Anirudh Prabhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Anirudh Prabhu has a total of 199 co-authors. Here are the top co-authors by number of shared publications:
- Robert M. Hazen
Earth and Planets Laboratory, Carnegie Institution for Science , Washington, DC 20015
22 shared publications - Shaunna M. Morrison
Department of Earth and Planetary Sciences, Rutgers University, New Brunswick, NJ 08854, USA
22 shared publications Ahmed Eleish
14 shared publicationsPeter Fox
14 shared publications- Michael L. Wong
Earth and Planets Laboratory Carnegie Institution for Science Washington DC USA
12 shared publications Robert M. Hazen
11 shared publications
Latest Publications
- Open Access
- 18 August 2026
- Published by Wiley in Journal of Metamorphic Geology
- Vol. 44 (9) , 665-682
Metamorphic or Igneous Zircon? Classification Through Rare Earth Elements, Machine Learning and Logistic Regression
Zircon is a common, highly refractory accessory mineral found in sedimentary, igneous and metamorphic rocks that forms through various processes (e.g., magmatic, hydrothermal, metamorphic growth and recrystallization). Trace element compositions of detrital zircon have been widely applied to understanding tectonic processes and continental reconstruction. Previous studies have shown that no single compositional parameter (i.e., rare earth elements [REE] pattern and Th/U) can distinguish zircon petrogenesis. Here, we employ novel machine learning methods to differentiate between ‘metamorphic‐like’ and ‘igneous‐like’ zircon, independent of researcher‐labelled lithologies and categorized by their dominant REE signatures. With advancements and the adoption of machine learning algorithms by the geochemical community, we holistically analyse n‐dimensional geochemical data (14 dimensions for the full REE suite) to ascertain or confirm complex geological processes. We utilize a dataset of previously identified zircon with varying proposed origins (i.e., metamorphic, igneous, S‐type granites and early Earth detrital) and unsupervised machine learning algorithms (i.e., UMAP and Mclust), which reveal two distinct clusters that we interpret as the dominant magmatic‐like and metamorphic‐like REE signatures. The two REE signature clusters are used to define a comprehensive REE equation that matches an unknown zircon into the most similar interpreted cluster (magmatic‐like or metamorphic‐like) through probabilistic bimodal logistic regression. The logistic regression equation was derived exclusively from REE signatures independent of previous classification. Model validation was achieved using confusion matrices and yielded a mean accuracy of 0.91 (balanced accuracy = 0.88), with average precision = 0.90, recall = 0.80, F1 = 0.85 and AUC = 0.96, indicating robust discriminative performance. Unsupervised machine learning demonstrates that two distinct REE signatures emerge, which vary in their HREE enrichment and LREE depletion. We demonstrate that machine learning can decipher complex multi‐elemental relationships in zircon REE data and can be used to classify zircon.
- 18 August 2026
- Published by Wiley in Journal of Metamorphic Geology
- Vol. 44 (9) , 665-682
Open AccessMetamorphic or Igneous Zircon? Classification Through Rare Earth Elements, Machine Learning and Logistic Regression
Zircon is a common, highly refractory accessory mineral found in sedimentary, igneous and metamorphic rocks that forms through various processes (e.g., magmatic, hydrothermal, metamorphic growth and recrystallization). Trace element compositions of detrital zircon have been widely applied to understanding tectonic processes and continental reconstruction. Previous studies have shown that no single compositional parameter (i.e., rare earth elements [REE] pattern and Th/U) can distinguish zircon petrogenesis. Here, we employ novel machine learning methods to differentiate between ‘metamorphic‐like’ and ‘igneous‐like’ zircon, independent of researcher‐labelled lithologies and categorized by their dominant REE signatures. With advancements and the adoption of machine learning algorithms by the geochemical community, we holistically analyse n‐dimensional geochemical data (14 dimensions for the full REE suite) to ascertain or confirm complex geological processes. We utilize a dataset of previously identified zircon with varying proposed origins (i.e., metamorphic, igneous, S‐type granites and early Earth detrital) and unsupervised machine learning algorithms (i.e., UMAP and Mclust), which reveal two distinct clusters that we interpret as the dominant magmatic‐like and metamorphic‐like REE signatures. The two REE signature clusters are used to define a comprehensive REE equation that matches an unknown zircon into the most similar interpreted cluster (magmatic‐like or metamorphic‐like) through probabilistic bimodal logistic regression. The logistic regression equation was derived exclusively from REE signatures independent of previous classification. Model validation was achieved using confusion matrices and yielded a mean accuracy of 0.91 (balanced accuracy = 0.88), with average precision = 0.90, recall = 0.80, F1 = 0.85 and AUC = 0.96, indicating robust discriminative performance. Unsupervised machine learning demonstrates that two distinct REE signatures emerge, which vary in their HREE enrichment and LREE depletion. We demonstrate that machine learning can decipher complex multi‐elemental relationships in zircon REE data and can be used to classify zircon.
