Data analysis and Machine learning with Perovskite database

past

Semester/Master project

Context

Perovksite solar cells (PSCs) with impressive improvements in their efficiencies from <4% to current levels of >25% make them one of the strongest competitiors to the established Si solar cells industry. The technology has following advantages as compared to the conventional solar cells:

  • low material consumption
  • low-temperature solution based processing
  • roll-to-roll printing/ deposition compatibility i.e, high scalability
  • efficiencies comparable to silicon solar cells > 25%
  • compatible with tandem PV technologies having efficiencies > 30% with easily tunable bandgaps

With the above mentioned pros and progress, it is important to realise the plethora of choices (in terms of material choices, composition of PSCs, fabrication conditions etc.) the technology presents in order to design them which have effects on various KPIs related to the technology like cost, efficiency, stability etc. In this project, the focus is on doing exploratory data analysis on the developed PSCs database while adding more features to the database by connecting to different online databases and also collecting the data from existing literature. Later, it involves developing pipeline with different regression and classification techniques that will be applied to extract meaningful relationship from the database which can help in identifying the pathways for improving the efficiency and stability of the overall cells.

Project

The project will be structured in the following parts:

  • developing an understanding of the existing database
  • feature engineering, identifying the feature importance using dimensionality reduction techniques
  • creating more exhaustive database by adding the required features from existing literature and online existing database
  • developing different ML models based on classification or regression techniques to identify and predict interesting insights

Skills

  • Interest and understanding of PV technologies and other energy technologies
  • independent and motivated
  • Coding skills in Python or other language are necessary
  • Results interpretation and report writing
  • Language skills: English (C1/C2 level)
  • Systematic thinker and problem-solver oriented
  • Background: Data science, Machine learning, Micro engineering, Energy science, others

Lectures: - Applied machine learning/ machine learning - Fundamentals & processes for photovoltaic devices - Energy conversion and renewable energy

Supervision

If interested, please contact Naveen Bhati (naveen.bhati@epfl.ch) attaching your CV, Cover Letter and transcript of records (Bachelor’s and Master’s). Short-listed candidates will be interviewed. Early applications are encouraged

Practical information

The IPESE laboratory is located in the Sion EPFL campus. Working in Sion office or remotely depends on Covid situation. Travels between Lausanne and Sion are compensated by EPFL.

References:

  1. Ahmadi, M., Ziatdinov, M., Zhou, Y., Lass, E. A., & Kalinin, S. V. (2021). Machine learning for high-throughput experimental exploration of metal halide perovskites. Joule, 5(11), 2797-2822. https://www.cell.com/joule/pdf/S2542-4351(21)00445-1.pdf
  2. Park, H., Mall, R., Ali, A., Sanvito, S., Bensmail, H., & El-Mellouhi, F. (2020). Importance of structural deformation features in the prediction of hybrid perovskite bandgaps. Computational Materials Science, 184, 109858. https://www.sciencedirect.com/science/article/pii/S0927025620303499
  3. Jacobsson, T. J., Hultqvist, A., García-Fernández, A., Anand, A., Al-Ashouri, A., Hagfeldt, A., … & Unger, E. (2022). An open-access database and analysis tool for perovskite solar cells based on the FAIR data principles. Nature Energy, 7(1), 107-115. https://www.nature.com/articles/s41560-021-00941-3