SEARCH · Engineering Papers

Results for “latent space learning”

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.

SourceResearch connectionFrom yearThrough year

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

233 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Learning in continuous action space for developing high dimensional potential energy models

Reinforcement learning (RL) approaches that combine a tree search with deep learning have found remarkable success in searching exorbitantly large, albeit discrete action spaces, as in chess, Shogi and Go. Many real-world materials discovery and design applications, however, involve multi-dimensional search problems and learning domains that have continuous action spaces. Exploring high-dimensional potential energy models of materials is an example. Traditionally, these searches are time consuming (often several years for a single bulk system) and driven by human intuition and/or expertise and more recently by global/local optimization searches that have issues with convergence and/or do not scale well with the search dimensionality. Here, in a departure from discrete action and other gradient-based approaches, we introduce a RL strategy based on decision trees that incorporates modified rewards for improved exploration, efficient sampling during playouts and a “window scaling scheme" for enhanced exploitation, to enable efficient and scalable search for continuous action space problems. Using high-dimensional artificial landscapes and control RL problems, we successfully benchmark our approach against popular global optimization schemes and state of the art policy gradient methods, respectively. We demonstrate its efficacy to parameterize potential models (physics based and high-dimensional neural networks) for 54 different elemental systems across the periodic table as well as alloys. We analyze error trends across different elements in the latent space and trace their origin to elemental structural diversity and the smoothness of the element energy surface. Broadly, our RL strategy will be applicable to many other physical science problems involving search over continuous action spaces.

36 MATERIALS SCIENCE↗

DOE OSTI2025

VAIM-CFF: a variational autoencoder inverse mapper solution to Compton form factor extraction from deeply virtual exclusive reactions

We develop a new methodology for extracting Compton form factors (CFFs) from deeply virtual exclusive reactions such as the unpolarized DVCS cross section using a specialized inverse problem solver, a variational autoencoder inverse mapper (VAIM). The VAIM-CFF framework not only allows us access to a fitted solution set possibly containing multiple solutions in the extraction of all 8 CFFs from a single cross section measurement, but also accesses the lost information contained in the forward mapping from CFFs to cross section. We investigate various assumptions and their effects on the predicted CFFs such as cross section organization, number of extracted CFFs, use of uncertainty quantification technique, and inclusion of prior physics information. We then use dimensionality reduction techniques such as principal component analysis to visualize the missing physics information tracked in the latent space of the VAIM framework. Through re-framing the extraction of CFFs as an inverse problem, we gain access to fundamental properties of the problem not comprehensible in standard fitting methodologies: exploring the limits of the information encoded in deeply virtual exclusive experiments.

Accelerator Physics↗

DOE OSTI2023

Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders *

Abstract Recent advances in scanning tunneling and transmission electron microscopies (STM and STEM) have allowed routine generation of large volumes of imaging data containing information on the structure and functionality of materials. The experimental data sets contain signatures of long-range phenomena such as physical order parameter fields, polarization, and strain gradients in STEM, or standing electronic waves and carrier-mediated exchange interactions in STM, all superimposed onto scanning system distortions and gradual changes of contrast due to drift and/or mis-tilt effects. Correspondingly, while the human eye can readily identify certain patterns in the images such as lattice periodicities, repeating structural elements, or microstructures, their automatic extraction and classification are highly non-trivial and universal pathways to accomplish such analyses are absent. We pose that the most distinctive elements of the patterns observed in STM and (S)TEM images are similarity and (almost-) periodicity, behaviors stemming directly from the parsimony of elementary atomic structures, superimposed on the gradual changes reflective of order parameter distributions. However, the discovery of these elements via global Fourier methods is non-trivial due to variability and lack of ideal discrete translation symmetry. To address this problem, we explore the shift-invariant variational autoencoders (shift-VAEs) that allow disentangling characteristic repeating features in the images, their variations, and shifts that inevitably occur when randomly sampling the image space. Shift-VAEs balance the uncertainty in the position of the object of interest with the uncertainty in shape reconstruction. This approach is illustrated for model 1D data, and further extended to synthetic and experimental STM and STEM 2D data. We further introduce an approach for training shift-VAEs that allows finding the latent variables that comport to known physical behavior. In this specific case, the condition is that the latent variable maps should be smooth on the length scale of the atomic lattice (as expected for physical order parameters), but other conditions can be imposed. The opportunities and limitations of the shift VAE analysis for pattern discovery are elucidated.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2002

