The partnership is not starting from a blank page. Under the memorandum, a joint research team has already completed first-phase, hands-on evaluations of superconducting quantum RF sensors for signals intelligence applications, conducted at the Jesper Munch Quantum Laboratories at Adelaide University in South Australia. Signals intelligence, the discipline of collecting, intercepting and analyzing electronic signals, underpins defense planning, secure communications and emergency response, and the sensors at the heart of this collaboration are designed to give analysts more usable information from the same crowded electromagnetic environment.

The physics behind the approach is rooted in the behavior of electrons inside superconducting materials. In such materials, RF signals have a dramatic effect on the dynamics of electrons, the negatively charged building blocks of atoms. Ultrasensitive, longer-range quantum RF sensing devices exploit changes in electron trajectory to extract more information from the RF environment than conventional antennas can manage. Precision circuits fabricated from superconducting materials convert those microscopic responses into raw data that yields accurate signal measurements, forming the basis of a sensing architecture that its developers argue outperforms traditional hardware in both sensitivity and information content.

Superconducting quantum RF systems leverage the unique properties of superconducting materials to detect and characterize signals across a broad swath of the electromagnetic spectrum. That breadth matters because the practical alternative, especially aboard military ships and aircraft where every cubic meter is contested, is a collection of bulky antennas each tuned to a portion of the spectrum. Compact quantum systems offer the potential to replace those installations outright, collapsing multiple frequency-specific apertures into a single small package.

Staff Engineer Michael Quinn, who leads quantum RF research and development in SwRI’s Defense and Intelligence Solutions Division offices in Warner Robins, Georgia, framed the size advantage as fundamental rather than incremental. Unlike conventional antennas, which grow bulkier as frequencies get lower, quantum RF device size is independent of frequency, he explained. According to Quinn, these systems achieve broad coverage from kilohertz to terahertz with the same compact hardware, providing more critical information while occupying less space. That combination, he noted, is a major advantage for defense and intelligence missions where size, weight and power are critical considerations, the classic SWaP constraints that shape nearly every airborne and shipboard system design.

The hardware that makes this possible is grown, in a literal sense, at Adelaide University. The university’s quantum laboratories house a state-of-the-art molecular beam epitaxy system, or MBE, that builds advanced superconductor and quantum materials one atomic layer at a time, a process its researchers liken to a 3D printer operating at the atomic scale. The MBE transforms raw materials into a Superconducting QUantum Interference Device, better known as a SQUID, which is then supercooled to minus 452.47 degrees Fahrenheit to activate its superconducting properties and its characteristic RF wave response. At those cryogenic temperatures, the device becomes sensitive to extraordinarily faint electromagnetic signals.

Cryogenics remains one of the technology’s biggest practical hurdles, and reducing that burden is an explicit goal of the collaboration. Researchers are exploring new material architectures designed to raise SQUID operating temperatures, cut cooling requirements and improve portability and operational practicality. Every degree by which the operating temperature can climb translates into smaller, lighter and less power-hungry cooling systems, which in turn determines whether quantum RF sensors can leave the laboratory and fly on real platforms. The partnership deliberately pairs Adelaide University’s expertise in superconducting quantum materials and sensor development with SwRI’s strengths in advanced RF engineering, signals processing and operational applications, covering the full chain from atomic-scale fabrication to fielded mission use.

Professor Giuseppe C. Tettamanzi, director of the Jesper Munch Quantum Laboratories and leader of Adelaide University’s superconducting quantum technologies research program, described how the first phase of joint work unfolded. The SwRI team tested and assessed selected performance metrics of the superconducting quantum RF technology developed by Adelaide University, he said. By combining their complementary expertise, he added, the two institutions are accelerating the development and maturation of quantum RF technologies with the potential to address the challenges of increasingly congested electromagnetic environments and complex operational scenarios. Tettamanzi also positioned the project as an example of the value of deep scientific alliances between Australia and the United States in advancing technologies critical to future security and economic prosperity.

