Engineering PapersSearch

SEARCH · Engineering Papers

Results for “MISSE”

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 37 records · Page 2

MISSE-X: An ISS External Platform for Space Environmental Studies in the Post-Shuttle Era

Materials International Space Station Experiment-X (MISSE-X) is a proposed International Space Station (ISS) external platform for space environmental studies designed to advance the technology readiness of materials and devices critical for future space exploration. The MISSE-X platform will expand ISS utilization by providing experimenters with unprecedented low-cost space access and return on investment (ROI). As a follow-on to the highly successful MISSE series of ISS experiments, MISSE-X will provide advances over the original MISSE configurations including incorporation of plug-and-play experiments that will minimize return mass requirements in the post-Shuttle era, improved active sensing and monitoring of the ISS external environment for better characterization of environmental effects, and expansion of the MISSE-X user community through incorporation of new, customer-desired capabilities. MISSE-X will also foster interest in science, technology, engineering, and math (STEM) in primary and secondary schools through student collaboration and participation.1,2

Thibeault, Sheila A.

Missing Data and Multiple Imputation: An Unbiased Approach

The default method of dealing with missing data in statistical analyses is to only use the complete observations (complete case analysis), which can lead to unexpected bias when data do not meet the assumption of missing completely at random (MCAR). For the assumption of MCAR to be met, missingness cannot be related to either the observed or unobserved variables. A less stringent assumption, missing at random (MAR), requires that missingness not be associated with the value of the missing variable itself, but can be associated with the other observed variables. When data are truly MAR as opposed to MCAR, the default complete case analysis method can lead to biased results. There are statistical options available to adjust for data that are MAR, including multiple imputation (MI) which is consistent and efficient at estimating effects. Multiple imputation uses informing variables to determine statistical distributions for each piece of missing data. Then multiple datasets are created by randomly drawing on the distributions for each piece of missing data. Since MI is efficient, only a limited number, usually less than 20, of imputed datasets are required to get stable estimates. Each imputed dataset is analyzed using standard statistical techniques, and then results are combined to get overall estimates of effect. A simulation study will be demonstrated to show the results of using the default complete case analysis, and MI in a linear regression of MCAR and MAR simulated data. Further, MI was successfully applied to the association study of CO2 levels and headaches when initial analysis showed there may be an underlying association between missing CO2 levels and reported headaches. Through MI, we were able to show that there is a strong association between average CO2 levels and the risk of headaches. Each unit increase in CO2 (mmHg) resulted in a doubling in the odds of reported headaches.

Foy, M.

Development of a Computer Tool to Analyze MISSE Images

The Materials International Space Station Experiment (MISSE) contains individual experiments focused on the investigation of the effects that occur because of the exposure of the material to the space environment. The specimens are mounted on the exterior of the International Space Station (ISS) on the MISSE-Flight Facility (MISSE-FF) and are exposed to the extreme environmental conditions. There have been 14 MISSE missions since the establishment in 2001. This project will evaluate MISSE 9 - MISSE 13 specimens and how they change due to the space environment.

MISSE

The performance of missing transverse momentum reconstruction and its significance with the ATLAS detector using 140 $\hbox {fb}^{-1}$ of $\sqrt{s}=13$ TeV pp collisions