Better Weather Prediction and Climate Diagnostics Using Rainfall Measurements from Space

Progress in understanding of the role of water in global weather and climate is currently limited by our knowledge of the spatial and temporal variability of primary hydrological fields such as precipitation and evaporation. The Tropical Rainfall Measuring Mission (TRMM) has recently demonstrated that use of microwave-based rainfall observations from space in data assimilation can provide better climate data sets and improve short-range weather forecasting. At NASA, we have been exploring non-traditional approaches to assimilating TRMM Microwave Imager (TMI) and Special Sensor Microwavehager (SSM/I) surface rain rate and latent heating profile information in global systems. In this talk we show that assimilating microwave rain rates using a continuous variational assimilation scheme based on moisture tendency corrections improves quantitative precipitation estimates (QPE) and related clouds, radiation energy fluxes, and large-scale circulations in the Goddard Earth Observing System (GEOS) reanalyses. Short-range forecasts initialized with these improved analyses also yield better QPE scores and storm track predictions for Hurricanes Bonnie and Floyd. We present a status report on current efforts to assimilate convective and stratiform latent heating profile information within the general variational framework of model parameter estimation to seek further improvements. Within the next 5 years, there will be a gradual increase in microwave rain products available from operational and research satellites, culminating to a target constellation of 9 satellites to provide global rain measurements every 3 hours with the proposed Global Precipitation Measurement (GPM) mission in 2007/2008. Based on what has been learned from TRMM, there is a high degree of confidence that these observations can play a'major role in improving weather forecasts and producing better global datasets for understanding the Earth's water and energy cycle. The key to success is to adopt an integrated approach to retrieval, validation, modeling, and data assimilation in a coordinated end-to-end observation-application program.

Hou, Arthur↗

DOE OSTI2025

Design of diverse, functional mitochondrial targeting sequences across eukaryotic organisms using variational autoencoder

Mitochondria play a key role in energy production and metabolism, making them a promising target for metabolic engineering and disease treatment. However, despite the known influence of passenger proteins on localization efficiency, only a few protein-localization tags have been characterized for mitochondrial targeting. To address this limitation, we leverage a Variational Autoencoder to design novel mitochondrial targeting sequences. In silico analysis reveals that a high fraction of the generated peptides (90.14%) are functional and possess features important for mitochondrial targeting. We characterize artificial peptides in four eukaryotic organisms and, as a proof-of-concept, demonstrate their utility in increasing 3-hydroxypropionic acid titers through pathway compartmentalization and improving 5-aminolevulinate synthase delivery by 1.62-fold and 4.76-fold, respectively. Moreover, we employ latent space interpolation to shed light on the evolutionary origins of dual-targeting sequences. Overall, our work demonstrates the potential of generative artificial intelligence for both fundamental research and practical applications in mitochondrial biology.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2018

Trusted Communication: Utilizing Speech Communication to Enhance Human-Machine Teaming Success

An area of increasing interest for the next generation of aircraft is autonomy and the integration of increasingly autonomous systems into the national airspace. Such an integration requires humans to work closely with autonomous systems, forming teams. Our hypothesis is that a team composed of both humans and autonomous systems will operate better than either entity alone. We have existing procedures for certifying pilots to operate in the national airspace and are currently working on methods for validating the function of autonomous systems, however we have no method in place for assessing the interaction of these two disparate systems. Communication is one avenue. This paper will examine the use of language as a metric for ascertaining human-machine teaming effectiveness. A proof-of-concept of the application of two communication-based analysis techniques, Linguistic Inquiry and Word Count (LIWC) and Latent Semantic Analysis (LSA), for the prediction of success in human/chatbot teaming was conducted. By running these analyses over data from the 2014 and 2015 Loebner Prize competitions of human/chatbot teaming, numerical scores were obtained that can be associated with scores provided by human judges during the competition. Correlating their LIWC and LSA data with the scores provided by the judges, and using linear regression over this correlation, formulae were obtained that predict the score of human/chatbot interaction. These formulae were tested over the 2013 Loebner Prize transcripts, determining that, though there was strong correlation between predicted and actual scores, the predictive success of this method was not strong. However, with specialized topic spaces and lexica, as well as larger data sets, the predictive power of these metrics will improve. Given the importance of providing metrics for human-machine system team success and given the promise shown by the communication-basedLIWCand LSAmethods, continuing research in this area is necessary. After examining the potential for using communication and spoken language as a metric for the success of human/autonomous system teaming, this paper then examines aspects inherent to communication systems that may contribute to unreliability and reduced trust. Modern natural language processing tools rely on deep learning algorithms to create language rules that produce accurate results, but these rules are uninterpretable. The resulting blackbox system lacks transparency necessary for full validation and complete trust. Additionally, speech-based interfaces pose other difficulties to developing coordinated teamwork between humans and autonomous systems. Human communication is infrequently limited to speech only, instead usually relying on a combination of verbal, gestural, and general body language communication. Reducing an analysis of team effectiveness to a study of spoken language alone is problematic as it leaves these other equally important forms of communication out. This paper will examine these problems and the general deficiencies in speech-based metrics for human-machine teaming.

