DeepONet code to train a deep operator network for mapping from XANES data to EXAFS data

Code by Amanda Howard
To accompany "A machine learning approach to interpreting x-ray spectra by converting XANES to EXAFS"
Micah Prange, Amanda Howard, Niranjan Govind, Panos Stinis, Eugene Ilton

Input files: 
"input.txt" contains two integers, the initial and final indices of the XANES profile used in training. If input.txt does not exist in the output folder, default values will be used. 

Usage: 
1) To train a DeepONet and save the outputs, run DeepONet.py
2) To plot the predictions generated by the DeepONet for FEFF values, run Plot_results_FEFF.py


This research was supported by Laboratory Directed Research and Development (LDRD) at Pacific Northwest National Laboratory (PNNL). The computational work was performed using PNNL Institutional Computing at Pacific Northwest National Laboratory. PNNL is a multiprogram national laboratory operated for the U.S. Department of Energy (DOE) by Battelle Memorial Institute under Contract No. DE-AC06-76RLO-1830.


DeepONet architecture from: 
S. Wang, H. Wang, and P. Perdikaris, Improved architectures and training algorithms for deep operator networks, Journal of Scientific Computing 92, 35 (2022).