This paper presents the reconstruction of missing transverse momentum ($p_{\text {T}}^{\text {miss}}$ ) in proton–proton collisions, at a center-of-mass energy of 13 TeV. This is a challenging task involving many detector inputs, combining fully calibrated electrons, muons, photons, hadronically decaying $\tau$ -leptons, hadronic jets, and soft activity from remaining tracks. Possible double counting of momentum is avoided by applying a signal ambiguity resolution procedure which rejects detector inputs that have already been used. Several $p_{\text {T}}^{\text {miss}}$ ‘working points’ are defined with varying stringency of selections, the tightest improving the resolution at high pile-up by up to 39% compared to the loosest. The $p_{\text {T}}^{\text {miss}}$ performance is evaluated using data and Monte Carlo simulation, with an emphasis on understanding the impact of pile-up, primarily using events consistent with leptonic Z decays. The studies use $140~\text {fb}^{-1}$ of data, collected by the ATLAS experiment at the Large Hadron Collider between 2015 and 2018. The results demonstrate that $p_{\text {T}}^{\text {miss}}$ reconstruction, and its associated significance, are well understood and reliably modelled by simulation. Finally, the systematic uncertainties on the soft $p_{\text {T}}^{\text {miss}}$ component are calculated. After various improvements the scale and resolution uncertainties are reduced by up to 76% and 51%, respectively, compared to the previous calculation at a lower luminosity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

MISSE 1 and 2 Tray Temperature Measurements

The Materials International Space Station Experiment (MISSE 1 & 2) was deployed August 10,2001 and retrieved July 30,2005. This experiment is a co-operative endeavor by NASA-LaRC. NASA-GRC, NASA-MSFC, NASA-JSC, the Materials Laboratory at the Air Force Research Laboratory, and the Boeing Phantom Works. The objective of the experiment is to evaluate performance, stability, and long term survivability of materials and components planned for use by NASA and DOD on future LEO, synchronous orbit, and interplanetary space missions. Temperature is an important parameter in the evaluation of space environmental effects on materials. The MISSE 1 & 2 had autonomous temperature data loggers to measure the temperature of each of the four experiment trays. The MISSE tray-temperature data loggers have one external thermistor data channel, and a 12 bit digital converter. The MISSE experiment trays were exposed to the ISS space environment for nearly four times the nominal design lifetime for this experiment. Nevertheless, all of the data loggers provided useful temperature measurements of MISSE. The temperature measurement system has been discussed in a previous paper. This paper presents temperature measurements of MISSE payload experiment carriers (PECs) 1 and 2 experiment trays.

Harvey, Gale A.

MISSE Thermal Control Materials with Comparison to Previous Flight Experiments

Many different passive thermal control materials were flown as part of the Materials on International Space Station Experiment (MISSE), including inorganic coatings, anodized aluminum, and multi-layer insulation materials. These and other material samples were exposed to the low Earth orbital environment of atomic oxygen, ultraviolet radiation, thermal cycling, and hard vacuum, though atomic oxygen exposure was limited for some samples. Materials flown on MISSE-1 and MISSE-2 were exposed to the space environment for nearly four years. Materials flown on MISSE-3, MISSE-4, and MISSE-5 were exposed to the space environment for one year. Solar absorptance, infrared emittance, and mass measurements indicate the durability of these materials to withstand the space environment. Effects of short duration versus long duration exposure on ISS are explored, as well as comparable data from previous flight experiments, such as the Passive Optical Sample Assembly (POSA), Optical Properties Monitor (OPM), and Long Duration Exposure Facility (LDEF).

Finckenor, Miria

Part Marking and Identification Materials on MISSE

Many different spacecraft materials were flown as part of the Materials on International Space Station Experiment (MISSE), including several materials used in part marking and identification. The experiment contained Data Matrix symbols applied using laser bonding, vacuum arc vapor deposition, gas assisted laser etch, chemical etch, mechanical dot peening, laser shot peening, and laser induced surface improvement. The effects of ultraviolet radiation on nickel acetate seal versus hot water seal on sulfuric acid anodized aluminum are discussed. These samples were exposed on the International Space Station to the low Earth orbital environment of atomic oxygen, ultraviolet radiation, thermal cycling, and hard vacuum, though atomic oxygen exposure was very limited for some samples. Results from the one-year exposure on MISSE-3 and MISSE-4 are compared to those from MISSE-1 and MISSE-2, which were exposed for four years. Part marking and identification materials on the current MISSE -6 experiment are also discussed.

Finckenor, Miria M.

