Artificial intelligence (AI) is becoming an increasingly integral component of measurement systems and processes, enabling advanced data processing, feature extraction, pattern recognition, anomaly detection, prediction, sensor fusion and automated decision-making capabilities. In application domains ranging from industrial monitoring and condition assessment to biomedical engineering and environmental measurements, AI-based methods provide opportunities to derive meaningful information from complex, high-dimensional and heterogeneous data.

Nevertheless, the growing presence of AI in the measurement process introduces new challenges for measurement science. When measurement results depend directly or indirectly on data-driven models, it is no longer possible to assess their reliability solely in terms of conventional model accuracy or predictive performance. Robustness, interpretability, traceability, reproducibility, sensitivity to input data and distribution shifts, and uncertainty associated with AI-generated outputs are all essential factors in establishing confidence in measurement results. These aspects also align with the broader requirements for trustworthy and reliable AI as set out in current regulatory frameworks, including the EU AI Act.

From a metrological perspective, the adoption of AI should be considered a technological opportunity and a challenge in terms of model characterisation and measurement validation. Appropriate methodologies are needed to evaluate the effect of AI models on the reliability and trustworthiness of measurements, to identify and assess their contribution to measurement uncertainty, and to establish the conditions under which their outputs remain reliable, comparable and fit for purpose. This includes developing validation procedures, performance metrics, and uncertainty evaluation frameworks and techniques. It also involves assessing sensitivity to training and input data, and investigating the stability and consistency of AI-assisted measurements under varying operating conditions.

The aim of this Special Session is to bring together researchers working at the intersection of artificial intelligence and measurement science. The focus will be on the metrological foundations, validation methodologies, and practical implementation of AI-assisted measurement systems. The session will provide a forum for discussing methodological advances, experimental studies, validation frameworks, and real-world applications, as well as the challenges that still need to be overcome to ensure that AI-supported measurements are reliable, transparent, traceable, and scientifically sound. Contributions that address the normative and standardisation perspective are also welcome, including emerging standards, guidelines and regulatory requirements for AI-assisted measurements.

Topics of interest include, but are not limited to:
• AI-based methods for measurement data processing and interpretation
• Machine learning and deep learning for sensor systems and instrumentation
• Metrological validation of AI-assisted measurement systems
• Uncertainty evaluation in AI-based measurements
• Traceability, comparability, and reliability of AI-derived measurement results
• Explainability, transparency, and robustness of AI models in measurement applications
• Sensitivity of AI-assisted measurements to data quality and operating conditions
• AI for anomaly detection, predictive maintenance, and decision support in measurement contexts
• Applications of AI-assisted measurements in industry, healthcare, environment, and smart systems
• Standards, guidelines, and regulatory aspects for AI in metrology