Prediction of Products from Supercritical Water Co-Gasification of Coal and Sludge Driven by Interpretable Machine Learning

Xiao Feng; Tang Yan; Ma Miaomiao; An Guangchen; Zhang Shuyuan; Su Lei; Chen Yunan; Chen bin

doi:null

您当前的位置：

首页 >

文章列表页 >

Prediction of Products from Supercritical Water Co-Gasification of Coal and Sludge Driven by Interpretable Machine Learning

更新时间：2026-07-20

- Prediction of Products from Supercritical Water Co-Gasification of Coal and Sludge Driven by Interpretable Machine Learning
- JOURNAL OF XI’AN JIAOTONG UNIVERSITY (2026)
- 作者机构：
  
  1.西安交通大学绿色氢电全国重点实验室，西安，710049
  2.国家电投集团四川电力有限公司，成都，610213
  3.航空工业陕西航空电气有限责任公司，西安，710065
- 作者简介：
- 基金信息：
- DOI：
  CLC： TK91
- Received：06 March 2026，
  
  Revised：2026-06-26，
  
  Accepted：20 July 2026，
- 稿件说明：
移动端阅览
Xiao Feng, Tang Yan, Ma Miaomiao, et al. Prediction of Products from Supercritical Water Co-Gasification of Coal and Sludge Driven by Interpretable Machine Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026.
DOI：

Xiao Feng, Tang Yan, Ma Miaomiao, et al. Prediction of Products from Supercritical Water Co-Gasification of Coal and Sludge Driven by Interpretable Machine Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026. DOI：

摘要

针对传统方法难以刻画小样本煤与污泥超临界水共气化实验数据中复杂非线性关系与多因素交互作用的问题，本文构建了基于机器学习的产物预测与可解释性分析框架。采用留一法交叉验证评估随机森林（RF）、极端梯度提升（XGBoost）、梯度提升回归（GBR）和支持向量回归（SVR）对H

、CH

、CO和CO

产率的预测性能，并联合网格搜索和Optuna方法对模型超参数进行调优。结果表明，XGBoost模型整体预测表现最优，经Optuna优化后进一步提升（平均

²=0.828，

MAE

=0.614，

RMSE

=0.839）。SHAP特征重要性分析表明温

度对气体产率总体贡献最大（约45%）；偏依赖图进一步揭示了实验参数对气化产物分布的非线性影响规律及其交互作用特征。本研究构建的机器学习框架适用于小样本超临界水气化实验数据，可为煤与污泥共气化过程参数优化及产物调控提供数据驱动方法参考。

Abstract

To address the limitation of traditional methods in capturing complex nonlinear relationships and multi-factor interactions in small-sample experimental data from supercritical water co-gasification of coal and sludge

this study developed a machine learning-based framework for gasification product prediction and model interpretation. Leave-one-out cross-validation was employed to evaluate random forest (RF)

extreme gradient boosting (XGBoost)

gradient boosting regression (GBR)

and support vector regression (SVR) models for predicting H₂

CH₄

and CO₂ yields

while grid search and Optuna were used for hyperparameter optimization. The results showed that XGBoost exhibited the best overall predictive performance

with an average R² of 0.828

MAE of 0.614

and RMSE of 0.839 after Optuna optimization. SHAP analysis identified reaction temperature as the most influential factor

contributing approximately 45% to the model output. Partial dependence plots further revealed the nonlinear effects of key experimental parameters on gasification product distribution and their interaction characteristics. The proposed framework is suitable for small-sample SCWG datasets and provides a data-driven approach for parameter optimization and product distribution regulation in coal and sludge co-gasification.

关键词

Keywords

references

International Energy Agency (IEA) . Global Hydrogen Review 2025 [R ] . Paris : IEA , 2025 .

Hu Y , Liu M , Li H , et al . Recent research progress in supercritical water gasification of biomass for hydrogen production [J ] . Chemical Communications , 2025 , 61 ( 96 ): 19004 - 19019 .

Bai J , Wang Y , Liu S , et al . Sustainable hydrogen production from coal tar residue via supercritical water gasification [J ] . Journal of Cleaner Production , 2025 , 519 : 145967 .

郭栋 , 周臣臣 , 葛志伟 , 等 . 煤炭超临界水气化技术研究进展 [J ] . 现代化工 , 2024 , 44 ( 3 ): 43 - 47 .

GUO D , ZHOU C , GE Zi , et al . Advances on coal supercritical water gasification [J ] . Modern Chemical Industry , 2024 , 44 ( 03 ): 43 - 47 .

郭烈锦 , 王乐 , 黄勇 , 等 . 农林业固废超临界水热化学制氢进展——反应机理 [J ] . 西安交通大学学报 , 2023 , 57 ( 1 ): 1 - 14 .

GUO L , WANG L , HUANG Y , et al . Review of thermochemical conversion of agriculture and forestry waste for hydrogen production in supercritical water——mechanism analysis [J ] . Journal of Xi'an Jiaotong University , 2023 , 57 ( 01 ): 1 - 14 .

Heeley K , Orozco R L , Macaskie L E , et al . Supercritical water gasification of microalgal biomass for hydrogen production-A review [J ] . International Journal of Hydrogen Energy , 2024 , 49 : 310 - 336 .

Fang H , Fan D , Yao B , et al . Supercritical water gasification of plastic waste for hydrogen production: A review [J ] . Journal of the Energy Institute , 2025 , 123 : 102239 .

王玉龙 , 王树众 , 蒋华义 , 等 . 市政污泥超临界水气化制氢技术研究进展 [J ] . 石油学报（石油加工） , 2023 , 39 ( 4 ): 931 - 940 .

