Floyd Nichols
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Floyd Nichols has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Alexandra Pontefract
Space Exploration Sector Johns Hopkins University Applied Physics Laboratory Laurel MD USA
3 shared publicationsAndrew L. Masterson
Department of Earth & Planetary Sciences Northwestern University Evanston IL USA
2 shared publications- Christopher E. Carr
School of Earth and Atmospheric Sciences, Georgia Institute of Technology, Atlanta, Georgia, USA
2 shared publications - Magdalena Rose Osburn
Department of Earth, Environmental, and Planetary Sciences Northwestern University Evanston IL USA
2 shared publications Andrew L Masterson
Northwestern University
1 shared publication- Hannah Dion-Kirschner
Division of Geological and Planetary Sciences, California Institute of Technology, Pasadena, USA
1 shared publication
Latest Publications
- Open Access
- 23 June 2024
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 1 (2)
Leveraging Machine Learning Approaches to Predict Organic Carbon Abundance in Mars‐Analog Hypersaline Lake Sediments
Modern advancements in laboratory and instrumental techniques in astrobiology have improved our life detection capabilities on both Earth and beyond. These advancements have also increased the complexity of data often resulting in data sets that are characterized by complex and non‐linear relationships. Machine learning methods are underutilized in astrobiology; however, these methods are extremely effective at revealing structure and patterns in complex data sets when paired with the right algorithms. Here, we employ a series of classification and regression algorithms to predict the abundance of organic carbon (OC) from X‐ray fluorescence (XRF) heavy element (>Mg) data in dynamic Mars‐analog hypersaline lake sediments. More specifically, we constructed models using the random forest, k‐nearest neighbors (KNN), support vector machine, and logistic regression algorithms. Overall, our trained models showed good performance with predicting the abundance of OC, with accuracies from 80% to 94%. Machine learning approaches such as classification and regression algorithms offer insight into complex data while providing agnostic insights, ultimately creating a more efficient search for OC. We applied our trained model on XRF data from Martian soil using rover‐based (PIXL) and orbital (Odyssey) data sets to produce probability predictions of OC abundance. Our predictions show a high probability that OC abundance is low which is comparable to OC data from recently landed missions. These results highlight the potential for predictive machine learning models to be trained on data from analog environments on Earth and then applied to extraterrestrial targets, ultimately, improving life detection efforts.
- 23 June 2024
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 1 (2)
Open AccessLeveraging Machine Learning Approaches to Predict Organic Carbon Abundance in Mars‐Analog Hypersaline Lake Sediments
Modern advancements in laboratory and instrumental techniques in astrobiology have improved our life detection capabilities on both Earth and beyond. These advancements have also increased the complexity of data often resulting in data sets that are characterized by complex and non‐linear relationships. Machine learning methods are underutilized in astrobiology; however, these methods are extremely effective at revealing structure and patterns in complex data sets when paired with the right algorithms. Here, we employ a series of classification and regression algorithms to predict the abundance of organic carbon (OC) from X‐ray fluorescence (XRF) heavy element (>Mg) data in dynamic Mars‐analog hypersaline lake sediments. More specifically, we constructed models using the random forest, k‐nearest neighbors (KNN), support vector machine, and logistic regression algorithms. Overall, our trained models showed good performance with predicting the abundance of OC, with accuracies from 80% to 94%. Machine learning approaches such as classification and regression algorithms offer insight into complex data while providing agnostic insights, ultimately creating a more efficient search for OC. We applied our trained model on XRF data from Martian soil using rover‐based (PIXL) and orbital (Odyssey) data sets to produce probability predictions of OC abundance. Our predictions show a high probability that OC abundance is low which is comparable to OC data from recently landed missions. These results highlight the potential for predictive machine learning models to be trained on data from analog environments on Earth and then applied to extraterrestrial targets, ultimately, improving life detection efforts.
- Open Access
- 24 January 2024
- Published by Wiley
Leveraging Machine Learning Approaches to Predict Organic Carbon Abundance in Mars-Analog Hypersaline Lake Sediments
Modern advancements in laboratory and instrumental techniques in astrobiology have improved our life detection capabilities on both Earth and beyond. These advancements have also increased the complexity of data often resulting in datasets that are characterized by complex and non-linear relationships. Machine learning methods are underutilized in astrobiology; however, these methods are extremely effective at revealing structure and patterns in complex datasets when paired with the right algorithms. Here, we employ a series of classification and regression algorithms to predict the abundance of organic carbon (OC) from X-ray fluorescence (XRF) data in dynamic Mars-analog hypersaline lake sediments. More specifically, we constructed models using the random forest (RF), k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR) algorithms. Overall, our trained models showed good performance with predicting the abundance of OC, with accuracies from 80% to 94%. Our results show how applying predictive models to astrobiology datasets can help life detection efforts. Machine learning approaches such as classification and regression algorithms offer insight into complex data while providing agnostic insights, ultimately creating a more efficient search for OC. We applied our trained model on XRF data from Martian soil using PIXL and Odyssey datasets to produce probability predictions of OC abundance. Our predictions show a high probability that OC abundance is low which is comparable to OC data from recently landed missions. These results highlight the potential for machine learning models to be trained on data from analog environments on Earth and then transferred (transfer learning) to extraterrestrial targets.
