Abstract
Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.
| Original language | English (US) |
|---|---|
| Title of host publication | 2019 International Joint Conference on Neural Networks, IJCNN 2019 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781728119854 |
| DOIs | |
| State | Published - Jul 2019 |
| Event | 2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary Duration: Jul 14 2019 → Jul 19 2019 |
Publication series
| Name | Proceedings of the International Joint Conference on Neural Networks |
|---|---|
| Volume | 2019-July |
Conference
| Conference | 2019 International Joint Conference on Neural Networks, IJCNN 2019 |
|---|---|
| Country | Hungary |
| City | Budapest |
| Period | 7/14/19 → 7/19/19 |
Fingerprint
ASJC Scopus subject areas
- Software
- Artificial Intelligence
Cite this
}
Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening. / Paul, Arindam; Jha, DIpendra; Al-Bahrani, Reda; Liao, Wei Keng; Choudhary, Alok; Agrawal, Ankit.
2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8852446 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening
AU - Paul, Arindam
AU - Jha, DIpendra
AU - Al-Bahrani, Reda
AU - Liao, Wei Keng
AU - Choudhary, Alok
AU - Agrawal, Ankit
PY - 2019/7
Y1 - 2019/7
N2 - Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.
AB - Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.
UR - http://www.scopus.com/inward/record.url?scp=85073264937&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85073264937&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2019.8852446
DO - 10.1109/IJCNN.2019.8852446
M3 - Conference contribution
AN - SCOPUS:85073264937
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2019 International Joint Conference on Neural Networks, IJCNN 2019
PB - Institute of Electrical and Electronics Engineers Inc.
ER -