Resources for Neural Emulators and Scientific Machine Learning

Thesis by Felix Kohler has a good overview of this area and his work. More work can be found by Prof. Nils Thuerey and his group at TUM. Their work on emulators also comes with a pytorch package for training neural emulators for PDEs.

For stochastic benchmarks, recently the group also developed a Stochbench https://tum-pbs.github.io/stocbench/ for comparing different methods for next time prediction.

Courses in Scientific Machine Learning: https://neu4mes.github.io/teaching/ https://physicsbaseddeeplearning.org/intro.html

Geometric deep learning and graph neural networks: https://geometricdeeplearning.com/lectures/

AGU released Impactful daatsets

https://data.agu.org/impactful-datasets/

Resources for Data Assimilation and Uncertainty Quantification

AI4OCEAN

https://ai-for-ocean.github.io/workshop2026/

Deep Learning Collection

https://visionbook.mit.edu/backpropagation.html#alg-backpropagation-backprop_for_chains

Journal to Submit to

https://link.springer.com/collections/jfajjbiajd

Visionbookmit

https://visionbook.mit.edu/backpropagation.html#alg-backpropagation-backprop_for_chains

Handbook of Bayesian Deep Learning

https://zenodo.org/records/22114549

Thesis

file:///C:/Users/Shashank/Downloads/Alet-alet-PhD-EECS-2022-thesis.pdf

On writing

https://www.microsoft.com/en-us/research/academic-program/how-to-write-a-great-research-proposal/