PFM Social Network

Making DCNN work in real time on SPM - kudos to Yongtao Liu and Maxim Ziatdinov! We get computer to identify domain walls of interest and run hysteresis loop measurements only at these selected locations.

Exploring Physics of Ferroelectric Domain Walls in Real Time: Deep Learning Enabled Scanning Probe Microscopy The functionality of ferroelastic domain walls in ferroelectric materials is explored in real-time via the in-situ implementation of computer vision algorithms in scanning probe microscopy (SPM) experiment. The robust deep convolutional neural network (DCNN) is implemented based on a deep residual l...

If you are interested in Bayesian Active learning for scanning probe microscopy (or electron microscopy, or nanoindentation) - we have the grand overview out! GPax, GPim, and AtomAI libraries by are there if interested to apply for own systems and microscopes!

Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning Recent progress in machine learning methods, and the emerging availability of programmable interfaces for scanning probe microscopes (SPMs), have propelled automated and autonomous microscopies to the forefront of attention of the scientific community. However, enabling automated microscopy requires...

Can the machine learning algorithm run the microscope to learn physics of domain formation via exploring competing hypotheses?

Also, extension to other automated experiments is synthesis or scientific instrumentation is straightforward. Physics is all it takes.

Hypothesis-Driven Automated Experiment in Scanning Probe Microscopy: Exploring the Domain Growth Laws in Ferroelectric Materials We report the development and implementation of a hypothesis learning based automated experiment, in which the microscope operating in the autonomous mode identifies the physical laws behind the material's response. Specif**ally, we explore the bias induced transformations that underpin the function...

As an interesting development, looks like Bruker has implemented the commercial version of the SS-PFM mode with the option for complex spectroscopies. This is really great, since now systematic studies of polarization dynamics are becoming possible on commercial tools!

Exactly 15 years after the Rev. Sci. Instr. paper introducing this mode for the first time, https://aip.scitation.org/doi/abs/10.1063/1.2214699, and adding more complex capabilities as in https://aip.scitation.org/doi/abs/10.1063/1.2980031 and https://pubs.acs.org/doi/abs/10.1021/nn505176a

https://www.bruker.com/en/products-and-solutions/microscopes/materials-afm/afm-modes/ss-pfm.html

Switching Spectroscopy Piezoresponse Force Microscopy (SS-PFM) Switching Spectroscopy Piezoresponse Force Microscopy (SS-PFM) mode provides highly accurate ferroelectric hysteresis loop measurement by improving the sensitivity and accuracy of PFM

Very important paper for ferroelectric and PFM community - if we remember that there is water meniscus between tip and the surface.

Ferroelectric 2D ice under graphene confinement - Nature Communications Ferroelectric ordering of water has been at the heart of intense debates due to its importance in enhancing our understanding of the condensed matter. Here, the authors observe ferroelectric properties of water ice in a two dimensional phase under confinement between two graphene layers.

Lectures from ORNL workshop on Automated Experiment and Machine Learning in Scanning Probe Microscopy -> online. Featuring lectures by Mikhail Katsnelson , Leroy Cronin, Danilo J. Rezende , and many others, as well as tutorials on variational autoencoders for image and spectral analysis, Bayesian Optimization, and deep convolutional networks and deep kernel learning. See:

Machine Learning and Automated Experiments in Scanning Probe Microscopy Virtual School Recordings, October 4-7, 2021 | ORNL Organizers: Rama Vasudevan, Kyle Kelley, Maxim Ziatdinov, Josh Agar, and Sergei V. Kalinin This virtual school on ML and AE in SPM, held October 4-7, 2021, combined invited and contributed presentations at the forefront of ML applications in Scanning Probe Microscopy, including both atomically resol...

Some automated experiment in PFM - based on prior-known descriptors. Aka define what domain wall you want to study, find it, and measure polarization loops or current-voltage curves - right at the wall, or at some separation from it, as a function of curvature, or other characteristics.

Probing polarization dynamics at specific domain configurations: Computer-vision based automated experiment in piezoresponse force microscopy Topological defects in ferroelectric materials have attracted much attention due to the emergence of conductive, ferroic, and magnetic functionalities. However, many topological configurations dyna...

Can multi objective Bayesian Optimization help find right Ferro (or antiferro) electric for specific application? Especially with chemical (or interfacial) control?

