Search NASA⌕ Search

SEARCH · Search NASA

Results for “prediction algorithms”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,009 records · Page 56

Autonomous Assessment and Predictive Capabilities for Low-Altitude Urban Flight Operations

The integration of unmanned aerial vehicles in the national airspace will introduce new vehicle types, technologies, and operational paradigms for which safety must be maintained and hazards mitigated. One approach is to attempt to design for possible hazards and unsafe incidents that can occur at different phases of flight (pre-flight, in-flight, and post-flight) and during ground operations. Another is to mitigate safety incidents by implementing changes to policies, procedures, regulations, and design to cover personnel, equipment, and aircraft during operations. These and other techniques, not described herein, are typically conservative or adhoc in that they reduce the likelihood of risk after safety incidents have occurred. In this work, the goal is to develop a more predictive capability to monitor and mitigate risk and hazards to safety “in-time” enough for decisions to be made. In line with NASA’s Aeronautics Mission Directorate Strategic Thrust 5 [1] (In-Time System-Wide Safety Assurance), the System-Wide Safety (SWS) project under which this work falls, is developing and demonstrating innovative and safety-oriented solutions that enable modernization and aviation transformation. To that effect, this work will detail data-driven efforts on the SWS project to develop a number of safety-critical services for in-time monitoring and mitigation of hazards to low-altitude flight operations. First, hazards to these operations are identified based on previous work by NASA [2,3] and others in the aerospace industry. These hazards include (i) unsafe proximity to other vehicles, property, and people on the ground, (ii) critical system failures such as communication signal/GPS loss, unexpected propulsion system degradation, engine/power failure, and (iii) operational/environmental issues such as severe weather and gusty winds. For these hazards, safety metrics, which can be quantified and assessed are defined, models to monitor and predict them are developed, and flight test data is generated to develop, validate, and test these models, considering the complex interplay of the different hazards that define them [4-6]. In addition, the uncertainty in the non-deterministic effects that cannot be modeled nor predicted and unknown unknowns that arise after design/testing and during operations must be handled in rigorous manner. As a result, for each of the developed safety metrics, their dependencies on one another are characterized and a framework for handling the uncertainties inherent in the modeling, algorithms, and measurements required for prediction is also developed [7]. To that effect, this presentation will describe the safety metrics and services already developed and underway under the System-Wide Safety project that utilize data-driven techniques for the identification of anomalies, precursors, and trends (APTs) to monitor and mitigate hazards to safety, in-time, for urban flight operations in low-altitude airspace.

Okolo, Wendy A.↗

A model for the progressive failure of laminated composite structural components

Laminated continuous fiber polymeric composites are capable of sustaining substantial load induced microstructural damage prior to component failure. Because this damage eventually leads to catastrophic failure, it is essential to capture the mechanics of progressive damage in any cogent life prediction model. For the past several years the authors have been developing one solution approach to this problem. In this approach the mechanics of matrix cracking and delamination are accounted for via locally averaged internal variables which account for the kinematics of microcracking. Damage progression is predicted by using phenomenologically based damage evolution laws which depend on the load history. The result is a nonlinear and path dependent constitutive model which has previously been implemented to a finite element computer code for analysis of structural components. Using an appropriate failure model, this algorithm can be used to predict component life. In this paper the model will be utilized to demonstrate the ability to predict the load path dependence of the damage and stresses in plates subjected to fatigue loading.

