Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning

Mehvish Bilal; Zaher Mundher Yaseen; Syed Masiur Rahman

doi:10.1109/FET68771.2026.11601220

Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning

Mehvish Bilal^*
, Zaher Mundher Yaseen
, Syed Masiur Rahman

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Coastal water quality monitoring is essential for effective marine ecosystem management; however, it is often constrained by sparse observations and high monitoring costs. This study examines the application of AlphaEarth embeddings in integration with in-situ measurements to predict Total Nitrogen (TN) concentrations in coastal waters using a data-driven machine learning model. Multiple regression models were systematically evaluated using the LazyPredict framework, and the Extra Trees Regressor was identified as the best-performing model. The selected model achieved strong predictive performance, with a coefficient of determination (R²) of 0.874.

Original language	English
Title of host publication	2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798319518866
DOIs	https://doi.org/10.1109/FET68771.2026.11601220
State	Published - 2026

Publication series

Name	2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026

Bibliographical note

Publisher Copyright:
© 2026 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 6 Clean Water and Sanitation
SDG 14 Life Below Water

Keywords

AlphaEarth Embeddings
Coastal Water Quality
Machine Learning Models
Total Nitrogen

ASJC Scopus subject areas

Industrial and Manufacturing Engineering
Energy Engineering and Power Technology
Civil and Structural Engineering
Artificial Intelligence

Access to Document

10.1109/FET68771.2026.11601220

Cite this

Bilal, M., Yaseen, Z. M., & Rahman, S. M. (2026). Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning. In 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026 (2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FET68771.2026.11601220

Bilal, Mehvish ; Yaseen, Zaher Mundher ; Rahman, Syed Masiur. / Coastal Water Quality Modelling Using AlphaEarth Embeddings : Insights from the LazyPredict-Based Machine Learning. 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026. Institute of Electrical and Electronics Engineers Inc., 2026. (2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026).

@inproceedings{b5686c8fd4e94106a7961f85c28c4aec,

title = "Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning",

abstract = "Coastal water quality monitoring is essential for effective marine ecosystem management; however, it is often constrained by sparse observations and high monitoring costs. This study examines the application of AlphaEarth embeddings in integration with in-situ measurements to predict Total Nitrogen (TN) concentrations in coastal waters using a data-driven machine learning model. Multiple regression models were systematically evaluated using the LazyPredict framework, and the Extra Trees Regressor was identified as the best-performing model. The selected model achieved strong predictive performance, with a coefficient of determination (R2) of 0.874.",

keywords = "AlphaEarth Embeddings, Coastal Water Quality, Machine Learning Models, Total Nitrogen",

author = "Mehvish Bilal and Yaseen, \{Zaher Mundher\} and Rahman, \{Syed Masiur\}",

note = "Publisher Copyright: {\textcopyright} 2026 IEEE.",

year = "2026",

doi = "10.1109/FET68771.2026.11601220",

language = "English",

series = "2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026",

address = "United States",

}

Bilal, M, Yaseen, ZM & Rahman, SM 2026, Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning. in 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026. 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/FET68771.2026.11601220

Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning. / Bilal, Mehvish; Yaseen, Zaher Mundher ; Rahman, Syed Masiur.
2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026. Institute of Electrical and Electronics Engineers Inc., 2026. (2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Coastal Water Quality Modelling Using AlphaEarth Embeddings

T2 - Insights from the LazyPredict-Based Machine Learning

AU - Bilal, Mehvish

AU - Yaseen, Zaher Mundher

AU - Rahman, Syed Masiur

PY - 2026

Y1 - 2026

N2 - Coastal water quality monitoring is essential for effective marine ecosystem management; however, it is often constrained by sparse observations and high monitoring costs. This study examines the application of AlphaEarth embeddings in integration with in-situ measurements to predict Total Nitrogen (TN) concentrations in coastal waters using a data-driven machine learning model. Multiple regression models were systematically evaluated using the LazyPredict framework, and the Extra Trees Regressor was identified as the best-performing model. The selected model achieved strong predictive performance, with a coefficient of determination (R2) of 0.874.

AB - Coastal water quality monitoring is essential for effective marine ecosystem management; however, it is often constrained by sparse observations and high monitoring costs. This study examines the application of AlphaEarth embeddings in integration with in-situ measurements to predict Total Nitrogen (TN) concentrations in coastal waters using a data-driven machine learning model. Multiple regression models were systematically evaluated using the LazyPredict framework, and the Extra Trees Regressor was identified as the best-performing model. The selected model achieved strong predictive performance, with a coefficient of determination (R2) of 0.874.

KW - AlphaEarth Embeddings

KW - Coastal Water Quality

KW - Machine Learning Models

KW - Total Nitrogen

UR - https://www.scopus.com/pages/publications/105046136333

U2 - 10.1109/FET68771.2026.11601220

DO - 10.1109/FET68771.2026.11601220

M3 - Conference contribution

AN - SCOPUS:105046136333

T3 - 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026

BT - 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bilal M, Yaseen ZM , Rahman SM. Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning. In 2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026. Institute of Electrical and Electronics Engineers Inc. 2026. (2026 International Conference on Frontiers of Engineering and Emerging Technologies, FET 2026). doi: 10.1109/FET68771.2026.11601220

Coastal Water Quality Modelling Using AlphaEarth Embeddings: Insights from the LazyPredict-Based Machine Learning

Abstract

Publication series

Bibliographical note

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this