WANG Y , WANG S , JIANG H , et al . Research progress of hydrogen production from municipal sludge gasification in supercritical water [J ] . Acta Petrolei Sinica(Petroleum Processing Section) , 2023 , 39 ( 04 ): 931 - 940 .

Wei J , Gong Y , Guo Q , et al . A mechanism investigation of synergy behaviour variations during blended char co-gasification of biomass and different rank coals [J ] . Renewable Energy , 2019 , 131 : 597 - 605 .

Faki E , Üzden Ş T , Seçer A , et al . Hydrogen production from low temperature supercritical water Co-Gasification of low rank lignites with biomass [J ] . International Journal of Hydrogen Energy , 2022 , 47 ( 12 ): 7682 - 7692 .

Bian C , Zhang R , Dong L , et al . Hydrogen/Methane Production from Supercritical Water Gasification of Lignite Coal with Plastic Waste Blends [J ] . Energy & Fuels , 2020 , 34 ( 9 ): 11165 - 11174 .

Ma M , Zhang S , Chen Y , et al . Optimization of hydrogen-rich syngas from coal and sewage sludge co-gasification in supercritical water [J ] . Chemical Engineering Journal , 2024 , 497 : 154792 .

Okolie J A , Epelle E I , Nanda S , et al . Modeling and process optimization of hydrothermal gasification for hydrogen production: A comprehensive review [J ] . The Journal of Supercritical Fluids , 2021 , 173 : 105199 .

Khandelwal K , Dalai A K . Prediction of Individual Gas Yields of Supercritical Water Gasification of Lignocellulosic Biomass by Machine Learning Models [J ] . Molecules , 2024 , 29 ( 10 ): 2337 .

Wang M , Chen L , Chen D , et al . Modeling study on biomass gasification for H2-rich syngas production based on machine learning: A comprehensive review [J ] . Renewable and Sustainable Energy Reviews , 2026 , 226 : 116223 .

Zhao S , Li J , Chen C , et al . Interpretable machine learning for predicting and evaluating hydrogen production via supercritical water gasification of biomass [J ] . Journal of Cleaner Production , 2021 , 316 : 128244 .

Yan S , Mao J , Wei X , et al . Co-gasification of coal, biomass with waste plastic in a fluidized bed: Machine learning model optimized and gasification scheme [J ] . Journal of Environmental Chemical Engineering , 2025 , 13 ( 6 ): 119916 .

Gil M V , Jablonka K M , Garcia S , et al . Biomass to energy: a machine learning model for optimum gasification pathways [J ] . Digital Discovery , 2023 , 2 ( 4 ): 929 - 940 .

Liu S , Yang Y , Yu L , et al . Predicting gas production by supercritical water gasification of coal using machine learning [J ] . Fuel , 2022 , 329 : 125478 .

Al-Salih O G , Guangjian D , Al-Mudhafar W J , et al . Using extreme gradient boosting with Optuna hyperparameter tuning for efficient lost circulation prediction [J ] . Energy Geoscience , 2026 , 7 ( 2 ): 100540 .

Almarzooq H , Bin Waheed U . Automating hyperparameter optimization in geophysics with Optuna: A comparative study [J ] . Geophysical Prospecting , 2024 , 72 ( 5 ): 1778 - 1788 .

Devasahayam S , Albijanic B . Predicting hydrogen production from co-gasification of biomass and plastics using tree based machine learning algorithms [J ] . Renewable Energy , 2024 , 222 : 119883 .

Tian J , Dong R , Jia H , et al . Interpretable machine learning for predicting and evaluating hydrogen production from supercritical water gasification of coal [J ] . Fuel , 2026 , 404 : 136173 .

Li J , Li L , Tong Y W , et al . Understanding and optimizing the gasification of biomass waste with machine learning [J ] . Green Chemical Engineering , 2023 , 4 ( 1 ): 123 - 133 .

Abioye S O , Babatunde Y O , Abikoye O A , et al . Optimized machine learning algorithms with SHAP analysis for predicting compressive strength in high-performance concrete [J ] . AI in Civil Engineering , 2025 , 4 ( 1 ): 16 - 32 .

Khandelwal K , Nanda S , Dalai A K . Machine learning modeling of supercritical water gasification for predictive hydrogen production from waste biomass [J ] . Biomass and Bioenergy , 2025 , 197 : 107816 .

徐功迅 , 陈伟 , 方真 . 生物质超临界水制氢研究进展 [J ] . 农业工程学报 , 2023 , 39 ( 7 ): 24 - 35 .

XU G , CHEN W , FANG Z . Research progress of supercritical water hydrogen production from biomass [J ] . Transactions of the Chinese Society of Agricultural Engineering , 2023 , 39 ( 7 ): 24 - 35 .

Chen J , Wang Q , Xu Z , et al . Process in supercritical water gasification of coal: A review of fundamentals, mechanisms, catalysts and element transformation [J ] . Fuel Processing Technology , 2022 , 237 : 107456 .

戚新刚 , 路利波 , 陈渝楠 , 等 . 造纸黑液超临界水气化制氢与高附加值化学品回收研究进展 [J ] . 化工学报 , 2022 , 73 ( 8 ): 3338 - 3354 .

QI X , LU L , CHEN Y , et al . Review of black liquor supercritical water gasification for hydrogen production with high value-added chemicals recovery [J ] . CIESC Journal , 2022 , 73 ( 8 ): 3338 - 3354 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

Diffusion Characteristics and Influencing Factors in Case of Hydrogen Leakage from Fuel Cell Vehicles Running in Tunnels

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Related Author

No data

Related Institution

No data

⁰