Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.

Accurate prediction of multi-dimensional water quality indicators is critical for sustainable water resource management, yet existing methods often fail to address the high-dimensional, nonlinear, and spatially correlated nature of data from heterogeneous IoT sensors. To overcome these limitations,...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Bo, Lv Junrui, Luo Xuegang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0326870
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850099876536254464
author Li Bo
Lv Junrui
Luo Xuegang
author_facet Li Bo
Lv Junrui
Luo Xuegang
author_sort Li Bo
collection DOAJ
description Accurate prediction of multi-dimensional water quality indicators is critical for sustainable water resource management, yet existing methods often fail to address the high-dimensional, nonlinear, and spatially correlated nature of data from heterogeneous IoT sensors. To overcome these limitations, we propose TGMHA (Tensor Decomposition and Gated Neural Network with Multi-Head Self-Attention), a novel hybrid model that integrates three key innovations: 1) Tensor-based Feature Extraction: We combine Standard Delay Embedding Transformation (SDET) with Tucker tensor decomposition to reconstruct raw time series into low-rank tensor representations, capturing latent spatio-temporal patterns while suppressing sensor noise. 2) Multi-Head Self-Attention for Inter-Indicator Dependencies: A multi-head self-attention mechanism explicitly models complex inter-dependencies among diverse water quality indicators (e.g., pH, dissolved oxygen, conductivity) via parallel feature subspace learning. 3) Efficient Long-Term Dependency Modeling: An encoder-decoder architecture with gated recurrent units (GRUs), optimized by adaptive rank selection, ensures efficient modeling of long-term dependencies without compromising computational performance. By unifying these components into an end-to-end trainable system, TGMHA surpasses conventional approaches in handling complex water quality dynamics, particularly in scenarios with missing data and nonlinear interactions. Rigorous evaluation against six state-of-the-art benchmarks confirms TGMHA's superior capability, offering a robust and interpretable paradigm for multi-sensor fusion and water quality forecasting in environmental informatics.
format Article
id doaj-art-86a63e3013714a42b5fd8dea73ff7b61
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-86a63e3013714a42b5fd8dea73ff7b612025-08-20T02:40:24ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032687010.1371/journal.pone.0326870Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.Li BoLv JunruiLuo XuegangAccurate prediction of multi-dimensional water quality indicators is critical for sustainable water resource management, yet existing methods often fail to address the high-dimensional, nonlinear, and spatially correlated nature of data from heterogeneous IoT sensors. To overcome these limitations, we propose TGMHA (Tensor Decomposition and Gated Neural Network with Multi-Head Self-Attention), a novel hybrid model that integrates three key innovations: 1) Tensor-based Feature Extraction: We combine Standard Delay Embedding Transformation (SDET) with Tucker tensor decomposition to reconstruct raw time series into low-rank tensor representations, capturing latent spatio-temporal patterns while suppressing sensor noise. 2) Multi-Head Self-Attention for Inter-Indicator Dependencies: A multi-head self-attention mechanism explicitly models complex inter-dependencies among diverse water quality indicators (e.g., pH, dissolved oxygen, conductivity) via parallel feature subspace learning. 3) Efficient Long-Term Dependency Modeling: An encoder-decoder architecture with gated recurrent units (GRUs), optimized by adaptive rank selection, ensures efficient modeling of long-term dependencies without compromising computational performance. By unifying these components into an end-to-end trainable system, TGMHA surpasses conventional approaches in handling complex water quality dynamics, particularly in scenarios with missing data and nonlinear interactions. Rigorous evaluation against six state-of-the-art benchmarks confirms TGMHA's superior capability, offering a robust and interpretable paradigm for multi-sensor fusion and water quality forecasting in environmental informatics.https://doi.org/10.1371/journal.pone.0326870
spellingShingle Li Bo
Lv Junrui
Luo Xuegang
Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
PLoS ONE
title Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
title_full Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
title_fullStr Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
title_full_unstemmed Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
title_short Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism.
title_sort multi dimensional water quality indicators forecasting from iot sensors a tensor decomposition and multi head self attention mechanism
url https://doi.org/10.1371/journal.pone.0326870
work_keys_str_mv AT libo multidimensionalwaterqualityindicatorsforecastingfromiotsensorsatensordecompositionandmultiheadselfattentionmechanism
AT lvjunrui multidimensionalwaterqualityindicatorsforecastingfromiotsensorsatensordecompositionandmultiheadselfattentionmechanism
AT luoxuegang multidimensionalwaterqualityindicatorsforecastingfromiotsensorsatensordecompositionandmultiheadselfattentionmechanism