The timing of the agreement reflects a broader surge of public investment in quantum science, which spans computing, communications and sensing and is being backed worldwide as well as at state and federal levels in the United States. In Texas, the recent Texas Quantum Initiative supports strategic planning for quantum technology funding and workforce training, an effort that gives in-state organizations such as SwRI a policy backdrop for expanding their quantum portfolios. At the federal level, the U.S. Department of War announced in June a Post Quantum Cryptography Strategy aimed at protecting critical government and military systems from emerging quantum threats, underscoring how quantum technologies are simultaneously viewed as an opportunity for new capabilities and a risk requiring defensive preparation.

For the engineers involved, the collaboration represents a rare chance to work at the frontier of an emerging discipline before it hardens into standard practice. Institute Engineer David Brown, based in Warner Robins and part of SwRI’s quantum technology exploration team, called quantum RF sensing an incredible new area of technology and described the project as a once-in-a-lifetime opportunity to be on the absolute cutting edge of science and explore the application of the most advanced technology of our lifetime. SwRI, he said, is eager to add these groundbreaking capabilities for its government and industry clients. With the memorandum of understanding now in place, the two institutions have established a foundation for future research, technology maturation and opportunities in quantum sensing, advanced RF systems and related mission applications, and the first-phase evaluations suggest the compact, cryogenically cooled sensors they are refining could eventually do the work of antenna farms many times their size.

Subject of Research: Superconducting quantum radio frequency sensing for signals intelligence applications

Article Title: SwRI, Adelaide University sign quantum RF research and development MOU

Article References: SwRI, Adelaide University sign quantum RF research and development MOU. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: quantum sensing, radio frequency, superconductors, SQUID, signals intelligence, SwRI, Adelaide University, molecular beam epitaxy, defense technology, electromagnetic spectrum, quantum materials, research partnership

Conventional approaches to unknown waveform detection have generally fallen into two camps. Statistical anomaly detection methods build a model of what normal signals look like and flag anything that deviates from it, an approach that is conceptually elegant but notoriously brittle in cluttered spectral environments where legitimate signals vary wildly in power, modulation and bandwidth. Deep learning classifiers, meanwhile, have delivered impressive results on benchmark datasets of known modulations, yet they stumble when confronted with waveform families absent from their training sets. Some researchers have tried to bridge this gap with generative techniques that synthesize artificial examples of unknown signals, but generating realistic synthetic samples is itself an unsolved problem, and poorly generated data can bias a model in ways that are difficult to diagnose. The result, in practice, is that fielded systems often fail exactly when they are needed most: during encounters with genuinely novel emitters.

The new discriminative model sidesteps synthetic sample generation altogether. Instead of trying to imagine what unknown waveforms might look like, it learns a richer description of the signals it does know, so that anything sufficiently different stands out sharply. The key architectural decision is the joint use of time-domain and frequency-domain representations. The time domain captures how a signal’s amplitude evolves moment to moment, preserving transient features, timing structure and modulation transitions that unfold in sequence. The frequency domain, obtained through transforms such as the Fourier transform, reveals how energy is distributed across the spectrum, exposing carrier offsets, spectral occupancy, harmonic structure and bandwidth fingerprints. Human signal analysts have long toggled between these two views on oscilloscopes and spectrum analyzers; the invention encodes that dual perspective directly into the learning pipeline.

But merely concatenating two views of a signal would not, by itself, guarantee better detection. The second pillar of the invention is a cosine similarity loss function that reshapes the model’s internal feature space. In machine learning, a loss function defines what a model is penalized for getting wrong, and therefore what it learns to prioritize. Cosine similarity measures the angle between two feature vectors rather than the distance between them, meaning it is sensitive to the direction of a representation but insensitive to its magnitude. By training with a cosine similarity objective, the system is pushed to align the feature vectors of signals from the same class more tightly while steering vectors of different classes apart. Class-specific features become more cleanly separated, and the model develops a sharper decision boundary between familiar waveform families and everything else.