Multi-objective Bayesian optimization of ferroelectric materials with interfacial control for memory and energy storage applications Optimization of materials performance for specific applications often requires balancing multiple aspects of materials functionality. Even for the cases where generative physical model of material behavior is known and reliable, this often requires search over multidimensional parameter space to ide...

We are excited to invite you to the virtual school “Machine Learning and Automated Experiment in Scanning Probe Microscopy” to be held at ORNL, October 4-7, 2021, organized by Rama Vasudevan, Kyle Kelley, Maxim Ziatdinov, Josh Agar, and Sergei V. Kalinin. Due to the close similarity between SPM and STEM, these topics may also be of interest for STEM community as well.

The registration deadline is August 25. Link to register:

https://www.surveymonkey.com/r/VDWFV5K

Machine learning (ML) has emerged as a powerful tool for data and image analysis and as an enabling component of autonomous systems in areas ranging from biological and medical imaging to self-driving cars. This rapid growth in ML applications poses the question as to which of these methods can be applied in scanning probe microscopy, both to derive insights into the physics and chemistry of real materials, enable optimization of imaging conditions, and engender transition to the automated and autonomous experiment. This virtual school on ML and AE for SPM, to be held virtually on October 4-7, 2021, will combine invited and contributed presentations at the forefront of ML applications in Scanning Probe Microscopy, including both atomically resolved Scanning Tunneling Microscopy and Spectroscopy and mesoscopic Scanning Probe Microscopy techniques.

Special emphasis will be made on necessary conditions for physically-meaningful machine learning analysis and especially automated experiments in SPM. It will feature tutorials on recent developments in ML analysis of mesoscopic and atomically resolved images and spectroscopy, including deep convolutional neural networks (DCNNs) for feature identif**ations, symmetry-invariant (variational) autoencoders ((V)AE), and Gaussian Processes and Deep Kernel Learning-based super-resolution imaging and image reconstruction, and reinforcement learning for image optimization and automated experiment. The presentations will be followed by hands-on tutorial sessions introducing the attendees to the AtomAI, GPim, PyroVED, and various Pycroscopy packages. All the technologies and workflows discussed during the tutorials will be open source. The attendees are encouraged to contact the organizers in advance to setup analysis of own datasets. The meeting will be free of charge. The final program will be available by September 2021.

If interested, please contact Sergei Kalinin ([email protected]) to submit the abstract.

Machine Learning and Automated Experiment in Scanning Probe Microscopy Take this survey powered by surveymonkey.com. Create your own surveys for free.

Using Bayesian Optimization to run Piezoresponse Force Microscopy experiment. Kudos to Rama Vasudevan for connecting DGX box to microscope, and Maxim Ziatdinov for writing the GPim library. Next stop - deep kernel learning!

Autonomous Experiments in Scanning Probe Microscopy and Spectroscopy: Choosing Where to Explore Polarization Dynamics in Ferroelectrics Polarization dynamics in ferroelectric materials are explored via automated experiment in piezoresponse force microscopy/spectroscopy (PFM/S). A Bayesian optimization (BO) framework for imaging is developed, and its performance for a variety of acquisition and pathfinding functions is explored using...

Effect of surface ionic screening on polarization reversal and phase diagrams in thin antiferroelectric films for information and energy storage The emergent behaviors in the antiferroelectric thin films due to coupling between surface electrochemistry and intrinsic polar, and structural instabilities are explored using the modified 2-4-6 Kittel-Landau-Ginzburg-Devonshire (KLGD) thermodynamic approach. The two polarization sublattices model....

For quite a while, we have been pondering how to describe mechanisms underpinning domain wall dynamics in ferroelectric materials from real space observations. Now, combination of multilayer rotationally invariant variational autoencoders (mrVAE) by Maxim Ziatdinov, excellent PFM data by Roger Proksch on the Roger Proksch - polished PZT (RPP - PZT), and insight, persistence, and effort of Yongtao Liu in putting these together make it possible!

Disentangling ferroelectric wall dynamics and identif**ation of pinning mechanisms via deep learning Field-induced domain wall dynamics in ferroelectric materials underpins multiple applications ranging from actuators to information technology devices and necessitates a quantitative description of the associated mechanisms including giant electromechanical couplings, controlled non-linearities, or....