- Open Access
- 29 June 2026
- Published by Oxford University Press (OUP) in PNAS Nexus
- Vol. 5 (7) , pgag215
Mineral biosignature identification from Raman spectroscopy using machine learning
Biosignature detection remains a key challenge in astrobiology, yet robust mineral biosignatures remain limited. Raman spectroscopy is increasingly applied in planetary exploration, but its high-dimensional spectral information has not yet been fully exploited for biosignature discrimination using data-driven approaches. Here, we integrate Raman spectroscopy with interpretable machine learning to distinguish biotic from abiotic apatite, a ubiquitous phosphate mineral in terrestrial and extraterrestrial environments. We compile 331 apatite Raman spectra from abiotic and biotic sources and extract 21 band-resolved spectral features. Principal component analysis reveals systematic separation between abiotic and biotic endmembers. A random forest classifier achieves 96.8% accuracy on an independent test set. Robustness is confirmed by multiple validation schemes, including leave-one-source-out cross-validation across 60 independent data sources, indicating that model performance generalizes beyond source- or instrument-specific artifacts. Feature importance identifies two dominant controls: phosphate-band broadening as a structural indicator of disorder and the carbonate-band intensity as a chemical signature of substitution. Density-functional calculations reproduce these features in simulated spectra and indicate that carbonate substitution doubles phosphate-tetrahedral distortion and increases formation energies by two orders of magnitude. Mechanically, higher carbonate contents during biomineral apatite formation reduce crystallinity and broaden Raman bands. We propose that the trained machine-learning model and a two-feature decision map enable the rapid probabilistic discrimination of unknown apatite samples. Our Raman-based machine-learning framework establishes a broadly applicable and mission-relevant strategy for deep-time archives and future planetary missions.
- 29 June 2026
- Published by Oxford University Press (OUP) in PNAS Nexus
- Vol. 5 (7) , pgag215
Open AccessMineral biosignature identification from Raman spectroscopy using machine learning
Biosignature detection remains a key challenge in astrobiology, yet robust mineral biosignatures remain limited. Raman spectroscopy is increasingly applied in planetary exploration, but its high-dimensional spectral information has not yet been fully exploited for biosignature discrimination using data-driven approaches. Here, we integrate Raman spectroscopy with interpretable machine learning to distinguish biotic from abiotic apatite, a ubiquitous phosphate mineral in terrestrial and extraterrestrial environments. We compile 331 apatite Raman spectra from abiotic and biotic sources and extract 21 band-resolved spectral features. Principal component analysis reveals systematic separation between abiotic and biotic endmembers. A random forest classifier achieves 96.8% accuracy on an independent test set. Robustness is confirmed by multiple validation schemes, including leave-one-source-out cross-validation across 60 independent data sources, indicating that model performance generalizes beyond source- or instrument-specific artifacts. Feature importance identifies two dominant controls: phosphate-band broadening as a structural indicator of disorder and the carbonate-band intensity as a chemical signature of substitution. Density-functional calculations reproduce these features in simulated spectra and indicate that carbonate substitution doubles phosphate-tetrahedral distortion and increases formation energies by two orders of magnitude. Mechanically, higher carbonate contents during biomineral apatite formation reduce crystallinity and broaden Raman bands. We propose that the trained machine-learning model and a two-feature decision map enable the rapid probabilistic discrimination of unknown apatite samples. Our Raman-based machine-learning framework establishes a broadly applicable and mission-relevant strategy for deep-time archives and future planetary missions.
