scholarly journals Mapping binary copolymer property space with neural networks

2019 ◽  
Vol 10 (19) ◽  
pp. 4973-4984 ◽  
Author(s):  
Liam Wilbraham ◽  
Reiner Sebastian Sprick ◽  
Kim E. Jelfs ◽  
Martijn A. Zwijnenburg
Keyword(s):  
Neural Networks ◽  
Optoelectronic Properties ◽  
Property Space ◽  
Binary Copolymers

We map the property space of binary copolymers to understand how copolymerisation can be used to tune the optoelectronic properties of polymers.

scholarly journals Mapping Binary Copolymer Property Space with Neural Networks

2019 ◽  
Author(s):  
Liam Wilbraham ◽  
Seb Sprick ◽  
Kim Jelfs ◽  
Martijn Zwijnenburg
Keyword(s):  
Large Volume ◽  
Optoelectronic Property ◽  
Data Generation ◽  
Light Emitting ◽  
Fine Grained ◽  
Donor And Acceptor ◽  
Property Space ◽  
One Step ◽  
Property Control ◽  
Binary Copolymers

The extremely large number of unique polymer compositions that can be achieved through copolymerisation makes it an attractive strategy for tuning their optoelectronic properties. However, this same attribute also makes it challenging to explore the resulting property space and understand the range of properties that can be realised. In an effort to enable the rapid exploration of this space in the case of binary copolymers, we train a neural network using a tiered data generation strategy to accurately predict the optical and electronic properties of 350,000 binary copolymers that are, in principle, synthesizable from their dihalogen monomers via Yamamoto, or Suzuki-Miyaura and Stille coupling after one-step functionalisation. By extracting general features of this property space that would otherwise be obscured in smaller datasets, we identify simple models that effectively relate the properties of these copolymers to the homopolymers of their constituent monomers, and challenge common ideas behind copolymer design. We find that binary copolymerisation does not appear to allow access to regions of the optoelectronic property space that are not already sampled by the homopolymers, although conceptually allows for more fine-grained property control. Using the large volume of data available, we test the hypothesis that copolymerisation of ‘donor’ and ‘acceptor’ monomers can result in copolymers with a lower optical gap than their related homopolymers. Overall, despite the prevalence of this concept in the literature, we observe that this phenomenon is relatively rare, and propose conditions that greatly enhance the likelihood of its experimental realisation. Finally, through a ‘topographical’ analysis of the co-polymer property space, we show how this large volume of data can be used to identify dominant monomers in specific regions of property space that may be amenable to a variety of applications, such as organic photovoltaics, light emitting diodes, and thermoelectrics. <div> <div> <div> <p> </p> </div> </div> </div>

Enabling the Exploration of Binary Copolymer Property Space with Neural Networks

2018 ◽  
Author(s):  
Liam Wilbraham ◽  
Seb Sprick ◽  
Kim Jelfs ◽  
Martijn Zwijnenburg
Keyword(s):  
Large Volume ◽  
Optoelectronic Property ◽  
Data Generation ◽  
Light Emitting ◽  
Fine Grained ◽  
Donor And Acceptor ◽  
Property Space ◽  
One Step ◽  
Property Control ◽  
Binary Copolymers

<div> <div> <div> <p>The extremely large number of unique polymer compositions that can be achieved through copolymerisation makes it an attractive strategy for tuning their optoelectronic properties. However, this same attribute also makes it challenging to explore the resulting property space and understand the range of properties that can be realised. In an effort to enable the rapid exploration of this space in the case of binary copolymers, we train a neural network using a tiered data generation strategy to accurately predict the optical and electronic properties of 350,000 binary copolymers that are, in principle, synthesizable from their dihalogen monomers via Yamamoto, or Suzuki-Miyaura and Stille coupling after one-step functionalisation. By extracting general features of this property space that would otherwise be obscured in smaller datasets, we identify simple models that effectively relate the properties of these copolymers to the homopolymers of their constituent monomers. We find that binary copolymerisation does not appear to allow access to regions of the optoelectronic property space that are not already sampled by the homopolymers, although conceptually allows for more fine-grained property control. Using the large volume of data available, we test the hypothesis that copolymerisation of ‘donor’ and ‘acceptor’ monomers can result in copolymers with a lower optical gap than their related homopolymers and propose a heuristic to predict promising combinations of monomers for which this behaviour is likely. Finally, through a ‘topographical’ analysis of the co-polymer property space, we show how this large volume of data can be used to identify dominant monomers in specific regions of property space that may be amenable to a variety of applications, such as organic photovoltaics, light emitting diodes, and thermoelectrics. </p> </div> </div> </div>

scholarly journals Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers

2021 ◽  
Vol 154 (2) ◽  
pp. 024906
Author(s):  
Chee-Kong Lee ◽  
Chengqiang Lu ◽  
Yue Yu ◽  
Qiming Sun ◽  
Chang-Yu Hsieh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Optoelectronic Properties ◽  
Conjugated Oligomers ◽  
Graph Neural Networks

scholarly journals Transfer Learning with Graph Neural Networks for Optoelectronic Properties of Conjugated Oligomers

