Related Experiment Video
Updated: Jan 11, 2026
08:24
Mesocosm-Scale Constructed Wetland Design for Wastewater Treatment
Published on: May 2, 2025
858
Integrating data-driven models and process expertise in soft-sensor design for a wastewater treatment digital twin
Henri Haimi1, Alexis Awaitey2, Anmol Kiran3
1Department of Built Environment, Aalto University, P.O. Box 15200, FI-00076 AALTO, Espoo, Finland
Summary
Researchers developed soft-sensors for wastewater treatment plants, successfully predicting ammonium-nitrogen (NH4-N) in real-time. While COD prediction showed promise, achieving simultaneous accuracy for both parameters remained a challenge.
Area of Science:
- Environmental Engineering
- Wastewater Treatment Technologies
- Digital Twin Applications
Background:
- Digital twin models require continuous real-time data for wastewater treatment plants (WWTPs).
- Data acquisition in harsh WWTP headworks presents significant challenges.
- Soft-sensors offer a solution for real-time process monitoring.
Purpose of the Study:
- To design soft-sensors for predicting primary effluent Chemical Oxygen Demand (COD) and Ammonium-Nitrogen (NH4-N).
- To integrate data-driven models with expert knowledge for enhanced prediction accuracy.
- To evaluate the performance of soft-sensors in real-time WWTP operations.
Main Methods:
- Combined data-driven models (Ordinary Least Squares, SARIMAX) with process expertise.
- Utilized flow rate and suspended solids concentration as input variables.
- Implemented process-insight-driven weights to improve prediction accuracy.
Main Results:
- Achieved excellent prediction accuracy for NH4-N, further enhanced by weights.
- Demonstrated good COD estimation accuracy or effective variability capture, but not simultaneously.
- Soft-sensors provided real-time predictions comparable to or better than laboratory data in simulations.
Conclusions:
- Soft-sensors integrating data-driven approaches and expert knowledge are effective for WWTP monitoring.
- Real-time NH4-N prediction was highly successful, with potential for COD prediction improvements.
- The developed soft-sensors can enhance WWTP operational efficiency and process optimization.
Related Concept Videos
01:30Typical Model Studies
610
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
610
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
653
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
653
01:12Modeling and Similitude
598
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
598