- 24 January 2024
- Published by Wiley
Open AccessLeveraging Machine Learning Approaches to Predict Organic Carbon Abundance in Mars-Analog Hypersaline Lake Sediments
Modern advancements in laboratory and instrumental techniques in astrobiology have improved our life detection capabilities on both Earth and beyond. These advancements have also increased the complexity of data often resulting in datasets that are characterized by complex and non-linear relationships. Machine learning methods are underutilized in astrobiology; however, these methods are extremely effective at revealing structure and patterns in complex datasets when paired with the right algorithms. Here, we employ a series of classification and regression algorithms to predict the abundance of organic carbon (OC) from X-ray fluorescence (XRF) data in dynamic Mars-analog hypersaline lake sediments. More specifically, we constructed models using the random forest (RF), k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR) algorithms. Overall, our trained models showed good performance with predicting the abundance of OC, with accuracies from 80% to 94%. Our results show how applying predictive models to astrobiology datasets can help life detection efforts. Machine learning approaches such as classification and regression algorithms offer insight into complex data while providing agnostic insights, ultimately creating a more efficient search for OC. We applied our trained model on XRF data from Martian soil using PIXL and Odyssey datasets to produce probability predictions of OC abundance. Our predictions show a high probability that OC abundance is low which is comparable to OC data from recently landed missions. These results highlight the potential for machine learning models to be trained on data from analog environments on Earth and then transferred (transfer learning) to extraterrestrial targets.
- Open Access
- 29 September 2023
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Biogeosciences
- Vol. 128 (10)
Lipid Biosignatures From SO4‐Rich Hypersaline Lakes of the Cariboo Plateau
Modern and ancient hypersaline brines have been identified across the solar system, but the habitability of these environments remains unknown. Here, we evaluate organic matter (OM) production in MgSO4 and Na2CO3 rich hypersaline lakes whose chemistries resemble deposits on Mars such as those identified in Jezero crater. We focus our analysis on lipid biomarkers including fatty acids, alkanes, and ether‐bound lipids in modern brines, salt deposits, and surface sediments. We also report total organic carbon (TOC), carbon/nitrogen (C/N) ratios, and bulk OC (δ13C and δ15N) isotopes to contextualize the lipid biomarker data. In all lakes, the predominant biosignatures include midchain (12 < C < 23) fatty acids and alkanes suggesting microbial origin. Sediments also incorporate a greater diversity of lipids. Ether‐bound lipids derived from archaea and bacteria constitute a minor but measurable fraction of the lipids. This result contrasts with typical findings from other studies with NaCl brines which contain significant archeal biomass. TOC concentrations in all sediments are high, ranging from 0.7% to 12% with sulfate‐rich sediments having the highest concentrations. The isotopic and elemental compositions of TOC corroborate the biomarker results, showing δ13C values and C/N values indicative of aquatic microbial origin. This richness of organic matter and in situ microbial biosignatures differ from previously studied Cl‐dominated Mars‐analog sites which have shown limited OM production and preservation and acidic SO4‐rich hypersaline environments which were dominated by terrestrial inputs. Overall, our results suggest that MgSO4‐rich hypersaline environments are conducive for life and harbor a rich microbial biomarker landscape.
- 29 September 2023
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Biogeosciences
- Vol. 128 (10)
Open AccessLipid Biosignatures From SO4‐Rich Hypersaline Lakes of the Cariboo Plateau
Modern and ancient hypersaline brines have been identified across the solar system, but the habitability of these environments remains unknown. Here, we evaluate organic matter (OM) production in MgSO4 and Na2CO3 rich hypersaline lakes whose chemistries resemble deposits on Mars such as those identified in Jezero crater. We focus our analysis on lipid biomarkers including fatty acids, alkanes, and ether‐bound lipids in modern brines, salt deposits, and surface sediments. We also report total organic carbon (TOC), carbon/nitrogen (C/N) ratios, and bulk OC (δ13C and δ15N) isotopes to contextualize the lipid biomarker data. In all lakes, the predominant biosignatures include midchain (12 < C < 23) fatty acids and alkanes suggesting microbial origin. Sediments also incorporate a greater diversity of lipids. Ether‐bound lipids derived from archaea and bacteria constitute a minor but measurable fraction of the lipids. This result contrasts with typical findings from other studies with NaCl brines which contain significant archeal biomass. TOC concentrations in all sediments are high, ranging from 0.7% to 12% with sulfate‐rich sediments having the highest concentrations. The isotopic and elemental compositions of TOC corroborate the biomarker results, showing δ13C values and C/N values indicative of aquatic microbial origin. This richness of organic matter and in situ microbial biosignatures differ from previously studied Cl‐dominated Mars‐analog sites which have shown limited OM production and preservation and acidic SO4‐rich hypersaline environments which were dominated by terrestrial inputs. Overall, our results suggest that MgSO4‐rich hypersaline environments are conducive for life and harbor a rich microbial biomarker landscape.