Analyze Mass Spectrometry data with Artificial Intelligence to assist the understanding of past habitability of Mars and provide insights for future missions (2310.11888v1)
Abstract: This paper presents an application of artificial intelligence on mass spectrometry data for detecting habitability potential of ancient Mars. Although data was collected for planet Mars the same approach can be replicated for any terrestrial object of our solar system. Furthermore, proposed methodology can be adapted to any domain that uses mass spectrometry. This research is focused in data analysis of two mass spectrometry techniques, evolved gas analysis (EGA-MS) and gas chromatography (GC-MS), which are used to identify specific chemical compounds in geological material samples. The study demonstrates the applicability of EGA-MS and GC-MS data to extra-terrestrial material analysis. Most important features of proposed methodology includes square root transformation of mass spectrometry values, conversion of raw data to 2D sprectrograms and utilization of specific machine learning models and techniques to avoid overfitting on relative small datasets. Both EGA-MS and GC-MS datasets come from NASA and two machine learning competitions that the author participated and exploited. Complete running code for the GC-MS dataset/competition is available at GitHub.1 Raw training mass spectrometry data include [0, 1] labels of specific chemical compounds, selected to provide valuable insights and contribute to our understanding of the potential past habitability of Mars.
- Detection of fraud in sesame oil with the help of artificial intelligence combined with chemometrics methods and chemical compounds characterization by gas chromatography–mass spectrometry. Lwt 167, 113863.
- Application of the logistic function to bio-assay. Journal of the American statistical association 39, 357–365.
- Spicam on mars express: Observing modes and overview of uv spectrometer data and scientific results. Journal of Geophysical Research: Planets 111.
- Random forests. Machine learning 45, 5–32.
- Planetary mass spectrometry for agnostic life detection in the solar system. Frontiers in Astronomy and Space Sciences 8, 755100.
- Jsc-rocknest: A large-scale mojave mars simulant (mms) based soil simulant for in-situ resource utilization water-extraction studies. Icarus 351, 113936.
- Planetary geochemical investigations using raman and laser-induced breakdown spectroscopy. Applied spectroscopy 68, 925–936.
- Ensemble methods in machine learning, in: International workshop on multiple classifier systems, Springer. pp. 1–15.
- The supercam infrared spectrometer for the perseverance rover of the mars2020 mission. Icarus 373, 114773.
- Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the thirteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings. pp. 249–256.
- Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12, 55–67.
- Optimal number of features as a function of sample size for various classification rules. Bioinformatics 21, 1509–1515.
- Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, in: Workshop on challenges in representation learning, ICML, p. 896.
- In situ analysis of martian regolith with the sam experiment during the first mars year of the msl mission: Identification of organic molecules by gas chromatography from laboratory measurements. Planetary and Space Science 129, 88–102.
- Co-pyrolysis of wood and plastic: Evaluation of synergistic effects and kinetic data by evolved gas analysis-mass spectrometry (ega-ms). Journal of Analytical and Applied Pyrolysis 159, 105308.
- NASA, 2023a. Mars spectrometry 2: Gas chromatography for the sample analysis at mars data (sam) instrument. URL: https://registry.opendata.aws/nasa-gcms/.
- NASA, 2023b. Mars spectrometry: Detect evidence for past habitability. URL: https://registry.opendata.aws/nasa-ega/.
- Machine learning for planetary rovers, in: Machine Learning for Planetary Science. Elsevier, pp. 169–191.
- Classification of cereal flour by gas chromatography–mass spectrometry (gc-ms) liposoluble fingerprints and automated machine learning. Analytical Letters 55, 2220–2226.
- Adapting a trusted ai framework to space mission autonomy, in: 2022 IEEE Aerospace Conference (AERO), IEEE. pp. 1–20.
- Cross-validatory choice and assessment of statistical predictions. Journal of the royal statistical society: Series B (Methodological) 36, 111–133.
- Determining degree of roasting in cocoa beans by artificial neural network (ann)-based electronic nose system and gas chromatography/mass spectrometry (gc/ms). Journal of the Science of Food and Agriculture 98, 3851–3859.
- Efficientnet: Rethinking model scaling for convolutional neural networks, in: International conference on machine learning, PMLR. pp. 6105–6114.
- Artificial intelligence for the advancement of lunar and planetary science and exploration. Bulletin of the American Astronomical Society 53, 222.
- A quantitative evolved gas analysis for extra-terrestrial samples. Planetary and Space Science 181, 104830.
- Oxidized and reduced sulfur observed by the sample analysis at mars (sam) instrument suite on the curiosity rover within the glen torridon region at gale crater, mars. Journal of Geophysical Research: Planets 127, e2021JE007084.
- A review of recurrent neural networks: Lstm cells and network architectures. Neural computation 31, 1235–1270.
- mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 .
- Application of evolved gas analysis technique for speciation of minor minerals in clays. Minerals 10, 824.