E L Meszaros↗

DOE OSTI2024

Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders

Abstract Coherent diffraction imaging (CDI) is an advanced non-destructive 3D X-ray imaging technique for measuring a sample’s electron density. The main challenge of CDI is loss of phase information in diffraction intensity measurements, resulting in lengthy iterative reconstruction processes that can return non-unique solutions, which pose challenges for experiments attempting to track dynamic sample evolution through multiple states. As the increased brightness of fourth-generation light sources enables faster sample measurements and drives operando experiments with Bragg CDI, there is a growing need for faster reconstruction techniques that can keep pace. We have developed an adaptive generative autoencoder approach for uniquely tracking a sample’s electron density as it dynamically evolves. Our approach adaptively tunes the low-dimensional latent embedding of a generative autoencoder, enabling a computationally efficient manner to account for time-varying shifting distributions in real-time. Analytic proof of convergence is provided as well as numerical demonstration of sample tracking with noisy measurements.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. Here, in this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.

artificial intelligence↗

DOE OSTI2024

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics

Abstract Background The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain‐relevant assessments via the analysis of relevant image statistics. Methods As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512 512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM‐generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results Fifty‐eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top‐ranked submission employed a conditional latent diffusion model, whereas the joint runners‐up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID‐based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions This Grand Challenge highlighted the need for domain‐specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Radiology, Nuclear Medicine & Medical Imaging↗

DOE OSTI2024

Stochastic machine learning via sigma profiles to build a digital chemical space

This work establishes a different paradigm on digital molecular spaces and their efficient navigation by exploiting sigma profiles. To do so, the remarkable capability of Gaussian processes (GPs), a type of stochastic machine learning model, to correlate and predict physicochemical properties from sigma profiles is demonstrated, outperforming state-of-the-art neural networks previously published. The amount of chemical information encoded in sigma profiles eases the learning burden of machine learning models, permitting the training of GPs on small datasets which, due to their negligible computational cost and ease of implementation, are ideal models to be combined with optimization tools such as gradient search or Bayesian optimization (BO). Gradient search is used to efficiently navigate the sigma profile digital space, quickly converging to local extrema of target physicochemical properties. While this requires the availability of pretrained GP models on existing datasets, such limitations are eliminated with the implementation of BO, which can find global extrema with a limited number of iterations. A remarkable example of this is that of BO toward boiling temperature optimization. Holding no knowledge of chemistry except for the sigma profile and boiling temperature of carbon monoxide (the worst possible initial guess), BO finds the global maximum of the available boiling temperature dataset (over 1,000 molecules encompassing more than 40 families of organic and inorganic compounds) in just 15 iterations (i.e., 15 property measurements), cementing sigma profiles as a powerful digital chemical space for molecular optimization and discovery, particularly when little to no experimental data is initially available.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

A Parametric, Data-Driven, Non-Intrusive Reduced-Order Model Framework for Crystal Plasticity Simulations of Voids