Allen, D. H.↗

Optimizing Medical Kits for Spaceflight

The Integrated Medical Model (IMM) is a probabilistic model that estimates medical event occurrences and mission outcomes for different mission profiles. IMM simulation outcomes describing the impact of medical events on the mission may be used to optimize the allocation of resources in medical kits. Efficient allocation of medical resources, subject to certain mass and volume constraints, is crucial to ensuring the best outcomes of in-flight medical events. We implement a new approach to this medical kit optimization problem. METHODS We frame medical kit optimization as a modified knapsack problem and implement an algorithm utilizing a dynamic programming technique. Using this algorithm, optimized medical kits were generated for 3 different mission scenarios with the goal of minimizing the probability of evacuation and maximizing the Crew Health Index (CHI) for each mission subject to mass and volume constraints. Simulation outcomes using these kits were also compared to outcomes using kits optimized..RESULTS The optimized medical kits generated by the algorithm described here resulted in predicted mission outcomes more closely approached the unlimited-resource scenario for Crew Health Index (CHI) than the implementation in under all optimization priorities. Furthermore, the approach described here improves upon in reducing evacuation when the optimization priority is minimizing the probability of evacuation. CONCLUSIONS This algorithm provides an efficient, effective means to objectively allocate medical resources for spaceflight missions using the Integrated Medical Model.

Optimization↗

Real-time control of connected vehicles in signalized corridors using pseudospectral convex optimization

Recent advances in Connected and Automated Vehicle (CAV) technologies have opened up new opportunities to enable safe, efficient, and sustainable transportation systems. However, developing reliable and rapid speed control algorithms in highly dynamic environments with complex inter-vehicle interactions and nonlinear vehicle dynamics is still a daunting task. In this paper, we develop a novel speed control method for CAVs to produce optimal speed profiles that minimize the fuel consumption and avoid idling at signalized intersections. To this end, an optimal control problem is formulated using the information of the upcoming traffic signal to adapt vehicles' speeds to avoid frequent stop-and-go driving patterns. Here, by applying the pseudospectral discretization method and the sequential convex programming method, the computational efficiency is greatly improved, enabling potential real-time on-vehicle applications. In addition, the algorithm is implemented under a model predictive control framework to ensure online control with instant response for collision avoidance and robust vehicle coordination. The proposed algorithm is verified through numerical simulations of three different traffic scenarios. The convergence and accuracy of the proposed approach are demonstrated by comparing with a popular nonlinear solver. Furthermore, the benefit of the proposed method in both traffic mobility and fuel efficiency is validated using the speed profile determined from a traffic following model in a simulation software as the baseline.

42 ENGINEERING↗

WE-AB-207B-05: Correlation of Normal Lung Density Changes with Dose After Stereotactic Body Radiotherapy (SBRT) for Early Stage Lung Cancer

Purpose: To investigate correlation of normal lung CT density changes with dose accuracy and outcome after SBRT for patients with early stage lung cancer. Methods: Dose distributions for patients originally planned and treated using a 1-D pencil beam-based (PB-1D) dose algorithm were retrospectively recomputed using algorithms: 3-D pencil beam (PB-3D), and model-based Methods: AAA, Acuros XB (AXB), and Monte Carlo (MC). Prescription dose was 12 Gy × 4 fractions. Planning CT images were rigidly registered to the followup CT datasets at 6–9 months after treatment. Corresponding dose distributions were mapped from the planning to followup CT images. Following the method of Palma et al .(1–2), Hounsfield Unit (HU) changes in lung density in individual, 5 Gy, dose bins from 5–45 Gy were assessed in the peri-tumor region, defined as a uniform, 3 cm expansion around the ITV(1). Results: There is a 10–15% displacement of the high dose region (40–45 Gy) with the model-based algorithms, relative to the PB method, due to the electron scattering of dose away from the tumor into normal lung tissue (Fig.1). Consequently, the high-dose lung region falls within the 40–45 Gy dose range, causing an increase in HU change in this region, as predicted by model-based algorithms (Fig.2). The patient with the highest HU change (∼110) had mild radiation pneumonitis, and the patient with HU change of ∼80–90 had shortness of breath. No evidence of pneumonitis was observed for the 3 patients with smaller CT density changes (<50 HU). Changes in CT densities, and dose-response correlation, as computed with model-based algorithms, are in excellent agreement with the findings of Palma et al. (1–2). Conclusion: Dose computed with PB (1D or 3D) algorithms was poorly correlated with clinically relevant CT density changes, as opposed to model-based algorithms. A larger cohort of patients is needed to confirm these results. This work was supported in part by a grant from Varian Medical Systems, Palo Alto, CA.

