A neural-network model to find correlations in astrochemical space
Abstract
The detection of new interstellar molecules is central to astrochemistry, and arguably the most transformative development in the field in past decade has been the increase in both number and diversity of detected species. Using natural language processing models, we develop a machine-learning pipeline, similar to other approaches reported in the literature, to connect molecular structures, encoded as chemical strings, and molecular column densities in TMC-1. The workflow generates astrochemically informed embeddings that can be employed in subsequent supervised learning tasks. These representations are used within a neural-network framework to perform column-density regression on both the original molecular inventory and out-of-distribution species. The resulting model achieves mean squared error values of 0.17/0.58 and mean absolute error values of 0.29/0.59, and coefficients of determination of 0.88/0.51 for the train+validation and validation datasets. The latent vectors learned by the model are rich mathematical objects that capture the underlying chemical relations and also the potential interstellar detectability of the molecule. Using these vectors in molecules obtained from systematic permutations of the TMC-1 inventory, we identify several promising candidates for future detection in this cloud, together with a large number of apolar species. By training the model on datasets reflecting different historical epochs of molecular detections in TMC-1, we show that recent molecular detections have substantially reshaped our understanding of interstellar chemistry, in a transformative, rather than incremental, way. Beyond accurate prediction of column-density trends for both in-distribution and out-of-distribution molecules, the latent-space representations produced by the model provide a stepping stone for developing new forms of data-driven astrochemical intuition and exploration.
Related
- Neural Network Guided Parameter Space Constraints for Gravitational Wave Searches from Binary Black Holes
- Revisiting 2D and 3D Dainotti Correlations for GRBs Using Bayesian Neural Networks
- The Galactic centre G+0.633-0.0604 molecular cloud: A new astrochemical gold mine: II. Chemical richness
- The Galactic centre G+0.633-0.0604 molecular cloud: A new astrochemical gold mine: I. Gas physical properties
- Tighter dark-matter constraints from the projected mass method: A neural-network-enhanced method for galaxy groups and clusters
BibTeX
@misc{vargas2026neuralnetwork,
title = {{A neural-network model to find correlations in astrochemical space}},
author = {Daniel Giovanni Vargas and Darío Barreiro-Lage and Marcelino Agúndez and Carlos Cabezas and José Cernicharo and Germán Molpeceres},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30842},
eprint = {2610.30842},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30842},
}
RIS
TY - UNPB
TI - A neural-network model to find correlations in astrochemical space
AU - Daniel Giovanni Vargas
AU - Darío Barreiro-Lage
AU - Marcelino Agúndez
AU - Carlos Cabezas
AU - José Cernicharo
AU - Germán Molpeceres
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.30842
UR - https://arxiv.org/abs/2610.30842
AB - The detection of new interstellar molecules is central to astrochemistry, and arguably the most transformative development in the field in past decade has been the increase in both number and diversity of detected species. Using natural language processing models, we develop a machine-learning pipeline, similar to other approaches reported in the literature, to connect molecular structures, encoded as chemical strings, and molecular column densities in TMC-1. The workflow generates astrochemically informed embeddings that can be employed in subsequent supervised learning tasks. These representations are used within a neural-network framework to perform column-density regression on both the original molecular inventory and out-of-distribution species. The resulting model achieves mean squared error values of 0.17/0.58 and mean absolute error values of 0.29/0.59, and coefficients of determination of 0.88/0.51 for the train+validation and validation datasets. The latent vectors learned by the model are rich mathematical objects that capture the underlying chemical relations and also the potential interstellar detectability of the molecule. Using these vectors in molecules obtained from systematic permutations of the TMC-1 inventory, we identify several promising candidates for future detection in this cloud, together with a large number of apolar species. By training the model on datasets reflecting different historical epochs of molecular detections in TMC-1, we show that recent molecular detections have substantially reshaped our understanding of interstellar chemistry, in a transformative, rather than incremental, way. Beyond accurate prediction of column-density trends for both in-distribution and out-of-distribution molecules, the latent-space representations produced by the model provide a stepping stone for developing new forms of data-driven astrochemical intuition and exploration.
ER -