MolDesign · Molecule design for next generation solar cells using machine learning approaches trained on large scale screening databases
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2018-04-01 → 2022-01-01
- EU contribution
- €208,964
- Participants
- 3
- Scheme
- MSCA-IF-GF
Lines connect the coordinator with its partners.
Results in brief
Molecule design for next generation solar cells using machine learning approaches trained on large scale screening databases
The development of new materials and molecules is of crucial importance for many global challenges, including new technologies for green energy and new chemicals to be used as drugs. Artificial intelligence and machine learning led to major breakthroughs in fields such as natural language processing and computer vision during the last decade. In natural sciences, in particular in materials science and chemistry, similar breakthroughs are possible but require the development of task specific machine learning methods. This project addresses multiple aspects of this challenging task. Firstly, the project aims to develop and apply novel representations of materials and molecules that can be used for discriminative and generative tasks, i.e. the virtual prediction of materials properties based on existing data, and the automated, computer-aided design of novel materials to be tested using simulations or experiments. Secondly, the project ultimately aims at generating new scientific understanding from data-driven approaches such as machine learning, which intrinsically are numerical procedures that are hard to interpret. Thirdly, the project aims to apply these machine learning methods to materials and technologies that are relevant for global challenges, e.g. to energy applications (e.g. organic solar cells).
Data: CORDIS, © European Union
Project objective
Research in organic electronics has already generated important applications, such organic light emitting diodes (OLEDs) in mobile displays that are already indispensable in our everyday life. Other applications, such as large scale displays and lighting, lightweight and flexible organic photovoltaics, carbon-based electronic paper, organic sensors and RFID tags, are under intense investigation.The multifunctional character of these applications poses enormous challenges for the development of novel materials, which are hard to meet with the present day trial-and-error strategies. The MolDesign project thus aims at computational material design by combining accurate but involved materials simulation methods with inexpensive novel machine learning methods to enable large scale guided materials screening. These methods will be used to improve small-molecule organic semiconductors, which are used as absorber materials in vapor-deposited organic solar cells. While some materials of this class are almost at the photovoltaics market, there is much room for improvement regarding properties such as charge carrier mobility as well as the integration of organic material into completely new applications, such as hole transport materials in highly promising perovskite solar cells.
Original text from CORDIS.
Participants
- KARLSRUHER INSTITUT FUER TECHNOLOGIE · KarlsruheCoordinatorGermany
- PRESIDENT AND FELLOWS OF HARVARD COLLEGE · CambridgeUnited States
- THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO · TorontoCanada
Links
Data: CORDIS, © European Union