SEARCH · Engineering Papers
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.
‘The Spatio Temporal Asset Catalogs (STAC) specification is a common language to describe geospatial information, so spatiotemporal assets can more easily be leveraged, indexed, and discovered. This presentation describes how this specification can be successfully applied to federated discovery.
Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.
NASA’s Artemis Program seeks to establish a long-term presence on the Moon to enable scientific exploration and expand the cis-lunar economy by utilizing lunar resources through public-private and international partnerships. Over the next decades, a lunar spaceport will need to be established to provide the services and facilities that are necessary to achieve this goal. Robotic construction technologies using in-situ materials must be developed to build up enabling infrastructure such as launch/landing pads, blast protection, power/communications infrastructure, improved roads, improved operational surfaces, and radiation protection shelters. Kennedy Space Center’s Granular Mechanics and Regolith Operations laboratory at Swamp Works has partnered with SpaceFactory and LERA Consulting Structural Engineers to develop the architectural and structural design of an unpressurized lunar shelter. The shelter, called Lunar Infrastructure Asset (LINA), is designed to support 2.3 m of regolith overburden to protect astronauts and surface assets from radiation, meteoroid impact, thermal gradients/cycling, and to withstand moonquakes. LINA’s structural design criteria and the resulting structure design are detailed in separate papers. A Fused Filament Fabrication (FFF) construction process using regolith polymer composites has been developed and is detailed in a separate publication. This paper presents material formulations and selection rationale for each of the composite components that were examined. Formulations include 70:30, 80:20, and 85:15 wt.% mixture ratios of lunar mare simulant Black Point-1 (BP-1): Polylactic Acid (PLA), 80:20 Lunar Highlands Simulant-1 (LHS-1): PLA and an 80:20 BP-1: PLA formulation with a flow enhancer additive. Test samples were printed in simulated lunar dirty thermal vacuum conditions (-190 °C, 10-3 torr). A series of tests were performed on each formulation to characterize the achieved mixture ratio, mechanical strength properties, off-gassing products during vacuum printing, and porosity and density of printed products. The LHS-1: PLA formulation yielded an advantageous combination of properties and was used in a final test that additively constructed a sub-scaled LINA on regolith simulant in dirty vacuum conditions. The materials and construction process presented in this paper are considered to be at Technology Readiness Level (TRL) 5 with additional testing necessary to characterize long term lunar environmental exposure effects.
NASA’s Artemis program has the goal of creating a sustained lunar presence to provide unprecedented opportunities for scientific discovery and to ensure industry’s access to the unlimited resources and commercial potential in space. To achieve this goal, NASA must incrementally develop and expand its capabilities beyond the short lunar stays of the Apollo program to a robust continued presence with infrastructure and equipment to reduce mission risk. Kennedy Space Center’s Granular Mechanics and Regolith Operations laboratory (a.k.a. Swamp Works) has partnered with SpaceFactory and LERA Consulting Structural Engineers to develop the architectural and structural design of a robotically constructable unpressurized shelter. The shelter, called Lunar Infrastructure Asset (LINA), is designed to protect astronauts and surface assets from radiation, meteoroid impact, thermal gradients, and to withstand moonquakes. A Fused Granular Fabrication (FGF) construction process using regolith polymer composites was developed. The construction system and associated print parameters are discussed along with the environmental simulation equipment and a summary of test conditions. Test samples were printed in dirty thermal vacuum conditions (~10-3 torr, ~-200 °C,) and subscale versions of LINA were printed on a regolith simulant substrate in vacuum (~10-4 torr). Full scale LINA design optimization, simulation, and construction concept of operations are discussed.
