Project description
Enhancing the stability of perovskite solar cells with physics-informed machine learning
Perovskite solar cells are among the most promising photovoltaic technologies, with record-breaking efficiencies now approaching 30 % within a few decades. However, their potential has yet to be exploited commercially, due to their limited operational lifetimes. To streamline the selection of stable materials, better models to predict device degradation are needed. With the support of the Marie Skłodowska-Curie Actions programme, the ACCELERATE-PER project will harness machine learning integrated with the physics of the materials, while also developing experimental paradigms compatible with machine learning. This will align machine learning algorithms with physical reality, while overcoming the data scarcity problem that has hindered the use of machine learning in experimental science.
Objective
The development of sustainable energy production technologies, such as new types of solar cells, has traditionally taken decades. These research cycles need to be accelerated in order to respond to the urgent climate change crisis. Perovskite solar cells (PSCs) are a recent technology that boast high electricity production efficiencies, however they suffer from insufficient lifetimes. Since there are thousands of material candidates even for a single layer of a PSC, it is challenging to search for stable materials and infer device degradation mechanisms. This project aims to implement machine learning (ML) as a part of the solution. I will create an accelerated, ML-assisted research cycle for improving the lifetime of PSCs: I will focusing on optimizing the composition of the light absorbing layer – perovskite – for stability. I will show the resulting stability improvements in full PSCs and develop faster inference of the remaining PSC degradation mechanisms. The acceleration in the cycle arises from i) using ML to save experimental bandwidth, ii) designing experiments that are directly compatible with ML (opposed to first collecting data and then figuring out how to use it with ML), and iii) maximizing effectiveness by teaching physics to the ML algorithm. For example, at the materials level, the algorithm needs to know that certain perovskite compositions do not exist as mixed materials according to density functional theory. The physics integration aligns ML algorithms with physical reality and alleviates data scarcity that has traditionally hindered the use of ML in experimental science. My highly collaborative and interdisciplinary project demonstrates the potential of integrated ML-assisted research cycles in accelerating stability research, and develops applied ML methods applicable to optimization in both research and industry. The project leads to more stable PSCs, thus taking us closer to sustainable energy production.
Fields of science
- engineering and technologyenvironmental engineeringenergy and fuelsrenewable energy
- social scienceseconomics and businesseconomicsproduction economics
- natural sciencesearth and related environmental sciencesatmospheric sciencesclimatologyclimatic changes
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Keywords
Programme(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Funding Scheme
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European FellowshipsCoordinator
02150 Espoo
Finland