

Energy-GNoME
A Living Database of Selected Materials for Energy Applications.
Explore the databases Read the PreprintExplore the project
-
Database Dashboards
Begin exploring, screening, and downloading the Energy-GNoME database effortlessly through the intuitive dashboard interface.
-
Documentation
Explore the documentation for the Python libraries developed in this project, designed to simplify contributions to the database.
-
How to Contribute
Energy-GNoME is a live database where the community actively contribute additional data points — experimental measurements or ab initio simulations — to the training set. Your contributions are always welcome!
-
About the Database
Learn about the methodology and the research work behind this database.
Database sizes1
Material class | # Sub-class | # Materials (unique) | Dashbard |
---|---|---|---|
Cathodes | 9 | 20454 | Explore Cathodes |
Perovskites | 2 | 4259 | Explore Perovskites |
Thermoelectrics | 6 | 13069 | Explore Thermoelectrics |
How to cite
Energy-GNoME Article
If you find this project valuable, please consider citing the following published work:
Energy-GNoME
De Angelis P., Barletta G.,, Trezza G., Asinari P., Chiavazzo E. "Energy-GNoME: A living database of selected materials for energy applications". Energy and AI 22, 100605, 2025. doi: 10.1016/j.egyai.2025.100605.
@article{DEANGELIS2025100605,
title = {Energy-GNoME: A living database of selected materials for energy applications},
journal = {Energy and AI},
volume = {22},
pages = {100605},
year = {2025},
issn = {2666-5468},
doi = {https://doi.org/10.1016/j.egyai.2025.100605},
url = {https://www.sciencedirect.com/science/article/pii/S2666546825001375},
author = {Paolo {De Angelis} and Giulio Barletta and Giovanni Trezza and Pietro Asinari and Eliodoro Chiavazzo},
keywords = {Energy materials, Artificial Intelligence, Machine Learning, Deep Learning, Thermoelectric, Battery, Perovskite},
abstract = {Artificial Intelligence (AI) in materials science is driving significant advancements in the discovery of advanced materials for energy applications. The recent GNoME protocol identifies over 380,000 novel stable crystals. From this, we identify over 38,500 materials with potential as energy materials forming the core of the Energy-GNoME database. Our unique combination of Machine Learning (ML) and Deep Learning (DL) tools mitigates cross-domain data bias using feature spaces, thus identifying potential candidates for thermoelectric materials, novel battery cathodes, and novel perovskites. First, classifiers with both structural and compositional features detect domains of applicability, where we expect enhanced reliability of regressors. Here, regressors are trained to predict key materials properties, like thermoelectric figure of merit (zT), band gap (Eg), and cathode voltage (ΔVc). This method significantly narrows the pool of potential candidates, serving as an efficient guide for experimental and computational chemistry investigations and accelerating the discovery of materials suited for electricity generation, energy storage and conversion.}
}
Energy-GNoME Database
When referencing the Energy-GNoME database, please use the following citation:
Database
De Angelis P., Trezza G., Barletta G., Asinari P., Chiavazzo E. "Energy-GNoME". Zenodo 2024. doi: 10.5281/ZENODO.14338533.
@misc{de_angelis_energy-gnome_2024,
title = {Energy-{GNoME}},
copyright = {Creative Commons Attribution 4.0 International},
url = {https://zenodo.org/doi/10.5281/zenodo.14338533},
urldate = {2024-12-09},
publisher = {Zenodo},
author = {De Angelis, Paolo and Trezza, Giovanni and Barletta, Giulio and Asinari, Pietro and Chiavazzo, Eliodoro},
collaborator = {De Angelis, Paolo and Trezza, Giovanni and Barletta, Giulio and Asinari, Pietro and Chiavazzo, Eliodoro},
month = dec,
year = {2024},
doi = {10.5281/ZENODO.14338533},
keywords = {Advanced Materials, Energy Materials, Materials Science, Artificial Intelligence, Machine Learning, Deep Learning, Computational Chemistry, Dataset, Thermoelectric, Battery, Perovskite},
}
Bias-Based Screening Method
Consider, also, to cite the seminal work on cross-domain data bias in materials discovery:
Cross-domain data bias
Trezza, G., Chiavazzo, E. "Classification-based detection and quantification of cross-domain data bias in materials discovery". Journal of Chemical Information and Modeling 65 (4), 1747–1761, 2024. doi: 10.1021/acs.jcim.4c01766.
GNoME Database
Additionally, please consider citing the foundational GNoME database work:
GNoME
Merchant, A., Batzner, S., Schoenholz, S.S. et al. "Scaling deep learning for materials discovery". Nature 624, 80-85, 2023. doi: 10.1038/s41586-023-06735-9.
E(3)NN Model
If your work involves the E(3)NN Graph Neural Network model, consider citing:
E(3)NN
Chen Z., Andrejevic N., Smidt T. et al. " Direct Prediction of Phonon Density of States With Euclidean Neural Networks." Advanced Science 8 (12), 2004214, 2021. doi: 10.1002/advs.202004214
-
Last update: 30/09/2025 13:46:05 ↩