60 APPLIED LIFE SCIENCES↗

Evaluation of Droplet Splashing Algorithm in LEWICE 3.0

The Icing Branch at NASA Glenn Research has developed a computer program to simulate ice formation on the leading edge of an aircraft wing during flight through cold, moist air. As part of the branch's current research, members have developed software known as LEWICE. This program is capable of predicting the formation of ice under designated weather conditions. The success of LEWICE is an asset to airplane manufacturers, ice protection system manufacturers, and the airline industry. Simulations of ice formation conducted in the tunnel and in flight is costly and time consuming. However, the danger of in-flight icing continues to be a concern for both commercial and military pilots. The LEWICE software is a step towards inexpensive and time efficient prediction of ice collection. In the most recent version of the program, LEWICE contains an algorithm for droplet splashing. Droplet splashing is a natural occurrence that causes accumulation of ice on aircraft surfaces. At impingement water droplets lose a portion of their mass to splashing. With part of each droplet joining the airflow and failing to freeze, early versions of LEWICE without the splashing algorithm over-predicted the collection of ice on the leading edge. The objective of my project was to determine whether the revised version of LEWICE accurately reflected the ice collection data obtained from the Icing Research Tunnel (IRT). The experimental data from the IRT was collected by Mark Potapczuk in January, March and July of 2001 and April and December of 2002. Experimental data points were the result of ice tracings conducted shortly after testing in the tunnel. Run sheets, which included a record of velocity, temperature, liquid water content and droplet diameter, served as the input of the LEWICE computer program. Parameters identical to the tunnel conditions were used to run LEWICE 2.0 and LEWICE 3.0. The results from IRT and versions of LEWICE were compared graphically. After entering the raw experimental data and computer output into a spread sheet, I mapped each ice formation onto a clean airfoil. The LEWICE output provided the data points to graphically depict ice formations developed by the program. weather conditions of runs conducted in January 2001, it was evident that the splashing algorithm of LEWICE 3.0 predicts ice formations more accurately than LEWICE 2.0. Especially at conditions with droplet size between 80 and 160 microns, the splashing algorithm of the new LEWICE version compensated for the loss of droplet mass as a result of splashing. In contrast, LEWICE 2.0 consistently over-predicted the mass of the ice in conditions with droplet size exceeding 80 microns. This evidence confirms that changes made to algorithms of LEWICE 3.0 have increased the accuracy of predicting ice collection.

Homenko, Hilary N.↗

Machine Learning Assisted Synthesis of Metal–Organic Nanocapsules

Herein, we report machine learning algorithms by training data sets from a set of both successful and failed experiments for studying the crystallization propensity of metal–organic nanocapsules (MONCs). Among a variety of studied machine learning algorithms, XGBoost affords the highest prediction accuracy of >90%. The derived chemical feature scores that determine importance of reaction parameters from the XGBoost model assist to identify synthesis parameters for successfully synthesizing new hierarchical structures of MONCs, showing superior performance to a well-trained chemist. This work demonstrates that the machine learning algorithms can assist the chemists to faster search for the optimal reaction parameters from many experimental variables, whose features are usually hidden in the high-dimensional space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Lossless Compression of Classification-Map Data

A lossless image-data-compression algorithm intended specifically for application to classification-map data is based on prediction, context modeling, and entropy coding. The algorithm was formulated, in consideration of the differences between classification maps and ordinary images of natural scenes, so as to be capable of compressing classification- map data more effectively than do general-purpose image-data-compression algorithms. Classification maps are typically generated from remote-sensing images acquired by instruments aboard aircraft (see figure) and spacecraft. A classification map is a synthetic image that summarizes information derived from one or more original remote-sensing image(s) of a scene. The value assigned to each pixel in such a map is the index of a class that represents some type of content deduced from the original image data for example, a type of vegetation, a mineral, or a body of water at the corresponding location in the scene. When classification maps are generated onboard the aircraft or spacecraft, it is desirable to compress the classification-map data in order to reduce the volume of data that must be transmitted to a ground station.