BACKGROUND: NASA has amassed sixty years of knowledge and experience relevant to maintenance of crew health and performance in low earth orbit. The Apollo Program introduced the importance of ensuring progressively autonomous operational capability. Earth Independent Medical Operations (EIMO) will require a gradual shift in the balance of medical responsibility, management, and authority from terrestrial to space-based assets. Terrestrial assets will continue to be essential for pre-mission screening and planning in addition to maintenance of crew health and performance. However, new capabilities are needed to enable EIMO and the amount of data required to support these systems, and mitigate the impacts of data transmission delays and reduced bandwidth coupled with lack of cloud-like resources and on-board computing capacity that is currently unclear or operationally insufficient. OVERVIEW: The overall goal of EIMO is to develop artificial intelligence (AI)-based solutions to analyze crew health and performance data utilizing a clinical decision support system (CDSS) to provide crew medical officers (CMO) with the equivalent of real-time, on-board medical consults. The EIMO ecosystem is envisioned as a “system of systems” where embedded reference databases and real-time data streams from multiple input vectors continuously and seamlessly assess crew health and performance. EIMO will be designed to make recommendations to the CMO using multi-modal AI-based natural language processing and machine learning methods with interoperability to push/pull data within and between multiple vehicle and habitat architectures. DISCUSSION: Data flows and storage/retrieval capacity are severely constrained during space missions and the challenges will become even greater during exploration missions. Just as each past program from Mercury to the International Space Station (ISS) required rethinking the interaction between ground-based controllers and space-based crew, so too will future missions to the Moon and Mars. While the NASA High-Performance Spaceflight Computing Processor project aims to increase computational capacity by 100 times over current spaceflight computers, the projected deliverable still lags considerably behind what will be needed to enable an AI-driven CDSS. Restrictions in processing speed and data storage capacity, coupled with transmission bottlenecks and delays, necessitate definition and optimization of an integrated data architecture to enable a progressively autonomous medical capability.
In-space assembly will revolutionize the creation, upgrade, and evolution of future space systems. In-space assembly represents an alternative deployment strategy that is not constrained by the requirement of using a single launch vehicle and enables a greater freedom of design for the initial emplacement of assets and their evolution over time. In-space assembly enables assets, such as observatories and science platforms, to become persistent, evolving over time like their terrestrial counterparts. Also, in-space assembly provides a direct path for utilization of in-space manufactured components designed exclusively for the operational environment. To highlight the advantages of an in-space assembly approach, the modular assembly of a 3 m to 4 m precision optical aperture based on thin meniscus technology coupled with structurally efficient TriTruss modules is presented. The 3 m to 4 m aperture stows compactly within two standard ride share slots (0.61 m by 0.71 m by 0.97 m). Placing instruments and the robotic system used for assembly in an adjacent ride share slot enables a capable observatory to be placed into service via modest ride share opportunities. Further, recent hardware assembly tests of similar modules and progress toward hardware tests to validate the overall architecture via diffraction limited testing will be summarized.
This manuscript presents an overview of NASA’s EXport Processes in the Ocean from Remote Sensing 2021 Field Campaign in the North Atlantic (EXPORTS NA) and provides quantitative and dynamical descriptions of the physical processes modulating water transformations during the study. A major programmatic goal was to conduct the sampling in a Lagrangian mode so that ocean ecological and biogeochemical changes can be observed independent from physical advective processes. To accomplish this goal, EXPORTS NA conducted a multi-ship, multi-asset field sampling program within a retentive, anticyclonic mode water eddy. Beneath depths of ∼100 m, Lagrangian sampling assets remained within the eddy core waters (ECWs) throughout the experiment, demonstrating that the ECWs within the mode water eddy were retentive. However, strong westerly winds from four storm events deepened the mixed layer (ML) of the surface core waters (SCWs) above the eddy’s mode water core by 25-40 m and exchanged some of the SCWs with surface waters outside of the eddy via Ekman transport. Estimates of flushing times ranged from 5-8 days, with surface exchange fractions ranging from 20-75% and were consistent with particle tracking advected by combined geostrophic and Ekman velocities. The relative contributions of horizontal and vertical advection on changes in ECW tracers depended on the horizontal and vertical gradients of that tracer. For example, horizontal advection played a large role in ECW salinity fluxes, while vertical entrainment played a larger role in the fluxes of nutrients into SCW ML. Each storm injected nutrients and low oxygen waters into the ML, after which the surface ocean ecosystem responded by reducing nutrient concentrations and increasing %O2 saturation levels. Overall, ECW values of chlorophyll and POC were the largest at the onset of the field program and decreased throughout the campaign. The analysis presented provides a physical oceanographic context for the many measurements made during the EXPORTS NA field campaign while illustrating the many challenges of conducting a production-flux experiment, even in a Lagrangian frame, and the inherent uncertainties of interpreting biological carbon pump observations that were collected in a Eulerian frame of reference.
