A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap
The bandgap (Egap) is the energy difference between the highest valence band and the lowest conduction band. Generally, the conductivity of a solid material increases as its Egap decreases. As the amount of experimental data stored in online databases continue to increase over the years, it has a...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/157102 |
| _version_ | 1826124762851573760 |
|---|---|
| author | Goh, Kai Leong |
| author2 | Lu Yunpeng |
| author_facet | Lu Yunpeng Goh, Kai Leong |
| author_sort | Goh, Kai Leong |
| collection | NTU |
| description | The bandgap (Egap) is the energy difference between the highest valence band and the lowest
conduction band. Generally, the conductivity of a solid material increases as its Egap decreases.
As the amount of experimental data stored in online databases continue to increase over the
years, it has allowed the possibility of using quantitative structure–property relationship
(QSPR) modelling to predict the physical properties of synthetic materials. Recently, a paper
by the Ramprasad Group has reported a highly accurate QSPR model for predicting the Egap
values of a dataset of 4209 polymers. This paper presents an alternative QSPR model named
LGB-Stack, which has achieved even higher accuracy scores using the same dataset. LGB-Stack
performs a two-level stacked generalisation with the help of the LightGBM (Light Gradient
Boosting Machine) algorithm, where multiple weak models are firstly trained, and secondly
combined into a stronger final model. This paper also presents an extremely fast and efficient
method of geometry optimisation that employs the Merck Molecular Force Field (MMFF).
Prior to the actual model training, the Simplified Molecular Input Line Entry System (SMILES)
notations of the polymers in the dataset were converted and optimised into 3D molecular
objects using the MMFF method. Subsequently, four different molecular fingerprints were
generated based on the 3D molecular objects, and used as the initial input features for training
the weak models. The outputs of the weak models were used as the new input features for
training the final model, which completes the LGB-Stack model training process. |
| first_indexed | 2024-10-01T06:25:41Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/157102 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:25:41Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1571022023-02-28T23:16:18Z A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap Goh, Kai Leong Lu Yunpeng School of Physical and Mathematical Sciences YPLu@ntu.edu.sg Science::Chemistry The bandgap (Egap) is the energy difference between the highest valence band and the lowest conduction band. Generally, the conductivity of a solid material increases as its Egap decreases. As the amount of experimental data stored in online databases continue to increase over the years, it has allowed the possibility of using quantitative structure–property relationship (QSPR) modelling to predict the physical properties of synthetic materials. Recently, a paper by the Ramprasad Group has reported a highly accurate QSPR model for predicting the Egap values of a dataset of 4209 polymers. This paper presents an alternative QSPR model named LGB-Stack, which has achieved even higher accuracy scores using the same dataset. LGB-Stack performs a two-level stacked generalisation with the help of the LightGBM (Light Gradient Boosting Machine) algorithm, where multiple weak models are firstly trained, and secondly combined into a stronger final model. This paper also presents an extremely fast and efficient method of geometry optimisation that employs the Merck Molecular Force Field (MMFF). Prior to the actual model training, the Simplified Molecular Input Line Entry System (SMILES) notations of the polymers in the dataset were converted and optimised into 3D molecular objects using the MMFF method. Subsequently, four different molecular fingerprints were generated based on the 3D molecular objects, and used as the initial input features for training the weak models. The outputs of the weak models were used as the new input features for training the final model, which completes the LGB-Stack model training process. Bachelor of Science in Chemistry and Biological Chemistry 2022-05-04T08:35:44Z 2022-05-04T08:35:44Z 2022 Final Year Project (FYP) Goh, K. L. (2022). A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157102 https://hdl.handle.net/10356/157102 en CHEM/21/095 application/pdf Nanyang Technological University |
| spellingShingle | Science::Chemistry Goh, Kai Leong A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title | A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title_full | A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title_fullStr | A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title_full_unstemmed | A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title_short | A stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| title_sort | stacked generalisation with gradient boosting for highly accurate predictions of polymer bandgap |
| topic | Science::Chemistry |
| url | https://hdl.handle.net/10356/157102 |
| work_keys_str_mv | AT gohkaileong astackedgeneralisationwithgradientboostingforhighlyaccuratepredictionsofpolymerbandgap AT gohkaileong stackedgeneralisationwithgradientboostingforhighlyaccuratepredictionsofpolymerbandgap |