Machine Learning to improve the speed and efficiency of Smart Measurements
Smart measurements can incorporate more efficient ways of scanning a sample’s surface such as a potentially fast sparse spiral route.
A project to explore how Machine Learning can be used to improve the speed and efficiency of Smart Measurements and remove uncertainty has begun.
A Smart Measurement is a simplified representative image which takes less time to acquire. The project will develop ways to create reliable, smart and robust measurements supporting using Machine Learning reconstruction algorithms.➠ The challenge of this project: can such algorithms be used to re-construct the original ‘true’ image? It will also look at how to assess errors and uncertainties in the Machine Learning approach in recreating the ‘ground truth’.
At Electrosciences we have been developing the ESPY Polar tool which probes the polarisation of Ferroelectric materials in 3D. There are some challenges though:
- Typically such measurements maps are time-consuming to acquire, limiting their industrial uptake and practical use.
- With the introduction of novel smart measurement methods and the Machine Learning reconstruction approaches being developed, we are confident that we can reduce this measurement time by a factor of at least 10 times.
The project (24DIT03 A3SmartML) has received funding from the European Partnership on Metrology, co-financed from the European Union’s Horizon Europe Research and Innovation Programme and by the Participating States.
