Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Thermal anomaly”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1984

Geophysical investigations of a geothermal anomaly at Wadi Ghadir, eastern Egypt

During regional heat flow studies a geothermal anomaly was discovered approximately 2 km from the Red Sea coast at Wadi Ghadir, in the Red Sea Hills of Eastern Egypt. A temperature gradient of 55 C/km was measured in a 150 m drillhole at this location, indicating a heat flow of approximately 175 mw/sqm, approximately four times the regional background heat flow for Egypt. Gravity and magnetic data were collected along Wadi Ghadir, and combined with offshore gravity data, to investigate the source of the thermal anomaly. Magnetic anomalies in the profile do not coincide with the thermal anomaly, but were observed to correlate with outcrops of basic rocks. Other regional heat flow and gravity data indicate that the transition from continental to oceanic type lithosphere occurs close to the Red Sea margin, and that the regional thermal anomaly is possibly related to the formation of the Red Sea.

Morgan, P.↗
NASA NTRS2018

Maps of Tethys' Thermophysical Properties

On 11th April 2015 Cassini's Composite Infrared Spectrometer (CIRS) made a series of observations of Tethys’ daytime anti-Saturn hemisphere over a nine-hour time period. During this time the sub-spacecraft position was remarkably stable (0.3° S to 3.9° S; 153.2° W to 221.8° W), and so these observations provide unprecedented coverage of diurnal temperature variations on Tethys’ anti-Saturn hemisphere. In 2012 a thermal anomaly was discovered at low latitudes on Tethys’ leading hemisphere; it appears cooler during the day and warmer at night than its surroundings (Howett et al., 2012) and is spatially correlated with a decrease in the IR3/UV3 visible color ratio (Schenk et al., 2011). The cause of this anomaly is believed to be surface alteration by high-energy electrons, which preferentially bombard low-latitudes of Tethys’ leading hemisphere (Schenk et al., 2011; Howett et al., 2012; Paranicas et al. 2014; Schaible et al., 2017). The thermal anomaly was quickly dubbed “Pac-Man” due to its resemblance to the 1980s video game icon. We use these daytime 2015 CIRS data, along with two sets of nighttime CIRS observations of Tethys (from 27 June 2007 and 17 August 2015) to make maps of bolometric Bond albedo and thermal inertia variations across the anti-Saturn hemisphere of Tethys (including the edge of its Pac-Man region). These maps confirm the presence of the Pac-Man thermal anomaly and show that while Tethys’ bolometric Bond albedo varies negligibly outside and inside the anomaly (0.69 plus or minus 0.02 inside, compared to 0.71 plus or minus 0.04 outside) the thermal inertia varies dramatically (29 plus or minus 10 J m−2 K−1 s−1/2 inside, compared to 9 plus or minus 4 J m−2 K−1 s−1/2 outside). These thermal inertias are in keeping with previously published values: 25 plus or minus 3 J m−2 K−1 s−1/2 inside, and 5 ± 1 J m−2 K−1 s−1/2 outside the anomaly (Howett et al., 2012). A detailed analysis shows that on smaller spatial-scales the bolometric Bond albedo does vary: increasing to a peak value at 180° W. For longitudes between approximately 100° W and approximately 160° W the thermal inertia increases from northern to southern latitudes, while the reverse is true for bolometric Bond albedo. The thermal inertia on Tethys generally increases towards the center of its leading hemisphere but also displays other notable small-scale variations. These thermal inertia and bolometric Bond albedo variations are perhaps due to differences in competing surface modification by E ring grains and high-energy electrons which both bombard Tethys’ leading hemisphere (but in different ways). A comparison between the observed temperatures and our best thermal model fits shows notable discrepancies in the morning warming curve, which may provide evidence of regional variations in surface roughness effects, perhaps again due to variations in surface alteration mechanisms.