- Open Access
- 19 June 2026
- Published by The Open Journal in Journal of Open Source Software
- Vol. 11 (122)
crystract: A Crystallography Package in R for .cif Data Processing
- 19 June 2026
- Published by The Open Journal in Journal of Open Source Software
- Vol. 11 (122)
Open Accesscrystract: A Crystallography Package in R for .cif Data Processing
- 20 March 2026
- Published by The R Foundation
crystract: Crystallographic Information File (CIF) Data Processing Tools
Provides a suite of functions to parse Crystallographic Information Files (.cif), extracting essential data such as chemical formulas, unit cell parameters, atomic coordinates, and symmetry operations. It also includes tools to calculate interatomic distances, identify bonded pairs using various algorithms (minimum_distance, brunner_nn_reciprocal, econ_nn, crystal_nn), determine nearest neighbor counts, and calculate bond angles. The package is designed to facilitate the preparation of crystallographic data for further analysis, including machine learning applications in materials science. Methods are described in: Brunner (1977) ; Hoppe (1979) ; O'Keeffe (1979) ; Shannon (1976) ; Pan et al. (2021) ; Pauling (1960, ISBN:978-0801403330).
- 20 March 2026
- Published by The R Foundation
crystract: Crystallographic Information File (CIF) Data Processing Tools
Provides a suite of functions to parse Crystallographic Information Files (.cif), extracting essential data such as chemical formulas, unit cell parameters, atomic coordinates, and symmetry operations. It also includes tools to calculate interatomic distances, identify bonded pairs using various algorithms (minimum_distance, brunner_nn_reciprocal, econ_nn, crystal_nn), determine nearest neighbor counts, and calculate bond angles. The package is designed to facilitate the preparation of crystallographic data for further analysis, including machine learning applications in materials science. Methods are described in: Brunner (1977) ; Hoppe (1979) ; O'Keeffe (1979) ; Shannon (1976) ; Pan et al. (2021) ; Pauling (1960, ISBN:978-0801403330).
- Open Access
- 19 December 2025
- Published by The Royal Society in Interface Focus
- Vol. 15 (6)
Selective funnelling and state-space expansion: a conceptual framework for novelty generation and origin events
Evolution, conceived broadly as encompassing both biological and abiological systems, generates novel structures and phenomena that are seemingly different, in important ways, from what came before. While it is always possible, in theory, to describe complex systems using the language of the most basic physical entities and laws, it is almost never practical to do so. When novel systems arise, their behaviour may be better explained and predicted using new sets of properties and principles. How can we understand this universal aspect of evolution—that is, the tendency of a system to produce astonishing novelty? Here, we introduce two new concepts: selective funnelling and state-space expansion. Together, these processes describe the mechanisms by which an evolving system shifts from one functional fitness landscape to another. During selective funnelling, non-equilibrium features from the previous level are ‘locked in’, promoting the increase of functional information in evolving systems with time. A state-space expansion event is characterized by significant changes in components of relevance, driving forces for exploring combinatorial possibilities and/or selection mechanisms. Together, selective funnelling and state-space expansion provide an abstract framework for understanding a plethora of diverse origin events, trends of increasing ‘complexity’ in the universe and the challenging phenomenon of ‘emergence’.