Part Marking and Identification Materials' for MISSE

The Materials on International Space Station Experiment (MISSE) is being conducted with funding from NASA and the U.S. Department of Defense, in order to evaluate candidate materials and processes for flight hardware. MISSE modules include test specimens used to validate NASA technical standards for part markings exposed to harsh environments in low-Earth orbit and space, including: atomic oxygen, ultraviolet radiation, thermal vacuum cycling, and meteoroid and orbital debris impact. Marked test specimens are evaluated and then mounted in a passive experiment container (PEC) that is affixed to an exterior surface on the International Space Station (ISS). They are exposed to atomic oxygen and/or ultraviolet radiation for a year or more before being retrieved and reevaluated. Criteria include percent contrast, axial uniformity, print growth, error correction, and overall grade. MISSE 1 and 2 (2001-2005), MISSE 3 and 4 (2006-2007), and MISSE 5 (2005-2006) have been completed to date. Acceptable results were found for test specimens marked with Data Matrix(TradeMark) symbols by Intermec Inc. and Robotic Vision Systems Inc using: laser bonding, vacuum arc vapor deposition, gas assisted laser etch, chemical etch, mechanical dot peening, laser shot peening, laser etching, and laser induced surface improvement. MISSE 6 (2008-2009) is exposing specimens marked by DataLase(Registed TradeMark), Chemico technologies Inc., Intermec Inc., and tesa with laser-markable paint, nanocode tags, DataLase and tesa laser markings, and anodized metal labels.

Roxby, Donald

Evaluating Failures and Near Misses in Human Spaceflight History for Lessons for Future Human Spaceflight

There have been a number of studies done in the past drawn on lessons learned with regard to human loss-of-life events. Generally, the systemic causes and proximate causes for fatal events have both been examined in considerable detail. However, an examination of near-fatal accidents and failures that narrowly missed being fatal could be equally useful, not only in detecting causes, both proximate and systemic, but also for determining what factors averted disaster, what design decisions and/or operator actions prevented catastrophe. Additionally, review of risk factors for upcoming or future programs will often look at trending statistics, generally focusing on failure/success statistics. Unfortunately, doing so can give a skewed or misleading view of past reliability or a reliability that cannot be presumed to apply to a new program. One reason for this might be that failure/success criteria aren't the same across programs, but also that apparent success can hide systemic faults that, under other circumstances, can be fatal to a program with different parameters. A program with a number of near misses can look more reliable than a consistently healthy program with a single out-of-family failure and provide very misleading data if it is not examined in detail. This is particularly true for a manned space program where failure/success includes more than making a particular orbit. Augmenting reliability evaluations with this near miss data can provide insight and expand on the limitations of a strictly pass/fail evaluation. Even more importantly, a thorough understanding of these near miss events can identify conditions that prevented fatalities. Those conditions may be key to a programs reliability, but, without insight to the repercussions if such conditions were not in place, their importance may not be readily clear. As programs mature and political and fiscal responsibilities come to the fore, often there is considerable incentive to eliminate unnecessary conservatism, design margin, redundancy, operational support, testing, training, or safety oversight. An evaluation that demonstrates how these features and capabilities averted disaster can ensure processes that saved lives or missions are not discarded without appropriate review and understanding. Close examination of accidents that almost were can also highlight differences in design from one program to another, either justifying reliability comparisons or negating them. It can also provide considerable insight into how those saving factors were developed and implemented so that similar methods can be used to ensure appropriate life-saving and mission saving factors can be developed, even for a dissimilar space program. The lessons are appropriate for seasoned manned space programs and agencies, but crucial for untried agencies and organizations that are interested in sending man into space. The large body of publicly available near miss and accident data available provide invaluable insight into programmatic, technical, and even political issues that can be addressed before they impact safety. In this paper, we examine a number of these near misses and accidents and steps a program, agency, or potential spacefaring company might take to improve their chances of success and avoid mission or safety disasters using this data.

