Evaluating Long-Term Treatment Performance and Cost of Nutrient Removal at Water Resource Recovery Facilities under Stochastic Influent Characteristics Using Artificial Neural Networks as Surrogates for Plantwide Modeling

Abstract

Integrated watershed modeling is needed to couple water resource recovery facilities (WRRFs) with agricultural management for holistic watershed nutrient management. Surrogate modeling can facilitate model coupling. This study applies artificial neural networks (ANNs) as surrogate models for WRRF models to efficiently evaluate the long-term treatment performance and cost under influent fluctuations. Specifically, we first developed five WRRFs, including activated sludge, activated sludge with chemical precipitation (ASCP), enhanced biological phosphorus removal (EBPR), EBPR with acetate addition (EBPR-A), and EBPR with struvite recovery (EBPR-S), in a high-fidelity simulation program (GPS-X). The five WRRFs were based on an existing plant that treats combined domestic and industrial wastewater. The ANNs have satisfactory performance in capturing nonlinear biological behaviors for all five WRRFs, even though the prediction performance (R-square) slightly decreases as the model complexity increases. We advanced ANNs application in WRRF models by simulating long-term (10-yr) performance with monthly influent fluctuations using ANNs trained by simulation data from steady-state models and evaluated their performance on Phosphorus (P) and Nitrogen (N) removal. EBPR-S shows the most resilience, while EBPR is more sensitive to influent characteristics impacted by stormwater inflow. When comparing life cycle costs of N and P removal for each layout over the 10-yr simulation period, EPBR-S is the most cost-effective alternative, highlighting both the operational and cost benefits of side-stream P recovery. By capturing both nonlinear behaviors of biological treatment and operating costs with computationally lean ANNs, this study provides a paradigm for integrating complex WRRF models within integrated watershed modeling frameworks.

Integrated Agricultural Practices and Engineering Technologies Enhance Synergies of Food-Energy-Water Systems in Corn Belt Watersheds

“…The sensitivity analysis sets ±20% cost parameter change from the baseline, based on our previous analysis ,, and historical cost data from Illinois Crop budgets, which represents a reasonable variation range of the cost for BMPs and EBTs. As shown in Table S9, high BMP cost and low EBT cost can enhance the system benefit by 5.7%, while a low BMP cost and high EBT cost will reduce system benefit by 3.1%, indicating that lowering costs of EBTs would result in more system benefit.…”

“…Specifically, five model components are included in ITEEM: (1) the Soil and Water Assessment Tool (SWAT) to simulate the impact of spatially distributed BMPs on watershed water quality, water quantity, and crop production; (2) wastewater treatment (WWT) models to evaluate treatment alternatives that impact point-source nutrient (both NO 3 –N and P) effluents at a monthly scale and P recovery potential as struvite; (3) corn biorefinery (CB) models developed using SuperPro Designer (Intelligen, Inc.) to investigate the potential for P recovery and assess energy consumption; , (4) a drinking water treatment model (DWT) that responds to nitrate and sediment inputs from SWAT to simulate the impacts of upstream agriculture on energy costs for nitrate and sediment removal; and (5) an empirical economic model that evaluates system-level benefits and the nonmarket value of water quality improvement based on a survey of the public. The five individual component models are integrated using surrogate models developed by various data-based modeling techniques (e.g., a modified response matrix method for SWAT, a machine learning approach for surrogating plant-wide WWT models). Detailed information about the component models, their surrogates, the interactions between the components, and the architecture of the integrated model are provided in a previous article …”

“…However, at present, disciplinary-specific efforts have resulted in siloed solutions that ignore or do not fully consider the impact of the FEWS nexus interactions . For example, for water quality control, individual projects that focus on point or nonpoint sources have been undertaken separately. − At the watershed scale, agricultural best management practices (BMPs) are usually implemented to reduce the nonpoint nutrient contribution to water bodies; − however, those efforts often leave out the impact of point-source discharges from wastewater treatment plants and industry. Meanwhile, environmental engineers and biological engineers have investigated technologies on nutrient removal for point-source reduction and nutrient recovery, such as struvite. − Unfortunately, nutrient recovery is often studied in disciplinary-specific models (e.g., biorefinery, wastewater), without considering the impact on other processes at the watershed scale. ,, For example, recovering P from a corn biorefinery can result in lower P in animal diets, which reduces P concentration in animal manure and reduces the probability of nonpoint source pollution from livestock manure in watersheds where animals are fed with reduced P content rations.…”

“…For example, for water quality control, individual projects that focus on point or nonpoint sources have been undertaken separately. − At the watershed scale, agricultural best management practices (BMPs) are usually implemented to reduce the nonpoint nutrient contribution to water bodies; − however, those efforts often leave out the impact of point-source discharges from wastewater treatment plants and industry. Meanwhile, environmental engineers and biological engineers have investigated technologies on nutrient removal for point-source reduction and nutrient recovery, such as struvite. − Unfortunately, nutrient recovery is often studied in disciplinary-specific models (e.g., biorefinery, wastewater), without considering the impact on other processes at the watershed scale. ,, For example, recovering P from a corn biorefinery can result in lower P in animal diets, which reduces P concentration in animal manure and reduces the probability of nonpoint source pollution from livestock manure in watersheds where animals are fed with reduced P content rations. Moreover, novel environmental and biological technologies (EBTs) often come with relatively high engineering cost. , Thus, understanding the interactions and complementarities among multiple interconnected physical processes (e.g., nutrient loading from landscape runoff and point-source discharges, reservoir trapping, and in-stream transport and deposition) is critical for optimizing point and nonpoint source nutrient management and efficiently achieving nutrient reduction targets. , Coordinated implementation of those practices requires interdisciplinary collaboration and knowledge transfer beyond the current status quo in silos.…”

Prediction and Evaluation of Indirect Carbon Emission from Electrical Consumption in Multiple Full-Scale Wastewater Treatment Plants via Automated Machine Learning-Based Analysis

“…As a complex system, the electrical consumption of WWTPs is influenced by diverse factors, such as treatment processes ( e.g. , different primary, secondary and tertiary treatment processes), influent quality, and detailed operation strategies, ,− which is time-consuming and complex to disclose their inter-relations manually. With the rapid development of machine learning (ML), some studies have established ML models for modeling the electrical consumption of WWTPs.…”