Scientific Machine Learning Research Lab
About
The SciML Research Lab excels in merging statistical inference, dynamical systems modeling, and AI to dissect complex phenomena. Our projects span from psychotherapy to environmental sciences, advocating physics-informed machine learning to weave neural networks with dynamic physical processes. As we push the frontiers of theory and practice, we remain committed to pioneering transformative solutions that empower data-driven decision-making and innovation across diverse sectors.
The research carried out in our lab is supported by Israel Science Foundation (ISF), Ministry of Agriculture and Rural Development, India-Israel Scientific Research Program & Israel Data science and AI initiative. We collaborate with industrial partners such as IBM and MIGAL Galilee Research Institute Ltd.
People
Publications
Khanonkin E., Schechter I., Dattner I. (2025). Compensation for Matrix Effects in High-Dimensional Spectral Data using Standard Addition. Sensors, 25(3), 612. https://doi.org/10.3390/s25030612
The article presents a new method to address matrix effects in high-dimensional spectral data, which often distort analyte quantification when blank samples or prior knowledge of the sample composition are unavailable. The authors extend the classic
Rozenkrantz L., Laskorunskyi, O., Zilcha-Mano S., Dattner I. (2025). Expectation-Updating: Understanding the Dynamics of Expectancy in Psychotherapy Outcome. Accepted to Psychotherapy Research.
The article examines the role of patients’ changing expectations about treatment outcomes in psychotherapy for depression. It shows that not only baseline expectations (before treatment starts) but also the within-person change in expectations over time independently