MEANN · Adapting recurrent neural network algorithms for single molecular break junction analysis
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2020-06-01 → 2022-05-31
- EU contribution
- €207,312
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Adapting recurrent neural network algorithms for single molecular break junction analysis
What is the problem or issue being addressed? Presently, the aim of molecular electronics investigations is to explore the unique electronic characteristics of molecules and correlate those characteristics with the electronic structure of the molecule. To do this, researchers need to be able to identify those measured characteristics which are from the molecule, and those which are artifacts. The nature of the measurements means the interesting signal is small compared to a number of noise-inducing influences. Thus, an important problem which must be solved is to develop experimental and analytical methods to distinguish the important signals from the noise. Why is it important for society? The aims of molecular electronics no longer focus on discovering molecular replacements for electronic components. Studies now focus on thermal and magnetic properties of single-molecule junctions. Single-molecule thermopower, for example, remains a hopeful avenue for developing small and versatile waste-heat capturing technologies. Single-molecule junctions also provide a unique test bed to investigate the complicated interplay between the macroscopic world, describing the electrodes and environment, and the quantum world, describing the electronic structure of the molecule. When these two worlds interact, interesting science happens. Most molecular-based candidates for future technological applications employ monolayers of molecules, not single molecules. Yet these applications hope to exploit the quantum nature of the molecules, and this is best studied at the single-molecule level. Thus, single-molecule junctions are still an important research focus. But our methods for understanding the results of this research depends on improving our data analysis methods, and our understanding of the complicated behavior of the molecules in the junction. What are the overall objectives? This project, MEANN, was designed to explore data science and simulation solutions to the challenges inherent in single-molecule break junction experiments. In recent years, data science methods have matured, providing researchers with toolboxes to explore relationships and patterns within large data sets. These toolboxes can be big and opaque, like deploying recurrent neural network machines, or small and transparent, like principal component analysis and other linear solutions. MEANN explored various machine learning methods, both big and small, to identify those with the most potential.
Data: CORDIS, © European Union
Project objective
Molecular Electronics Artificial Neural Networks (MEANN) will adapt for the first time a recurrent neural network (RNN) to address complex multivariate correlation questions that arise in single molecular break junction (SMBJ) experiments. The hypothesis is that a RNN will be better than a human at identifying relationships between nanoscopic geometry changes of the junctions and the measured variables in SMBJ data sets, with little or no human bias. These improvements in the data analysis approach will allow researchers to address many of the present problems in SMBJ research, most notably reproducibility and bridging the theory-experiment gap. The proposal has three objectives to implement this goal. I will: (1) generate simulated SMBJ data and use this simulated data to train a RNN to sort SMBJ data into classes with unique and significant features in the data; (2) measure large sets of experimental data while on secondment and apply the trained RNN to the experimental data to sort the experimental data into the classes the RNN has already identified in the simulated data; and (3) derive a deeper understanding of the relationships between the physical processes involved in the break junction, and the observable variables of the experiment. MEANN maximizes my development as a researcher by exposing me to three important opportunities: (1) a world class theoretical chemistry group where I will learn computational and management skills necessary for my future as a researcher, (2) new experimental physics techniques while on secondment, and (3) planning an Applied RNN Summit where I will network with industry leaders in RNN development, share my expertise with peers, and prepare teaching materials to introduce my research to students. As a result of MEANN, researchers will have new tools to generate simulated SMBJ data, analyse their experimental data quickly and objectively, and answer important questions in condensed matter physics and physical chemistry.
Original text from CORDIS.
Participants
- KOBENHAVNS UNIVERSITET · KOBENHAVNCoordinatorDenmark
Links
Data: CORDIS, © European Union