.png){kind=icon}
.png){kind=icon}
Return
Knowledge-Based Feature Selection Substantially Enhances Data-Driven Wastewater Treatment Modeling
.png){kind=icon}
OA
AI
S
S
R
K
J
J
B
T
L
H
DOI：10.1021/acs.est.6c04963.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Data-driven modeling in wastewater treatment is increasingly constrained by the reality of small, high-dimensional data, where the abundant monitoring parameters in small-sized data sets obscure fundamental mechanistic understandings. This study proposes a knowledge-driven feature selection framework that integrates mechanistic insights with statistical correlations to identify the most informative predictive features. Using nitrous oxide (N2O) emission prediction at a full-scale plant as a case study, we compared classic deep-learning feature selection algorithms using attention mechanisms against two new knowledge-based approaches: (i) expert-guided feature selection and (ii) large language model (LLM)-augmented feature selection. Expert-knowledge-guided feature selection substantially enhances predictive accuracy, achieving a mean R2 of 0.723 and an MAE of 0.033, compared to R2 = 0.712 and MAE = 0.033 for the best-performing attention-based architecture. More importantly, the proposed framework markedly improves model generalizability: under out-of-distribution high-flow conditions where the attention-based model fails to capture N2O emission patterns, the expert-selected model continues to reproduce the dominant temporal dynamics of N2O emissions. The LLM-assisted approach also delivers competitive accuracy (mean R2 = 0.596, MAE = 0.041) and similarly preserves generalizability under an input distributional shift. By introducing mechanistic understanding into the feature selection process, this framework offers a generalizable pathway for addressing complex wastewater treatment challenges while maintaining a computational efficiency.
Keywords:
Feature selection
wastewater modeling
high-dimensionality data
expert knowledge
machine learning
data driven
Journal
E
IF:
11.3
Papers:
1.9K
Citations:
1
Organization
Cited Papers