Hua, Xie↗

A scalable algorithm for the optimization of neural network architectures

In this work, we propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified by other hyperparameter search algorithms in terms of accuracy and computational cost. Numerical results performed on benchmark datasets show that, for these datasets, our method outperforms state-of-the-art hyperparameter optimization algorithms in terms of attainable predictive performance by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete.

97 MATHEMATICS AND COMPUTING↗

SU-E-T-508: End to End Testing of a Prototype Eclipse Module for Planning Modulated Arc Therapy On the Siemens Platform

Purpose: The latest clinical implementation of the Siemens Artiste linac allows for delivery of modulated arcs (mARC) using full-field flattening filter free (FFF) photon beams. The maximum doserate of 2000 MU/min is well suited for high dose treatments such as SBRT. We tested and report on the performance of a prototype Eclipse TPS module supporting mARC capability on the Artiste platform. Method: our spine SBRT patients originally treated with 12/13 field static-gantry IMRT (SGIMRT) were chosen for this study. These plans were designed to satisfy RTOG0631 guidelines with a prescription of 16Gy in a single fraction. The cases were re-planned as mARC plans in the prototype Eclipse module using the 7MV FFF beam and required to satisfy RTOG0631 requirements. All plans were transferred from Eclipse, delivered on a Siemens Artiste linac and dose-validated using the Delta4 system. Results: All treatment plans were straightforwardly developed, in timely fashion, without challenge or inefficiency using the prototype module. Due to the limited number of segments in a single arc, mARC plans required 2-3 full arcs to yield plan quality comparable to SGIMRT plans containing over 250 total segments. The average (3%/3mm) gamma pass-rate for all arcs was 98.5±1.1%, thus demonstrating both excellent dose prediction by the AAA dose algorithm and excellent delivery fidelity. Mean delivery times for the mARC plans(10.5±1.7min) were 50-70% lower than the SGIMRT plans(26±2min), with both delivered at 2000 MU/min. Conclusion: A prototype Eclipse module capable of planning for Burst Mode modulated arc delivery on the Artiste platform has been tested and found to perform efficiently and accurately for treatment plan development and delivered-dose prediction. Further investigation of more treatment sites is being carried out and data will be presented.

60 APPLIED LIFE SCIENCES↗

Code Verification Capabilities and Assessments in Support of ASC V&V Level 2 Milestone #6035

This document provides a summary of the code verification activities supporting the FY17 Level 2 V&V milestone entitled “Deliver a Capability for V&V Assessments of Code Implementations of Physics Models and Numerical Algorithms in Support of Future Predictive Capability Framework Pegposts.” The physics validation activities supporting this milestone are documented separately. The objectives of this portion of the milestone are: 1) Develop software tools to support code verification analysis; 2) Document standard definitions of code verification test problems; and 3) Perform code verification assessments (focusing on error behavior of algorithms). This report and a set of additional standalone documents serve as the compilation of results demonstrating accomplishment of these objectives.

