Elucidating an Atmospheric Brown Carbon Species—Toward Supplanting Chemical Intuition with Exhaustive Enumeration and Machine Learning

Abstract

Brown carbon (BrC) is involved in atmospheric light absorption and climate forcing and can cause adverse health effects. Understanding the formation mechanisms and molecular structure of BrC is of key importance in developing strategies to control its environment and health impact. Structure determination of BrC is challenging, due to the lack of experiments providing molecular fingerprints and the sheer number of molecular candidates with identical mass. Suggestions based on chemical intuition are prone to errors due to the inherent bias. We present an unbiased algorithm, using graph-based molecule generation and machine learning, which can identify all molecular structures of compounds involved in biomass burning and the composition of BrC. We apply this algorithm to C12H12O7, a light-absorbing “test case” molecule identified in chamber experiments on the aqueous photo-oxidation of syringol, a prevalent marker in wood smoke. Of the 260 million molecular graphs, the algorithm leaves only 36,518 (0.01%) as viable candidates matching the spectrum. Although no unique molecular structure is obtained from only a chemical formula and a UV/vis absorption spectrum, we discuss further reduction strategies and their efficacy. With additional data, the method can potentially more rapidly identify isomers extracted from lab and field aerosol particles without introducing human bias.

Resolution-vs.-Accuracy Dilemma in Machine Learning Modeling of Electronic Excitation Spectra

“…This is because all details of the global structure encoded in the geometry is not relevant for the target property as in the case of E 1 . Such poor learning rates for f 1 was noted in QML modeling of 'brown carbon' molecules that are atmospheric pollutants as in aerosols [29]. As in the case of E 1 , FCHL's performance for f 1 is inferior compared to that of SLATM.…”

“…Since QML modeling of electronic excited state properties is performed using global structural representations, such models suffer from an information overload (i.e., poor signal-to-noise ratio) in the feature space amounting to weak structure-property mapping. This effect manifests in unsatisfactory performances of QML models for excitation energies [28,29], and their zero-order approximations, the frontier molecular orbital (MO) energies [20,30,31].…”

“…Past studies have focused on excited-state modeling across the chemical space [28,29,32] as well as in potential energy surfaces (PESs) [27,29,[33][34][35]. A key difference in QML performances in these two application domains is that ambiguities due to atomic indices and size-extensivity that affect the quality of structural representations for chemical space explorations [36,37] do not arise in PES or dipole surface modeling [38][39][40], resulting in better learning rates.…”

“…On a similar note, quasi-particle density-of-states-interpreted as intensities in a photo-emission spectrum-have been successfully modeled [41,42]. Yet, intensities based on oscillator strengths derived from many-electron excited state wave functions obeying dipole selection rules exhibit slow learning rates [29].…”

Data-Driven Modeling of S0 -> S1 Excitation Energy in the BODIPY Chemical Space: High-Throughput Computation, Quantum Machine Learning, and Inverse Design

“…For excited state properties, in general, the error rates in QML have been noted to be inferior compared to that of ground state properties [61][62][63][64]. Yet, QML methods continue to find applications in excited state modeling in chemical space datasets [50,[65][66][67] as well as in potential surface manifolds [68][69][70][71][72][73]. Keeping abreast with the progress in QML, materials/molecules inverse-design protocols have also advanced since the earliest implementation nearly twenty years ago [74].…”