Machine Learning for Ionization Potentials and Photoionization Cross Sections of Volatile Organic Compounds

Abstract

Molecular ionization potentials (IP) and photoionization cross sections (σ) can affect the sensitivity of photoionization detectors (PIDs) and other sensors for gaseous species. This study employs several methods of machine learning (ML) to predict IP and σ values at 10.6 eV (117 nm) for a dataset of 1251 gaseous organic species. The explicitness of the treatment of the species electronic structure progressively increases among the methods. The study compares the ML predictions of the IP and σ values to those obtained by quantum chemical calculations. The ML predictions are comparable in performance to those of the quantum calculations when evaluated against measurements. Pretraining further reduces the mean absolute errors (ε) compared to the measurements. The graph-based attentive fingerprint model was most accurate, for which ε IP = 0.23 ± 0.01 eV and ε σ = 2.8 ± 0.2 Mb compared to measurements and computed cross sections, respectively. The ML predictions for IP correlate well with both the measured IPs (R 2 = 0.88) and with IPs computed at the level of M06-2X/aug-cc-pVTZ (R 2 = 0.82). The ML predictions for σ correlated reasonably well with computed cross sections (R 2 = 0.66). The developed ML methods for IP and σ values, representing the properties of a generalizable set of volatile organic compounds (VOCs) relevant to industrial applications and atmospheric chemistry, can be used to quantitatively describe the species-dependent sensitivity of chemical sensors that use ionizing radiation as part of the sensing mechanism, such as photoionization detectors.

Prediction of the Response of a Photoionization Detector to a Complex Gaseous Mixture of Volatile Organic Compounds Produced by α-Pinene Oxidation

“…The calculated photoionization cross sections for the MCM species relevant to α-pinene oxidation ranged from 4 to 20 Mb (unit, Mb = Megabarn, 1 Mb = 10 –18 cm 2 ). This 4–20 Mb range covers typical cross sections for organic molecules near 10 eV based on literature values. ,, …”

“…The group of products corresponded to >99% of the molecular yield of the Master Chemical Mechanism (section ). The calculations were described in ref . In brief, a species expressed in simplified molecular-input line-entry system (SMILES) was converted to a three-dimensional representation (i.e., Z -matrix form) using Open Babel v3.3.1 .…”

“…Results are listed in Table . The detailed methodology and validation were presented in ref . The predicted ionization potentials and response factors ranged from 8.15 to 10.46 eV and 0.28 to 1.47, respectively, for the MCM species relevant to α-pinene oxidation.…”

“…They can be used to reproduce the results of the machine learning methods. 77 Stored information includes the output data from Gaussian and ePolyScat as well as the training data set of ionization potentials and response factors.…”

“…In operation, a PID emits photons, typically 10.6 eV (116.9 nm), into a small-volume reaction chamber (Figure ). Direct ionization (M + hν → M + + e – ) of species having ionization energies below this threshold occurs according to a transition probability, dictated by the wave function overlap integral of the ground state molecule and ion . The ions and electrons generated from this process are attracted to the charged electrodes.…”