Dear colleagues

As a new development, for the last year the CNMS has been actively developing the synergy of the machine learning and direct image based-feedbacks to the operational SPM, i.e. automated experiment. As an example, we can collect the line or image signal, deploy the specific image analytics algorithm on top of it, and dependent perform specific action within the image plane based on these analyses. The set of these forms workflow for automated experiment.

As in many cases before, these capabilities have first been implemented for PFM. For example, we have demonstrated approaches to apply specific bias pulses exclusively at ferroelectric domain walls towards exploring their dynamics. Alternatively, we can identify the objects of interest in the image (e.g. regions of ferroelectric domain walls with high curvature) and perform piezoresponse or current-voltage spectroscopy only at these objects, etc. Some of the initial results are available as:

https://arxiv.org/abs/2001.03586

https://arxiv.org/abs/2004.11817

https://arxiv.org/abs/2011.13050

https://arxiv.org/abs/2103.12165

In this regard, we seek to open these opportunities for the user access, supported by the synergy of Data NanoAnalytics group (GL – Sergei Kalinin) and SPM group (GL – Stephen Jesse). Please let me know if you will be interested in exploring this opportunity, and we will be delighted to work with you to formulate it as a user proposal.

The relevant submission deadline will be May 5 (i.e. three weeks from now), leaving ample time for brainstorming and proposal development.

Dynamic manipulation in piezoresponse force microscopy: creating non-equilibrium phases with large electromechanical response Domains walls and topological defects in ferroelectric materials have emerged as a powerful new paradigm for functional electronic devices including memory and logic. Similarly, wall interactions and dynamics underpin a broad range of mesoscale phenomena ranging from giant electromechanical response...

How we learnt to love the rotationally invariant variational autoencoders (rVAE), and (almost)… Maxim Ziatdinov¹ ² & Sergei V. Kalinin¹

The encoder-decoder networks can be used to distill structure-property relationships in ferroelectrics from observational data via passing observed structure through latent bottleneck and expanding it to property descriptor. This further gives access to latent variables maps as measures of material behavior, and prediction uncertainties as a parameter to guide automated experiment.

Toward Decoding the Relationship between Domain Structure and Functionality in Ferroelectrics via Hidden Latent Variables Polarization switching mechanisms in ferroelectric materials are fundamentally linked to local domain structure and the presence of the structural defects, which both can act as nucleation and pinning centers and create local electrostatic and mechanical depolarization fields affecting wall dynamics...

Dear colleagues - we are looking for a postdoc candidate with UHV STM experience and knowledge/strong interest to Python ML. Please share and PM me.

Postdoctoral Research Associate - Machine Learning-guided Scanning Tunneling Microscopy Postdoctoral Research Associate - Machine Learning-guided Scanning Tunneling Microscopy

For ferroelectric enthusiasts - a tutorial on what machine learning can do!

Machine Learning Mesoscopic Phenomena in Ferroelectrics | IEEE IFCS-ISAF 2020 Platinum Patrons Gold Patrons Web Patrons Conference Sponsors Technical Sponsor Welcome Schedule Tracks Search Affiliates Contact Follow IEEE IFCS-ISAF 2020 Follow IEEE IFCS-ISAF on Facebook and Linkedin! -ISAF2020 CONFlux Platform Powered By Home  |  Sitemap/More Sites  |  Contact & Suppor...

Disentangling ferroelectric domain wall geometries and pathways in dynamic piezoresponse force microscopy via unsupervised machine learning Domain switching pathways in ferroelectric materials visualized via dynamic Piezoresponse Force Microscopy are explored via rotationally invariant variational autoencoders (rVAE). rVAEs simplify the elements of the observed domain structure, crucially allowing for rotational invariance, thereby redu...

Dear colleagues - if you or someone you know are interested in automated experiment in Scanning Probe Microscopy and specif**ally Piezoresponse Force Microscopy, now we have position open!

Postdoctoral Research Associate - Nanofabrication Lab Postdoctoral Research Associate - Nanofabrication Lab

Self-driving microscope: For 30 years, scanning probe microscopes performed a predefined set of operations. Now we have incorporated automated experiment workflow in Piezoresponse Force Microscopy, when microscope performs operation depending on detected feature. As a first try - creation of strongly nonequilibrim phases with Gian electromechanical response.

Kudos to Kyle Kelly and the whole CNMS SPM team to make it work!

