Artificial intelligence has transformed natural language processing by breaking continuous information into discrete tokens and modeling their relationships. Now, a new conceptual framework suggests that spectroscopy could offer the physical sciences an analogous information system: spectra can be treated as "physical tokens" generated when matter interacts with electromagnetic radiation. These tokens encode identity, local environment, dynamic change, and relationships governed by quantum mechanics. By reframing spectra as a computable language of matter rather than only an analytical readout, the framework could help connect spectroscopy, machine learning, inverse design, and automated experimentation, laying the groundwork for a more unified, AI-readable language for materials discovery.
Spectroscopy has long been used to identify substances and probe their structures through characteristic absorption, emission, vibrational, and diffraction signals. Yet conventional spectral analysis often depends on expert knowledge, curated reference databases, or computationally intensive quantum-chemical calculations. At the same time, artificial intelligence is increasingly being used to extract complex patterns from scientific data and to generate candidate materials with desired properties. What remains missing is a unified way to connect spectral features, physical laws, machine-readable representations, and generative design within one framework. Because of these challenges, deeper investigation is needed into how spectral information can be encoded and interpreted as a physically grounded language for AI-driven science.
In a Comment published (DOI: 10.1021/prechem.6c00070) on August 24, 2026, in Precision Chemistry, Yi Luo of the Hefei National Research Center for Physical Science at the Microscale, University of Science and Technology of China, and the Hefei National Laboratory, University of Science and Technology of China, proposes a unifying framework in which spectra function as "physical tokens." The article links spectral encoding, relational structure, AI-based interpretation, and spectrum-guided generation, arguing that spectroscopy could become a foundational information substrate for intelligent materials research.
The framework defines a physical token as a physically constrained unit of spectral information that can be represented at several levels. At the quantum level, tokens may correspond to transitions set by energy structures and selection rules; at the experimental level, they appear as peaks, shifts, intensities, line widths, splittings, and line-shape patterns; and at the machine-learning level, they can be discretized into spectral intervals, patches, multimodal descriptors, or latent representations. The article then extends the analogy from vocabulary to grammar. Relationships among spectral position, intensity, line shape, and environmental response encode the "syntax" of material behavior, allowing spectra to act as multidimensional maps of physicochemical interactions. This idea supports a shift from simple pattern matching toward more interpretable AI systems that learn links among spectrum, structure, composition, and function.
The most ambitious extension is spectrum-guided inverse design: a target function could be translated into a theoretical spectral blueprint, from which physics-informed generative models propose candidate structures. Synthesis and spectroscopic validation would then feed results back into the model, creating a closed loop from desired function to design, experiment, and refinement. The Comment emphasizes that spectra should be viewed not simply as fingerprints used after an experiment, but as an active information interface connecting physical laws, data, and design. In this view, AI systems could learn to read spectral patterns in ways that remain constrained by quantum mechanics while also using those patterns to guide what materials should be made next. This shift could move spectroscopy from passive characterization toward a more creative role, where spectral information helps organize scientific reasoning, generation, and experimental feedback within the same framework.
If developed further, the physical-token framework could influence how scientific datasets, AI models, and automated laboratories are built. The article calls for high-quality multimodal spectral databases; physics-informed models spanning infrared, Raman, nuclear magnetic resonance, and X-ray techniques; complete spectrum–structure–property pipelines; and tighter links between computational models, robotic synthesis, and high-throughput in situ characterization. Such infrastructure could support self-driving laboratories in which human researchers define goals, AI plans candidate pathways, robots execute experiments, and new spectra refine the next round of decisions. The broader implication is a more unified, machine-readable language for matter that connects observation, interpretation, and design across chemistry and materials science. For industry, this could accelerate the discovery of new materials with tailored properties, reducing reliance on trial-and-error experimentation. The framework also highlights the need for collaborative efforts, as exemplified by initiatives like Chuanlink Innovations, which fosters connections between revolutionary ideas and their realization.
