Day 4 - Autonomous Operation (guest lecture) - Longo

Day 4 - Autonomous Operation (guest lecture) - Longo

by Paolo Longo

Applied Sciences & Engineering Control & Robotics TJFElectronics engineeringTJFMAutomatic control engineering
🎙 Paolo Longo 👥 1K 📅 July 18, 2026 ⏱ 49 min 👁 10 📄 expert opinion 🧭 2026-08-16
Available in: English (current) Français

Keywords

autoscriptSTEMDPCadaptive scanningbeam blanker

Summary

Paolo Longo, a scientist at Thermo Fisher Scientific, delivers a guest lecture on leveraging scripting, automation, and AI to optimize Thermo Fisher microscopes, transforming materials characterization into a highly reproducible and controlled process. He begins by tracing the evolution of atomic-resolution microscopy over the past two decades, highlighting improvements in hardware, detectors, and software integration. The core challenge is that materials are evolving faster than characterization tools, and traditional manual operation is labor-intensive and limits efficiency. Longo proposes a future where AI acts as an adaptive feedback loop, separating the operator from the core experimental loop, enabling automated data acquisition, real-time decision-making, and multi-modal data integration. He emphasizes that hardware defines data quality, while AI defines data value, and true progress comes from their synergy. The lecture then focuses on scripting, particularly Thermo Fisher’s AutoScript interface, which provides an API to control every aspect of the microscope. Scripting transforms microscopy from a ’treasure hunt’ into a controlled experiment by encoding experimental methods, enabling reproducibility, explicit decision-making, and automated quality checks. Longo presents several practical examples: drift correction, atomic-level mapping of fluorine dopants in battery materials using a technique called ALCHiEM, and differential phase contrast (DPC) imaging of magnetic domains with automated vector overlay. He also discusses frame-based precession for strain analysis and the use of an electrostatic beam blanker on the Ilium microscope for dose reduction and adaptive scanning. Finally, he introduces AutoScript as an AI enabler, showing examples of adaptive scanning for nanoparticles and high-quality atomic imaging with minimal dose. The lecture concludes by emphasizing the importance of automation for reproducibility and the potential for AI to accelerate discovery.

270 words

Critical Evaluation

Value of the Information & Strength of the Argument

The lecture provides valuable insights into the practical application of scripting and automation in advanced electron microscopy, a topic of growing importance. The argumentation is solid, grounded in real-world examples and demonstrations. Longo effectively argues that scripting transforms microscopy from a manual, operator-dependent process into a controlled, reproducible experiment, which is crucial for scientific rigor. He supports his claims with concrete case studies, such as the ALCHiEM technique for mapping fluorine dopants and the DPC vector overlay for magnetic field visualization. The presentation is well-structured, progressing from general challenges to specific solutions, and includes a clear rationale for the synergy between hardware and AI. However, the lecture is somewhat promotional, as it focuses on Thermo Fisher’s products (AutoScript, Ilium) and may overstate the ease of implementation. The argumentation could be strengthened by addressing potential limitations or challenges of scripting, such as the learning curve or the risk of over-automation.

Scientific Rigor, Source Quality, Title Accuracy

The lecture demonstrates strong scientific rigor in its technical explanations and examples. Longo references specific techniques and methodologies, such as DPC, precession, and ALCHiEM, and provides detailed descriptions of the underlying physics. The sources cited are primarily internal to Thermo Fisher, including the AutoScript interface and the Ilium microscope, which are not independently verified. The title accurately reflects the content, focusing on autonomous operation and guest lecture. The lecture does not cite external scientific literature, which limits its academic rigor. However, the practical demonstrations and the logical flow of the argumentation contribute to its credibility. The content is consistent with current trends in microscopy automation, and the examples are plausible and well-documented within the presentation.

279 words

Title / Content Match

The title accurately reflects the content: a guest lecture on autonomous operation, focusing on scripting and AI in microscopy.

Quality & Reliability

8/10

The lecture is delivered by an expert from Thermo Fisher Scientific, presenting practical applications and technical details of scripting and automation in electron microscopy. The content is consistent with established practices in the field and includes specific examples with reproducible scripts. However, it is largely promotional and lacks peer-reviewed citations or independent validation.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

  • AutoScript for Thermo Scientific TEM — Mentioned as the scripting interface used for automation.
  • Ilium STEM — Mentioned as the flagship microscope with beam blanker and energy filter.

Concurring Sources

  • AutoScript for Thermo Scientific TEM — Official product page confirming the existence and features of AutoScript.
  • Ilium STEM — Official product page confirming the Ilium microscope's features.

Contribution & Novelties

The lecture provides a comprehensive overview of how scripting and AI can enhance electron microscopy, with practical examples from Thermo Fisher’s product line. The original contribution lies in demonstrating the transformation of microscopy from a manual, operator-dependent process to a controlled, reproducible experiment, emphasizing the importance of encoding experimental methods. The ALCHiEM technique for atomic-level mapping of light elements is a notable innovation, as it addresses a significant challenge in materials science. The lecture also highlights the potential of adaptive scanning and beam blankers for dose reduction, which is crucial for beam-sensitive materials.

Pour aller plus loin :

  • Differential phase contrast imaging — Provides background on DPC, a technique central to the lecture’s examples.
  • Scanning transmission electron microscopy — Explains the STEM technique used in the examples.
  • Machine learning in electron microscopy — Discusses AI applications in microscopy, relevant to the lecture’s AI integration.
  • Electron beam blanking — Background on beam blankers, used for dose control in the lecture.

159 words

Radar Profile

The radar profile shows high scores in quantity and quality of information, reflecting the detailed technical content and practical examples. The technical level is also high, indicating the lecture's depth. The global reliability is slightly lower, due to the promotional nature and lack of external citations.

Reliability 7/10

💬 No comments were provided for this video.