Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data
Abstract Future missions to icy ocean worlds (OW) such as Europa and Enceladus will evaluate the habitability and potential for biosignatures on these worlds. These missions will benefit from autonomous science and machine learning (ML) methods to process high volumes of data and prioritize signals...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2025-03-01
|
| Series: | Earth and Space Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2024EA003966 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849329597626187776 |
|---|---|
| author | Lily A. Clough Victoria DaPoian Jonathan D. Major Lauren M. Seyler Brett A. McKinney Bethany P. Theiling |
| author_facet | Lily A. Clough Victoria DaPoian Jonathan D. Major Lauren M. Seyler Brett A. McKinney Bethany P. Theiling |
| author_sort | Lily A. Clough |
| collection | DOAJ |
| description | Abstract Future missions to icy ocean worlds (OW) such as Europa and Enceladus will evaluate the habitability and potential for biosignatures on these worlds. These missions will benefit from autonomous science and machine learning (ML) methods to process high volumes of data and prioritize signals of interest for the first available downlink. Mass spectrometers (MS) are suitable instruments for implementing science autonomy due to their rich spectral data products and potential for biosignature detection. Light stable isotopes are strong candidates for biosignatures due to the large fractionations promoted by biological activity. However, complex abiotic geochemistry may obscure or mimic biogenic isotope fractionations. ML may accurately disentangle biosignatures from abiotic mimicry in MS data; however, ML model predictions can be inscrutable to human interpretation, compromising trust in scientifically significant detections. We develop and test a new biosignature detection ML model using a novel, laboratory‐generated, CO2 isotopologue data set of analogue OW samples. These data include various potential OW seawater chemistries and biotic mimicry. Our ML approach includes feature (variable) construction, providing mathematical and geochemical context for biosignatures, and a feature selection method called Nearest‐neighbors Projected Distance Regression (NPDR) that identifies important predictors. Our Random Forest biosignature model predicts the presence of biosignatures with 87.3% mean accuracy regardless of the sample brine chemistry. We add network visualization of main effects and statistical interactions for interpretation of model prediction mechanisms. We use single‐sample (local) variable importance scores to diagnose false predictions for individual samples, which is crucial for trust in astrobiology ML biosignature models. |
| format | Article |
| id | doaj-art-13de3d176d424227b9b7be0c25fa47b2 |
| institution | Kabale University |
| issn | 2333-5084 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Earth and Space Science |
| spelling | doaj-art-13de3d176d424227b9b7be0c25fa47b22025-08-20T03:47:13ZengAmerican Geophysical Union (AGU)Earth and Space Science2333-50842025-03-01123n/an/a10.1029/2024EA003966Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue DataLily A. Clough0Victoria DaPoian1Jonathan D. Major2Lauren M. Seyler3Brett A. McKinney4Bethany P. Theiling5Tandy School of Computer Science The University of Tulsa Tulsa OK USAPlanetary Environments Laboratory NASA Goddard Space Flight Center Greenbelt MD USASchool of Geosciences University of South Florida Tampa FL USASchool of Natural Sciences and Mathematics Stockton University Galloway NJ USATandy School of Computer Science The University of Tulsa Tulsa OK USAPlanetary Environments Laboratory NASA Goddard Space Flight Center Greenbelt MD USAAbstract Future missions to icy ocean worlds (OW) such as Europa and Enceladus will evaluate the habitability and potential for biosignatures on these worlds. These missions will benefit from autonomous science and machine learning (ML) methods to process high volumes of data and prioritize signals of interest for the first available downlink. Mass spectrometers (MS) are suitable instruments for implementing science autonomy due to their rich spectral data products and potential for biosignature detection. Light stable isotopes are strong candidates for biosignatures due to the large fractionations promoted by biological activity. However, complex abiotic geochemistry may obscure or mimic biogenic isotope fractionations. ML may accurately disentangle biosignatures from abiotic mimicry in MS data; however, ML model predictions can be inscrutable to human interpretation, compromising trust in scientifically significant detections. We develop and test a new biosignature detection ML model using a novel, laboratory‐generated, CO2 isotopologue data set of analogue OW samples. These data include various potential OW seawater chemistries and biotic mimicry. Our ML approach includes feature (variable) construction, providing mathematical and geochemical context for biosignatures, and a feature selection method called Nearest‐neighbors Projected Distance Regression (NPDR) that identifies important predictors. Our Random Forest biosignature model predicts the presence of biosignatures with 87.3% mean accuracy regardless of the sample brine chemistry. We add network visualization of main effects and statistical interactions for interpretation of model prediction mechanisms. We use single‐sample (local) variable importance scores to diagnose false predictions for individual samples, which is crucial for trust in astrobiology ML biosignature models.https://doi.org/10.1029/2024EA003966astrobiologybiosignaturesmachine learningfeature selection |
| spellingShingle | Lily A. Clough Victoria DaPoian Jonathan D. Major Lauren M. Seyler Brett A. McKinney Bethany P. Theiling Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data Earth and Space Science astrobiology biosignatures machine learning feature selection |
| title | Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data |
| title_full | Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data |
| title_fullStr | Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data |
| title_full_unstemmed | Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data |
| title_short | Interpretable Machine Learning Biosignature Detection From Ocean Worlds Analogue CO2 Isotopologue Data |
| title_sort | interpretable machine learning biosignature detection from ocean worlds analogue co2 isotopologue data |
| topic | astrobiology biosignatures machine learning feature selection |
| url | https://doi.org/10.1029/2024EA003966 |
| work_keys_str_mv | AT lilyaclough interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata AT victoriadapoian interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata AT jonathandmajor interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata AT laurenmseyler interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata AT brettamckinney interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata AT bethanyptheiling interpretablemachinelearningbiosignaturedetectionfromoceanworldsanalogueco2isotopologuedata |