Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames
Data-driven regression models are generally calibrated by minimizing a representation error. However, optimizing the model accuracy may create nonphysical wiggles. In this study, we propose topological consistency as a new metric to mitigate these wiggles. The key enabler is Persistent Data Topology...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2025-01-01
|
Series: | Energy and AI |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546824001228 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832585093333385216 |
---|---|
author | Hui Du Tianyu Wang Haogang Wei Guy Y. Cornejo Maceda Bernd R. Noack Lei Zhou |
author_facet | Hui Du Tianyu Wang Haogang Wei Guy Y. Cornejo Maceda Bernd R. Noack Lei Zhou |
author_sort | Hui Du |
collection | DOAJ |
description | Data-driven regression models are generally calibrated by minimizing a representation error. However, optimizing the model accuracy may create nonphysical wiggles. In this study, we propose topological consistency as a new metric to mitigate these wiggles. The key enabler is Persistent Data Topology (PDT) which extracts a topological skeleton from discrete scalar field data. PDT identifies the extrema of the model based on a neighborhood analysis. The topological error is defined as the mismatch of extrema between the data and the model. The methodology is exemplified for the modeling of the Laminar Burning Velocity (LBV) of ammonia-hydrogen flames. Four regression models, Multi-layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting Machine (Light GBM), are trained using the data generated by a modified GRI3.0 mechanism. In comparison, MLP builds a model that achieves the highest accuracy and preserves the topological structure of the data. We expect that the proposed topologically consistent regression modeling will enjoy many more applications in model calibration, model selection and optimization algorithms. |
format | Article |
id | doaj-art-bb9c243ff26f4515933468efe7380d8f |
institution | Kabale University |
issn | 2666-5468 |
language | English |
publishDate | 2025-01-01 |
publisher | Elsevier |
record_format | Article |
series | Energy and AI |
spelling | doaj-art-bb9c243ff26f4515933468efe7380d8f2025-01-27T04:22:19ZengElsevierEnergy and AI2666-54682025-01-0119100456Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flamesHui Du0Tianyu Wang1Haogang Wei2Guy Y. Cornejo Maceda3Bernd R. Noack4Lei Zhou5School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, ChinaChair of Artificial Intelligence and Aerodynamics, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, ChinaSchool of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, ChinaChair of Artificial Intelligence and Aerodynamics, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, ChinaChair of Artificial Intelligence and Aerodynamics, School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, China; Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, China; Corresponding authors.School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, 518055, Shenzhen, Guangdong, China; Corresponding authors.Data-driven regression models are generally calibrated by minimizing a representation error. However, optimizing the model accuracy may create nonphysical wiggles. In this study, we propose topological consistency as a new metric to mitigate these wiggles. The key enabler is Persistent Data Topology (PDT) which extracts a topological skeleton from discrete scalar field data. PDT identifies the extrema of the model based on a neighborhood analysis. The topological error is defined as the mismatch of extrema between the data and the model. The methodology is exemplified for the modeling of the Laminar Burning Velocity (LBV) of ammonia-hydrogen flames. Four regression models, Multi-layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting Machine (Light GBM), are trained using the data generated by a modified GRI3.0 mechanism. In comparison, MLP builds a model that achieves the highest accuracy and preserves the topological structure of the data. We expect that the proposed topologically consistent regression modeling will enjoy many more applications in model calibration, model selection and optimization algorithms.http://www.sciencedirect.com/science/article/pii/S2666546824001228Regression modelLaminar burning velocityTopological errorAmmoniaHydrogenChemical kinetic mechanism |
spellingShingle | Hui Du Tianyu Wang Haogang Wei Guy Y. Cornejo Maceda Bernd R. Noack Lei Zhou Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames Energy and AI Regression model Laminar burning velocity Topological error Ammonia Hydrogen Chemical kinetic mechanism |
title | Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames |
title_full | Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames |
title_fullStr | Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames |
title_full_unstemmed | Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames |
title_short | Topologically consistent regression modeling exemplified for laminar burning velocity of ammonia-hydrogen flames |
title_sort | topologically consistent regression modeling exemplified for laminar burning velocity of ammonia hydrogen flames |
topic | Regression model Laminar burning velocity Topological error Ammonia Hydrogen Chemical kinetic mechanism |
url | http://www.sciencedirect.com/science/article/pii/S2666546824001228 |
work_keys_str_mv | AT huidu topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames AT tianyuwang topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames AT haogangwei topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames AT guyycornejomaceda topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames AT berndrnoack topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames AT leizhou topologicallyconsistentregressionmodelingexemplifiedforlaminarburningvelocityofammoniahydrogenflames |