Accelerating the discovery of direct bandgap doped-spinel photovoltaic materials: A target-driven approach using interpretable machine learning
Source abstract
Abstract
The spinel structure, unifying tetrahedral and octahedral coordination within a single crystal lattice, emerges as a promising alternative to perovskite and traditional semiconductors, particularly in the context of photovoltaic applications. However, the majority of surveyed spinels exhibit an indirect bandgap, imposing substantial limitations on their utility. Consequently, doping is required to tailor indirect bandgap spinels into direct ones. In this study, leveraging machine learning (ML) algorithms, we design a target-driven framework to accelerate the ab initio predictions of unknown doped-spinels using elements from the periodic table. Utilizing this approach, we have introduced a novel machine learning classification model designed for the prediction of the direct-indirect bandgap nature in spinel materials. This pioneering model shows promising potential for achieving rapid and precise predictions, particularly in scenarios involving small dataset. Especially, a full list of potential 3449 (A xA′ 1-x)B 2X 4-type doped-spinels and 3809 A(B xB′ 2-x)X 4-type doped-spinels with direct bandgaps is identified from the vast pool of unknown doped-spinel materials. Further, the application of interpretable ML extracts the first ionization energy of the B-site ion as the most important feature for the nature of bandgap, offering insightful design rules. This research provides a novel perspective on unraveling spinel materials, and the proposed design framework proves effective in identifying high-performance materials within a vast chemical space, all while minimizing computational costs.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Learning in Materials Science · Electronic and Structural Properties of Oxides · Advanced Photocatalysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (51)
Show source-provided references
1. China can reach carbon neutrality before 2050 by improving economic development quality10.1016/j.energy.2021.123087 ↗
2. Assessment of renewable energy, financial growth and in accomplishing targets of China's cities carbon neutrality10.1016/j.renene.2022.11.026 ↗
3. Real-time corporate carbon footprint estimation methodology based on appliance identification10.1109/TII.2022.3154467 ↗
4. Strategies to achieve a carbon neutral society: a review10.1007/s10311-022-01435-8 ↗
5. Machine learning for perovskite materials design and discovery10.1038/s41524-021-00495-8 ↗
6. A critical review of machine learning of energy materials10.1002/aenm.201903242 ↗
7. From DFT to machine learning: recent approaches to materials science–a review
8. Big data creates new opportunities for materials research: a review on methods and applications of machine learning for materials design10.1016/j.eng.2019.02.011 ↗
9. Unsupervised learning methods for molecular simulation data10.1021/acs.chemrev.0c01195 ↗
10. Accelerating the discovery of materials for clean energy in the era of smart automation10.1038/s41578-018-0005-z ↗
11. Machine-learned potentials for next-generation matter simulations10.1038/s41563-020-0777-6 ↗
12. Machine learning for high performance organic solar cells: current scenario and future prospects10.1039/D0EE02838J ↗
13. Spinels: controlled preparation, oxygen reduction/evolution reaction application, and beyond10.1021/acs.chemrev.7b00051 ↗
14. Synthesis and advantages of spinel-type composites10.1039/D3QM00416C ↗
15. Dye sensitized solar cells go beyond using perovskite and spinel inorganic materials: a review10.1016/j.rser.2021.112047 ↗
16. Tunable spinel structure phosphors: dynamic change in near-infrared windows and their applications10.1002/adom.202301166 ↗
17. Materials design of solar cell absorbers beyond perovskites and conventional semiconductors via combining tetrahedral and octahedral coordination
18. Spinel-Type nitride compounds with improved features as solar cell absorbers10.1016/j.actamat.2020.07.034 ↗
19. Silicon-based optoelectronics10.1109/5.248958 ↗
20. p-Type ultrawide-band-gap spinel ZnGa2O4: new perspectives for energy electronics10.1021/acs.cgd.9b01669 ↗
21. Accelerated discovery of stable spinels in energy systems via machine learning10.1016/j.nanoen.2020.105665 ↗
22. Isomorphous substitution synthesis and photoelectric properties of spinel AgInSnS4 nanosheets10.1021/acs.chemmater.0c03404 ↗
23. Data-driven strategies for accelerated materials design10.1021/acs.accounts.0c00785 ↗
24. Target-driven design of deep-UV nonlinear optical materials via interpretable machine learning
25. Machine learning-aided band gap engineering of BaZrS3 chalcogenide perovskite10.1021/acsami.3c00618 ↗
26. Machine learning enabled development of unexplored perovskite solar cells with high efficiency10.1016/j.nanoen.2022.107394 ↗
27. Borderline over-sampling for imbalanced data classification10.1504/IJKESDP.2011.039875 ↗
28. Chawla · 2002
29. Lloyd shapley (1923–2016)10.1038/532178a ↗
30. Chemical hardness-driven interpretable machine learning approach for rapid search of photocatalysts10.1038/s41524-021-00669-4 ↗
31. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set10.1103/PhysRevB.54.11169 ↗
32. Self-consistent equations including exchange and correlation effects10.1103/PhysRev.140.A1133 ↗
33. Projector augmented-wave method10.1103/PhysRevB.50.17953 ↗
34. Higher-accuracy van der Waals density functional
35. Small data machine learning in materials science10.1038/s41524-023-01000-z ↗
36. Interpretable machine-learning and big data mining to predict gas diffusivity in metal-organic frameworks10.1002/advs.202301461 ↗
37. Commentary: the Materials Project: a materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
38. An overview of mixing augmentation methods and augmentation strategies10.1007/s10462-022-10227-z ↗
39. Accelerated discovery of stable spinels in energy systems via machine learning10.1016/j.nanoen.2020.105665 ↗
40. Machine learning for catalysis informatics: recent applications and prospects10.1021/acscatal.9b04186 ↗
41. High-throughput screening of gas sensor materials for decomposition products of eco-friendly insulation medium by machine learning10.1021/acssensors.3c00376 ↗
42. Tolerance factor and phase stability of the normal spinel structure
43. Machine learning for halide perovskite materials10.1016/j.nanoen.2020.105380 ↗
44. Enhancing the stability of organic photovoltaics through machine learning10.1016/j.nanoen.2020.105342 ↗
45. Machine learning-based discovery of vibrationally stable materials10.1038/s41524-022-00943-z ↗
46. Classification of ABO3 perovskite solids: a machine learning study10.1107/S2052520615013979 ↗
47. LightGBM: a highly efficient gradient boosting decision tree
48. New tolerance factor to predict the stability of perovskite oxides and halides10.1126/sciadv.aav0693 ↗
49. Optuna: a next-generation hyperparameter optimization framework
50. Compositionally restricted attention-based network for materials property predictions10.1038/s41524-021-00545-1 ↗
51. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties10.1103/PhysRevLett.120.145301 ↗