logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Modeling catalytic hydrodeoxygenation of lignin-derived phenolic compounds: A machine learning approach

delete2026-04-27
delete0
PRE
AI
Y
Yanming Qiao
H
Hao Ji
M
Meysam Madadi *
A
Alireza Shafizadeh *
DOI：10.1016/j.fuel.2026.139624delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Machine learning optimizes lignin-derived phenol hydrodeoxygenation (HDO). • Database integrates key catalyst traits and HDO reaction parameters. • Gaussian process regression excels in phenol conversion predictions (R2 = 0.80–0.90) • Catalyst pore size, H2 pressure, and reaction time drive conversion variability. • Framework enables precise control of biofuel quality and product distribution.
Keywords:
Hydrodeoxygenation
Lignin-derived phenol
Machine learning model
Gaussian process regression

Journal

Fuel cover
Fuel
IF:
7.5
Papers:
3.8W
Citations:
16.7W

Organization

U
University of Tehran
Scholars:
2.4W
Papers: 2.3W
Citations: 2.7W
J
Jiangnan University
Scholars:
3.9W
Papers: 2.7W
Citations: 4.7W
S
Shaanxi University of Technology
Scholars:
355
Papers: 120
Citations: 0
W
Wenzhou University
Scholars:
8.8K
Papers: 6.5K
Citations: 1.5W
researcher View more organizations