Barr, Stephanie

MISSE 6, 7 and 8 Materials Sample Experiments from the International Space Station Materials and Processes Team

The International Space Station Materials and Processes (ISS M&P) team has multiple material samples on MISSE 6, 7 and 8 to observe Low Earth Orbit (LEO) environmental effects on Space Station materials. Optical properties, thickness/mass loss, surface elemental analysis, visual and microscopic analysis for surface change are some of the techniques employed in this investigation. The ISS M&P team has participated in previous MISSE activities in order to better characterize the LEO effects on Space Station materials. This investigation will further this effort. Results for the following MISSE 6 samples materials will be presented: a comparison of anodize and chemical conversion coatings on various aluminum alloys, electroless nickel; AZ93 white ceramic thermal control coating with and without Teflon; Hyzod(TM) polycarbonate used to temporarily protect ISS windows; Russian quartz window material; reformulated Teflon (TM) coated Beta Cloth (Teflon TM without perfluorooctanoic acid (PFOA)) and a Dutch version of beta cloth. Discussion for current and future MISSE materials experiments will be presented. MISSE 7 samples are: deionized water sealed anodized aluminum Photofoil(TM); indium tin oxide (ITO)- coated Kapton(TM) used as thermo-optical surfaces; mechanically scribed tin-plated beryllium-copper samples for "tin pest" growth ( alpha/Beta transformation); Crew Exploration Vehicle (CEV) parachute soft goods. MISSE 8 sample: exposed "scrim cloth" (fiberglass weave) from the ISS solar array wing material, Davlyn fiberglass sleeve material, Permacel and Intertape protective tapes, and ITO-coated Kapton.

Kravchenko, Michael

Performance Testing of Lidar Components Subjected to Space Exposure in Space via MISSE 7 Mission

.The objective of the Materials International Space Station Experiment (MISSE) is to study the performance of novel materials when subjected to the synergistic effects of the harsh space environment for several months. MISSE missions provide an opportunity for developing space qualifiable materials. Several laser and lidar components were sent by NASA Langley Research Center (LaRC) as a part of the MISSE 7 mission. The MISSE 7 module was transported to the international space station (ISS) via STS 129 mission that was launched on Nov 16, 2009. Later, the MISSE 7 module was brought back to the earth via the STS 134 that landed on June 1, 2011. The MISSE 7 module that was subjected to exposure in space environment for more than one and a half year included fiber laser, solid-state laser gain materials, detectors, and semiconductor laser diode. Performance testing of these components is now progressing. In this paper, the current progress on post-flight performance testing of a high-speed photodetector and a balanced receiver is discussed. Preliminary findings show that detector characteristics did not undergo any significant degradation.

Prasad, Narasimha S.

Materials International Space Station Experiment-9 (MISSE-9) Polymers and Composites Experiment

Spacecraft in low Earth orbit (LEO) are subjected to harsh environmental conditions, including radiation (cosmic rays, ultraviolet, x-ray, and charged particle radiation), micrometeoroids and orbital debris, temperature extremes, thermal cycling, and atomic oxygen (AO). These environmental exposures can result in erosion, embrittlement and optical property degradation, threatening spacecraft performance and durability. To increase our understanding of effects such as AO erosion and radiation induced embrittlement of spacecraft materials, NASA Glenn has developed a series of experiments flown as part of the Materials International Space Station Experiment (MISSE) missions on the exterior of the International Space Station (ISS). These experiments have provided critical LEO space environment durability data such as AO erosion data for many materials and mechanical properties changes after long term space exposure. In continuing these studies, a new experiment called the Polymers and Composites Experiment has been selected for flight on the MISSE-Flight Facility (MISSE-FF). The Polymers and Composites Experiment will be flown as part of the MISSE-9 mission, the inaugural mission of MISSE-FF manifested on SpaceX-14. This experiment includes 138 samples being flown in ram, wake or zenith orientations for space environmental durability assessment. The primary objective is to determine the LEO AO erosion yield, Ey (the volume loss per incident oxygen atom (cm3/atom)), of polymers, composites, and coated samples, as a function of solar irradiation and AO fluence. In addition, epoxy samples with varying levels of ZnO powder are included to study the effect of filler quantity on AO erosion. An AO Scattering Chamber is included to help improve the understanding of AO scattering mechanisms for improved AO undercutting modeling. Indium tin oxide (ITO) coated samples are included to validate the durability of ITO conductive coatings in LEO. Tensile samples of Teflon fluorinated ethylene propylene (FEP) of varying thicknesses and back-surface coatings will be flown in wake and zenith orientations to study radiation embrittlement versus thickness, and the effect of heating on FEP embrittlement. Finally, shape memory composite and cosmic ray shielding samples will be flown for LEO durability assessment. This paper presents an overview of the MISSE-9 Polymers and Composites Experiment.

