Application of physics-informed neural networks (PINNs) for reaction-diffusion PDEs modeling an avascular growing tumor

Κατσίφης, Ηλίας; Katsifis, Ilias

dc.contributor.author	Κατσίφης, Ηλίας	el
dc.contributor.author	Katsifis, Ilias	en
dc.date.accessioned	2025-01-08T13:30:42Z
dc.date.available	2025-01-08T13:30:42Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/60667
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.28363
dc.description	Εθνικό Μετσόβιο Πολυτεχνείο--Μεταπτυχιακή Εργασία. Διεπιστημονικό-Διατμηματικό Πρόγραμμα Μεταπτυχιακών Σπουδών (Δ.Π.Μ.Σ.) “Υπολογιστική Μηχανική”
dc.rights	Default License
dc.subject	Machine Learning	en
dc.subject	PINNs	en
dc.subject	PDE	en
dc.subject	Tumor	en
dc.subject	Reaction-Diffusion	en
dc.subject	Μηχανική Μάθηση	el
dc.subject	Μερικές Διαφορικές Εξισώσεις	el
dc.subject	Όγκος	el
dc.subject	Αντίδραση-Διάχυση	el
dc.subject	Χωρίς Αγγείωση	el
dc.title	Application of physics-informed neural networks (PINNs) for reaction-diffusion PDEs modeling an avascular growing tumor	en
heal.type	masterThesis
heal.classification	Machine Learning	en
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-06-28
heal.abstract	This Master’s thesis explores the application of deep learning techniques for reaction-diffusion partial differential equations (PDEs) modeling an avascular growing tumor, specifically utilizing physics-informed neural networks (PINNs). PINNs are an innovative and effective approach for solving partial differential equations (PDEs) and conducting parameter inference. The study focuses on a diffusion-reaction model that simulates the interaction between a cancerous tumor and the nutrient oxygen. To enhance the convergence and effectiveness of the neural network, a novel method known as dynamic weights was employed. More specifically a weight was assigned in each term of the loss function which includes the PDEs, the initial conditions and the boundary conditions. This technique adjusts the weights of each term in the loss function to address potential gradient imbalances during training. Additionally, parameter inference was performed for diffusion coefficients, which vary between patients due to the personalized nature of these values. The results were highly satisfactory, indicating the potential for extending this approach to higher dimensions and more complex geometries, which are common challenges in numerical methods.	en
heal.advisorName	Kavousanakis, Mihalis	en
heal.committeeMemberName	Kokkoris, George	en
heal.committeeMemberName	Sarimveis, Haralambos	en
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Χημικών Μηχανικών	el
heal.academicPublisherID	ntua
heal.fullTextAvailability	false