Related papers: Understanding molecular ratios in the carbon and oxygen poor outer Milky Way with interpretable machine learning

Understanding molecular ratios in the carbon and oxygen poor outer Milky Way with interpretable machine learning

URL: http://arxiv.org/abs/2505.08410v1
Date: Tue, 13 May 2025 10:08:37 GMT
Title: Understanding molecular ratios in the carbon and oxygen poor outer Milky Way with interpretable machine learning
Authors: Gijs Vermariën, Serena Viti, Johannes Heyl, Francesco Fontani,
Abstract summary: We use interpretable machine learning to study 9 different molecular ratios.<n>We study the properties of molecular clouds of low oxygen and carbon initial abundance.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Context. The outer Milky Way has a lower metallicity than our solar neighbourhood, but still many molecules are detected in the region. Molecular line ratios can serve as probes to better understand the chemistry and physics in these regions. Aims. We use interpretable machine learning to study 9 different molecular ratios, helping us understand the forward connection between the physics of these environments and the carbon and oxygen chemistries. Methods. Using a large grid of astrochemical models generated using UCLCHEM, we study the properties of molecular clouds of low oxygen and carbon initial abundance. We first try to understand the line ratios using a classical analysis. We then move on to using interpretable machine learning, namely Shapley Additive Explanations (SHAP), to understand the higher order dependencies of the ratios over the entire parameter grid. Lastly we use the Uniform Manifold Approximation and Projection technique (UMAP) as a reduction method to create intuitive groupings of models. Results. We find that the parameter space is well covered by the line ratios, allowing us to investigate all input parameters. SHAP analysis shows that the temperature and density are the most important features, but the carbon and oxygen abundances are important in parts of the parameter space. Lastly, we find that we can group different types of ratios using UMAP. Conclusions. We show the chosen ratios are mostly sensitive to changes in the carbon initial abundance, together with the temperature and density. Especially the CN/HCN and HNC/HCN ratio are shown to be sensitive to the initial carbon abundance, making them excellent probes for this parameter. Out of the ratios, only CS/SO shows a sensitivity to the oxygen abundance.

Related papers

Machine Learning for Methane Detection and Quantification from Space -- A survey [49.7996292123687]
Methane (CH_4) is a potent anthropogenic greenhouse gas, contributing 86 times more to global warming than Carbon Dioxide (CO_2) over 20 years. This work expands existing information on operational methane point source detection sensors in the Short-Wave Infrared (SWIR) bands. It reviews the state-of-the-art for traditional as well as Machine Learning (ML) approaches.
arXiv Detail & Related papers (2024-08-27T15:03:20Z)
Studying Critical Parameters of Superconductor via Diamond Quantum Sensors [2.8505276433658175]
We develop the use of a single species of quantum sensor to determine and estimate several critical parameters. We demonstrate the use of diamond particles and a bulk diamond to probe the Meissner effect.
arXiv Detail & Related papers (2024-07-23T21:23:54Z)
Disentangling CO Chemistry in a Protoplanetary Disk Using Explanatory Machine Learning Techniques [0.0]
Molecular abundances in protoplanetary disks are highly sensitive to the local physical conditions. We present a new approach to understanding these chemical and physical interdependencies using machine learning.
arXiv Detail & Related papers (2023-12-08T18:59:22Z)
Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel [48.6168145845412]
We propose a method to abstract the collective information of atomic groups into a few $textitNeural Atoms$ by implicitly projecting the atoms of a molecular. Specifically, we explicitly exchange the information among neural atoms and project them back to the atoms' representations as an enhancement. With this mechanism, neural atoms establish the communication channels among distant nodes, effectively reducing the interaction scope of arbitrary node pairs into a single hop.
arXiv Detail & Related papers (2023-11-02T14:44:50Z)
Post-field ionization of Si clusters in atom probe tomography: A joint theoretical and experimental study [0.0]
A major challenge for Atom Probe Tomography (APT) is the inability to decouple ions which possess the same mass/charge-state ($m/n$) ratio but a different mass. We propose and then explore the applicability of a post-experimental analytical approach to resolve this problem. The ability to predict the behaviour of molecular ions as a function of operating conditions could offer the first step towards resolving peak overlap.
arXiv Detail & Related papers (2022-07-11T23:59:14Z)
Graph-based Molecular Representation Learning [59.06193431883431]
Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning.
arXiv Detail & Related papers (2022-07-08T17:43:20Z)
Local manifold learning and its link to domain-based physics knowledge [53.15471241298841]
In many reacting flow systems, the thermo-chemical state-space is assumed to evolve close to a low-dimensional manifold (LDM) We show that PCA applied in local clusters of data (local PCA) is capable of detecting the intrinsic parameterization of the thermo-chemical state-space.
arXiv Detail & Related papers (2022-07-01T09:06:25Z)
Time-inhomogeneous diffusion geometry and topology [69.55228523791897]
Diffusion condensation is a time-inhomogeneous process where each step first computes and then applies a diffusion operator to the data. We theoretically analyze the convergence and evolution of this process from geometric, spectral, and topological perspectives. Our work gives theoretical insights into the convergence of diffusion condensation, and shows that it provides a link between topological and geometric data analysis.
arXiv Detail & Related papers (2022-03-28T16:06:17Z)
Chemical-Reaction-Aware Molecule Representation Learning [88.79052749877334]
We propose using chemical reactions to assist learning molecule representation. Our approach is proven effective to 1) keep the embedding space well-organized and 2) improve the generalization ability of molecule embeddings. Experimental results demonstrate that our method achieves state-of-the-art performance in a variety of downstream tasks.
arXiv Detail & Related papers (2021-09-21T00:08:43Z)
End-to-End Differentiable Molecular Mechanics Force Field Construction [0.5269923665485903]
We propose an alternative approach that uses graph neural networks to perceive chemical environments. The entire process is modular and end-to-end differentiable with respect to model parameters. We show that this approach is not only sufficiently to reproduce legacy atom types, but that it can learn to accurately reproduce and extend existing molecular mechanics force fields.
arXiv Detail & Related papers (2020-10-02T20:59:46Z)
ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction [61.33144688400446]
We propose a novel framework called Active Semi-supervised Graph Neural Network (ASGN) by incorporating both labeled and unlabeled molecules. In the teacher model, we propose a novel semi-supervised learning method to learn general representation that jointly exploits information from molecular structure and molecular distribution. At last, we proposed a novel active learning strategy in terms of molecular diversities to select informative data during the whole framework learning.
arXiv Detail & Related papers (2020-07-07T04:22:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.