EELSFitter is an open-source Python-based framework developed for the analysis and interpretation of Electron Energy Loss Spectroscopy (EELS) measurements in Transmission Electron Microscopy (TEM). EELSfitter is based on the machine learning techniques developed by the NNPDF Collaboration in the context of applications in high energy physics, in particular feed-forward neural networks for unbiased regression in multidimensional problems.

EELSFitter has been used in the following scientific publications:

• Charting the low-loss region in Electron Energy Loss Spectroscopy with machine learning, Laurien I. Roest, Sabrya E. van Heijst, Luigi Maduro, Juan Rojo, Sonia Conesa-Boj.
• Illuminating the Electronic Properties of WS₂ Polytypism with Electron Microscopy, Sabrya E. van Heijst, Masaki Mukai, Eiji Okunishi, Hiroki Hashiguchi, Laurien I. Roest, Luigi Maduro, Juan Rojo, Sonia Conesa-Boj.
• Spatially-resolved band gap and dielectric function in 2D materials from Electron Energy Loss Spectroscopy, Abel Brokkelkamp, Jaco ter Hoeve, Isabel Postmes, Sabrya E. van Heijst, Luigi Maduro, Albert Davydov, Sergiy Krylyuk, Juan Rojo, Sonia Conesa-Boj.
• Localized exciton anatomy and band gap energy modulation in 1D MoS₂ nanostructures, Stijn van der Lippe, Abel Brokkelkamp, Juan Rojo, Sonia Conesa-Boj.
• Edge-induced excitations in Bi₂Te₃ from spatially-resolved electron energy-gain spectroscopy, Helena La, Abel Brokkelkamp, Stijn van der Lippe, Jaco ter Hoeve, Juan Rojo, Sonia Conesa-Boj.