Howett, C. J. A.↗
NASA NTRS1987

Using the Landsat Thematic Mapper to detect and monitor active volcanoes - An example from Lascar volcano, northern Chile

The Landsat Thematic Mapper (TM) offers a means of detecting and monitoring thermal features of active volcanoes. Using the TM, a prominent thermal anomaly has been discovered on Lascar volcano, northern Chile. Data from two short-wavelength infrared channels of the TM show that material within a 300-m-diameter pit crater was at a temperature of at least 380 C on two dates in 1985. The thermal anomaly closely resembles in size and radiant temperature the anomaly over the active lava lake at Erta'ale in Ethiopia. An eruption took place at Lascar on Sept. 16, 1986. TM data acquired on Oct. 27, 1986, revealed significant changes within the crater area. Lascar is in a much more active state than any other volcano in the central Andes, and for this reason it merits further careful monitoring. Studies show that the TM is capable of confidently identifying thermal anomalies less than 100 m in size, at temperatures of above 150 C, and thus it offers a valuable means of monitoring the conditions of active or potentially active volcanoes, particularly those in remote regions.

Francis, P. W.↗
NASA NTRSDate not supplied

The Stop-and-Go Mechanism: Towards an Integrated Approach to Model Seismicity, Outgassing, Deformation, and Thermal Unrest at Active Volcanoes

Connecting the geophysical and geochemical signals recorded at and above the surface of volcanoes with source mechanisms is fundamental to understand transitions from quiescence to eruption, and to integrate the behavior of volcanoes with their regional seismotectonic and hydrological context. Some of these signals include shallow volcanic tremor, a long-lasting (minutes-to-years) ground vibration detected in volcanic areas during unrest; volcanic outgassing, which shows intriguing periodicities over multiple scales, as revealed by space-borne instruments and by ground-based, high-frequency (~1 Hz), sampling methods; inflation and deflation of volcanic edifices, commonly associated with subsurface volume changes; and large-scale (from a few to tens of km2), low-temperature, thermal anomalies, a newly-discovered signal that has been observed to emerge on volcanic flanks from months-to-years prior to gas- and magma-driven eruptions. Traditionally, these geophysical and geochemical signals have been modelled independently, which limits our interpretation of subsurface processes and thus our assessment of unrest. In this work, we show through lumped-parameter models, numerical simulations, and preliminary laboratory experiments that many of the signals recorded around volcanoes can be integrated into a common “stop-and-go” mechanism. In particular, we found that they can arise spontaneously when taking into account the feedbacks between the temporary accumulation of gas and/or magma in the crust (“stop”), and the diffusive transfer of gas and heat towards the surface (“go”). For example, we find that the “stop-and-go” mechanism can explain: (i) the emergence of monochromatic, broadband, and harmonic tremor; (ii) the periodic components commonly observed in volcanic outgassing time series; (iii) the link between large-scale thermal anomalies and shallow hydrothermal systems; (iv) the reported time lags between large-scale thermal anomalies and deformation; and (v) the breathing of potentially destructive volcanic calderas. The “stop-and-go” mechanism provides a consistent and realistic framework to link multiple geophysical and geochemical signals with the processes leading to volcanic unrest and eruption.

volcanoes↗
DOE OSTI2024

Volatiles and Redox Along the East African Rift

Abstract The upper mantle under the Afar Depression in the East African Rift displays some of the slowest seismic wave speeds observed globally. Despite the extreme nature of the geophysical anomaly, lavas that erupted along the East African Rift record modest thermal anomalies. We present measurements of major elements, H 2 O, S, and CO 2 , and Fe 3+ /ΣFe and S 6+ /ΣS in submarine glasses from the Gulf of Aden seafloor spreading center and olivine‐, plagioclase‐, and pyroxene‐hosted melt inclusions from Erta Ale volcano in the Afar Depression. We combine these measurements with literature data to place constraints on the temperature, H 2 O, andfO 2 of the mantle sources of these lavas as well as the initial and final pressures of melting. The Afar mantle plume is C/FOZO/PHEM in isotopic composition, and we suggest that this mantle component is damp, with 852 ± 167 ppm H 2 O, not elevated infO 2 compared to the depleted MORB mantle, and has temperatures of ∼1401–1458°C. This is similar infO 2 and H 2 O to the estimates of C/FOZO/PHEM in other locations. Using the moderate H 2 O contents of the mantle together with the moderate thermal anomaly, we find that melting begins at around 93 km depth and ceases at around 63 km depth under the Afar Depression and at around 37 km depth under the Gulf of Aden, and that ∼1%–29% partial melts of the mantle can be generated under these conditions. We speculate that the presence of melt, and not elevated temperatures or high H 2 O contents, are the cause for the prominent geophysical anomaly observed in this region.

