Evaluation of LSTM‐Based Short‐Term Prediction of MBR Operational Parameters: Applicability and Limitations for Aeration Control Applications
Water Environment Research · 2026
DOI: 10.1002/wer.70528 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Water Environment Research, 2026. Verfasst von Minh Binh Nguyen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Engineering, Nagasaki University, Nagasaki, Japan. Hauptthemen laut MEDLINE: Bioreactors, Neural Networks, Computer, Membranes, Artificial, Waste Disposal, Fluid. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: JST SPRING, Japan, Kyowakiden Industry Co. Ltd., F.C.C. Co. Ltd..
Abstract (Originalsprache)
This study evaluated the predictive capability of long short‐term memory (LSTM) neural network models for forecasting key operational variables in a membrane bioreactor (MBR) using a comparatively modest training dataset, a limited number of sensors, and a basic model architecture, with practical implementation in mind. Time‐series data for dissolved oxygen (DO), pH, transmembrane pressure (TMP), mixed liquor suspended solids (MLSS), and airflow rate were collected from a laboratory‐scale MBR over several months of continuous operation. Separate training and testing periods were used to develop and evaluate the models. The LSTM models achieved good predictive accuracy for DO, pH, and TMP over a 6‐h prediction horizon and retained useful predictive capability at 12 h. However, the 12‐h predictions showed a systematic delay in responding to process changes, indicating reduced reliability at longer horizons. Correlation analysis between airflow rate and the other operational variables further showed that the LSTM models did not fully capture the dynamic responses of the MBR to changes in aeration. This limitation likely reflects the complex and nonlinear behavior of activated sludge processes. Overall, the results indicate that a basic LSTM architecture trained on a comparatively modest dataset can support operational forecasting over horizons of 6 and 12 h. However, improved representation of aeration‐related dynamics is required before the model can be used reliably for advanced operational decision support.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Graduate School of Engineering, Nagasaki University, Nagasaki, Japan.
- Graduate School of Integrated Science and Technology, Nagasaki University, Nagasaki, Japan.
- R&D Division, Kyowakiden Industry Co. Ltd, Nagasaki, Japan.
- F.C.C. Co. Ltd, Shizuoka, Japan.
ORCID-Profile: Minh Binh Nguyen, Vu Van Huynh, Tetsuo Imai, Tomoaki Itayama
Förderung
- JST SPRING, Japan
- Kyowakiden Industry Co. Ltd.
- F.C.C. Co. Ltd.
Zitieren
APA
Nguyen, M. B., Van Huynh, V., Ueyama, T., Hayashi, M., Imai, T., Miyazaki, K., & Itayama, T. (2026). Evaluation of LSTM‐Based Short‐Term Prediction of MBR Operational Parameters: Applicability and Limitations for Aeration Control Applications. Water Environment Research. https://doi.org/10.1002/wer.70528
Vancouver
Nguyen MB, Van Huynh V, Ueyama T, Hayashi M, Imai T, Miyazaki K, et al. Evaluation of LSTM‐Based Short‐Term Prediction of MBR Operational Parameters: Applicability and Limitations for Aeration Control Applications. Water Environment Research. 2026. doi:10.1002/wer.70528
BibTeX
@article{Nguyen2026,
author = {Nguyen, Minh Binh and Van Huynh, Vu and Ueyama, Tetsurou and Hayashi, Masatosi and Imai, Tetsuo and Miyazaki, Kazuto and Itayama, Tomoaki},
title = {Evaluation of LSTM‐Based Short‐Term Prediction of MBR Operational Parameters: Applicability and Limitations for Aeration Control Applications},
journal = {Water Environment Research},
year = {2026},
doi = {10.1002/wer.70528}
}
EUVIMED