Materials Scientist
Materials Scientist

Biography

Maxim Ziatdinov’s research is directed primarily toward the synergy of machine learning, experiment, and theory to accelerate discoveries in physical sciences. This includes the development of science-informed machine learning workflows capable of incorporating prior domain knowledge or simulations and the enablement of on-the-fly analysis of streaming data for feedback and instrument control. Ziatdinov is a creator of several open-source software packages widely used in the experimental community, including AtomAI for deep and machine learning applications in microscopy, pyroVED for applications of invariant autoencoders in image and spectral analysis, and GPax for physics-guided active learning and Bayesian optimization in automated experiments. Prior to joining Pacific Northwest National Laboratory, Ziatdinov spent eight and half years at Oak Ridge National Laboratory working on the development of the "self-driving" electron and scanning probe microscopy platforms.

View Ziatdinov’s Google Scholar page.

Disciplines and Skills

  • Bayesian methods
  • Computer vision
  • Condensed matter physics
  • Deep learning
  • Machine learning
  • Materials science
  • Physics
  • Physics-informed learning machines
  • Probabilistic models
  • Surface science

Education

  • PhD in engineering science, Tokyo Institute of Technology
  • MS in engineering, Tokyo Institute of Technology

Publications

2024

  • Biswas A., Y. Liu, N. Creange, et al. 2024. “A dynamic Bayesian optimized active recommender system for curiosity-driven partially Human-in-the-loop automated experiments.” npj Computational Materiels 10, 29. doi:10.1038/s41524-023-01191-5
  • Kalinin S.V., M.A. Ziatdinov, M. Ahmadi, A. Ghosh, K. Roccapriore, Y. Liu, and R. Vasudevan. 2024. "Designing Workflows for Materials Characterization." Applied Physics Reviews 11, no. 1:11314. PNNL-SA-193503. doi:10.1063/5.0169961
  • Narasimha G., S. Hus, A. Biswas, R. Vasudevan, M. Ziatdinov. 2024. "Autonomous convergence of STM control parameters using Bayesian optimization." APL Machine Learning 2, 016121. doi:10.1063/5.0185362
  • Roccapriore K.M., M. Ziatdinov, A.R. Lupini, A.P. Singh, U. Philipose, S.V. Kalinin. 2024. "Discovering invariant spatial features in electron energy loss spectroscopy images on the mesoscopic and atomic levels." Journal of Applied Physics 135, 114303. doi:10.1063/5.0193607
  • Valleti M., R.K.Vasudevan, M. Ziatdinov, S.V. Kalinin. 2024. "Deep kernel methods learn better: from cards to process optimization." Machine Learning: Science and Technology 5 015012. doi:10.1088/2632-2153/ad1a4f 

