Related Experiment Video
Updated: Oct 13, 2025

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
Published on: December 9, 2012
A radial basis function neural network based multi-objective optimization for simultaneously enhanced nitrogen and
Yiping Li1, Linda A Nuamah1, Yashuai Pu1
1College of Environment, Hohai University, Nanjing 210098, PR China.
This study optimized nitrogen and phosphorus removal in wetlands using a radial basis function neural network (RBFNN) model. The model identified optimal operating conditions for enhanced water treatment efficiency.
Area of Science:
- Environmental Engineering
- Water Treatment Technologies
- Computational Modeling
Background:
- Declining nitrogen and phosphorus removal efficiencies in a 6-year-old integrated treatment wetland-pond system were observed.
- Effluent concentrations of nitrogen and phosphorus showed an increasing trend, indicating reduced system performance.
- Interactions between operating parameters significantly affected the final effluent quality.
Purpose of the Study:
- To develop and implement a radial basis function neural network (RBFNN) model for multi-objective optimization.
- To determine optimal hydraulic loading rate (HLR), hydraulic retention time (HRT), and mass loading rates (MLR) for enhanced nutrient removal.
- To achieve simultaneous 80% removal efficiencies for total nitrogen and total phosphorus.
Main Methods:
- Development and application of a radial basis function neural network (RBFNN) model.
- Multi-objective optimization procedure to identify optimal operating parameters.
- Simulation of total nitrogen and total phosphorus removal efficiencies using the RBFNN model.
Main Results:
- The RBFNN model demonstrated high accuracy with R² values of 0.99 for total nitrogen and 0.98 for total phosphorus removal.
- Optimal average operating parameters were determined: HLR of 0.10860 ± 0.03 m d⁻¹, HRT of 30.43 ± 9.96 d, and MLR of 306.416 ± 89.54 mg m⁻² d⁻¹.
- These optimal parameters are predicted to achieve 80% simultaneous removal efficiencies for nitrogen and phosphorus.
Conclusions:
- The study confirms the feasibility of using RBFNN modeling for optimizing the performance of treatment wetland systems.
- The identified optimal operating conditions provide a practical guideline for enhancing nutrient removal in similar water treatment systems.
- This approach offers a robust method for improving the efficiency and effectiveness of wastewater treatment wetlands.
Related Concept Videos
Design Example: Design of an Irrigation Channel
Rapidly Varying Flow
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Typical Model Studies
Response Surface Methodology
The process of RSM involves several key steps:
Energy Considerations in Open Channel Flow