- 19 December 2025
- Published by The Royal Society in Interface Focus
- Vol. 15 (6)
Open AccessSelective funnelling and state-space expansion: a conceptual framework for novelty generation and origin events
Evolution, conceived broadly as encompassing both biological and abiological systems, generates novel structures and phenomena that are seemingly different, in important ways, from what came before. While it is always possible, in theory, to describe complex systems using the language of the most basic physical entities and laws, it is almost never practical to do so. When novel systems arise, their behaviour may be better explained and predicted using new sets of properties and principles. How can we understand this universal aspect of evolution—that is, the tendency of a system to produce astonishing novelty? Here, we introduce two new concepts: selective funnelling and state-space expansion. Together, these processes describe the mechanisms by which an evolving system shifts from one functional fitness landscape to another. During selective funnelling, non-equilibrium features from the previous level are ‘locked in’, promoting the increase of functional information in evolving systems with time. A state-space expansion event is characterized by significant changes in components of relevance, driving forces for exploring combinatorial possibilities and/or selection mechanisms. Together, selective funnelling and state-space expansion provide an abstract framework for understanding a plethora of diverse origin events, trends of increasing ‘complexity’ in the universe and the challenging phenomenon of ‘emergence’.
- Open Access
- 17 November 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (47)
Organic geochemical evidence for life in Archean rocks identified by pyrolysis–GC–MS and supervised machine learning
Throughout Earth’s history, organic molecules from both abiogenic and biogenic sources have been buried in sedimentary rocks. Most of these organic molecules have been significantly altered by geologic processes through deep time. Nonetheless, the nature and distribution of those ancient fragmentary organic remains have the potential to reveal diagnostic biomolecular information after billions of years of burial. Here, we analyzed 406 fossil, modern biological, meteoritic, and synthetic samples using pyrolysis gas chromatography and mass spectrometry. We explored these analytical data via supervised machine-learning methods to discriminate samples of biogenic vs. abiogenic origin, plant vs. animal phylogenetic affinity, and photosynthetic vs. nonphotosynthetic physiology. Dividing 272 samples with known phylogenetic affinity and physiology into 9 categories, each further divided into 75% training and 25% testing sets, our random forest models accurately predict pairwise assignments of modern vs. fossil or meteoritic organics (100% correct assignments), fossil plant tissues vs. meteoritic organics (97%), modern vs. fossil plant tissues (98%), and modern plants vs. animal tissues (95%). Pairwise comparisons between fossil biogenic samples vs. abiogenic samples resulted in 93% correct classifications, while analysis of modern and ancient photosynthetic vs. nonphotosynthetic samples also resulted in 93% correct assignments. Our analyses demonstrate that molecular biosignatures can survive in ancient fossils and allow for the identification of organismal origins and traits. Consistent with previous morphological and isotopic inferences, we present evidence for biogenic molecular assemblages in Paleoarchean rocks (3.33 Ga) and for photoautotrophy in Neoarchean rocks (2.52 Ga).
- 17 November 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (47)
Open AccessOrganic geochemical evidence for life in Archean rocks identified by pyrolysis–GC–MS and supervised machine learning
Throughout Earth’s history, organic molecules from both abiogenic and biogenic sources have been buried in sedimentary rocks. Most of these organic molecules have been significantly altered by geologic processes through deep time. Nonetheless, the nature and distribution of those ancient fragmentary organic remains have the potential to reveal diagnostic biomolecular information after billions of years of burial. Here, we analyzed 406 fossil, modern biological, meteoritic, and synthetic samples using pyrolysis gas chromatography and mass spectrometry. We explored these analytical data via supervised machine-learning methods to discriminate samples of biogenic vs. abiogenic origin, plant vs. animal phylogenetic affinity, and photosynthetic vs. nonphotosynthetic physiology. Dividing 272 samples with known phylogenetic affinity and physiology into 9 categories, each further divided into 75% training and 25% testing sets, our random forest models accurately predict pairwise assignments of modern vs. fossil or meteoritic organics (100% correct assignments), fossil plant tissues vs. meteoritic organics (97%), modern vs. fossil plant tissues (98%), and modern plants vs. animal tissues (95%). Pairwise comparisons between fossil biogenic samples vs. abiogenic samples resulted in 93% correct classifications, while analysis of modern and ancient photosynthetic vs. nonphotosynthetic samples also resulted in 93% correct assignments. Our analyses demonstrate that molecular biosignatures can survive in ancient fossils and allow for the identification of organismal origins and traits. Consistent with previous morphological and isotopic inferences, we present evidence for biogenic molecular assemblages in Paleoarchean rocks (3.33 Ga) and for photoautotrophy in Neoarchean rocks (2.52 Ga).