Geochemistry & Geophysics↗
DOE OSTI2021

Aerial 3D Building Reconstruction from Drone Imagery (A3DBR) v1

This toolkit is composed of several modules for extracting buildings geometrical and thermal characteristics from RGB and thermal imagery captured using a drone. - Building 3D reconstruction module: leverage a photogrammetry software to construct a 3D point cloud from RGB drone imagery, which is then used in conjunction with image processing and geometric methods to extract building footprint and building height (i.e., 3D model of the building). - Windows to wall ratio estimation module: leverage deep learning semantic segmentation modeling to detect windows on 2D drone RGB images. The detected windows are then projected onto the extracted building 3D model (using building 3D reconstruction module) and their area is computed to obtain window to wall ratio estimation. - Thermal anomalies detection module: leverage image processing and machine learning algorithm to detect on 2D drone thermal images potential thermal anomalies within building's facades and roofs.

Granderson, Jessica↗
NASA NTRS2003

The Global Three Dimensional Distribution and Temperature of Near-Surface Martian Ground Ice: New Results from MGS TES

We have discovered significant global-scale seasonal thermal anomalies in the MGS TES surface temperature observations that coincide spatially with the Odyssey GRS observations of enhanced near-surface hydrogen abundance. The TES thermal anomalies can be explained quantitatively by the widespread presence of cold, high thermal inertia material within millimeters to centimeters of the surface that we interpret as evidence for ground ice that must extend to depths of many meters. The results provide significant insights into the properties and processes that govern the behavior of Martian water under current climatic conditions, the surface geology of the planet, as well as much higher resolution Martian ground ice maps than have been previously available.

D A Paige↗
NASA NTRSDate not supplied

Thermal radiation effects in the atmosphere initiated by pre-earthquake processes

The science community is still looking for pre-earthquake indicators of major seismic events in order to minimize the loss of human life. Recent advances in satellite technology have helped to increase the scientific understanding of the nature of pre-earthquake phenomena in the atmosphere and their relationship with transitional thermal anomalies. It was realized that the thermal heat fluxes over areas of earthquake preparation are a result of air ionization by Rn222, its isotopes and progenies and consequent water vapor condensation on newly formed ions. Latent heat (LH) is released as a result of this process and leads to the formation of local thermal radiation anomalies (TRA) known as outgoing longwave radiation (OLR). We recorded data from the most recent major earthquakes in California (2014) Nepal (2015) that allowed us to summaries TRA's main morphological features. It was also established that the TRA is part of a more complex chain of the short‐term earthquake precursors, which are explained within the framework of a Lithosphere-Atmosphere-Ionosphere Coupling (LAIC) model.

Dimitar Ouzounov↗
NASA NTRS2011

Radiolytic Impacts of Energetic Electron Irradiation on Enceladus and Mimas

Episodic overturn of the south polar terrain on Enceladus would convey radio lytic oxidants from surface irradiation by Saturn's inner magnetospheric electrons to the putative underlying polar sea and contribute to CO2 and other gas production driving the visibly active cryovolcanism. Low duty cycle of active episodes below 1 - 10 percent would raise the relative importance of the continuous radiolytic chemical energy input for mass and heat outflow, e.g. as compared to heating by gravitational tides. The "Pac-Man" thermal anomaly on Mimas most likely arises from leading-trailing asymmetry of electron irradiation and resultant radio lytic processing of the moon ice to a few centimeters of depth. The Mimas thermal anomaly distribution suggests a relatively stable surface unmodified by Enceladus-like geologic overturn or cryovolcanic activity. In both cases, the heavily irradiated skin depth corresponds to the sensible thermal layer probed by Cassini infrared measurements. Neutral gas and dust emissions from Enceladus limit energetic ion and plasma electron fluxes in the inner magnetosphere, thereby governing the irradiation of Mimas and other Saturn moons.

