.png){kind=logo}
Dmitry Mikhaylov is a scientist focused on developing physics-aware artificial intelligence – AI systems that combine machine learning with an understanding of the physical processes behind the data. One of the practical directions of this work is acoustic AI, where sound from the human body, machines, or natural ecosystems is analyzed to detect disease, predict equipment failures, and measure biodiversity in real time.
Dmitry Mikhaylov is University of Warwick (UK) graduate. He earned a PhD in Artificial Intelligence as well as an MBA in R&D Management.
His research focuses on integrating the laws and constraints of physics into artificial intelligence, developing physics-aware models that ensure physical consistency and operational stability. By combining signal processing, domain-specific physics, and remote sensing technologies, he designs AI systems applied across a range of fields, including industry, environmental monitoring, and healthcare.
Dmitry Mikhaylov has authored more than 100 peer-reviewed scientific papers and holds over 30 international patents.
Alongside his work in artificial intelligence, Dmitry Mikhaylov has also contributed to fundamental physics research. He participated in the preparation of the “International Large Detector: Interim Design Report”, a document outlining the reference design for a next-generation detector for an electron–positron collider.
During the course of his career, Dmitry Mikhaylov served as a Supervising Professor at Khalifa University in the UAE as well as an Associate Professor in AI at the National University of Singapore.
Dmitry Mikhaylov was a guest lecturer at a number of top national universities across the globe: Tufts University (USA), University of Sydney (Australia), Tashkent State Agrarian University (Uzbekistan) and Dankook University (South Korea).
Since 2022, Dmitry Mikhaylov has been included in the pool of United Nations experts on AI-governance and continues to serve both as a United Nations expert and a researcher on AI for the Sustainable Development Goals.
Dmitry Mikhaylov’s physics-aware AI methods have been applied in several technology ventures around the world. These include a UAE-based systemthat applies artificial intelligence and biofeedback in therapeutic games to enhance attention and cognitive performance; a Singapore-based initiative developing computer vision systems for insect farming and agriculture; a solution focused on optimizing airline operations; and a venture applying AI-driven approaches to advanced materials and industrial applications, among other projects.
Dmitry Mikhaylov’s research and work in artificial intelligence have been recognized in several international media rankings and innovation awards. His projects have been featured among the Top 100 Artificial Intelligence Companies in the UAE (2025) and among the top gaming and technology startups in the UAE (2024).
In 2024, his work received the Global Generative AI Award in the Healthcare and Life Sciences category for innovations in generative AI applications.
His research in artificial intelligence and applied technologies was also included in the nomination list of the Arabian Business Achievement Awards 2023 for innovations in AI.
In addition to international recognition, in 2024 Mikhaylov received a Kyrgyzstan government award for his work with the United Nations on projects supporting the country’s sustainable development.
Physics-aware AI can be applied across many domains, and as a practical scientist Dmitry Mikhaylov has explored a wide range of such applications. One of the areas he became particularly passionate about is acoustic artificial intelligence – a field where his work has received multiple awards and resulted in several strong research publications.
Mikhaylov’s work on acoustic AI focuses on how sound can reveal hidden information about complex systems. Acoustic signals – whether produced by the human body, machines, or natural environments – contain patterns that artificial intelligence can analyze to detect subtle changes that humans cannot easily hear.
This research direction began in Singapore during the COVID-19 pandemic, when the government actively supported the development of new technologies to help detect and control the virus. During his work at the National University of Singapore, Mikhaylov and his team explored how artificial intelligence could analyze cough sounds to detect respiratory infections.
The idea was simple but powerful: when a person coughs into a smartphone where Mikhaylov’s application is installed, the sound carries acoustic signatures produced by the lungs and airways. Machine-learning models were trained to recognize patterns associated with COVID-19 and distinguish them from other respiratory conditions. The mobile application could analyze cough recordings and provide rapid screening with accuracy approaching that of PCR testing, offering a fast and accessible diagnostic tool.
The technology later received regulatory recognition in Vietnam, where it was certified as a national digital health tool. After Mikhaylov moved to the UAE, he worked to apply the solution there as well, particularly during Dubai’s innovation push around Expo 2020 and the search for new technologies to help monitor and control the spread of COVID-19. The project attracted international attention and was later included in the nomination list of the Arabian Business Achievement Awards 2023 as one of the most impactful medical technology solutions, alongside leading global healthcare innovations.
After the pandemic, the same acoustic AI technology was adapted by Mikhaylov for industrial applications. Machines constantly produce sound during operation, and these sounds often change slightly before mechanical problems occur.
By placing acoustic sensors near engines, turbines, HVAC systems, and other industrial equipment, artificial intelligence can analyze sound patterns and identify early signals of wear or malfunction. Long before a failure becomes visible, the system detects unusual acoustic signatures and alerts operators that maintenance may be required.
This approach allows companies to repair equipment before breakdowns occur, reducing downtime and preventing costly damage. Such acoustic monitoring systems have been applied in industrial facilities in the UAE, where they help operators maintain complex infrastructure more efficiently.
Following his practical approach to research, Mikhaylov later applied the same acoustic AI technology to environmental monitoring. Natural ecosystems are full of sound – birds, insects, frogs, and other animals constantly produce acoustic signals that reflect the state of the environment.
The idea was straightforward: if these sounds can be recorded and analyzed, they can reveal what species are present and how active the ecosystem is. Small microphones are installed in forests or natural reserves to continuously capture the surrounding soundscape. Artificial intelligence then analyzes these recordings, identifying species and patterns of activity that indicate the health of the ecosystem.
From this data, the system generates biodiversity scores that show how rich and balanced the environment is. Such measurements make it possible to track ecological changes objectively and provide reliable indicators for conservation projects and environmental investment.
This approach has been implemented in Zimbabwe, where acoustic sensors placed in national parks help researchers monitor wildlife activity and evaluate the condition of local ecosystems.
Mikhaylov often describes his vision of artificial intelligence through practical signal interpretation – teaching machines to understand patterns hidden in sound, behavior, and physical processes rather than simply processing large volumes of data.
In his work, acoustic AI becomes a tool for solving real-world problems: detecting disease through cough analysis, identifying early signs of mechanical failure in machines, or measuring biodiversity by listening to natural ecosystems.
For Dr. Dmitry Mikhaylov, the future of AI lies in systems that can “listen” to the world – interpreting signals from people, technology, and nature in order to support better decisions and more resilient systems
