Kinetic Signature Decomposition and SHAP-Based Interpretability for Pretreatment Selection in Sludge Anaerobic Digestion
- 1Hangzhou Polytechnic University , ,
- 2Zhejiang University , , ,
Abstract
Anaerobic digestion (AD) of sludge is often limited by hydrolysis, and various pretreatments are deployed to accelerate this step. However, comparing pretreatments with incommensurable operating parameters remains challenging. Here, three mechanistically distinct pretreatments (zerovalent iron–peroxydisulfate (ZVI-PDS) oxidation, ultrasonication, and NaOH alkali) were systematically evaluated under mesophilic batch AD. All cumulative methane curves were fitted to the modified Gompertz model, projecting each condition onto three kinetic signatures (potential P, maximum rate Rmax, and lag phase λ). A unified feature space enabled predictive modeling and SHAP-based decomposition of which drivers control each kinetic dimension, with bootstrap resampling quantifying uncertainty. Results showed that ultrasonication gave the highest mean methane yield (97.24 mL/g VSadded) but the poorest cost-effectiveness and largest variability; ZVI-PDS offered the best cost-effectiveness (0.648 mL/g VSadded per CNY/m3) with narrow uncertainty; alkali was cheapest but was associated with possible sodium and alkalinity stress, showing the longest lag (λ̅ = 2.17 d). SHAP revealed that solubilization (ΔSCOD) dominated P and cumulative yield, whereas Rmax was cocontrolled by ΔSCOD and Fe0 dose, and λ bore a strong alkali-specific chemical penalty beyond solubilization. This kinetic fingerprint framework bridges heterogeneous pretreatments, exposes method-specific inhibition windows, and supports rational, uncertainty-aware pretreatment selection.
Related
- Divergent anaerobic fates of biodegradable plastics in landfill leachate
- 多孔框架材料用于食品中新污染物的样品前处理研究进展 Recent progress on sample pretreatment methods of emerging pollutants in food based on porous framework materials
- Effects of Pretreatment on the Isotopic Composition of Structural Carbonate in Ray‐Finned Fish Teeth
- Molecular interpretability of the bulk electrochemical impedance of concentrated electrolytes
- Identifying Key Features of Polyoxometalate Catalysts for the Anaerobic Conversion of Glucose Into Lactic Acid.
BibTeX
@article{hu2026kinetic,
title = {{Kinetic Signature Decomposition and SHAP-Based Interpretability for Pretreatment Selection in Sludge Anaerobic Digestion}},
author = {Yangqing Hu and Shuiqin Zhou and Jun Dong and Guojun Lv and Fei Wang},
journal = {ACS Omega},
year = {2026},
month = nov,
doi = {10.1021/acsomega.6c11152},
url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c11152/5468320/Kinetic-Signature-Decomposition-and-SHAP-Based},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Kinetic Signature Decomposition and SHAP-Based Interpretability for Pretreatment Selection in Sludge Anaerobic Digestion
AU - Yangqing Hu
AU - Shuiqin Zhou
AU - Jun Dong
AU - Guojun Lv
AU - Fei Wang
PY - 2026
DA - 2026/11/11
JO - ACS Omega
DO - 10.1021/acsomega.6c11152
UR - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c11152/5468320/Kinetic-Signature-Decomposition-and-SHAP-Based
AB - Anaerobic digestion (AD) of sludge is often limited by hydrolysis, and various pretreatments are deployed to accelerate this step. However, comparing pretreatments with incommensurable operating parameters remains challenging. Here, three mechanistically distinct pretreatments (zerovalent iron–peroxydisulfate (ZVI-PDS) oxidation, ultrasonication, and NaOH alkali) were systematically evaluated under mesophilic batch AD. All cumulative methane curves were fitted to the modified Gompertz model, projecting each condition onto three kinetic signatures (potential P, maximum rate Rmax, and lag phase λ). A unified feature space enabled predictive modeling and SHAP-based decomposition of which drivers control each kinetic dimension, with bootstrap resampling quantifying uncertainty. Results showed that ultrasonication gave the highest mean methane yield (97.24 mL/g VSadded) but the poorest cost-effectiveness and largest variability; ZVI-PDS offered the best cost-effectiveness (0.648 mL/g VSadded per CNY/m3) with narrow uncertainty; alkali was cheapest but was associated with possible sodium and alkalinity stress, showing the longest lag (λ̅ = 2.17 d). SHAP revealed that solubilization (ΔSCOD) dominated P and cumulative yield, whereas Rmax was cocontrolled by ΔSCOD and Fe0 dose, and λ bore a strong alkali-specific chemical penalty beyond solubilization. This kinetic fingerprint framework bridges heterogeneous pretreatments, exposes method-specific inhibition windows, and supports rational, uncertainty-aware pretreatment selection.
SN - 2470-1343
ER -