- Open Access
- 8 September 2025
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 170 (4) , 210
Predicting Exoplanet Occurrence Using Association Analysis
Over the past few decades, a remarkable surge in exoplanet discoveries has led to a substantial increase in available data. As of this writing, over 5000 exoplanets have been confirmed, with thousands more expected from current and future observatories. This wealth of data calls for a need to efficiently and thoroughly process complex exoplanetary data sets in order to identify significant trends and gain insights into the characteristics of exoplanets. In this paper, we demonstrate the advantage of leveraging machine learning to understand exoplanet occurrence and formation based on patterns observed within astronomical data. We use a technique called association analysis to identify frequent co-occurring planet subtypes in thousands of exoplanetary systems and generate association rules. We then explore the association rules derived from our algorithm to discover and understand the significant patterns found in the data. For instance, one of our rules shows that a planetary system with a stellar spectral type of “M” and containing a temperate gas giant (≥200 and <400 K) tends to also include a cold gas giant (<200 K). Our findings include rules that predict the presence of cold and long-period gas giants in systems with G and M dwarf stars, despite observational biases against detecting such planets. Additionally, we uncovered patterns suggesting the potential presence of temperate gaseous planets, which are of interest to astrobiology. Overall, this project establishes a valuable and extendable framework for future research, with its predictive power expected to grow along with the continually increasing abundance of exoplanet data.
- 8 September 2025
- Published by American Astronomical Society in The Astronomical Journal
- Vol. 170 (4) , 210
Open AccessPredicting Exoplanet Occurrence Using Association Analysis
Over the past few decades, a remarkable surge in exoplanet discoveries has led to a substantial increase in available data. As of this writing, over 5000 exoplanets have been confirmed, with thousands more expected from current and future observatories. This wealth of data calls for a need to efficiently and thoroughly process complex exoplanetary data sets in order to identify significant trends and gain insights into the characteristics of exoplanets. In this paper, we demonstrate the advantage of leveraging machine learning to understand exoplanet occurrence and formation based on patterns observed within astronomical data. We use a technique called association analysis to identify frequent co-occurring planet subtypes in thousands of exoplanetary systems and generate association rules. We then explore the association rules derived from our algorithm to discover and understand the significant patterns found in the data. For instance, one of our rules shows that a planetary system with a stellar spectral type of “M” and containing a temperate gas giant (≥200 and <400 K) tends to also include a cold gas giant (<200 K). Our findings include rules that predict the presence of cold and long-period gas giants in systems with G and M dwarf stars, despite observational biases against detecting such planets. Additionally, we uncovered patterns suggesting the potential presence of temperate gaseous planets, which are of interest to astrobiology. Overall, this project establishes a valuable and extendable framework for future research, with its predictive power expected to grow along with the continually increasing abundance of exoplanet data.
