AI-Generated Control Software to Democratize Automation of Materials Science Instruments

Large language models (LLMs) are one of the AI technologies that are transforming the landscape of chemistry and materials science. Recent examples of LLM-accelerated experimental research include virtual assistants for parsing synthesis recipes from the literature, or using the extracted knowledge to guide synthesis and characterization. However, these AI-driven materials advances are limited to a few laboratories with existing automated instruments and control software, whereas the rest of materials science research remains highly manual. AI-crafted control code for automating scientific instruments would democratize and further accelerate materials research advances, but reports of such AI applications remain scarce. In this presentation, we will discuss how we swiftly established a Python-based control module for a scientific measurement instrument solely through interactions with ChatGPT-4. Through a series of test and correction cycles, we achieved successful management of a common Keithley 2400 electrical source measure unit instrument with minimal human-corrected code. Additionally, a user-friendly graphical user interface (GUI) was created by ChatGPT-4, effectively linking many instrument controls to interactive screen elements. Finally, we integrated this AI-crafted instrument control software with a high-performance Differential Evolution algorithm to facilitate rapid and automated extraction of electronic device parameters related to semiconductor charge transport mechanisms from current-voltage (IV) measurement data. This integration resulted in a comprehensive open-source toolkit for semiconductor device characterization and analysis using IV curve measurements. We will also discuss the application of these tools to the analysis of IV data from a Pt/Cr₂O₃:Mg/β-Ga₂O₃ heterojunction diode, a novel stack for high-power and high-temperature electronic devices. We will present the challenges encountered during our interactions with ChatGPT-4, and how to evolve from this prompt-based conversation approach to an automated workflow using tools such as <i>LangChain</i>, where LLMs can effectively take control of the instrument and actively develop control solutions based on real-time tests.