In-space assembly will revolutionize the creation, upgrade, and evolution of future space systems. In-space assembly represents an alternative deployment strategy that is not constrained by the requirement of using a single launch vehicle and enables a greater freedom of design for the initial emplacement of assets and their evolution over time. In-space assembly enables assets, such as observatories and science platforms, to become persistent, evolving over time like their terrestrial counterparts. Also, in-space assembly provides a direct path for utilization of in-space manufactured components designed exclusively for the operational environment. To highlight the advantages of an in-space assembly approach, the modular assembly of a 3 m to 4 m precision optical aperture based on thin meniscus technology coupled with structurally efficient TriTruss modules is presented. The 3 m to 4 m aperture stows compactly within two standard ride share slots (0.61 m by 0.71 m by 0.97 m). Placing instruments and the robotic system used for assembly in an adjacent ride share slot enables a capable observatory to be placed into service via modest ride share opportunities. Further, recent hardware assembly tests of similar modules and progress toward hardware tests to validate the overall architecture via diffraction limited testing will be summarized.
NASA’s Artemis campaign seeks to return humans to the moon and establish a sustained presence on the lunar surface. This session will emphasize how habitation capabilities on the moon and in cislunar space can potentially contribute to the sustainability objectives of Artemis. Habitable elements represent opportunities to enable longer duration stays, increase the number of crew members present, enhance science and utilization activities, drive technology development for future Mars exploration, perform analog missions, and fuel economic opportunities for US industry. Panelists include Paul Kessler (NASA Marshall Space Flight Center, deputy lead for lunar surface habitation); Andrew Choate (NASA Marshall Space Flight Center, Mars habitation lead); Krystofer Dudzinski (NASA Marshall Space Flight Center, a space architect within the MSFC Advanced Concepts Office); and Larry Toups (retired from NASA Johnson Space Center, currently an adjunct professor at University of Houston in space architecture). The panel is moderated by Tracie Prater (NASA Marshall Space Flight Center, Habitation Systems Development Office). The panel will begin with an overview of the history of habitation concepts and an academic perspective on general considerations in space habitat design (Larry Toups). Paul Kessler and Andrew Choate will introduce NASA’s principle of “architecting from the right” to help define objectives for Artemis missions, needs/characteristics, use cases, and functions (as published in the agency’s Architecture Definition Document) and provide perspective on how this principle informs habitation concept development work. NASA panelists will discuss key engineering challenges identified for developing, deploying, and operating habitable assets on the lunar surface and/or in deep space. These may include dust mitigation, outfitting of inflatable softgoods (for concepts which may use softgoods as a primary structural material), survival in lunar darkness, human health and performance considerations, maintenance/repair/sparing, and autonomy. These identified challenges represent risks for habitation systems development and relate closely to capability gaps identified by the agency. While the work of NASA Marshall Space Flight Center’s habitation development office is primarily focused on habitats which are launched from earth pre-integrated (referred to as Class I in the framework previously developed by NASA space architects Kennedy/Cohen) or launched from earth and deployed at the point of use (Class II), there is also extensive work in NASA, academia, and companies on constructed habitats, which would be built on a planetary surface using indigenous resources (Class III habitats). Panelist Krystopher Dudzinski will discuss potential evolutionary pathways from Class I and Class II habitats to Class III habitats, unique and common architectural challenges within each habitat class, and key gaps in implementing Class III habitats from an architectural perspective. NASA panelists and the moderator will also provide an overview of partnership opportunities and avenues for further engagement to advance habitation systems for the SpaceCom audience. NASA is currently developing notional concepts for a lunar surface habitat and Mars transit habitat, which will be discussed during this panel session and used as examples. These concepts represent options for habitation system design and are a point of departure. They do not represent a final plan or formal recommendation on the part of the agency. Based on the most recent analysis cycle, NASA’s lunar surface habitat (SH) concept nominally supports two crew members for 30 days, with the capacity to support four crew during a surge period where crew will swap between the SH and another surface asset, such as a pressurized rover. This example design has a metallic airlock for ingress/egress and the upper portion is an inflatable material system which serves as the habitation module. The notional interior of the habitat is a three-deck layout/configuration which supports all crew