Embrittlement

Overview of the MISSE-16 Mission and Preliminary Characterization of Novel Space Weathered Materials

The Materials International Space Station Experiment (MISSE) project is a series of experiments that began in 2001, involving the deployment of external experiment platforms on the International Space Station (ISS). Since then, more than 4,000 materials were tested yielding valuable data and insights into the performance of materials and coatings in the harsh space environment, as well as providing a platform for testing and validating new materials and technologies. The results of the MISSE experiments have contributed to the development of more durable and reliable spacecraft and equipment, as well as improving our understanding of the space environment and its effects on human space exploration. To gain deeper insights into the changes in material properties of both novel and heritage spacecraft materials over the course of a mission, we proposed to enhance the MISSE hardware. This was achieved by integrating a high-resolution camera that can capture both RGB and IR color data, along with an updated illumination scheme. The identical sets of selected materials were mounted on the Zenith, Ram, and Wake faces of the ISS to expose them to predominant vacuum ultraviolet (VUV), atomic oxygen, and high-energy electron conditions. In addition, we exposed flight duplicates of these materials to a simulated space environment, which included sequential exposure to the same irradiation species on the ground. This allowed us to study the effects of space exposure on the materials in a controlled manner and to compare their behavior in both real and simulated space environments. The MISSE-FF flight sample collection comprised different classes of polymers, including polyimides from the Kapton family, manufactured by E.I du Pont de Nemours and Co., Polyethylene terephthalate (PET) materials, liquid crystal polymers, PI/Polyhedral Oligomeric Silsesquioxanes (POSS), and carbon and glass fiber reinforced polymers. The experimental cadence during the MISSE-16 mission (~6 months) included daily images of each sample for the first week, weekly for the next 2 months, and monthly the remaining duration of the mission. This paper will focus on the flight duplicate as well as the postflight optical characterization of novel and heritage materials currently under observation on the MISSE-FF.

Jainisha R Shah

Contamination Results of MISSE 8 Wake and Nadir Samples After 2 Years of Space Exposure on the International Space Station

Spacecraft in low Earth orbit (LEO) are subjected to harsh environmental conditions, including radiation (cosmic rays, ultraviolet, x-ray and charged particle radiation), micrometeoroids and orbital debris, temperature extremes, thermal cycling, and atomic oxygen. In addition, on-orbit spacecraft contamination is a serious spaceflight issue, with silicone contamination being a particular concern. In an effort to understand on-orbit contamination of Materials International Space Station Experiment 8 (MISSE 8) flight samples and other International Space Station (ISS) payloads, contamination studies were conducted post-flight on retrieved Teflon fluorinated ethylene propylene (FEP) samples flown in the wake and nadir orientations on MISSE 8. The wake sample was Teflon FEP (M8-W11) flown as part of the Glenn MISSE 8 Polymers Experiment on the Optical Reflector Materials Experiment-III Ram/Wake (ORMatE-III R/W) tray and exposed to the LEO wake environment for 2.0 years. The nadir samples were silver-Teflon FEP radiator pieces taken from the MISSE 8 Single Events Upset Xilinx-Sandia Experiment II (SEUXSE II) Power Box and exposed to the LEO nadir environment for 2.14 years. The Teflon FEP flight materials were analyzed for changes in surface morphology and chemistry as compared to pristine control samples. The wake samples were also analyzed for changes in optical properties. There was no evidence of a molecular contamination layer present on the surface of the MISSE 8 wake or nadir facing Teflon FEP flight samples, although both the wake and nadir flight samples contained particulate contamination in some regions. The analyzed nadir particles were primarily zinc rich. The majority of analyzed wake particles were comprised of oxidized aluminum with small amounts of zinc and magnesium. The wake particles appear to have arrived early in the mission (or pre-flight) during a single event. This paper provides details of the MISSE 8 sample contamination analyses.

