You can visit my GitHub profile to explore additional projects, as well as materials from tutorials, courses, and workshops.
doppleriann
Doppler-shift Inference with Artificial Neural Networks (DopplerIANN)
doppleriann is Python package for modeling Doppler shifts in high-resolution stellar spectra using physically motivated spectral-shell representations and deep learning. It contains the methodological framework presented in our paper: doi.org/10.1051/0004-6361/202659375.
- Library GitHub repository: igomezv/doppleriann
- Docs: doppleriann/Docs
SimpleMC
Cosmological parameter inference toolkit for Bayesian analysis and statistical sampling.
SimpleMC is a cosmological parameter estimation framework originally developed by Dr. A. Slosar and Dr. J. A. Vázquez. Between 2019 and 2023, I contributed to the development and maintenance of the codebase, including nested sampling implementations, convergence criteria for Metropolis–Hastings algorithms, post-processing utilities, and additional analysis modules.
Links
- Library GitHub repository: ja-vazquez/SimpleMC
- Documentation: igomezv/SimpleMC/Docs
- Workshop/tutorial: igomezv/simplemc_workshop
nnogada
Neural networks optimized with genetic algorithms for data-driven inference and reconstruction.
nnogada (Neural Networks Optimized by Genetic Algorithms in Data Analysis) is a framework combining neural networks and genetic algorithms for flexible modeling, reconstruction, and parameter inference in astrophysical and cosmological applications.
Links
- Library GitHub repository: igomezv/nnogada
- Documentation: docs/nnogada
Projects using nnogada
neuralike
Bayesian inference for accelerating cosmological likelihood evaluations.
neuralike implements deep-learning surrogate models combined with genetic-algorithm optimization to accelerate Bayesian inference workflows in cosmology, particularly for computationally expensive likelihood evaluations within sampling pipelines.
Links
- Library GitHub repository: igomezv/neuralike
- Integration with
SimpleMCand nested sampling usingdynesty: igomezv/simplemc_tests
ANN Reconstructions
Neural-network cosmological reconstructions with uncertainty quantification.
Collection of Python implementations for model-independent reconstruction of cosmological observables using artificial neural networks, Monte Carlo Dropout uncertainty estimation, and hyperparameter optimization techniques.
Repositories
- Unified reconstruction library: igomezv/alp
- Galaxy rotation curves: igomezv/Reconstructing-RC-with-ANN
- LSST supernova simulations: igomezv/LSST_DE_neural_reconstruction
- Cosmological observables reconstruction: igomezv/neuralCosmoReconstruction
NCosmoVAE
Variational autoencoders for fast generative modeling of cosmological N-body simulations.
Variational autoencoder framework trained on N-body cosmological simulations to generate realistic dark matter halo realizations. Hyperparameter optimization with genetic algorithms using the optuna Python library.
Links
- Library repository: igomezv/NcosmoVAE
- Related: PRD paper.
