Problem description
Predicting the atomic coordinates of carbon nanotubes.
Abstract of this https://link.springer.com/article/10.1007/s00339-016-0153-1 paper is a good summary of this problem.
Problem source (URL)
https://link.springer.com/article/10.1007/s00339-016-0153-1
https://www.kaggle.com/datasets/inancigdem/carbon-nanotubes or https://link.springer.com/article/10.1007/s00339-016-0153-1
Codebase description
This codebase uses FNN (feedforward neural network) to predict atomic coordinates of carbon nanotubes based on the initial coordinates and chiral vectors.
Codebase source (URL)
https://www.kaggle.com/code/guangyum/an-easy-feed-forward-neural-network-model
Dataset description
This dataset contains 10721 initial and calculated atomic coordinates of carbon nanotubes (CNTs) and their chiral networks obtained from a simulation software named as BIOVIA Materials Studio CASTEP (CASTEP).
CASTEP can simulate a wide range of properties of materials properties using density functional theory (DFT). DFT is the most successful method calculates atomic coordinates faster than other mathematical approaches, and it also reaches more accurate results. The dataset is generated with CASTEP using CNT geometry optimization. Many CNTs are simulated in CASTEP, then geometry optimizations are calculated. Initial coordinates of all carbon atoms are generated randomly. Different chiral vectors are used for each CNT simulation. The atom type is selected as carbon, bond length is used as 1.42 A° (default value). CNT calculation parameters are used as default parameters. To finalise the computation, CASTEP uses a parameter named as elec_energy_tol (electrical energy tolerance) (default 1x10-5 eV) which represents that the change in the total energy from one iteration to the next remains below some tolerance value per atom for a few self-consistent field steps. Initial atomic coordinates (u, v, w), chiral vector (n, m) and calculated atomic coordinates (u’, v’, w’) are obtained from the output files.
Dataset source (URL)
https://www.kaggle.com/datasets/inancigdem/carbon-nanotubes/data
Citations:
ACI, M , AVCI, M . (2016). ARTIFICIAL NEURAL NETWORK APPROACH FOR ATOMIC COORDINATE PREDICTION OF CARBON NANOTUBES. . Applied Physics A, 122, 631. https://doi.org/10.1007/s00339-016-0153-1
ACI, M , AVCI, M , ACI, Ç . (2017). REDUCING SIMULATION DURATION OF CARBON NANOTUBE USING SUPPORT VECTOR REGRESSION METHOD. Journal of the Faculty of Engineering and Architecture of Gazi University, 32 (3), 901-907. DOI: 10.17341/gazimmfd.337642