2023

  • Checa M., A.S. Fuhr, C. Sun, et al. 2023. “High-speed mapping of surface charge dynamics using sparse scanning Kelvin probe force microscopy.” Nature Communications 14, 7196. doi:10.1038/s41467-023-42583-x
  • Biswas A., R. Vasudevan, M. Ziatdinov, S.V. Kalinin. 2023. “Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach.” Machine Learning: Science and Technology 4 015011. doi:10.1088/2632-2153/acb316
  • Biswas A., M. Ziatdinov, S.V. Kalinin. 2023. “Combining variational autoencoders and physical bias for improved microscopy data analysis.” Machine Learning: Science and Technology 4 045004. doi:10.1088/2632-2153/acf6a9
  • Ghosh A., S.V. Kalinin, M. Ziatdinov. 2023. “Discovery of structure–property relations for molecules via hypothesis-driven active learning over the chemical space.” APL Machine Learning 1, 046102. doi:10.1063/5.0157644
  • Kalinin S.V., O. Dyck, A. Ghosh, Y. Liu, B.G. Sumpter, M. Ziatdinov. 2023. “Unsupervised machine learning discovery of structural units and transformation pathways from imaging data.” APL Machine Learning 1 (2): 026117. doi:10.1063/5.0147316
  • Kalinin S.V., D. Mukherjee, K. Roccapriore, B. Blaiszik, A. Ghosh, M. Ziatdinov, and A. Al-Najjar, et al. 2023. "Machine Learning for Automated Experimentation in Scanning Transmission Electron Microscopy." npj Computational Materials 9. PNNL-SA-183322. doi:10.1038/s41524-023-01142-0
  • Kalinin S.V., R. Vasudevan, Y. Liu, A. Ghosh, K. Roccapriore, M. Ziatdinov. 2023. “Probe microscopy is all you need.” Machine Learning: Science and Technology 4 023001. doi:10.1088/2632-2153/acccd5
  • Liu Y., R.K. Vasudevan, K.P. Kelley, et al. 2023. “Learning the right channel in multimodal imaging: automated experiment in piezoresponse force microscopy.” npj Computational Materials 9, 34. doi:10.1038/s41524-023-00985-x
  • Liu Y., J. Yang, B.J. Lawrie, K.P. Kelley, M. Ziatdinov, S.V. Kalinin, M. Ahmadi. 2023. “Disentangling Electronic Transport and Hysteresis at Individual Grain Boundaries in Hybrid Perovskites via Automated Scanning Probe Microscopy.” ACS Nano, Vol.17(10), p.9647-9657. doi:10.1021/acsnano.3c03363
  • Liu Y., J. Yang, R.K. Vasudevan, K.P. Kelley, M. Ziatdinov, S.V. Kalinin, M. Ahmadi. 2023. “Exploring the Relationship of Microstructure and Conductivity in Metal Halide Perovskites via Active Learning-Driven Automated Scanning Probe Microscopy.” The Journal of Physical Chemistry Letters, Vol.14(13), p.3352-3359. doi:10.1021/acs.jpclett.3c00223
  • Saranathan G., M. Foltin, A. Tripathy, M. Ziatdinov, A.M.J.  Koomthanam, S. Bhattacharya, A. Ghosh, K. Roccapriore, S.R. Sukumar, and P. Faraboschi. 2023. “Towards Rapid Autonomous Electron Microscopy with Active Meta-Learning.” In Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W '23). Association for Computing Machinery, New York, NY, USA, 81–87. doi:10.1145/3624062.3626085
  • Venkatakrishnan S.V., C.M. Fancher, M. Ziatdinov, R. Vasudevan, K. Saleeby, J. Haley, D. Yu, K. An, A. Plotkowski. 2023. “Adaptive sampling for accelerating neutron diffraction-based strain mapping.” Machine Learning: Science and Technology 4 025001. doi:10.1088/2632-2153/acc512
  • Vasudevan R.K., S.M. Valleti, M. Ziatdinov, G. Duscher, S. Somnath. 2023. “A Processing and Analytics System for Microscopy Data Workflows: The Pycroscopy Ecosystem of Packages.” Advanced Theory and Simulations, Vol.6(11). doi:10.1002/adts.202300247
  • Yaman M.Y., S.V. Kalinin, K.N. Guye, D.S. Ginger, and M. Ziatdinov. 2023. "Learning and predicting photonic responses of plasmonic nanoparticle assemblies via dual variational autoencoders." Nano Micro Small 19, no. 25:Art. No. 2205893. PNNL-SA-180000. doi:10.1002/smll.202205893
  • Ziatdinov M., C.Y.T. Wong, S.V. Kalinin. 2023. “Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders.” Machine Learning: Science and Technology 4 045033. doi:10.1088/2632-2153/ad073b

