Skip to main navigation Skip to search Skip to main content

Graph Attention Sensor Transformer for Industrial Emission Forecasting: A Comparative Study Against Classical and Deep Learning Baselines

  • Seoul National University of Science and Technology (SNUST)

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

Abstract

Abstract: Effective monitoring of industrial emissions is essential for environmental sustainability. This study presents the Graph Attention Sensor (GAS), a forecasting framework that integrates graph attention networks with Time2Vec to model complex multivariate dependencies among co-located emission sensors. Unlike conventional time-series models, GAS represents pollutant sensors as nodes in a relational graph, enabling selective attention to inter-pollutant interactions while preserving causal temporal dynamics. GAS is benchmarked against random forest, NBeats (neural basis expansion analysis for interpretable time series), temporal convolutional network (TCN), long short-term memory (LSTM), and temporal fusion transformer (TFT) under nested cross-validation on real-world emission data from a high-purity ferrosilicon industrial plant. Results reveal that GAS achieves the highest performance for TSP forecasting under constrained context windows (P≤22) across all forecast horizons, while NBeats dominates for gaseous pollutants (SOx, NOx) with extended historical context. Across all architectures, GAS exhibits the most stable cross-horizon degradation, maintaining positive R2 for TSP at t6, where random forest collapses to sub-baseline performance. Analysis of aggregated attention maps reveals that GAS identifies that NOx is associated with the furnace thermal state, a physically grounded relationship that emerges from the data without explicit encoding. These findings support a pollutant-stratified deployment strategy and provide practical guidance for model selection in industrial emission monitoring.

Original languageEnglish
Pages (from-to)991-1018
Number of pages28
JournalMathematical Geosciences
Volume58
Issue number3
DOIs
StatePublished - Apr 2026

UN SDGs

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

  1. SDG 9 - Industry, Innovation, and Infrastructure
    SDG 9 Industry, Innovation, and Infrastructure
  2. SDG 17 - Partnerships for the Goals
    SDG 17 Partnerships for the Goals

Keywords

  • Emission forecasting
  • Graph attention networks
  • Graph-based time series
  • Industrial air pollution
  • Predictive analytics
  • Sustainable industrial practices

Fingerprint

Dive into the research topics of 'Graph Attention Sensor Transformer for Industrial Emission Forecasting: A Comparative Study Against Classical and Deep Learning Baselines'. Together they form a unique fingerprint.

Cite this