The influence of the internal structure at micrometer length scales on the deformation of polycrystalline materials can be effectively captured using crystal plasticity finite element methods (CPFEM). However, the complexity and nonlinearity of the deformation equations CPFEM solves demand significant computational power and resources to achieve accurate predictions, limiting its broader application. To address this challenge, we have identified a reduced-order representation of the complex data in order to establish a computationally efficient reduced-order models (ROM) and drastically reduce the computational expense of CPFEM. Specifically, in this work, we developed a parametric, data-driven, and non-intrusive ROM framework for CPFEM using proper orthogonal decomposition (POD) and sparse variational Gaussian process (SVGP) regression for single-crystal microstructures under tensile loading conditions. The developed protocol enables one to compress field into a latent/low-dimensional space described by principal component analysis (PCA) via the singular value decomposition (SVD) algorithm. As a result, the high-dimensional data are reduced to a significantly smaller amount of dimensions with POD bases and POD coefficients. Furthermore, we deployed an ensemble of SVGPs—extended from the classical Gaussian process (GP) regression for scalability and handling big data—in a massively parallel manner to train and predict latent POD coefficients using known POD bases from a set of previously obtained simulations results. Lastly, using the predicted POD coefficients, we reconstructed the full-field results and showed reasonable agreement compared with the true values obtained from running CPFEM. The developed framework is validated with a set of CPFEM simulations of a single embedded void in single-crystal aluminum alloy. While the framework is broadly applicable, this work specifically focuses on single-crystal microstructures, a single load case (e.g., tensile), and a specific void geometry (spherical).

Anisotropy↗

NASA NTRS2004

Winds, Water Budgets and Stable Isotopes in Tropical Cyclones using TRMM and QUICKSCAT

Water vapor is the most abundant greenhouse gas in the atmosphere. Changes in its concentration and distribution are controlled by the hydrologic cycle. Because of its capacity to absorb and emit long wave radiation, release latent heat during condensation in storms and reflect short wave radiation when clouds form it has a major impact on Global climate change. The stable isotope ratios of water are H20 H2l6O and H0 H2l6O. These ratios change whenever water undergoes a phase change. They also change in both rain and water vapor whenever an air parcel is exposed to rain. In addition the relative changes in the two ratios differ as a &nction of the relative humidity. In short, the stable isotope ratios in water vapor in the atmosphere contain an integrated history of the processes affecting the concentration and distribution of water vapor in the atmosphere. Therefore the measurement and interpretation of changes in these stable isotope ratios are a powerful tool matched by no other method in tracing the transport history of water in the atmosphere. Our initial studies under this grant focused on the changes of the stable isotope ratios of precipitation and water vapor in tropical cyclones. The changes in time and space were found to be very large and to trace the transport of water in the storms reflecting changes in basic structural features. Because the stable isotope ratios of rains from tropical cyclones are so low flooding associated with land falling tropical cyclones introduces a negative isotopic spike into the coastal surface waters. In addition the stable isotope ratios of water vapor in the vicinity of tropical cyclones is anomalously low. This suggests that carbonate shelled organisms such as ostracoda living in coastal waters have the potential to record the isotopic spike and thereby provide a long term record of tropical storm activity in sediment cores containing fossil shells. Likewise, tree rings in coastal environments offer a similar potential. We have analyzed the oxygen isotopic composition of ostrcoda shells formed in the floodwaters of Tropical Storm Allison (2001) and discovered the negative isotopic 1 16 spike. Because we had learned that storm activity has a major impact on the stable isotope ratios of water vapor in the tropics and sub-tropics we decided to analyze the isotopic compositions of water vapor in different locations in the tropics. We did this in Puerto Escondido, Mexico in July 1998, near Kwajalein Island in the Pacific in 1999 as part of a TRMM summer field program and in 2001 in Key West, Florida as part of the CAMEX 4 summer field program. Our isotopic studies along with our earlier tropical cyclone studies showed that the low isotopic ratios in water vapor induced by exposure to rains the storms persisted for 48 hours often far away from the original storm site. We also noted that positive isotopic spikes were introduced into atmospheric water vapor if winds were high and extensive sea spray was present. These findings have a significant impact on the interpretation of the stable isotope studies of tropical ice cores found in the high mountain regions of the tropics. The assumption made in interpreting the ice core record is that the source water vapor evaporated from the sea surface is in near isotopic equilibrium with the seawater and undergoes a decrease during its transport that reflects the change in temperature from the sea surface to the site of the ice core. Because an additional isotopic depletion occurs at the sea surface source area that depends on the intensity, duration and size of the tropical rain system the isotopic variations found in the ice cores must take into account changes in past storm activity in the tropics. These systems must be an important source of water vapor to the ice cores because they charge the troposphere with water vapor to a far greater vertical height than evaporation in quiescent regions. Finally, an interest in increased heat transfer in thnterior of tropical cyclones resulting from greater amounts of sea spray is a topic of considerable interest to the research community. Increases in sea spray may be related to rapid changes in the intensity of hurricanes, a feature of hurricanes that currently is very poorly forecast. Project CBLAST of the Hurricane Research Division of NOAA is an active program that uses P3 research aircraft to evaluate this problem. An instrument has been designed and built at the University of Houston that will be placed on the P3 research aircraft during the 2004 hurricane season. It continuously measures the salt content of rain in hurricanes. Changes in the salt content of the rains should reflect the abundance of sea spray at the sea surface. In this way maps of sea spray intensity in hurricanes may be forthcoming. This should help computer modelers who simulate hurricanes to better understand the potential of changes in sea spray to change the intensity of hurricanes. The cost of designing, building and installing this instrument was borne largely by funding from this NASA grant. A list of presentations at national meetings and publications that were as the result of funding from this NASA grant are found in the report.