The practical consequence of this design is a measurable jump in performance. In testing against comparable models that lacked the combined time-frequency representation and the cosine similarity mechanism, the invention delivered approximately a 10 percent improvement in detection accuracy for unknown waveforms. A ten percent gain may sound incremental, but in the context of unknown-signal detection, where baseline systems frequently operate in regimes of unreliable performance, it represents a substantial margin. It means fewer missed detections of genuinely anomalous emitters and fewer false alarms triggered by ordinary variations in known signals, both of which carry real operational costs. The improvement stems directly from the model’s enhanced ability to differentiate subtle waveform variations that do not appear in its training data, rather than from any increase in raw computational capacity.

Robustness and generalization are the qualities that make this improvement durable rather than dataset-specific. Because the model’s features are aligned by direction in the feature space, they are less sensitive to the scale of a signal’s power, a property that matters enormously in realistic radio environments where the same emitter may be received at wildly different strengths depending on distance, terrain and antenna orientation. The dual-domain representation also provides redundancy: a waveform feature that is ambiguous in the time domain, such as a slight shift in spectral occupancy, may be unmistakable in the frequency domain, and vice versa for temporal phenomena. This built-in cross-checking gives the system a form of resilience that single-representation classifiers lack, allowing it to maintain accurate classification under the noisy, adversarial conditions that characterize contested spectrum.

The anticipated applications span both military and civilian domains. In electronic warfare, the ability to detect and classify unknown communication signals is foundational to situational awareness, since an adversary’s new emitter is by definition absent from any pre-existing threat library. Spectrum management authorities could deploy the technology to monitor and enforce the use of the electromagnetic spectrum, identifying rogue transmissions and interference sources that conventional monitoring tools miss. Intelligence, surveillance and reconnaissance operations depend on reliable waveform identification, and the invention’s resistance to the biases introduced by synthetic sample generation makes it a more trustworthy analytic tool. Radio astronomers, who fight a constant battle against radio-frequency interference contaminating observations of faint cosmic sources, could use the model to detect and mitigate intruding signals. Communication security systems, meanwhile, could apply it to flag unauthorized or anomalous transmitters operating within protected networks.

The technology is at technology readiness level 3, the stage at which a concept has been proven analytically and experimentally in laboratory conditions but has not yet been integrated into an operational prototype. It is patent pending and available for licensing through the Research Foundation for the State University of New York, the nation’s largest research foundation, which supports research across the SUNY system in areas including artificial intelligence for the public good, quantum technologies, next-generation semiconductors, biotech and medicine, and energy and climate solutions. SUNY, the largest comprehensive system of higher education in the United States, oversees nearly a quarter of academic research in New York, with research expenditures of nearly 1.5 billion dollars in fiscal year 2025, and the foundation offers multiple pathways for translating such innovations into commercial and economic development opportunities.

What makes the invention notable beyond its immediate applications is the clarity of its underlying insight. Much of modern machine learning progress has come from adding scale: more layers, more parameters, more data. This work demonstrates that careful attention to how a signal is represented, and to how a model is trained to organize its internal features, can yield decisive gains without any of that overhead. By combining two complementary mathematical descriptions of the same physical phenomenon and aligning them with a geometry-aware loss function, the researchers have built a system that sees the electromagnetic world the way an experienced analyst does, from multiple angles at once. As the radio spectrum grows more crowded and the population of uncooperative or unrecognized transmitters continues to expand, tools that can reliably distinguish the known from the genuinely unknown will only grow in importance, and this time-frequency approach offers a concrete, testable step toward that goal.

Subject of Research: An AI model combining time-domain and frequency-domain features with cosine similarity loss for detecting unknown electromagnetic waveforms.

Article Title: Contrasting time-frequency representations for unknown waveform detection

Article References: Contrasting time-frequency representations for unknown waveform detection. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: unknown waveform detection, cosine similarity loss, time-frequency analysis, electromagnetic spectrum, machine learning, electronic warfare, spectrum management, radio-frequency interference, signal classification, deep learning, radio astronomy, SUNY licensing