Dynamic manipulation in piezoresponse force microscopy: creating non-equilibrium phases with large electromechanical response Domains walls and topological defects in ferroelectric materials have emerged as a powerful new paradigm for functional electronic devices including memory and logic. Similarly, wall interactions and dynamics underpin a broad range of mesoscale phenomena ranging from giant electromechanical response...

Dear Colleagues and Friends! Please come to the next PFM conference in Ekaterinburg in August 2020! Visit the conference web page https://nanocenter.urfu.ru/pfm2020spm. Note that next year it will be combined with the International Conference on Scanning Probe Microscopy and Russian Conference on Ferroelectricity! You are all welcome to Russia!

Dear colleagues

The YouTube channel "M*N: Microscopy, Machine Learning, Materials" dedicated to the applications of big data, machine learning, and artificial intelligence in Scanning Transmission Electron Microscopy and Scanning Probe Microscopy is now fully updated with the historical overview lectures. These include:

1. Unsupervised learning in Scanning Probe Microscopy: Spectroscopies
2. Supervised learning in Scanning Probe Microscopy: Spectroscopies
3. Linear unmixing: basic techniques and some applications in microscopy and spectroscopy
4. Supervised and unsupervised learning in Scanning Probe Microscopy: Imaging
5. Supervised and Unsupervised Learning in Scanning Transmission Electron Microscopy
6. Learning Physics (and Chemistry) from Scanning Transmission Electron Microscopy
7. Atomic fabrication by STEM: feedback, compressed sensing, and non-rectangular beam paths

The channel now also features the "Z Corner" list started Maxim Ziatdinov, containing the short tutorial lectures on recent developments on ML in STEM, including:
1. Jupyter papers: scientific papers with data and code
2. Introduction to deep learning with PyTorch in Google Colab
3. How to work with AICrystallographer in Google Colab
The new lectures are becoming available once the associated Jupyter notebooks are developed.

The channel is available at:

https://www.youtube.com/channel/UCyh-7XlL-BuymJD7vdoNOvw

These lectures are closely tied to the on-line data and code resources. The codes are (or will be) shared via the PyCroscopy domain on the GitHub.
https://github.com/pycroscopy/pyCroscopy

Subscribe, join, and stay tuned!

M*N: Microscopy, Machine Learning, Materials Lectures on Scanning Probe Microscopy: Piezoresponse Force Microscopy, Electrochemical Strain Microscopy, and Kelvin Probe Force Microscopy

M*N: Microscopy, Machine Learning, Materials Lectures on Scanning Probe Microscopy: Piezoresponse Force Microscopy, Electrochemical Strain Microscopy, and Kelvin Probe Force Microscopy

If you always wanted to do machine learning for PFM data and need to know how - ask Josh Agar. And use his Jupyter paper on own data!

Google Colaboratory

PFM board quasi-meeting. N(bottles) > M(people)

PFM 2019 opening! Roughly 150 people, 3 days of talks and posters, unlimited excitement.

Jupyter paper (paper with executable code) A brief introduction to "Jupyter paper" concepts

We would like to bring to your attention the YouTube channel "M*N: Microscopy, Machine Learning, Materials" dedicated to the applications of big data methods, machine learning, and artificial intelligence in Scanning Probe Microscopy and Scanning Transmission Electron Microscopy. The channel is available at:
https://www.youtube.com/channel/UCyh-7XlL-BuymJD7vdoNOvw

We aim to create the vibrant environment for sharing recent advances in this rapidly growing field, as well as to cover some of the historical developments over last decade and notable achievements in (potentially) related fields. The channel will start with 7-lecture overview of some of the developments over the last decade, including:

1. Unsupervised learning in Scanning Probe Microscopy: Spectroscopies

2. Supervised learning in Scanning Probe Microscopy: Spectroscopies

3. Linear unmixing: basic techniques and some applications in microscopy and spectroscopy

4. Supervised and unsupervised learning in Scanning Probe Microscopy: Imaging

5. Supervised and Unsupervised Learning in Scanning Transmission Electron Microscopy

6. Learning Physics (and Chemistry) from Scanning Transmission Electron Microscopy

7. Atomic fabrication by STEM: feedback, compressed sensing, and non-rectangular beam paths

The lectures will be posted weekly (or close to it), with the first one being posted on-line today.