mission functions, including exercise, stowage, extravehicular activity (EVA), sleep, hygiene waste collection, maintenance and repair, and meal preparation. Under analysis assumptions for habitation, the Mars Transit Habitat (TH) concept would support four crew on an up to 1,200 day Mars mission. One option for the concept is to initially dock Transit Habitat at Gateway, where it can be used to increase the duration of crew stays in cislunar space and perform shakedown and analog missions prior to a Mars departure. One challenge in longer duration missions which involve both surface exploration and transit is understanding crew adaptation when transitioning between partial gravity and microgravity environments. TH at Gateway offers an opportunity to study this transition and in doing so reduce risks associated with future Mars exploration. Like lunar SH, the most recent analysis cycle concept of a Mars TH is a hybrid structure design, with a metallic section supporting EVAs, axial/radial docking, and Safe Haven capabilities, and an inflatable softgoods structure for the primary habitation function. Interior layouts to optimize crew usability and livability are currently under trade. The panel will include presentation material, but also seeks to engage the audience in a highly interactive conversation regarding the potential role for habitation in future exploration initiatives. Potential topics for discussion include the influence of the crew experience on habitation systems design and livability/usability considerations, the benefits of space habitation development in terrestrial applications, and challenges and opportunities in “feeding forward” lunar surface habitation systems development to Mars exploration.
Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.
As the vanguard of human spaceflight increasingly transitions from one of low Earth orbit (LEO) to Lunar and subsequently Martian missions, there is a commensurate imperative for Earth-based medical authority to transition to space-based assets for the continued assurance of optimal astronaut health and performance. The transition to Earth Independent Medical Operations (EIMO) will be a process that enables progressively resilient systems and crews to reduce risk and enhance wellness and overall mission success for deep space exploration. Terrestrial assets will continue to be paramount in pre-mission screening, planning, maintenance, and prevention. Yet on-board care, response to unexpected medical events, and management of communication delays and dropouts will increasingly become the purview of the crew for primary management.
NASA’s Artemis program has the goal of creating a sustained lunar presence to provide unprecedented opportunities for scientific discovery and to ensure industry’s access to the unlimited resources and commercial potential in space. To achieve this goal, NASA must incrementally develop and expand its capabilities beyond the short lunar stays of the Apollo program to a robust continued presence with infrastructure and equipment to reduce mission risk. Kennedy Space Center’s Granular Mechanics and Regolith Operations laboratory (a.k.a. Swamp Works) has partnered with SpaceFactory and LERA Consulting Structural Engineers to develop the architectural and structural design of a robotically constructable unpressurized shelter. The shelter, called Lunar Infrastructure Asset (LINA), is designed to protect astronauts and surface assets from radiation, meteoroid impact, thermal gradients, and to withstand moonquakes. A Fused Granular Fabrication (FGF) construction process using regolith polymer composites was developed. The construction system and associated print parameters are discussed along with the environmental simulation equipment and a summary of test conditions. Test samples were printed in dirty thermal vacuum conditions (~10-3 torr, ~-200 °C,) and subscale versions of LINA were printed on a regolith simulant substrate in vacuum (~10-4 torr). Full scale LINA design optimization, simulation, and construction concept of operations are discussed.
Wildland fires take place most often in remote areas without access to communications infrastructure. Communication during wildfire operations is crucial for safe and effective command and control of air assets, ground-based firefighters, and fire management. Without connectivity, Incident Command (IC) cannot exchange information, receive alerts or work with all parties involved in the wildfire suppression operation. Current policy directs IC to use voice radio communications, which require no prior infrastructure, to provide information needed for the command, control and safety of personnel and resources. Cellular communications are used only for logistical purposes unless no other method is available. To address some of the shortcomings of the current state of communications, the Advanced Capabilities for Emergency Response Operations (ACERO) Second Shift (SS) technical team is developing characteristics of an air-to-ground Mesh Radio System (MRS) and preparing for a future demonstration. The MRS will allow air and ground assets to automatically join a radio network without relying on existing infrastructure and exchange information critical to maintaining situation awareness and air traffic management by the onsite IC. The MRS will also give users more options for communications in addition to voice communications.