- Open Access
- 22 July 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 2 (3)
Detecting Biosignatures in Complex Molecular Mixtures From Pyrolysis‐Gas Chromatography‐Mass Spectrometry Data Using Machine Learning
Understanding how measured molecular signals can distinguish the chemistry of life from the chemistry of the nonliving world is a central focus of astrobiology and paleobiology. We train and compare several machine learning (ML) classification models on data from pyrolysis‐gas chromatography‐mass spectrometry (py‐GC‐MS)—a widely available analytical method that has been employed in space missions. We analyzed various organic carbon‐bearing geomaterials to consider relationships among suites of molecules that can help identify their biogenicity and potentially be used to analyze data from various solar system exploration missions. These supervised classification models can discriminate between abiotic and biotic samples with ∼86–89% accuracy. We use and compare 4 different ML models, coupled with range of statistical and visualization methods, to investigate the patterns and distribution of diagnostic features— specific combinations of chromatographic retention time and mass‐to‐charge ratio, which contribute to the classification of the samples into biologically derived versus abiologically derived materials. These diagnostic discriminators are common in biotic samples and rare in most abiotic samples and hence point to a potential agnostic molecular biosignature. They also tend to have higher normalized intensity values in biologically derived materials and display different distributions in contemporary biotic samples compared to taphonomically altered biotic samples. We utilize the full resolution of the 3D structure of the py‐GC‐MS data and describe in detail the preprocessing steps and the ML pipeline for analyzing such data, which could be automated for future data collection.
- 22 July 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 2 (3)
Open AccessDetecting Biosignatures in Complex Molecular Mixtures From Pyrolysis‐Gas Chromatography‐Mass Spectrometry Data Using Machine Learning
Understanding how measured molecular signals can distinguish the chemistry of life from the chemistry of the nonliving world is a central focus of astrobiology and paleobiology. We train and compare several machine learning (ML) classification models on data from pyrolysis‐gas chromatography‐mass spectrometry (py‐GC‐MS)—a widely available analytical method that has been employed in space missions. We analyzed various organic carbon‐bearing geomaterials to consider relationships among suites of molecules that can help identify their biogenicity and potentially be used to analyze data from various solar system exploration missions. These supervised classification models can discriminate between abiotic and biotic samples with ∼86–89% accuracy. We use and compare 4 different ML models, coupled with range of statistical and visualization methods, to investigate the patterns and distribution of diagnostic features— specific combinations of chromatographic retention time and mass‐to‐charge ratio, which contribute to the classification of the samples into biologically derived versus abiologically derived materials. These diagnostic discriminators are common in biotic samples and rare in most abiotic samples and hence point to a potential agnostic molecular biosignature. They also tend to have higher normalized intensity values in biologically derived materials and display different distributions in contemporary biotic samples compared to taphonomically altered biotic samples. We utilize the full resolution of the 3D structure of the py‐GC‐MS data and describe in detail the preprocessing steps and the ML pipeline for analyzing such data, which could be automated for future data collection.
- Top Cited Papers
- 1 June 2025
- Published by Mineralogical Society of America in American Mineralogist: Journal of Earth and Planetary Materials
- Vol. 110 (6) , 833-844
Mindat.org: The open access mineralogy database to accelerate data-intensive geoscience research
The mindat.org website (Mindat) has been operating since October 2000 as a free, crowd-sourced, and expert-curated database particularly focused on mineral species and their occurrences worldwide. The project has transformed from a hobbyist site in the beginning into a resource that has found use in various scientific research projects and educational programs. Together with other open data resources, Mindat has helped accelerate scientific discoveries in many fields, such as mineral evolution, mineral ecology, and the co-evolution of the geosphere and biosphere. Recently, through open data efforts, machine interfaces and software packages have been established to enable flexible data discovery and download from Mindat. We assume that the data access and usage will further scale up in the next years. Although Mindat is curated by a team of geoscience and database experts across the world, the crowd-sourced records in Mindat possess some bias. In this paper, we first present an overview of the primary data subjects in Mindat and then give extensive details about the characteristics and partiality of three of the most popular data subjects: locality, mineral species, and mineral occurrence. In the discussion, we also give an outlook on appropriate data usage and future extension of data records. We hope users can obtain a more comprehensive view of the Mindat database through this paper and thus better plan their data use. We also hope more people will be inspired to contribute to the data curation work to make Mindat a sustained data ecosystem for geoscience research.
