Visualization of large experimental space using holographic mapping and artificial neural networks. Benchmark analysis of multicomponent catalysts for the water gas shift reaction

A. Tompos, József L. Margitfalvi, Lajos Végvári, Alfred Hagemeyer, Tony Volpe, C. J. Brooks

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper reports the combination of Holographic Mapping (HM) and Artificial Neural Networks (ANNs) in order to provide a benchmark visualization of a multi-dimensional space in two-dimensional forms. In this approach each matrix point in HM represents virtual catalytic data generated by means of ANNs in order to visualize the given multi-dimensional experimental space. A 12-dimensional experimental space related to the composition of catalysts designed for the water gas shift reaction (WGSR) from 12 possible components supported on ZrO2 is visualized. Catalytic data obtained in an earlier combinatorial screening process at 300 °C were used for training of the ANNs. The results show that the visualization of large experimental spaces having more than half a million virtual experimental points can be accomplished. The analysis of synergistic effects between different components revealed that the key components of water gas shift catalysts at 300 °C were Pt, Fe, Eu and V, while Co, Ru, Sb, Ge and Mo had a pronounced negative effect on the activity.

Original languageEnglish
Pages (from-to)100-107
Number of pages8
JournalTopics in Catalysis
Volume53
Issue number1-2
DOIs
Publication statusPublished - Feb 2010

Fingerprint

Water gas shift
Visualization
Neural networks
Catalysts
Screening
Chemical analysis

Keywords

  • Artificial neural networks
  • Combinatorial catalysis
  • High-throughput experimentation
  • Information mining
  • Multi-dimensional experimental spaces
  • Visualization
  • WGSR

ASJC Scopus subject areas

  • Catalysis
  • Chemistry(all)

Cite this

Visualization of large experimental space using holographic mapping and artificial neural networks. Benchmark analysis of multicomponent catalysts for the water gas shift reaction. / Tompos, A.; Margitfalvi, József L.; Végvári, Lajos; Hagemeyer, Alfred; Volpe, Tony; Brooks, C. J.

In: Topics in Catalysis, Vol. 53, No. 1-2, 02.2010, p. 100-107.

Research output: Contribution to journalArticle

Tompos, A. ; Margitfalvi, József L. ; Végvári, Lajos ; Hagemeyer, Alfred ; Volpe, Tony ; Brooks, C. J. / Visualization of large experimental space using holographic mapping and artificial neural networks. Benchmark analysis of multicomponent catalysts for the water gas shift reaction. In: Topics in Catalysis. 2010 ; Vol. 53, No. 1-2. pp. 100-107.
@article{6c437da93e6a4eb880c617c3f5e36684,
title = "Visualization of large experimental space using holographic mapping and artificial neural networks. Benchmark analysis of multicomponent catalysts for the water gas shift reaction",
abstract = "This paper reports the combination of Holographic Mapping (HM) and Artificial Neural Networks (ANNs) in order to provide a benchmark visualization of a multi-dimensional space in two-dimensional forms. In this approach each matrix point in HM represents virtual catalytic data generated by means of ANNs in order to visualize the given multi-dimensional experimental space. A 12-dimensional experimental space related to the composition of catalysts designed for the water gas shift reaction (WGSR) from 12 possible components supported on ZrO2 is visualized. Catalytic data obtained in an earlier combinatorial screening process at 300 °C were used for training of the ANNs. The results show that the visualization of large experimental spaces having more than half a million virtual experimental points can be accomplished. The analysis of synergistic effects between different components revealed that the key components of water gas shift catalysts at 300 °C were Pt, Fe, Eu and V, while Co, Ru, Sb, Ge and Mo had a pronounced negative effect on the activity.",
keywords = "Artificial neural networks, Combinatorial catalysis, High-throughput experimentation, Information mining, Multi-dimensional experimental spaces, Visualization, WGSR",
author = "A. Tompos and Margitfalvi, {J{\'o}zsef L.} and Lajos V{\'e}gv{\'a}ri and Alfred Hagemeyer and Tony Volpe and Brooks, {C. J.}",
year = "2010",
month = "2",
doi = "10.1007/s11244-009-9428-5",
language = "English",
volume = "53",
pages = "100--107",
journal = "Topics in Catalysis",
issn = "1022-5528",
publisher = "Springer Netherlands",
number = "1-2",

}

TY - JOUR

T1 - Visualization of large experimental space using holographic mapping and artificial neural networks. Benchmark analysis of multicomponent catalysts for the water gas shift reaction

AU - Tompos, A.

AU - Margitfalvi, József L.

AU - Végvári, Lajos

AU - Hagemeyer, Alfred

AU - Volpe, Tony

AU - Brooks, C. J.

PY - 2010/2

Y1 - 2010/2

N2 - This paper reports the combination of Holographic Mapping (HM) and Artificial Neural Networks (ANNs) in order to provide a benchmark visualization of a multi-dimensional space in two-dimensional forms. In this approach each matrix point in HM represents virtual catalytic data generated by means of ANNs in order to visualize the given multi-dimensional experimental space. A 12-dimensional experimental space related to the composition of catalysts designed for the water gas shift reaction (WGSR) from 12 possible components supported on ZrO2 is visualized. Catalytic data obtained in an earlier combinatorial screening process at 300 °C were used for training of the ANNs. The results show that the visualization of large experimental spaces having more than half a million virtual experimental points can be accomplished. The analysis of synergistic effects between different components revealed that the key components of water gas shift catalysts at 300 °C were Pt, Fe, Eu and V, while Co, Ru, Sb, Ge and Mo had a pronounced negative effect on the activity.

AB - This paper reports the combination of Holographic Mapping (HM) and Artificial Neural Networks (ANNs) in order to provide a benchmark visualization of a multi-dimensional space in two-dimensional forms. In this approach each matrix point in HM represents virtual catalytic data generated by means of ANNs in order to visualize the given multi-dimensional experimental space. A 12-dimensional experimental space related to the composition of catalysts designed for the water gas shift reaction (WGSR) from 12 possible components supported on ZrO2 is visualized. Catalytic data obtained in an earlier combinatorial screening process at 300 °C were used for training of the ANNs. The results show that the visualization of large experimental spaces having more than half a million virtual experimental points can be accomplished. The analysis of synergistic effects between different components revealed that the key components of water gas shift catalysts at 300 °C were Pt, Fe, Eu and V, while Co, Ru, Sb, Ge and Mo had a pronounced negative effect on the activity.

KW - Artificial neural networks

KW - Combinatorial catalysis

KW - High-throughput experimentation

KW - Information mining

KW - Multi-dimensional experimental spaces

KW - Visualization

KW - WGSR

UR - http://www.scopus.com/inward/record.url?scp=78049257850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049257850&partnerID=8YFLogxK

U2 - 10.1007/s11244-009-9428-5

DO - 10.1007/s11244-009-9428-5

M3 - Article

VL - 53

SP - 100

EP - 107

JO - Topics in Catalysis

JF - Topics in Catalysis

SN - 1022-5528

IS - 1-2

ER -