Cooper, J. F.↗
NASA NTRS2012

Global Burned Area and Biomass Burning Emissions from Small Fires

In several biomes, including croplands, wooded savannas, and tropical forests, many small fires occur each year that are well below the detection limit of the current generation of global burned area products derived from moderate resolution surface reflectance imagery. Although these fires often generate thermal anomalies that can be detected by satellites, their contributions to burned area and carbon fluxes have not been systematically quantified across different regions and continents. Here we developed a preliminary method for combining 1-km thermal anomalies (active fires) and 500 m burned area observations from the Moderate Resolution Imaging Spectroradiometer (MODIS) to estimate the influence of these fires. In our approach, we calculated the number of active fires inside and outside of 500 m burn scars derived from reflectance data. We estimated small fire burned area by computing the difference normalized burn ratio (dNBR) for these two sets of active fires and then combining these observations with other information. In a final step, we used the Global Fire Emissions Database version 3 (GFED3) biogeochemical model to estimate the impact of these fires on biomass burning emissions. We found that the spatial distribution of active fires and 500 m burned areas were in close agreement in ecosystems that experience large fires, including savannas across southern Africa and Australia and boreal forests in North America and Eurasia. In other areas, however, we observed many active fires outside of burned area perimeters. Fire radiative power was lower for this class of active fires. Small fires substantially increased burned area in several continental-scale regions, including Equatorial Asia (157%), Central America (143%), and Southeast Asia (90%) during 2001-2010. Globally, accounting for small fires increased total burned area by approximately by 35%, from 345 Mha/yr to 464 Mha/yr. A formal quantification of uncertainties was not possible, but sensitivity analyses of key model parameters caused estimates of global burned area increases from small fires to vary between 24% and 54%. Biomass burning carbon emissions increased by 35% at a global scale when small fires were included in GFED3, from 1.9 Pg C/yr to 2.5 Pg C/yr. The contribution of tropical forest fires to year-to-year variability in carbon fluxes increased because small fires amplified emissions from Central America, South America and Southeast Asia-regions where drought stress and burned area varied considerably from year to year in response to El Nino-Southern Oscillation and other climate modes.

Randerson, J. T.↗
NASA NTRS1995

Volcanic eruptions on Io: Heat flow, resurfacing, and lava composition

We model an infrared outburst on Io as being due to a large, erupting lava flow which increased its area at a rate of 1.5 x 10(exp 5)/sq m and cooled from 1225 to 555 K over the 2.583-hr period of observation. The inferred effusion rate of 3 x 10(exp 5) cu m/sec for this eruption is very high, but is not unprece- dented on the Earth and is similar to the high eruption rates suggested for early lunar volcanism. Eruptions occur approxi- mately 6% of the time on Io. These eruptions provide ample resurfacing to explain Io's lack of impact craters. We suggest that the large total radiometric heat flow, 10(exp 14) W, and the size and temperature distribution of the thermal anomalies (McEwen et al. 1992; Veeder et al. 1994) can be accounted for by a series of silicate lava flows in various stages of cooling. We propose that the whole suite of Io's currently observed thermal anomalies was produced by multiple, high-eruptive-rate silicate flows within the past century.

Blaney, Diana L.↗
NASA NTRS1981

Evaluation of HCMM satellite data for estuarine tidal circulation patterns and thermal inertia soil moisture measurements

Digital thermal maps of the Cooper River (SC) and the Potomac River estuaries were prepared from heat capacity mapping radiometer (HCMR) tapes. Tidal phases were correctly interpreted and verified. Synoptic surface circulation patterns were charted by location thermal fronts and water mass boundaries within the estuaries. Thermal anomalies were detected adjacent of a conventional power plant on the Potomac. Under optimum conditions, estuaries as small as the Cooper River can be monitored for generalized thermal/tidal circulation patterns by the HCMM-type IR sensors. The HCMM thermal inertia approach to estimating soil moisture at the Luverne (MN) test site was found to be unsatisfactory as a NESS operational satellite technique because of cloud cover interference. Thermal-IR data show similar structure of the Baltimore and Washington heat islands when compared to NOAA AVHRR thermal-IR data. Thermal anomalies from the warm water discharge water of a nuclear power plant were mapped in Lake Anna, Virginia.