- 1 June 2025
- Published by Mineralogical Society of America in American Mineralogist: Journal of Earth and Planetary Materials
- Vol. 110 (6) , 833-844
Top Cited PapersMindat.org: The open access mineralogy database to accelerate data-intensive geoscience research
The mindat.org website (Mindat) has been operating since October 2000 as a free, crowd-sourced, and expert-curated database particularly focused on mineral species and their occurrences worldwide. The project has transformed from a hobbyist site in the beginning into a resource that has found use in various scientific research projects and educational programs. Together with other open data resources, Mindat has helped accelerate scientific discoveries in many fields, such as mineral evolution, mineral ecology, and the co-evolution of the geosphere and biosphere. Recently, through open data efforts, machine interfaces and software packages have been established to enable flexible data discovery and download from Mindat. We assume that the data access and usage will further scale up in the next years. Although Mindat is curated by a team of geoscience and database experts across the world, the crowd-sourced records in Mindat possess some bias. In this paper, we first present an overview of the primary data subjects in Mindat and then give extensive details about the characteristics and partiality of three of the most popular data subjects: locality, mineral species, and mineral occurrence. In the discussion, we also give an outlook on appropriate data usage and future extension of data records. We hope users can obtain a more comprehensive view of the Mindat database through this paper and thus better plan their data use. We also hope more people will be inspired to contribute to the data curation work to make Mindat a sustained data ecosystem for geoscience research.
- Open Access
- 20 January 2025
- Published by Copernicus GmbH
X-informatics at the center of scientific discovery: Detecting biosignatures, predicting mineral occurrences, and characterizing planetary kinds.
Data Science and Informatics methods have been at the center of many recent scientific discoveries and have opened up new frontiers in many areas of scientific inquiry. In this talk, I will take you through some of the most recent and exciting discoveries we've made and how informatics methods planned a central role in these discoveries. First, we will look at our work on data-driven biosignature detection, specifically how we combine pyrolysis-gas chromatography-mass spectrometry and machine learning to build an agnostic molecular biosignature detection model. Next, we will talk about how we used association analysis to predict the locations of as-yet-unknown mineral deposits on Earth and potentially Mars. These advances hold the potential to unlock new avenues of economic growth and sustainable development.Finally, we will set our sights on exoplanets—celestial bodies orbiting distant stars. The discovery of thousands of exoplanets in recent years has fueled the quest to understand their formation, composition, and potential habitability. We develop informatics approaches to better understand, classify and predict the occurrence of exoplanets by embracing the complexity and multidimensionality of exoplanets and their host stars.
- 20 January 2025
- Published by Copernicus GmbH
Open AccessX-informatics at the center of scientific discovery: Detecting biosignatures, predicting mineral occurrences, and characterizing planetary kinds.
Data Science and Informatics methods have been at the center of many recent scientific discoveries and have opened up new frontiers in many areas of scientific inquiry. In this talk, I will take you through some of the most recent and exciting discoveries we've made and how informatics methods planned a central role in these discoveries. First, we will look at our work on data-driven biosignature detection, specifically how we combine pyrolysis-gas chromatography-mass spectrometry and machine learning to build an agnostic molecular biosignature detection model. Next, we will talk about how we used association analysis to predict the locations of as-yet-unknown mineral deposits on Earth and potentially Mars. These advances hold the potential to unlock new avenues of economic growth and sustainable development.Finally, we will set our sights on exoplanets—celestial bodies orbiting distant stars. The discovery of thousands of exoplanets in recent years has fueled the quest to understand their formation, composition, and potential habitability. We develop informatics approaches to better understand, classify and predict the occurrence of exoplanets by embracing the complexity and multidimensionality of exoplanets and their host stars.