Lawrence, James R.↗

DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗

NASA NTRS1999

TRMM and Its Connection to the Global Water Cycle

The importance of quantitative knowledge of tropical rainfall, its associated latent heating and variability is summarized in the context of the global hydrologic cycle. Much of the tropics is covered by oceans. What land exists, is covered largely by rainforests that are only thinly populated. The only way to adequately measure the global tropical rainfall for climate and general circulation models is from space. The TRMM orbit is inclined 35 degrees leading to good sampling in the tropics and a rapid precession to study the diurnal cycle of precipitation. The precipitation instrument complement consists of the first rain radar to be flown in space (PR), a multi-channel passive microwave sensor (TMI) and a five-channel VIS/IR (VIRS) sensor. The precipitation radar operates at a frequency of 13.6 GHz. The swath width is 220 km, with a horizontal resolution of 4 km and the vertical resolution of 250 m. The minimum detectable signal from the precipitation radar has been measured at 17 dBZ. The TMI instrument is designed similar to the SSM/I with two important changes. The 22.235 GHz water vapor absorption channel of the SSM/I was moved to 21.3 GHz in order to avoid saturation in the tropics and 10.7 GHz V&H polarized channels were added to expand the dynamic range of rainfall estimates. The resolution of the TMI varies from 4.6 km at 85 GHz to 36 km at 10.7 GHz. The visible and infrared sensor (VIRS) measures radiation at 0.63, 1.6, 3.75, 10.8 and 12.0 microns. The spatial resolution of all five VIRS channels is 2 km at nadir. In addition to the three primary rainfall instruments, TRMM will also carry a Lightning Imaging Sensor (LIS) and a Clouds and the Earth's Radiant Energy System (CERES) instrument. This presentation will focus primarily on the advances in our understanding of tropical rain systems needed to interpret the TRMM data. Global averages, as well as case studies from TRMM radar (PR), the TRMM Microwave Imager (TMI) and Visible and Infrared Sensor (VIRS) will be presented. Comparisons and contrasts among the different sensors will be drawn. Results will also be compared to previous rainfall climatologies generated from the SSM/I instrument. In particular this paper will focus on the synergy between the TRMM radar and passive microwave radiometer and what we have learned from is synergy.

Kummerow, Chiristian↗

NASA NTRS1999

TRMM and its Connection to the Global Water Cycle

The importance of quantitative knowledge of tropical rainfall, its associated latent heating and variability is summarized in the context of the global hydrologic cycle. Much of the tropics is covered by oceans. What land exists, is covered largely by rainforests that are only thinly populated. The only way to adequately measure the global tropical rainfall for climate and general circulation models is from space. The Tropical Rainfall Measuring Mission (TRMM) orbit is inclined 35 degrees leading to good sampling in the tropics and a rapid precession to study the diurnal cycle of precipitation. The precipitation instrument complement consists of the first rain radar to be flown in space (PR), a multi-channel passive microwave sensor (TMI) and a five-channel VIS/IR (VIRS) sensor. The precipitation radar operates at a frequency of 13.6 GHz. The swath width is 220 km, with a horizontal resolution of 4 km and the vertical resolution of 250 m. The minimum detectable signal from the precipitation radar has been measured at - 17 dBZ. The TMI instrument is designed similar to the SSM/I with two important changes. The 22.235 GHz water vapor absorption channel of the SSM/I was moved to 21.3 GHz in order to avoid saturation in the tropics and 10.7 GHz V&H polarized channels were added to expand the dynamic range of rainfall estimates. The resolution of the TMI varies from 4.6 km at 85 GHz to 36 km at 10.7 GHz. The visible and infrared sensor (VIRS) measures radiation at 0.63, 1.6, 3.75, 10.8 and 12.0 microns. The spatial resolution of all five VIRS channels is 2 km at nadir. In addition to the three primary rainfall instruments, TRMM will also carry a Lightning Imaging Sensor (LIS) and a Clouds and the Earth's Radiant Energy System (CERES) instrument. This presentation will focus primarily on the advances in our understanding of tropical rain systems needed to interpret the TRMM data. Global averages, as well as case studies from TRMM radar (PR), the TRMM Microwave Imager (TMI) and Visible and Infrared Sensor (VIRS) will be presented. Comparisons and contrasts among the different sensors will be drawn. Results will also be compared to previous rainfall climatologies generated from the SSM/I instrument. In particular this paper will focus on the synergy between the TRMM radar and passive microwave radiometer and what we have learned from its synergy.

