Hi 👋, I'm Milad Panahi

A Passionate Early Stage Researcher

About Me

I am a third-year PhD candidate in Civil and Environmental Engineering at Politecnico di Milano, specializing in Scientific Machine Learning and Data-Driven Scientific Computing for Geo-Hydro-Chemical systems. My research leverages physics-informed machine learning to enhance modeling and uncertainty quantification in subsurface hydrology, bridging the gap between theoretical advancements and real-world applications.

My academic journey began at Sharif University of Technology (SUT), where I earned my bachelor’s degree in Civil Engineering. I then pursued research in Hydrometeorology at the University of Arizona, before joining the MIPORE research group at Politecnico di Milano. Throughout my career, I have been fortunate to be mentored by leading experts in the field, including Prof. Hoshin Gupta, a pioneer in Dynamical Systems Modeling and Systems Theory, and Prof. Alberto Guadagnini, a renowned researcher in subsurface flow and stochastic hydrogeology. Their guidance has been instrumental in shaping my scientific approach, blending rigorous theory with impactful, data-driven applications.

Along the way, I have had the privilege of receiving funding from NASA and the prestigious Marie Skłodowska-Curie European Industrial Doctorate (EID) programme, recognizing the significance of my work at the intersection of computational science and engineering.

Currently, I am part of REMEDI - an Innovative Training Network (ITN), an EU-funded Innovative Training Network (ITN) under Horizon 2020, where I collaborate with both academic institutions and industry partners to develop cutting-edge methodologies for environmental and geoscience applications. My work focuses on integrating uncertainty-aware, physics-based AI models with real-world data, aiming to advance sustainable decision-making in environmental engineering and risk assessment.

I am always eager to connect with researchers, industry professionals, and organizations looking to explore the transformative potential of AI-driven modeling in engineering and the environmental sciences. Let’s discuss how data-driven insights and physics-inspired AI can drive innovation in your field.

What I'm Working On

🔭 PhD research on leveraging physics-inspired machine learning methods for Geo-Hydrologic dynamical systems.
👯 Contributing to the SciML community - where physical science and machine learning converge.
🌱 Learning about Bayesian networks, Graph NNs, Gaussian process kernels, and more.

My Erdős Number Connections

I'm fascinated by the web of collaborations in science and mathematics. Through my supervisors and mentors, I have several paths connecting me to the legendary Paul Erdős.

My current shortest Erdős number is 5, primarily through my PhD work. I also have connections of length 6 from earlier research experiences. Hopefully, future collaborations will shorten this number!

Paths to Erdős (Erdős Number 5)

Path 1 (via Prof. Alberto Guadagnini):
Paul Erdős → Diaconis, Persi W. → Newman, Charles M. → Shlomo P. Neuman → Alberto Guadagnini → Milad Panahi (Me)

Path 2 (via Prof. Giovanni Michele Porta):
Paul Erdős → Alon, Noga → Barkai, Naama → Berkowitz, Brian → Giovanni Michele Porta → Milad Panahi (Me)

Other Connections (Erdős Number 6)

Path 3 (via Prof. Hoshin V. Gupta):
Paul Erdős → Gerencsér, László → Szigeti, Ferenc → Carrera, Jesús → Hoshin V. Gupta → Ali Behrangi → Milad Panahi (Me)

Path 4 (via Prof. Xubin Zeng):
Paul Erdős → Winkler, Peter Mann → Kandel, Daniel → Domany, Eytan → Eykholt, R. → Xubin Zeng → Milad Panahi (Me)

You can explore collaboration distances using tools like the AMS MathSciNet Collaboration Distance Calculator.