About
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…
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…
This study introduces a novel mechanistic modeling and statistical framework for analyzing motion energy dynamics within psychotherapy sessions. We transform raw motion energy data into an interpretable narrative of therapist-patient interactions, thereby revealing unique insights into the nature of these dynamics. Our methodology is established through three detailed case studies, each shedding light on the complexities of dyadic interactions. A key component of our approach is an analysis spanning four years of one therapist's sessions, allowing us to distinguish between trait-like and state-like dynamics. This research represents a significant advancement in the quantitative understanding of motion dynamics in psychotherapy, with the potential to substantially influence both future research and therapeutic practice.
Ordinary differential equations (ODEs) are foundational in modeling intricate dynamics across a gamut of scientific disciplines. Yet, a possibility to represent a single phenomenon through multiple ODE models, driven by different understandings of nuances in internal mechanisms or abstraction levels, presents a model selection challenge. This study introduces a testing-based approach for ODE model selection amidst statistical noise. Rooted in the model misspecification framework, we adapt foundational insights from classical statistical paradigms (Vuong and Hotelling) to the ODE context, allowing for the comparison and ranking of diverse causal explanations without the constraints of nested models. Our simulation studies validate the theoretical robustness of our proposed test, revealing its consistent size and power. Real-world data examples further underscore the algorithm's applicability in practice. To foster accessibility and encourage real-world applications, we provide a user-friendly Python implementation of our model selection algorithm, bridging theoretical advancements with hands-on tools for the scientific community.
Dr. Itai Dattner has been awarded the prestigious Ministry of Innovation, Science & Technology Research Grant! The winning research project, titled "Hybrid-AI Quantile Regression: Combining Nonparametric Statistical Methods and Physics-Informed Neural Networks for Analyzing Spatio-temporal Climate Data," explores groundbreaking applications of AI in addressing one of the most pressing global challenges – climate change.
Welcome Daniel Polster to the SciML Lab Team! We are delighted to introduce our newest team member, Daniel Polster, who joins us as a Research Assistant. We look forward to achieving new milestones together and exploring the frontiers of AI research. We're thrilled to have you on board, Daniel!
Dr. Itai Dattner have received a research grant from the Ministry of Ministry of Agriculture and Rural Development. His winning research project, titled: Innovative AI-Driven Approach for the Development of Postharvest Protocols Under Extreme Climatic Conditions, focuses on the development of postharvest protocols using physics-informed machine learning for assessing the quality of cucumbers, zucchini, champignon, and portobello mushrooms under extreme climatic conditions. By integrating advanced AI with physics-based insights, the project aims to accurately predict produce fitness through image analysis.
Projects Hybrid-AI Quantile Regression for Spatio-Temporal Climate Analysis This project develops a Hybrid-AI Quantile Regression framework, merging nonparametric statistical methods with physics-informed neural networks.It aims to enhance the understanding and…
Project 2Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut elit tellus, luctus nec ullamcorper mattis, pulvinar dapibus leo.
Past ProjectsLorem ipsum dolor sit amet, consectetur adipiscing elit. Ut elit tellus, luctus nec ullamcorper mattis, pulvinar dapibus leo.