Capturing chemical intuition in synthesis of metal-organic frameworks

Authors: Seyed Mohamad Moosavi1, Arunraj Chidambaram1, Leopold Talirz1,2, Maciej Haranczyk3, Kyriakos C. Stylianou1, Berend Smit1,4*

  1. Laboratory of Molecular Simulation, Institut des Sciences et Ingénierie Chimiques, Valais, Ecole Polytechnique Fédérale de Lausanne (EPFL), Rue de l’Industrie 17, CH-1951 Sion, Switzerland
  2. Theory and simulation of materials (THEOS), Faculté des Sciences et Techniques de l’Ingénieur, École Polytechnique Fédérale de Lausanne (EPFL), Station 9, CH-1015 Lausanne, Switzerland
  3. IMDEA Materials Institute, C/Eric Kandel 2, 28906 Getafe, Madrid, Spain
  4. Department of Chemical and Biomolecular Engineering, University of California, Berkeley, California 94720, United States
  • Corresponding author email: berend.smit@epfl.ch

DOI10.24435/materialscloud:2018.0011/v2 (version v2, submitted on 10 December 2018)

[There are newer versions. Click here to view the latest version v4]

How to cite this entry

Seyed Mohamad Moosavi, Arunraj Chidambaram, Leopold Talirz, Maciej Haranczyk, Kyriakos C. Stylianou, Berend Smit, Capturing chemical intuition in synthesis of metal-organic frameworks, Materials Cloud Archive (2018), doi: 10.24435/materialscloud:2018.0011/v2.

Description

We report a methodology using machine learning to capture chemical intuition from a set of (partially) failed attempts to synthesize a metal organic framework. We define chemical intuition as the collection of unwritten guidelines used by synthetic chemists to find the right synthesis conditions. As (partially) failed experiments usually remain unreported, we have reconstructed a typical track of failed experiments in a successful search for finding the optimal synthesis conditions that yields HKUST-1 with the highest surface area reported to date. We illustrate the importance of quantifying this chemical intuition for the synthesis of novel materials.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive entry.

Files

File name Size Description
CuBTC_synthesis.csv
MD5MD5: ee3a5f860cc84bb1170bad02aa995080
3.9 KiB Synthesis conditions and their corresponding fitness scores for the synthesis trials of the three generations of the genetic algorithm optimization for Cu-HKUST-1
SyCoFinder_movie.mp4
MD5MD5: 8fa477622aeb32893d1c7440ff9ce009
14.5 MiB Video introducing Sy-Co-Finder web application which combines scripts used in this study to find optimal synthesis conditions.

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.

External references

Journal reference (Article where the data is discussed)
Seyed Mohamad Moosavi, Arunraj Chidambaram, Leopold Talirz, Maciej Haranczyk, Kyriakos C. Stylianou, Berend Smit. Submitted.
Software (Web application for finding optimal synthesis conditions)
Leopold Talirz, & SeyedMohamadMoosavi. (2018, July 16). ltalirz/sycofinder: First alpha release (Version v0.1.0a1). Zenodo. doi:10.5281/zenodo.1312815

Keywords

Machine learning Synthesis Optimisation Genetic algorithms Metal-Organic frameworks Robotic synthesi MARVEL

Version history

03 March 2019

04 January 2019

10 December 2018 [This version]

14 July 2018