Adapting a Trusted AI Framework to Space Mission Autonomy

Slingerland, Philip; Perry, Lauren; Kaufman, James C.; Bycroft, Benjamen; Linstead, Erik; Mandrake, Lukas; Doran, Gary; Goel, Ashish; Feather, Martin S.; Fesq, Lorraine; Ono, Hiro; Amini, Rashied

doi:10.1109/aero53065.2022.9843376

Cited by 13 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The onboard science autonomy use‐case presents unique requirements that sharply differ from laboratory data analysis in terms of computational constraints, robustness to unanticipated inputs, and interpretability (Slingerland et al., 2021 ). For example, while abundant open source software packages exist to find peaks in mass spectrometer data such as OpenMS (Sturm et al., 2008 ), XCMS (Smith et al., 2006 ), CWT (Du et al., 2006 ), MZmine2 (Pluskal et al., 2010 ), or more recently deep learning (Liu et al., 2019 ; Zhao et al., 2021 ), most of these algorithms are too computational expensive for space‐borne applications.…”

Section: Methodsmentioning

confidence: 99%

Autonomous CE Mass‐Spectra Examination for the Ocean Worlds Life Surveyor

Mauceri

Lee

Wronkiewicz

et al. 2022

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

The search for extraterrestrial life is one of the great motivators for exploring worlds beyond Earth. Ocean worlds, such as Europa and Enceladus, offer protected, potentially habitable environments that may be sampled from the surface through inclusions in thermally convected ice, pressure driven fluid through fractures, or deposition by active plumes, for example (Carr et al., 1998;Postberg et al., 2009;Quick et al., 2017). To prepare for such deep space missions to these icy worlds, NASA's Jet Propulsion Laboratory (JPL) is developing the ocean worlds life surveyor (OWLS), an in-situ instrument suite capable of detecting multiple, independent biosignatures indicative of life. At the molecular scale, terrestrial life may be detected by the presence of key organic compounds such as metabolites and amino acids. However, as extant life may have resulted from a separate genesis, an in-situ instrument must be sensitive to as broad a spectrum of life-like molecules as possible. This challenging analytic goal must be achieved on an ice sample, using only the limited computation available to space missions, and in an autonomous fashion (

show abstract

Section: Methodsmentioning

confidence: 99%

Autonomous CE Mass‐Spectra Examination for the Ocean Worlds Life Surveyor

Mauceri

Lee

Wronkiewicz

et al. 2022

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning equips spacecraft and rovers, like NASA's Mars rovers, to navigate and collect data independently, optimizing paths in real time. Research expands AI's role in autonomous spacecraft technology and space law [105,106], with a focus on developing trusted AI systems for mission autonomy [107]. These AI advancements promise to significantly enhance the efficiency, autonomy, and intelligence of space missions, marking a new era in space exploration and analysis.…”

Section: Space Exploration: Autonomous Exploration and Data Analysismentioning

confidence: 99%

Artificial Intelligence: A Promising Tool for Application in Phytopathology

González-Rodríguez,

Izquierdo-Bueno,

Cantoral

et al. 2024

Horticulturae

View full text Add to dashboard Cite

Artificial intelligence (AI) is revolutionizing approaches in plant disease management and phytopathological research. This review analyzes current applications and future directions of AI in addressing evolving agricultural challenges. Plant diseases annually cause 10–16% yield losses in major crops, prompting urgent innovations. Artificial intelligence (AI) shows an aptitude for automated disease detection and diagnosis utilizing image recognition techniques, with reported accuracies exceeding 95% and surpassing human visual assessment. Forecasting models integrating weather, soil, and crop data enable preemptive interventions by predicting spatial-temporal outbreak risks weeks in advance at 81–95% precision, minimizing pesticide usage. Precision agriculture powered by AI optimizes data-driven, tailored crop protection strategies boosting resilience. Real-time monitoring leveraging AI discerns pre-symptomatic anomalies from plant and environmental data for early alerts. These applications highlight AI’s proficiency in illuminating opaque disease patterns within increasingly complex agricultural data. Machine learning techniques overcome human cognitive constraints by discovering multivariate correlations unnoticed before. AI is poised to transform in-field decision-making around disease prevention and precision management. Overall, AI constitutes a strategic innovation pathway to strengthen ecological plant health management amidst climate change, globalization, and agricultural intensification pressures. With prudent and ethical implementation, AI-enabled tools promise to enable next-generation phytopathology, enhancing crop resilience worldwide.

show abstract

“…The onboard science autonomy use-case presents unique requirements that sharply differ from laboratory data analysis in terms of computational constraints, robustness to unanticipated inputs, and interpretability (Slingerland et al, 2021). For example, while abundant open source software packages exist to find peaks in mass spectrometer data such as OpenMS (Sturm et al, 2008), XCMS (Smith et al, 2006), CWT (Du et al, 2006), MZmine2 (Pluskal et al, 2010), or more recently deep learning (Liu et al, 2019;Zhao et al, 2021), most of these algorithms maximize sensitivity with little consideration for computational efficiency or the requirement for real-time user parameter adjustment.…”

Section: Peak Detection Algorithmmentioning

confidence: 99%

Autonomous CE Mass-Spectra Examination (ACME) for the Ocean Worlds Life Surveyor (OWLS)

Mauceri

Lee

Wronkiewicz

et al. 2022

Preprint

View full text Add to dashboard Cite

Ocean worlds such as Europa and Enceladus are high priority targets in the search for past or extant life beyond Earth. Evidence of life may be preserved in samples of surface ice by processes such as deposition from active plumes or thermal convection. Terrestrial life produces unique distributions of organic molecules that translate into recognizable biosignatures. Identification and quantification of these organic compounds can be achieved by separation science such as capillary electrophoresis coupled to mass spectrometry (CE-MS). However, the data generated by such an instrument can be multiple orders of magnitude larger than what can be transmitted back to Earth during an ocean worlds mission. This requires onboard science data analysis capabilities that summarize and prioritize CE-MS observations with limited compute resources. In response, the Autonomous Capillary Electrophoresis Mass-spectra Examination (ACME) onboard science autonomy system was created for application to the Ocean Worlds Life Surveyor (OWLS) instrument suite. ACME is able to compress raw mass spectra by two to three orders of magnitude while preserving most of its scientifically relevant information content. This summarization is achieved by the extraction of raw data surrounding autonomously identified ion peaks and the detection and parameterization of unique background regions. Prioritization of the summarized observations is then enabled by providing estimates of scientific utility, the uniqueness of an observation relative to previous observations, and the presence of key target compound signatures.

show abstract

Adapting a Trusted AI Framework to Space Mission Autonomy

Cited by 13 publications

References 38 publications

Autonomous CE Mass‐Spectra Examination for the Ocean Worlds Life Surveyor

Autonomous CE Mass‐Spectra Examination for the Ocean Worlds Life Surveyor

Artificial Intelligence: A Promising Tool for Application in Phytopathology

Autonomous CE Mass-Spectra Examination (ACME) for the Ocean Worlds Life Surveyor (OWLS)

Contact Info

Product

Resources

About