Machine Learning for Prediction of Thermodynamic Descriptors
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Our objective is to apply machine learning (ML) algorithms for the prediction of molecular catalysis descriptors from geometric properties derived from experimental crystallographic databases. Catalysis is often considered a “low-data” discipline that is poorly suited for ML methods. An exception is the extensive structural information that is available for molecular catalysts through the Cambridge Structural Database (CSD), which contains atomically precise molecular structures from X-ray diffraction analysis for >600K metal complexes. As a proof-of-principle, we targeted the prediction of hydricity, a thermodynamic property that provides understanding and control of catalytic hydride transfer. We built a training set composed of ~100 molecular complexes with a known hydricity and structural information from the CSD. This data set was converted into a machine-readable format using the smooth overlap of atomic positions (SOAP) representation and further labeled with simple electronic descriptors for the metal centers. Multiple different neural networks were trained on this data set, and the accuracy of the hydricity predictions ranged from < 2 kcal/mol to 20 kcal/mol. The accuracy of each model was highly sensitive to which compounds were in the train versus test set, underscoring the challenges associated with small and chemically diverse data sets. Finally, to further augment the data set, we attempted to experimentally measure several new hydricity values, however these experiments were unsuccessful due to undesired chemical reactivity of the selected complexes.
- Research Organization:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 2203236
- Report Number(s):
- PNNL--35049
- Country of Publication:
- United States
- Language:
- English
Similar Records
Thermodynamic and Kinetic Activity Descriptors for the Catalytic Hydrogenation of Ketones
A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
Journal Article
·
Sun Mar 03 19:00:00 EST 2024
· Journal of the American Chemical Society
·
OSTI ID:2407275
A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters
Journal Article
·
Tue Jul 14 00:00:00 EDT 2020
· Journal of Chemical Physics
·
OSTI ID:1644767
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
Journal Article
·
Sun Apr 19 20:00:00 EDT 2015
· International Journal of Quantum Chemistry
·
OSTI ID:1392322