2020 ◽  
Author(s):  
Chee Kong Lee ◽  
Chengqiang Lu ◽  
Yue Yu ◽  
Qiming Sun ◽  
Chang-Yu Hsieh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Excited State ◽  
Transfer Learning ◽  
State Energy ◽  
Optoelectronic Properties ◽  
Training Data ◽  
Conjugated Oligomers ◽  
Excited State Energy ◽  
Tddft Calculations ◽  
Graph Neural Networks

Despite the remarkable progress of machine learning (ML) techniques in chemistry, modeling the optoelectronic properties of long conjugated oligomers and polymers with ML remains challenging due to the difficulty in obtaining sufficient training data. Here we use transfer learning to address the data scarcity issue by pre-training graph neural networks using data from short oligomers. With only a few hundred training data, we are able to achieve an average error of about 0.1 eV for excited state energy of oligothiophenes against TDDFT calculations. We show that the success of our transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers. Finally, we demonstrate the transferability of our approach by modeling the lowest-lying excited-state energies of poly(3-hexylthiopnene) (P3HT) in its single-crystal and solution phases using the transfer learning models trained with data of gas-phase oligothiophenes. The transfer learning predicted excited-state energy distributions agree quantitatively with TDDFT calculations and capture some important qualitative features observed in experimental absorption spectra.<br>

scholarly journals Mapping Binary Copolymer Property Space with Neural Networks

2019 ◽  
Author(s):  
Liam Wilbraham ◽  
Seb Sprick ◽  
Kim Jelfs ◽  
Martijn Zwijnenburg
Keyword(s):  
Large Volume ◽  
Optoelectronic Property ◽  
Data Generation ◽  
Light Emitting ◽  
Fine Grained ◽  
Donor And Acceptor ◽  
Property Space ◽  
One Step ◽  
Property Control ◽  
Binary Copolymers

The extremely large number of unique polymer compositions that can be achieved through copolymerisation makes it an attractive strategy for tuning their optoelectronic properties. However, this same attribute also makes it challenging to explore the resulting property space and understand the range of properties that can be realised. In an effort to enable the rapid exploration of this space in the case of binary copolymers, we train a neural network using a tiered data generation strategy to accurately predict the optical and electronic properties of 350,000 binary copolymers that are, in principle, synthesizable from their dihalogen monomers via Yamamoto, or Suzuki-Miyaura and Stille coupling after one-step functionalisation. By extracting general features of this property space that would otherwise be obscured in smaller datasets, we identify simple models that effectively relate the properties of these copolymers to the homopolymers of their constituent monomers, and challenge common ideas behind copolymer design. We find that binary copolymerisation does not appear to allow access to regions of the optoelectronic property space that are not already sampled by the homopolymers, although conceptually allows for more fine-grained property control. Using the large volume of data available, we test the hypothesis that copolymerisation of ‘donor’ and ‘acceptor’ monomers can result in copolymers with a lower optical gap than their related homopolymers. Overall, despite the prevalence of this concept in the literature, we observe that this phenomenon is relatively rare, and propose conditions that greatly enhance the likelihood of its experimental realisation. Finally, through a ‘topographical’ analysis of the co-polymer property space, we show how this large volume of data can be used to identify dominant monomers in specific regions of property space that may be amenable to a variety of applications, such as organic photovoltaics, light emitting diodes, and thermoelectrics. <div> <div> <div> <p> </p> </div> </div> </div>

scholarly journals Transfer Learning with Graph Neural Networks for Optoelectronic Properties of Conjugated Oligomers

2020 ◽  
Author(s):  
Chee Kong Lee ◽  
Chengqiang Lu ◽  
Yue Yu ◽  
Qiming Sun ◽  
Chang-Yu Hsieh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Excited State ◽  
Transfer Learning ◽  
State Energy ◽  
Optoelectronic Properties ◽  
Training Data ◽  
Conjugated Oligomers ◽  
Excited State Energy ◽  
Tddft Calculations ◽  
Graph Neural Networks

Despite the remarkable progress of machine learning (ML) techniques in chemistry, modeling the optoelectronic properties of long conjugated oligomers and polymers with ML remains challenging due to the difficulty in obtaining sufficient training data. Here we use transfer learning to address the data scarcity issue by pre-training graph neural networks using data from short oligomers. With only a few hundred training data, we are able to achieve an average error of about 0.1 eV for excited state energy of oligothiophenes against TDDFT calculations. We show that the success of our transfer learning approach relies on the relative locality of low-lying electronic excitations in long conjugated oligomers. Finally, we demonstrate the transferability of our approach by modeling the lowest-lying excited-state energies of poly(3-hexylthiopnene) (P3HT) in its single-crystal and solution phases using the transfer learning models trained with data of gas-phase oligothiophenes. The transfer learning predicted excited-state energy distributions agree quantitatively with TDDFT calculations and capture some important qualitative features observed in experimental absorption spectra.<br>

Sign in / Sign up

Export Citation Format

Share Document