abundancia del agua potable

Cite this

Feature importance analysis for enhanced interpretability of spectrophotometric Machine Learning (ML) models in water quality monitoring

Keywords

Access to Document

Other files and links

Projects

Desarrollo de una plataforma tecnológica escalable y modular para el registro de variables físicas y químicas asociadas a la calidad y abundancia del agua potable

Cite this