2022

  • Creange N., O. Dyck. R.K. Vasudevan, M.A. Ziatdinov, S.V. Kalinin. 2022. “Towards automating structural discovery in scanning transmission electron microscopy*.” Machine Learning: Science and Technology, 3 015024. doi:10.1088/2632-2153/ac3844
  • Fuentes-Cabrera, M., J.K. Sakkos, D.C. Ducat, M. Ziatdinov. 2022. “Investigating Carboxysome Morphology Dynamics with a Rotationally Invariant Variational Autoencoder.” The Journal of Physical Chemistry, Vol.126(30), p.5021-5030. doi:10.1021/acs.jpca.2c02179
  • Ghosh, A., M. Ziatdinov, O. Dyck, et al. 2022. “Bridging microscopy with molecular dynamics and quantum simulations: an atomAI based pipeline.” npj Comput Mater 8, 74. doi:10.1038/s41524-022-00733-7
  • Ignatans, R., M. Ziatdinov, R. Vasudevan, M. Valleti, V. Tileli, S.V. Kalinin. 2022. “Latent Mechanisms of Polarization Switching from In Situ Electron Microscopy Observations.” Advanced Functional Materials, Vol.32(23). doi:10.1002/adfm.202100271
  • Kalinin, S.V., A. Ghosh, R. Vasudevan, et al. 2022. “From atomically resolved imaging to generative and causal models.” Nat. Phys. 18, 1152–1160. doi:10.1038/s41567-022-01666-0
  • Kalinin, S.V., C. Ophus, P.M. Voyles, et al. 2022. “Machine learning in scanning transmission electron microscopy.” Nat. Rev. Methods Primers 2, 11. doi:10.1038/s43586-022-00095-w
  • Kalinin S.V., J.J. Steffes, Y. Liu, B.D. Huey, M. Ziatdinov. 2022. “Disentangling ferroelectric domain wall geometries and pathways in dynamic piezoresponse force microscopy via unsupervised machine learning.” Nanotechnology 33 055707. doi:10.1088/1361-6528/ac2f5b
  • Kalinin S.V., M. Ziatdinov, S.R. Spurgeon, C. Ophus, E.A. Stach, T. Susi, and J. Agar, et al. 2022. "Deep Learning for Electron and Scanning Probe Microscopy: From Materials Design to Atomic Fabrication." MRS Bulletin 47, no. 9:931-939. PNNL-SA-171109. doi:10.1557/s43577-022-00413-3
  • Liu, Y., K.P. Kelley, H. Funakubo, S.V. Kalinin, M. Ziatdinov. 2022. “Exploring Physics of Ferroelectric Domain Walls in Real Time: Deep Learning Enabled Scanning Probe Microscopy.” Advanced Science, Vol.9(31). doi:10.1002/advs.202203957
  • Liu, Y., K.P. Kelley, R.K. Vasudevan, et al. 2022. “Experimental discovery of structure–property relationships in ferroelectric materials via active learning.” Nat Mach Intell 4, 341–350. doi:10.1038/s42256-022-00460-0
  • Liu, Yongtao, M. Ziatdinov, S.V. Kalinin. 2022. “Exploring Causal Physical Mechanisms via Non-Gaussian Linear Models and Deep Kernel Learning: Applications for Ferroelectric Domain Structures.” ACS Nano, Vol.16(1), p.1250-1259. doi:10.1021/acsnano.1c09059
  • Roccapriore K.M., M.G. Boebinger, O. Dyck, A. Ghosh, R.R. Unocic, S.V. Kalinin, and M. Ziatdinov. 2022. “Probing Electron Beam Induced Transformations on a Single-Defect Level via Automated Scanning Transmission Electron Microscopy.” ACS Nano 16 (10), 17116-17127. doi:10.1021/acsnano.2c07451
  • Roccapriore K.M., O. Dyck, M.P. Oxley, M. Ziatdinov, S.V. Kalinin. 2022. ACS Nano, Vol.16(5), p.7605-7614. doi:10.1021/acsnano.1c11118
  • Roccapriore K. M., S. V. Kalinin, M. Ziatdinov. 2022. “Physics Discovery in Nanoplasmonic Systems via Autonomous Experiments in Scanning Transmission Electron Microscopy.” Advanced Science., 9(36). doi:10.1002/advs.202203422
  • Valleti S.M.P., S.V. Kalinin, C.T. Nelson, J.J.P. Peters, W. Dong, R. Beanland, X. Zhang, I. Takeuchi, M. Ziatdinov. 2022. “Unsupervised learning of ferroic variants from atomically resolved STEM images.” AIP Advances 12 (10): 105122. doi:10.1063/5.0105406
  • Vasudevan R.K., A. Ghosh, M. Ziatdinov. S.V. Kalinin. 2022. “Exploring electron beam induced atomic assembly via reinforcement learning in a molecular dynamics environment*.” Nanotechnology 33, 115301. doi:10.1088/1361-6528/ac394a
  • Wang X., K. Jin, C.Y. Wong, D. Chen, H. Bei, Y. Wang, M. Ziatdinov, W.J. Weber, Y. Zhang, J. Poplawsky, K.L. More. 2022. “Understanding effects of chemical complexity on helium bubble formation in Ni-based concentrated solid solution alloys based on elemental segregation measurements.” Journal of Nuclear Materials, Volume 569, 153902. doi:10.1016/j.jnucmat.2022.153902.
  • Ziatdinov, M.A., A. Ghosh, S.V. Kalinin. 2022. “Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process.” Machine Learning: Science and Technology, 3 015003. doi:10.1088/2632-2153/ac4baa
  • Ziatdinov, M., Y. Liu, K. Kelley, R. Vasudevan, S.V. Kalinin. 2022. “Bayesian Active Learning for Scanning Probe Microscopy: From Gaussian Processes to Hypothesis Learning.” ACS nano., Vol.16(9), p.13492-13512. doi:10.1021/acsnano.2c05303
  • Ziatdinov, M.A., Y. Liu, A.N. Morozovska, E.A. Eliseev, X. Zhang, I. Takeuchi, S.V. Kalinin. 2022. “Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries.” Advanced Materials, Vol.34(20). doi:10.1002/adma.202201345
  • Ziatdinov, M., Ghosh, A., Wong, C.Y. et al. 2022. “AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy.” Nat Mach Intell 4, 1101–1112. doi:10.1038/s42256-022-00555-8