Kummerow, Christian↗

DOE OSTI2026

Reconstructing Quasar Spectra and Measuring the Lyα Forest with SpenderQ

Quasar spectra carry the imprint of foreground intergalactic medium (IGM) through absorption features. In particular, absorption caused by neutral hydrogen gas, the "Lyα forest," is a key spectroscopic tracer for cosmological analyses used to measure cosmic expansion and test physics beyond the standard model. Despite their importance, current methods for measuring Lyα absorption cannot directly derive the intrinsic quasar continuum and make strong assumptions on its shape, thus distorting the measured Lyα clustering. We present SpenderQ , a ML-based approach for directly reconstructing the intrinsic quasar spectra and measuring the Lyα forest from observations. SpenderQ uses the Spender spectrum autoencoder to learn a compact and redshift-invariant latent encoding of quasar spectra, combined with an iterative procedure to identify and mask absorption regions. To demonstrate its performance, we apply SpenderQ to 400,000 synthetic quasar spectra created to validate the Dark Energy Spectroscopic Instrument Year 1 Lyα cosmological analyses. SpenderQ accurately reconstructs the true intrinsic quasar spectra, including the broad Lyβ, Lyα, SiIV, CIV, and CIII emission lines. Redward of Lyα, SpenderQ provides percent-level reconstructions of the true quasar spectra. Blueward of Lyα, SpenderQ reconstructs the true spectra to < 5%. SpenderQ reproduces the shapes of individual quasar spectra more robustly than the current state-of-the-art. We, thus, expect it will significantly reduce biases in Lyα clustering measurements and enable studies of quasars and their physical properties. SpenderQ also provides informative latent variable encodings that can be used to, e.g., classify quasars with Broad Absorption Lines. Overall, SpenderQ provides a new data-driven approach for unbiased Lyα forest measurements in cosmological, quasar, and IGM studies.

Hahn, ChangHoon [Arizona U., Astron. Dept. - Stewa↗

NASA NTRS2023

Neural-Based Compression Scheme for Solar Image Data

Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold decision to make. Stronger compression methods, by distorting the data, can increase data throughput at the cost of accuracy which could affect scientific analysis of the data. On the other hand, preserving subtle details in the compressed data requires a high amount of data to be transferred, reducing the desired gains from compression. In this work, we propose a neural network-based lossy compression method to be used in NASA’s data-intensive imagery missions. We chose NASA’s Solar Dynamics Observatory (SDO) mission which transmits 1.4 terabytes of data each day as a proof of concept for the proposed algorithm. In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image resulting in a better trade-off in rate-distortion (RD) compared to conventional hand-engineered codecs. The RD variational autoencoder used in this work is jointly trained with a channel-dependent entropy model as a shared prior between the analysis and synthesis transforms to make the entropy coding of the latent code more effective. We also studied how optimizing perceptual losses could help our neural compressor to preserve high-frequency details of the data in the reconstructed compressed image. Our neural image compression algorithm outperforms currently-in-use and state-of-the-art codecs such as JPEG and JPEG-2000 in terms of the RD performance when compressing extreme-ultraviolet (EUV) data. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole (CH) detection using our compressed images, and generated consistent segmentations, even at a compression rate of ∼ 0.1 bits per pixel (compared to 8 bits per pixel on the original data) using EUV data from SDO.

Image coding↗