97 MATHEMATICS AND COMPUTING↗

Reliable Broadcast under Cascading Failures in Interdependent Networks

Reliable broadcast is an essential tool to disseminate information among a set of nodes in the presence of failures. We present a novel study of reliable broadcast in interdependent networks, in which the failures in one network may cascade to another network. In particular, we focus on the interdependency between the communication network and power grid network, where the power grid depends on the signals from the communication network for control and the communication network depends on the grid for power. In this paper, we build a resilient solution to handle crash failures in the communication network that may cause cascading failures and may even partition the network. In order to guarantee that all the correct nodes deliver the messages, we use soft links, which are inactive backup links to non-neighboring nodes that are only active when failures occur. At the core of our work is a fully distributed algorithm for the nodes to predict and collect the information of cascading failures so that soft links can be maintained to correct nodes prior to the failures. In the presence of failures, soft links are activated to guarantee message delivery and new soft links are built accordingly for long term robustness. Our evaluation results show that the algorithm achieves low packet drop rate and handles cascading failures with little overhead.

cascading failures↗

PPCM: Combing Multiple Classifiers to Improve Protein-Protein Interaction Prediction

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using an assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. This pipeline will be useful for predicting PPI in nonmodel species.

59 BASIC BIOLOGICAL SCIENCES↗

Learning From User Behavior: A Survey-Assist Algorithm for Longitudinal Mobility Data Collection

GPS-based travel surveys are widely used in mobility studies to gather crucial qualitative data, like purpose, transportation mode and replaced mode. However, survey response still poses a burden to users, especially in long-term mobility studies, leading to response fatigue. We explore a survey-assist strategy to ease this burden by a novel, user-level modeling approach that leverages past responses from each user to predict responses for new trips, without relying on external data sources like GIS data. We investigate three main algorithms for predicting responses: (i) clustering trips and extrapolating responses for similar trips, (ii) using random forest classification, and (iii) clustering that uses a hybrid algorithm to determine spatial structure, which is then fed as input to a classic random forest classifier. The clustering approach can flexibly predict responses for even complex qualitative survey questions; it achieved F-scores of 65%. The random forest pipeline uses architecture that restricts it to predicting three predetermined survey questions: trip purpose, mode, and replaced mode. However, it achieved F-scores of 78%. While the survey-assist approach has been implemented by several proprietary systems, to our knowledge, this is the first exploration in the academic literature. It follows that this is also the first rigorous evaluation of multiple algorithms that can implement the approach. The evaluation uses a large scale, publicly available, longitudinal dataset consisting of ~ 92k trips from 235 users over a period of roughly one and a half years. With this approach, travel surveys can be pre-filled with the predicted responses for each trip, thus streamlining the survey process for users. Combined with an active learning system that requests user input on low-confidence predictions, models can be updated and improved over time to better support the long-term collection of longitudinal qualitative data.

clustering↗

Barium stars as tracers of s -process nucleosynthesis in AGB stars: II. Using machine learning techniques on 169 stars

Barium (Ba) stars are characterised by an abundance of heavy elements made by the slow neutron capture process (s-process). This peculiar observed signature is due to the mass transfer from a stellar companion, bound in a binary stellar system, to the Ba star observed today. The signature is created when the stellar companion is an asymptotic giant branch (AGB) star. We aim to analyse the abundance pattern of 169 Ba stars using machine learning techniques and the AGB final surface abundances predicted by the FRUITY and Monash stellar models. We developed machine learning algorithms that use the abundance pattern of Ba stars as input to classify the initial mass and metallicity of each Ba star’s companion star using stellar model predictions. We used two algorithms. The first exploits neural networks to recognise patterns, and the second is a nearest-neighbour algorithm that focuses on finding the AGB model that predicts the final surface abundances closest to the observed Ba star values. In the second algorithm, we included the error bars and observational uncertainties in order to find the best-fit model. The classification process was based on the abundances of Fe, Rb, Sr, Zr, Ru, Nd, Ce, Sm, and Eu. We selected these elements by systematically removing s-process elements from our AGB model abundance distributions and identifying the elements whose removal had the biggest positive effect on the classification. We excluded Nb, Y, Mo, and La. Our final classification combined the output of both algorithms to identify an initial mass and metallicity range for each Ba star companion. With our analysis tools, we identified the main properties for 166 of the 169 Ba stars in the stellar sample. The classifications based on both stellar sets of AGB final abundances show similar distributions, with an average initial mass of M = 2.23 M ⊙ and 2.34 M ⊙ and an average [Fe/H] = –0.21 and –0.11, respectively. We investigated why the removal of Nb, Y, Mo, and La improves our classification and identified 43 stars for which the exclusion had the biggest effect. We found that these stars have statistically significant and different abundances for these elements compared to the other Ba stars in our sample. We discuss the possible reasons for these differences in the abundance patterns.

