Machine Learning-Guided Equations for Super-Fast Prediction of Methane Storage Capacities of COFs

2020 ◽  
Author(s):  
Alauddin Ahmed
Keyword(s):  
Machine Learning ◽  
Methane Storage ◽  
Fast Prediction

scholarly journals Machine learning model for fast prediction of the natural frequencies of protein molecules

RSC Advances ◽  
2020 ◽  
Vol 10 (28) ◽  
pp. 16607-16615
Author(s):  
Zhao Qin ◽  
Qingyi Yu ◽  
Markus J. Buehler
Keyword(s):  
Machine Learning ◽  
Natural Frequencies ◽  
Protein Structures ◽  
Learning Model ◽  
Natural Vibrations ◽  
Existing Structures ◽  
Machine Learning Model ◽  
Protein Molecules ◽  
Fast Prediction

Natural vibrations and resonances are intrinsic features of protein structures and can be learnt from existing structures.

scholarly journals Machine Learning-Guided Equations for Super-Fast Prediction of Methane Storage Capacities of COFs

2020 ◽  
Author(s):  
Alauddin Ahmed
Keyword(s):  
High Capacity ◽  
Nanoporous Materials ◽  
Department Of Energy ◽  
Percentage Error ◽  
Methane Storage ◽  
On Demand ◽  
Temperature And Pressure ◽  
Pressure Swing ◽  
Fast Prediction ◽  
Methane Capacity

Covalent organic framework (COF) is a prominent class of nanoporous materials under consideration for vehicular methane storage. However, evaluating a COF for its methane capacity involves multiple experimental or computational steps, which is expensive and time consuming. Consequently, the discovery of high-capacity COFs for methane storage is very slow. Here we developed equations for super-fast prediction of deliverable methane capacities of COFs from a small number (3 to 7) of physically meaningful and measurable crystallographic features. We provided a set of equations with different fidelities for on-demand predictions based on the accessibility of crystallographic features. We found that an equation with only three crystallographic primary features, as variables, can predict deliverable capacities of 84,800 COFs with a root-mean-square error (RMSE) of 10 cm<sup>3</sup> (standard temperature and pressure, STP) cm<sup>-3</sup> and mean absolute percentage error (MAPE) of 5%. However, the highest fidelity equation developed here contains seven crystallographic primary features of COFs with RMSE and MAPE of 8.1 cm<sup>3</sup> (STP) cm<sup>-3</sup> and 4.2%, respectively. With that, we predicted methane storage capacities of 468,343 previously unexplored COFs using the highest fidelity equation and identified several hundred promising candidates with record-setting performance. CUBE_PBB_BA2, a hypothetical COF not yet synthesized, sets the new record of balancing gravimetric (0.396 g g-1) and volumetric (221 cm<sup>3</sup> (STP) cm<sup>-3</sup>) deliverable methane storage capacities under the pressure swing between 65 and 5.8 bar at 298K. Also, 3D-HNU5, a previously synthesized COF, has shown the potential to achieve the gravimetric and volumetric methane storage U.S. Department of Energy target (0.5 g g<sup>-1</sup> and 315 cm<sup>3</sup> (STP) cm<sup>-3</sup>) simultaneously with uptakes of 0.755 g g<sup>-1</sup> and 334 cm<sup>3</sup> (STP) cm<sup>-3</sup> at 100 bar/270 K.

scholarly journals How to represent crystal structures for machine learning: Towards fast prediction of electronic properties

2014 ◽  
Vol 89 (20) ◽  
Author(s):  
K. T. Schütt ◽  
H. Glawe ◽  
F. Brockherde ◽  
A. Sanna ◽  
K. R. Müller ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electronic Properties ◽  
Crystal Structures ◽  
Fast Prediction

scholarly journals B-SOiD, an open-source unsupervised algorithm for identification and fast prediction of behaviors

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Alexander I. Hsu ◽  
Eric A. Yttri
Keyword(s):  
Machine Learning ◽  
Animal Model ◽  
Open Source ◽  
Animal Behavior ◽  
Movement Disorders ◽  
Processing Speed ◽  
Spatiotemporal Patterns ◽  
New Methods ◽  
Fast Prediction ◽  
Kinematic Measures

AbstractStudying naturalistic animal behavior remains a difficult objective. Recent machine learning advances have enabled limb localization; however, extracting behaviors requires ascertaining the spatiotemporal patterns of these positions. To provide a link from poses to actions and their kinematics, we developed B-SOiD - an open-source, unsupervised algorithm that identifies behavior without user bias. By training a machine classifier on pose pattern statistics clustered using new methods, our approach achieves greatly improved processing speed and the ability to generalize across subjects or labs. Using a frameshift alignment paradigm, B-SOiD overcomes previous temporal resolution barriers. Using only a single, off-the-shelf camera, B-SOiD provides categories of sub-action for trained behaviors and kinematic measures of individual limb trajectories in any animal model. These behavioral and kinematic measures are difficult but critical to obtain, particularly in the study of rodent and other models of pain, OCD, and movement disorders.

Sign in / Sign up

Export Citation Format

Share Document