After this initial round of lectures, we plan to post lecture tutorials on recent developments in the field of big data, machine learning, and artificial intelligence in electron, scanning probe microscopy and chemical imaging, with the lectures being planned on:

- Deep learning in Scanning Transmission Electron Microscopy

- Deep Learning in Scanning Tunneling Microscopy

- Workflows for creation of STEM image libraries and their applications

- and many more



These lectures are closely tied to the on-line data and code resources. The codes are (or will be) shared via the PyCroscopy domain on the GitHub.

https://github.com/pycroscopy/pyCroscopy

The libraries of STEM images are disseminated via the CITRINation platform.



Finally, the imaging tools can accessed via the Center for Nanophase Materials Sciences.

https://www.ornl.gov/facility/cnms

Subscribe, join, and stay tuned!

M*N: Microscopy, Machine Learning, Materials Lectures on Scanning Probe Microscopy: Piezoresponse Force Microscopy, Electrochemical Strain Microscopy, and Kelvin Probe Force Microscopy

The deadline for PFM user proposal submissions for the Center for Nanophase Materials Sciences is May 1! If you have new material or are looking for nano solution for ferroelectric problem, CNMS is the place to go. The information on the full spectrum of PFM imaging and spectroscopy methods available at CNMS can be found at YouTube channel:

M*N: Microscopy, Machine Learning, Materials

https://www.youtube.com/channel/UCyh-7XlL-BuymJD7vdoNOvw

The information on CNMS user proposals can be found at www.cnms.ornl.gov

Contact Sergei V. Kalinin directly for additional information ([email protected])

CNMS Landing Page | ORNL Overview The Center for Nanophase Materials Sciences (CNMS) at Oak Ridge National Laboratory (ORNL) provides a national and international user community access to expertise and equipment for a broad range of nanoscience research, including nanomaterials synthesis, nanofabrication, imaging/microscopy...

You have a last chance to submit your abstract to PFM-2019 in Seoul, Korea. Plenary talks by S. Kalinin, J.-F. Li, and C.-H. Yang. More details at http://www.pfm2019.org/...

Asia-Pacific PFM 2019 2019 Asia-Pacific Workshop on Piezoresponse Force Microscopy and Nanoscale Electromechanics of Functional Materials and Electrochemical Systems (Asia-Pacific PFM 2019)

We are still waiting for the submissions to our Special Issue on Nanoscale Ferroelectrics and Their Applications! More details at https://www.mdpi.com/journal/materials/special_issues/Ferroelectrics_Applications

Materials

USID and Pycroscopy -- Open frameworks for storing and analyzing spectroscopic and imaging data Materials science is undergoing profound changes due to advances in characterization instrumentation that have resulted in an explosion of data in terms of volume, velocity, variety and complexity. Harnessing these data for scientific research requires an evolution of the associated computing and da...

Our Polyplexus social media platform is now open to the public! Through it, DARPA aims to quicken the pace of U.S. technology development by applying the power of social networks to research and development. We're seeking participation from anyone interested in sharing and learning about emerging science and technology, including researchers, practitioners, and even retirees. https://go.usa.gov/xEMDy

Polyplexus facilitates connections among experts across academic disciplines so they can propel novel research opportunities together. Beta-launched for academics only in 2018, Polyplexus is now open to the broader research and development community and features an initial offering of research topics for collaboration and potential funding. During the Beta test phase, DARPA awarded funding to multiple proposals generated by founding members on the platform.

Polyplexus is composed of three integrated components: a public information feed where users can promote interesting research and connect it to other research via tweet-like summary statements called micropubs; a private tool for synthesizing new ideas, known as micropub portfolios; and an incubator environment. Incubators allow research sponsors in government and industry to post specific topics of interest and find research and development specialists to address their challenges.

Learn more: https://go.usa.gov/xEMDy.

Ferroelectric or non-ferroelectric: Why so many materials exhibit “ferroelectricity” on the nanoscale Ferroelectric materials have remained one of the major focal points of condensed matter physics and materials science for over 50 years. In the last 20 years, the development of voltage-modulated scanning probe microscopy techniques, exemplified by Piezoresponse force microscopy (PFM) and associated...

First review on polar properties and domains in hybrid perovskites https://www.sciencedirect.com/science/article/abs/pii/S0010854518305988

Hybrid organic-inorganic perovskites: Polar properties and applications Inorganic perovskite materials such as SrTiO3, BaTiO3, and Pb(Zr,Ti)O3 have been widely used in the past because of their excellent dielectric, ferroe…