News

How machine learning can support atmospheric compound discovery

Researchers from the CEST group assess potential of machine learning to identify atmospheric compounds from experiments and field-studies in recent perspective article
graphic showing clouds and chemicals on blue background
Graphic by Hilda Sandström

The identification of chemical compounds found in the atmosphere is challenging and tedious, currently relying on mass spectrometry measurements. A new perspective paper is now discussing what promise machine learning holds to accelerate and improve the accuracy of ongoing studies aimed at mapping new atmospheric compounds. Such compounds are worthwhile studying as they contribute to atmospheric particle formation, therefore directly impacting climate as well as air quality.

Portrait of woman in green shirt
CEST researcher Hilda Sandström

CEST researchers Hilda Sandström and Patrick Rinke, along with collaborators from Aalto University, the University of Helsinki and Tampere University, conducted a comprehensive review of the current state of data-driven compound identification in atmospheric mass spectrometry. This perspective article outlines crucial steps required from the atmospheric chemistry community to implement the identification of compounds using modern smart algorithms.

Despite the acknowledged complexity and sheer number of potential atmospheric organic compounds, detailed knowledge of their reaction mechanisms, intermediates, and products is lacking. Efforts to gain new fundamental knowledge about these atmospheric processes persist, primarily relying on mass spectrometry. However, existing experimental data libraries and manual identification methods struggle to cope with the shear number, large variability and complexity inherent in atmospheric compounds and processes.

While smart compound identification algorithms have demonstrated state-of-the-art performance in other chemical disciplines, their implementation in atmospheric chemistry has been hindered by the scarcity of training data from such atmospheric mass spectrometry studies. The researchers have provided examples of how these machine learning-based compound identification tools could be effectively utilized in conjunction with soft ionization techniques commonly employed in atmospheric mass spectrometry.

Establishing automated and improved identification methods for atmospheric compounds is pivotal to advance our basic understanding of atmospheric chemistry. Crucially, the paper proposes an action plan to create an infrastructure for development of data-driven compound identification in atmospheric mass spectrometry. Following this initial review, Sandström and collaborators now aim to initiate the development and testing of these future intelligent identification methods to help identify atmospheric compounds.

The perspective article was published in Advanced Science under DOI: 10.1002/advs.202306235.

For more details contact

Hilda Sandström

  • Updated:
  • Published:
Share
URL copied!

Read more news

Person with blurred face in black jacket and hoodie standing by large metal pipes in a park
Appointments, Research & Art Published:

Professor Kari Juusonen: “In animation, anything is possible”

According to the professor of animation and digital AV production, animation’s greatest strength lies in its boundlessness. In the future, personal touches and strong content will be what matter most.
Two people with backpacks stand among sunflowers and greenery in an urban area with buildings in the background.
Cooperation, Research & Art Published:

In search of carbon wisdom – scavenger hunts help you get to know urban nature better

CO-CARBON researchers have designed four themed scavenger hunt routes for the Helsinki metropolitan area that take seekers on a hunt for carbon-smart treasures.
Text Radical Creativity Interviews, blurred people in studio with equipment and papers
Research & Art Published:

What is radical creativity in practice? An interview series offers perspectives on new ways of thinking

The discussions in the interview series on radical creativity highlight creativity, uncertainty, collaboration, and the courage to experiment.
AI playground
Press releases, Research & Art, University Published:

ARTS launches AI Playground pilot in Väre

A new pilot space in Väre gives ARTS staff access to shared AI-ready workstations, with student access planned for 2026–2027.