Erosion

Improving missing transverse momentum estimation with a deep neural network

At hadron colliders, the net transverse momentum of particles that do not interact with the detector (missing transverse momentum, $^→_𝑝$$^{miss}_{T}$) is a crucial observable in many analyses. In the standard model, $^→_𝑝$$^{miss}_{T}$ originates from neutrinos. Many beyond-the-standard-model particles, such as dark matter candidates, are also expected to leave the experimental apparatus undetected. This paper presents a novel deep neural network based $^→_𝑝$$^{miss}_{T}$ estimator, DeepMET, developed by the CMS Collaboration at the LHC. The DeepMET algorithm produces a weight for each reconstructed particle based on its properties. The estimator is based on the negative vector sum of the weighted transverse momenta of all reconstructed particles in an event. Compared with other estimators currently employed by CMS, DeepMET improves the $^→_𝑝$$^{miss}_{T}$ resolution by 10%–30%, shows improvement for a wide range of final states, is easier to train, and is more resilient against the effects of additional proton-proton interactions accompanying the collision of interest.

artificial neural networks

Space Environmental Effects on Additively Manufactured (AM) Parts on MISSE-9/10

The Materials on International Space Station Experiment (MISSE) experiments have made a continuous presence on the ISS and allowed for testing of performance and durability of materials exposed to the Low Earth Orbit (LEO) space environment. Additive Manufacturing (AM) has been included on several MISSE flights, and many companies (Made in Space and Stratasys) and NASA centers wanted to test various AM material samples. The goal of studying Space Environmental Effects on AM Parts with MISSE 9/10 was to fly promising metal and polymer AM material samples (dogbones) that could have future manufacturing capabilities in space and conduct post-flight analysis of these materials via mechanical and optical properties. On these flights, MISSE-9 contained three Inconel and 12 polymer samples and MISSE-10 included three Inconel and 16 polymer samples. Before flying to the ISS, all the samples underwent thermal vacuum bakeout (at 60°C for 24 hours and 10-6 torr). After bakeout, control and flight experiments were weighed, and optical properties were taken. Optical properties such as solar absorptance and infrared emittance were taken on the control samples and the flight samples (preflight and postflight). To understand more about the mechanical properties of the AM samples, tensile testing was conducted on the samples to determine the yield and ultimate tensile strength of the dogbone samples against the control. Lastly, the torque on the fasteners securing the dogbone samples were loosened and measured using a torque wrench, and they were compared to their preflight torque specification required. Optical properties and masses were recorded before flight, and the postflight results were recorded and collected in June 2022 to study the effects. With the postflight analysis, NASA engineers can now better characterize how UV radiation and thermal cycling affect the material properties.