The achievement of industrial and scientific goals set by the National Aeronautics and Space Administration (NASA) Artemis missions within the Moon to Mars (M2M) architecture greatly relies on the breadth and efficacy of lunar surface exploration. The lunar surface environment presents various challenges and complexities to sustainable mission operations and activities. Power generation and distribution capabilities are vital for exploration on the lunar surface, which can enable activities such as subsurface sample collection, permanently shadowed region (PSR) prospecting, and lunar terrain mapping. Innovative power technologies that demonstrate flexibility, reliability, and high capacity are desirable to achieve sustainable operations and infrastructure on the lunar surface. Studies have proposed solar-powered spacecraft in cislunar orbit capable of beaming power to lunar surface assets as a solution to this problem. This study analyzes the benefit that space-based solar power (SBSP) assets could deliver to the M2M architecture by measuring its potential to augment lunar surface exploration opportunity. Qualitative measures of SBSP’s potential impact will include, but not be limited to, power available across surface elements, surface mobility range, and delivered landed mass. These measures are assessed for a notional surface architecture measured against its baseline configuration (no external power augmentation). Additionally, this presentation will provide an overview of the SBSP system design configuration trade space, subsystem parameter trade space, and results from preliminary spacecraft concept of operations (ConOps) and sizing.
Presentation illustrates over 60 years of aerial measurements and establishment of Aerial Measuring System asset by the DOE. The presentation will be used as part of the training new AMS personnel. Presentation illustrates over 60 years of aerial measurements and establishment of Aerial Measuring System asset by the DOE. The presentation will be used as part of the training new AMS personnel.
The example embodiments are directed to a system and method for neutralizing abnormal signals in a cyber-physical system. In one example, the method includes receiving input signals comprising time series data associated with an asset and transforming the input signals into feature values in a feature space, detecting one or more abnormal feature values in the feature space based on a predetermined normalcy boundary associated with the asset, and determining an estimated true value for each abnormal feature value, and performing an inverse transform of each estimated true value to generate neutralized signals comprising time series data and outputting the neutralized signals.
An industrial asset may be associated with a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time representing current operation of the industrial asset. An abnormality detection computer may determine that at least one abnormal monitoring node is currently being attacked or experiencing a fault. A virtual sensing estimator may continuously execute an adaptive learning process to create or update virtual sensor models for the monitoring nodes. Responsive to an indication that a monitoring node is currently being attacked or experiencing a fault, the virtual sensing estimator may be dynamically reconfigured to estimate a series of virtual node values for the abnormal monitoring node or nodes based on information from normal monitoring nodes and appropriate virtual sensor models. The series of monitoring node values from the abnormal monitoring node or nodes may then be replaced with the virtual node values.
Building Energy Use Intensity (EUI) has been commonly used to facilitate policy makers and utilities to design energy efficacy programs and help building managers prioritize investment in building upgrades. Buildings with higher EUIs are usually chosen as better candidates for retrofit. Our study of nearly one hundred buildings in Seattle’s Building Tune Up Accelerator program and thousands of buildings in the Asset Score database reveals that EUI (after weather/location/use type normalization) alone is not the best indicator of a building’s potential to save energy, especially for those buildings in the mid-range (30-70 percentile EUI). In this paper, we introduce the concept of “retrofit-ability” — a building’s real potential to reduce its energy use cost-effectively — as a supplementary metric to inform energy efficiency policy and investment. Currently, such potential analyses are predicted for a building stock using prototypical building models or statistical data. However, typical buildings or general historical data may not sufficiently represent building configurations in a portfolio and predict their saving potentials. We utilized machine learning to investigate how key building characteristics (such as envelope attributes, HVAC type, location, use type, etc.) affect a building’s improvement potentials and developed a low-cost method to quantify such potentials for a portfolio of buildings. The supplementary perspective provided by “retrofit-ability” highlights which building assets correlate most with a building’s energy savings potential across region, building use type and more.