Wiesnet, D. R.↗
DOE OSTI2024

SSTDR and FDR Detection of Un-Energized and Energized Cable Anomalies Including Thermal Degradation Using Machine Learning

Historically, cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages. A related technology that has found some acceptance in the aircraft and rail industry is spread spectrum time domain reflectometry (SSTDR). This technology has been implemented with a custom commercial instrument by LiveWire Innovation that is designed to operate on live cables up to 1000 volts and with a bandwidth of 48 MHz. Initial evaluation by the Pacific Northwest National Laboratory (PNNL) of the Live Wire system indicated that a broader bandwidth (BW) SSTDR may be better for many kinds of flaws. This led PNNL to develop an SSTDR laboratory instrument suitable for tests up to 500 MHz bandwidth. Testing on energized cables is also desirable for online monitoring systems so an inductive clamshell coupler was developed that allows energized cables to be tested up to at least 5 kV and likely higher voltage levels. Dielectric spectroscopy and tan delta testing plus various laboratory destructive tests were included in this data acquisition campaign directed to feed a machine learning (ML) study. With these kinds of developments, online energized cable tests may be possible with industrial adoption of such hardware advances but it will be completely impractical to have highly skilled data analysts continually examine these complex signals for indications of damage or compromised conditions. If online testing is to be implemented in new test hardware, it must be accompanied by software that can interpret the signals and alert plant operators of changing or degraded conditions. The thermally aged, shielded cable investigated here was separately treated for ML analysis. Visual analysis of electrical data showed generally increasing peaks where the cable entered and exited the oven. These peaks were not exactly aligned with expected locations, but these differences were attributed to velocity of propagation calibration errors. Only supervised ML was applied to the thermally aged data as this data was only available shortly before the committed publication date of this report. The supervised ML was structured to divide the 0 to 70-day responses as ‘normal’ from 0 to 35 days or ‘anomalous’ from 36 to 70 days, based on cable tensile elongation at break (EAB) insulation characterization. Using 80% of the data for training and 20% for testing, the supervised ML predicted normal versus anomalous was 70% accurate. Important conclusions include: • Accuracy to predict the presence of cable damage is improved from the 2023 effort by more training data. Weighted accuracies for comparisons among the instruments ranged from 67 to 89 % for unsupervised ML and 71 to 99% for supervised ML. • Based on the synthetic data tests, the unsupervised models are more generalizable to unseen anomalies. The Multi-Layer Perceptron classifier (MLP) model reported as high as 99.7% accuracy on the test data, but this dropped to 58.3% when tested on the synthetic data. In contrast, the unsupervised Pointwise model only achieved 89.7% accuracy on the experimental data but reported 78.3% accuracy on the synthetic data. • The best anomaly indicators are higher frequency (400 MHz BW) FDR data. Other tests may be interesting but for this study, this was the best predicter.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

SSTDR and FDR Detection of Un-Energized and Energized Cable Anomalies Including Thermal Degradation Using Machine Learning

Historically, cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages.

36 MATERIALS SCIENCE↗
NASA NTRS2004

Satellite IR Thermal Measurements Prior to the September 2004 Earthquakes in Central California