Materials on International Space Station Experimen

Filling the Gaps: A Bayesian Mixture Model for Imputing Missing Soil Water Content Data

ABSTRACT Soil water content (SWC) data are central to evaluating how soil moisture varies over time and space and influences critical plant and ecosystem functions, especially in water‐limited drylands. However, sensors that record SWC at high frequencies often malfunction, leading to incomplete timeseries and limiting our understanding of dryland ecosystem dynamics. We developed an analytical approach to impute missing SWC data, which we tested at six eddy flux tower sites along an elevation gradient in the southwestern United States. We impute missing data as a mixture of linearly interpolated SWC between the observed endpoints of a missing data gap and SWC simulated by an ecosystem water balance model (SOILWAT2). Within a Bayesian framework, we allowed the relative utility (mixture weight) of each component (linearly interpolated vs. SOILWAT2) to vary by depth, site and gap characteristics. We explored “fixed” weights versus “dynamic” weights that vary as a function of cumulative precipitation, average temperature, and time since the start of the gap. Both models estimated missing SWC data well ( R 2 = 0.70–0.88 vs. 0.75–0.91 for fixed vs. dynamic weights, respectively), but the utility of linearly interpolated versus SOILWAT2 values depended on site and depth. SOILWAT2 was more useful for more arid sites, shallower depths, longer and warmer gaps and gaps that received greater precipitation. Overall, the mixture model reliably gap‐fills SWC, while lending insight into processes governing SWC dynamics. This approach to impute missing data could be adapted to accommodate more than two mixture components and other types of environmental timeseries.

Ogle, Kiona [School of Informatics, Computing, and

Denoising Autoencoder for Reconstructing Sensor Observation Data and Predicting Evapotranspiration: Noisy and Missing Values Repair and Uncertainty Quantification

Abstract Machine learning (ML) methods applied in scientific research often deal with interrelated features in high‐dimensional data. Reducing data noise and redundancy is needed to increase prediction accuracy and efficiency especially when dealing with data from field sensors. We explored an unsupervised learning method, the denoising autoencoder (DAE), to extract the underlying data structure from noisy raw data in the context of predicting hydrologic quantities from multiple field sensors. These sensors have intrinsic instrumental noise and occasional malfunctions that cause missing values. Our DAE neural network reconstructed meteorological sensor data containing noise and missing values to predict evapotranspiration in a mountainous watershed. The DAE reconstructed the sensor variables with a mean coefficient of determination value of 0.77 across 15 dimensions representing individual sensors. It reduced variance and bias uncertainties compared to a classical autoencoder model. The reconstruction quality varied across dimensions depending on their cross‐correlation and alignment with the underlying data structure. Uncertainties arising from the model structure were overall higher than those resulting from data corruption. We attached the DAE structure to a downstream ET‐prediction neural network in three formats and achieved reasonably accurate ET predictions . The use of the DAE notably reduced variance uncertainty in ET prediction. However, excessive variance reduction may be accompanied by an increase in bias due to the intrinsic bias‐variance tradeoff. Our method of evaluating and reducing uncertainties in aggregated data from different sources can be used to improve predictive models, process understanding, and uncertainty quantification for better water resource management. Plain Language Summary We present a machine learning method, namely the denoising autoencoder, which reduces the effects of data noise and missing values typically present in scientific data sets collected through sensor measurements. This method selects the most relevant information from noisy raw data collected by the instruments and fills in missing values. To demonstrate the effectiveness of our method, we applied it to predict evapotranspiration, a hydrologic variable that represents the water moved from the land surface to the atmosphere through a combination of evaporation and plant water use (transpiration). We also used a random sampling technique (the Monte Carlo method) to compare the uncertainty in the predictions when using the raw and noisy data versus the reconstructed data. The denoising process produced more accurate predictions of evapotranspiration with less uncertainty. Improved predictions of evapotranspiration can lead to a better understanding and accounting of water budgets. This ML approach is broadly suitable for a wide variety of applications that involve noisy sensor data with missing values. Key Points We used a denoising autoencoder (DAE) neural network to reduce noise in meteorological and soil sensor observations by on average We used Monte Carlo sampling to estimate the bias and variance of all model outputs, including uncertainty sources from data and the model We attached the DAE component to a downstream neural network to predict ET with the variance reduced by , compared to that without the DAE

denoising autoencoder