Dataset
Dataset and Code for Rapid In-line Monitoring of Full-Scale Anaerobic Co-Digestion Using Diffuse Reflectance Spectroscopy and Machine Learning
University of Iowa
11/20/2025
DOI: 10.25820/data.008042
Abstract
In-line diffuse reflectance spectroscopy (DRS) with partial least squares regression (PLS) was piloted at a full-scale municipal anaerobic co-digestion (AcoD) facility to evaluate rapid monitoring of heterogeneous feedstocks and digestate. Models developed from 42 high-strength waste and 146 digestate samples successfully predicted volatile solids, fats, carbohydrates, chemical oxygen demand, volatile fatty acids, and alkalinity with operationally useful accuracy (RMSE% 15–30; R2 up to 0.96). Protein predictions were less reliable due to limitations in reference data. Importantly, predicted volatile acid:alkalinity ratios provided rapid indicators of digester stability. Downsampling analysis demonstrated that effective models could be developed with fewer than 50 training samples for several parameters, highlighting opportunities to reduce analytical costs. Field deployment during periods of digester instability, including foaming and failure, further validated the robustness of DRS models under dynamic operating conditions. These results establish DRS as a potentially cost-effective tool for improving process stability, biogas yield, and decision-making at full-scale AcoD facilities.
Details
- Title: Subtitle
- Dataset and Code for Rapid In-line Monitoring of Full-Scale Anaerobic Co-Digestion Using Diffuse Reflectance Spectroscopy and Machine Learning
- Creators
- Zoe A.M. Kramin - University of IowaCraig L Just - University of Iowa, Civil and Environmental Engineering
- Contributors
- Brian Westra (Data Curator) - University of Iowa, Humanities and Social Sciences/Scholarly Impact
- Resource Type
- Dataset
- DOI
- 10.25820/data.008042
- Publisher
- University of Iowa
- Grants
- Iowa Biotech-TP: Predoctoral Program in Biotechnology, T32GM152268, National Institute of General Medical Sciences (United States, Bethesda) - NIGMS
- Grant note
- This study was supported financially by the Bioenergy Innovation Fund at the University of Iowa Center for Advancement and the Donald E. Bently Professorship at the University of Iowa and funding to support Zoe Kramin’s efforts was partially provided from the Iowa Biotech Training Program as funded by a T32 grant awarded by the National Institute of General Medical Sciences Predoctoral Institutional Research Training Grant (NIGMS T32 GM152268) and administered by the Center for Biocatalysis and Bioprocessing (CBB) at the University of Iowa.
- Language
- English
- Date collected
- 12/20/2023–05/31/2024
- Date published
- 11/20/2025
- Academic Unit
- Civil and Environmental Engineering; Humanities and Social Sciences/Scholarly Impact
- Record Identifier
- 9984948241202771
Metrics
1 File views/ downloads
3 Record Views