We present and discuss observed variations in thermal transients and radiation fields prior to the earthquakes of September 18 near Bodie (M5.5) and September 28,2004 near Parkfield(M6.0) in California. Previous analysis of earthquake events have indicated the presence of a thermal anomaly, where temperatures increased or did not return to its usual nighttime value. The procedures used in our work is to analyze weather satellite data taken at night and to record the general condition where the ground cools after sunset. Two days before the Bodie earthquake lower temperature radiation was observed by the NOAA/AVHRR satellite. This occurred when the entire region was relatively cloud-free. IR land surface nighttime temperature from the MODIS instrument rose to +4 C in a 100 km radius around the Bodie epicenter. The thermal transient field recorded by MODIS in the vicinity of Parkfield, also with a cloud free environment, was around +l C and it is significantly smaller than the Parkfield epicenter, however, for that period showed a steady increase 4 days prior to the earthquake and a significant drop of the night before the quake. Geosynchronous weather satellite thermal IR measurements taken every half hour from sunset to dawn, were also recorded for 10 days prior to the Parkfield event and 5 days after as well as the day of the quake. To establish a baseline we also obtained GOES data for the same Julian sets were then used to systematically observe and record any thermal anomaly prior to the events that deviated from the baseline. Our recent results support the hypothesis of a possible relationship between an thermodynamic processes produced by increasing tectonic stress in the Earth's crust and a subsequent electro-chemical interaction between this crust and the atmosphere/ionosphere.

Ouzounov, D.↗
NASA NTRS1994

Venus' center of figure-center of mass offset

Magellan altimetry data reveal that the center of figure (CF) of Venus is displaced approximately 280 m from its center of mass (CM) toward 4.4 deg S, 135.8 deg E, a location in Aphrodite Terra. This offset is smaller than those of other terrestrial planets but larger than the estimated error, which is no more than a few tens of meters. We examine the possibility that the CF-CM offset is related to specific geologic provinces on Venus by deriving three simple models for the offset: a thick-crust model, a hotspot model, and a thick-lithosphere model. The offset caused by a region of thick crust depends upon the region's extent, the crust-mantle density contrast, and the thickness of excess crust. A hotspot-related offset depends on the extent of the thermally anomalous region and the magnitude of the thermal anomaly. Offset due to a region of thick lithosphere depends upon the extent of the region, the average temperature contrast across the lithosphere, and the amount of excess lithosphere. We apply the three models to Venus plateau-shaped highlands, volcanic rises, and lowlands, respectively, in an attempt to match the observed CF-CM offset location and magnitude. The influence of most volcanic rises and of Ishtar Terra on the CF-CM offset must be quite small if we are to explain the direction of the observed offset. The lack of influence of volcanic rises can be explained if the related thermal anomalies are limited to a few hundred degrees or less and are plume-shaped (i.e., characterized by a flattened sublithospheric `head' with a narrow cylindrical feeder `tail'). The unimportance of Ishtar Terra is most easily explained if it lies atop a significant mantle downwelling.

Bindschadler, Duane L.↗
DOE OSTI2022

Scaling Building Energy Audits through Machine Learning Methods on Novel Drone Image Data

Building energy audits are time-consuming and labor-intensive. This paper describes a new method using machine learning (ML) techniques on novel data sources (drone images) to improve the identification of building characteristics and retrofit opportunities, and thereby reduce the effort for audits. The new ML method includes: (1) Building footprint extraction using line extraction, polygonization, and polygon-merging, (2) Building envelope extraction using PIX4d modeling software to reconstruct a building 3D model, (3) Visualization tool for viewing images from the 3D model, (4) Window-to-wall ratio (WWR) using state-of-art deep neural network semantic segmentation, (5) Envelope thermal anomaly detection using an unsupervised machine learning clustering algorithm, and (6) Rooftop energy equipment detection based on an object detection algorithm. The testing of this method involved a comparison of additional ML-generated information overlaid on current ‘state-of-practice’ audit and remote assessment baselines using evaluation metrics: labor time and associated cost, marginal benefits of using ML-generated information in workflows for audits and remote assessments, integration potential with existing processes and tools, and replicability/scalability of the method. In two test buildings in California that had comprehensive drawings and meter data available, the ML method effectively generated a building footprint, envelope, rooftop equipment, WWR, and locations of envelope thermal anomalies. Projected target segments of the ML method are sites with minimal drawings and energy data, and underserved sectors such as multistoried housing, disadvantaged communities, and schools for which the ML method can enable identification of building asset characteristics and prioritization of envelope retrofits and decentralized energy equipment retrofits.

Singh, Reshma↗