79 ASTRONOMY AND ASTROPHYSICS↗

Predictability of Seawater DMS During the North Atlantic Aerosol and Marine Ecosystem Study (NAAMES)

This work presents an overview of a unique set of surface ocean dimethylsulfide (DMS) measurements from four shipboard field campaigns conducted during the North Atlantic Aerosol and Marine Ecosystem Study (NAAMES) project. Variations in surface seawater DMS are discussed in relation to biological and physical observations. Results are considered at a range of timescales (seasons to days) and spatial scales (regional to sub-mesoscale). Elevated DMS concentrations are generally associated with greater biological productivity, although chlorophyll a (Chl) only explains a small fraction of the DMS variability (15%). Physical factors that determine the location of oceanic temperature fronts and depth of vertical mixing have an important influence on seawater DMS concentrations during all seasons. The interplay of biomass and physics influences DMS concentrations at regional/seasonal scales and at smaller spatial and shorter temporal scales. Seawater DMS measurements are compared with the global seawater DMS climatology and predictions made using a recently published algorithm and by a neural network model. The climatology is successful at capturing the seasonal progression in average seawater DMS, but does not reproduce the shorter spatial/temporal scale variability. The input terms common to the algorithm and neural network approaches are biological (Chl) and physical (mixed layer depth, photosynthetically active radiation, seawater temperature). Both models predict the seasonal North Atlantic average seawater DMS trends better than the climatology. However, DMS concentrations tend to be under-predicted and the episodic occurrence of higher DMS concentrations is poorly predicted. The choice of climatological seawater DMS product makes a substantial impact on the estimated DMS flux into the North Atlantic atmosphere. These results suggest that additional input terms are needed to improve the predictive capability of current state-of-the-art approaches to estimating seawater DMS.

54 ENVIRONMENTAL SCIENCES↗

Potential for Integrating Entry Guidance into the Multi-Disciplinary Entry Vehicle Optimization Environment

The state-of-the-art in vehicle design decouples flight feasible trajectory generation from the optimization process of an entry spacecraft shape. The disadvantage to this decoupled process is seen when a particular aeroshell does not meet in-flight requirements when integrated into Guidance, Navigation, and Control simulations. It is postulated that the integration of a guidance algorithm into the design process will provide a real-time, rapid trajectory generation technique to enhance the robustness of vehicle design solutions. The potential benefit of this integration is a reduction in design cycles (possible cost savings) and increased accuracy in the aerothermal environment (possible mass savings). This work examines two aspects: 1) the performance of a reference tracking guidance algorithm for five different geometries with the same reference trajectory and 2) the potential of mass savings from improved aerothermal predictions. An Apollo Derived Guidance (ADG) algorithm is used in this study. The baseline geometry and five test case geometries were flown using the same baseline trajectory. The guided trajectory results are compared to separate trajectories determined in a vehicle optimization study conducted for NASA's Mars Entry, Descent, and Landing System Analysis. This study revealed several aspects regarding the potential gains and required developments for integrating a guidance algorithm into the vehicle optimization environment. First, the generation of flight feasible trajectories is only as good as the robustness of the guidance algorithm. The set of dispersed geometries modelled aerodynamic dispersions that ranged from +/-1% to +/-17% and a single extreme case was modelled where the aerodynamics were approximately 80% less than the baseline geometry. The ADG, as expected, was able to guide the vehicle into the aeroshell separation box at the target location for dispersions up to 17%, but failed for the 80% dispersion cases. Finally, the results revealed that including flight feasible trajectories for a set of dispersed geometries has the potential to save mass up to 430 kg.

spacecraft guidance↗

A Science-Focused Artificial Intelligence (AI) Responding in Real-Time to New Information: Capability Demonstration for Ocean World Missions

Introduction: Artificial intelligence (AI) has long been considered a potential mechanism to explore increasingly challenging environments, including those with extreme temperatures and pressures, limited communication capabilities, or those with demanding terrain. We posit that missions in extreme environments could deploy an onboard AI focused on science observations and goals in order to augment a traditional concept(s) of operations (ConOps). An onboard AI capability could perform functions such as data analysis in order to make high-level decisions, including prioritized data transmission for analysis by ground-based teams or autonomously-guided follow-on analyses that maximize science return. Such a capability would empower missions to respond to scientific data of interest in real-time; a mission could make observations and perform a preliminary analysis to alert ground-based scientists to an observation of interest, enabling an informed, rapid response from Earth-based teams. Enceladus Case Study for Onboard AI: We are developing an onboard AI capability for real-time telemetry response that formulates and carries-out informed decisions in service to established mission goals, enabling increased science return of a mission. We focus our AI development for use on a constellation of SmallSats orbiting Enceladus. Our Enceladus case study tests autonomous decision-making capabilities in scenarios with complex orbital dynamics, plume ejecta, extreme cold environments, power restrictions, and a requirement to maximize science return for a potential positive detection of life, while critically evaluating the potential for false positives. Telemetry includes simulated scientific data, spacecraft onboard operational data (e.g., position, velocity, and rotation), and engineering hardware performance data. Enceladus SmallSat Constellation. Our constellation includes eight SmallSat spacecraft in an 8:35 resonant orbit-based formation, leveraging Saturn’s gravitational forces to maintain stable orbits with global coverage around Enceladus. To our knowledge, we simulate the first stable configuration of multiple spacecraft in closed orbits around Enceladus, using a full ephemeris force model (Russell and Lara, 2009). Each spacecraft’s orbit will precess, causing an eastward ground track shift (from an orbiter’s perspective) of each spacecraft for each orbit. However, all spacecraft return to their original positions relative to Enceladus after eight Enceladus revolutions around Saturn. We model communication pathways between SmallSats to understand how information would need to be transmitted across the constellation to enable AI-driven decision-making and resource allocation across the fleet. Capability Demonstration. Our simulated capability demonstration inputs position, velocity, and rotation telemetry from our Enceladus-focused constellation simulations, and mass spectrometry data collected from abiotic and biotic laboratory-analog ocean world experiments (Theiling et al., 2018; Theiling, 2021; Da Poian et al., 2023). Data from these experiments are used to simulate MS measurements and different scenarios of science observations for onboard analysis performed on each of the eight spacecraft. For these demonstrations, we integrate 24 machine learning (ML) algorithms into an onboard intelligence as a ‘knowledge base’, including algorithms evaluating data quality and those predicting (with % confidence) gas composition, ocean aqueous chemistry, and whether the sample was influenced by microbial life. The onboard AI capability is designed to use the knowledge base to come to a consensus-based decision in the interpretation of the observed data in order to request additional action outside of a pre-defined ConOps. Requested actions could include e.g., prioritized downlink to Earth (for analysis by ground-based teams) or follow-on analyses performed across the constellation. The spacecraft’s intelligent onboard planner must then determine whether sufficient resources (e.g., time, power, etc.) are available and weigh the request with mission priorities. In our simulation, the constellation is able to identify potential biosignatures using onboard ML algorithms, evaluate the confidence of that prediction, and perform follow-on analyses across the fleet to confirm the detection, in order to best prepare a transmission of these data to Earth-based teams.

astrobiology↗