Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Overhead Image”

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.

156 records · Page 9

Parametric binary dissection

Binary dissection is widely used to partition non-uniform domains over parallel computers. This algorithm does not consider the perimeter, surface area, or aspect ratio of the regions being generated and can yield decompositions that have poor communication to computation ratio. Parametric Binary Dissection (PBD) is a new algorithm in which each cut is chosen to minimize load + lambda x(shape). In a 2 (or 3) dimensional problem, load is the amount of computation to be performed in a subregion and shape could refer to the perimeter (respectively surface) of that subregion. Shape is a measure of communication overhead and the parameter permits us to trade off load imbalance against communication overhead. When A is zero, the algorithm reduces to plain binary dissection. This algorithm can be used to partition graphs embedded in 2 or 3-d. Load is the number of nodes in a subregion, shape the number of edges that leave that subregion, and lambda the ratio of time to communicate over an edge to the time to compute at a node. An algorithm is presented that finds the depth d parametric dissection of an embedded graph with n vertices and e edges in O(max(n log n, de)) time, which is an improvement over the O(dn log n) time of plain binary dissection. Parallel versions of this algorithm are also presented; the best of these requires O((n/p) log(sup 3)p) time on a p processor hypercube, assuming graphs of bounded degree. How PBD is applied to 3-d unstructured meshes and yields partitions that are better than those obtained by plain dissection is described. Its application to the color image quantization problem is also discussed, in which samples in a high-resolution color space are mapped onto a lower resolution space in a way that minimizes the color error.

Bokhari, Shahid H.↗

If We Build Them, They Will Run: Automated HPC Apps Deployment and Profiling with eBPF in Cloud

The high performance computing (HPC) community is in a period of transition. The rise of AI/ML coupled with a changing landscape of resources deems portability a new metric of performance, and methods to move between on-premises and cloud environments and assess compatibility are paramount. Here we design and test a strategy for bridging the gap between traditional HPC and Kubernetes environments – first containerizing applications, providing automated orchestration to run studies, and packaging the setup with automated means to assess performance using low overhead eXtended Berkeley Packet Filter (eBPF) programs. We first assess different designs for eBPF collection, demonstrating a tradeoff between number of programs deployed on a node and overhead added. We develop 5 low overhead eBPF programs that combine with streaming ML models to assess CPU, futex, TCP, shared memory, and file access across four different builds of an HPC application for CPU and GPU. We use eBPF data to generate insights into the possible underlying etiology of scaling issues. We then assess compatibility of a well-known benchmark, HPCG, across matrices of micro-architectures and optimization levels (217 containers across 24 instance types and over 7500 runs). We provide to the community 30 applications to deploy in our automated setup and perform a scaling study from 4 to a maximum of 256 nodes for both CPU and GPU applications. Finally, we use our gained knowledge about performance to generate compatibility artifacts that are used by a newly developed Kubernetes controller to intelligently select instance type based on optimizing a figure of merit. Along with insights to scaling in this environment with a collection of applications and templates to work from, we provide an overall strategy for approaching HPC application deployment and image selection based on compatibility in cloud.

Computer science↗

Apodized Pupil Lyot Coronagraphs for arbitrary apertures. V. Hybrid shaped pupil designs for imaging earth-like planets with future space observatories

We introduce a new class of solutions for Apodized Pupil Lyot Coronagraphs (APLC) with segmented aperture telescopes to remove broadband diffracted light from a star with a contrast level of 10{sup 10}. These new coronagraphs provide a key advance to enabling direct imaging and spectroscopy of Earth twins with future large space missions. Building on shaped pupil (SP) apodization optimizations, our approach enables two-dimensional optimizations of the system to address any aperture features such as central obstruction, support structures, or segment gaps. We illustrate the technique with a design that could reach a 10{sup 10} contrast level at 34 mas for a 12 m segmented telescope over a 10% bandpass centered at a wavelength of λ{sub 0} = 500 nm. These designs can be optimized specifically for the presence of a resolved star and, in our example, for stellar angular size up to 1.1 mas. This would allow one to probe the vicinity of Sun-like stars located beyond 4.4 pc, therefore, fully retiring this concern. If the fraction of stars with Earth-like planets is η{sub ⊕}=0.1, with 18% throughput, assuming a perfect, stable wavefront and considering photon noise only, 12.5 exo-Earth candidates could be detected around nearby stars with this design and a 12 m space telescope during a five-year mission with two years dedicated to exo-Earth detection (one total year of exposure time and another year of overheads). Our new hybrid APLC/SP solutions represent the first numerical solution of a coronagraph based on existing mask technologies and compatible with segmented apertures, and that can provide contrast compatible with detecting and studying Earth-like planets around nearby stars. They represent an important step forward toward enabling these science goals with future large space missions.

79 ASTRONOMY AND ASTROPHYSICS↗

Acoustic Phased Array Quantification of Quiet Technology Demonstrator 3 Advanced Inlet Liner Noise Component

Acoustic phased array flyover noise measurements were acquired as part of the Boeing 737 MAX-7 NASA Advanced Inlet Liner segment of the Quiet Technology Demonstrator 3 (QTD3) flight test program. This paper reports on the processes used for separating and quantifying the engine inlet, exhaust and airframe noise source components and provides sample phased array-based comparisons of the component noise source levels associated with the inlet liner treatment configurations. Full scale flyover noise testing of NASA advanced inlet liners was conducted as part of the Quiet Technology Demonstrator 3 flight test program in July and August of 2018. Details on the inlet designs and testing are provided in the companion paper of Reference 1. The present paper provides supplemental details relating to the acoustic phased array portion of the analyses provided in Ref. 1. In brief, the test article was a Boeing 737MAX-7 aircraft with a modified right hand (starboard side) engine inlet, which consisted of either a production inlet liner, a NASA designed inlet liner or a simulated hard wall configuration (accomplished by applying speed tape over the inlet acoustic treatment areas). In all three configurations, the engine forward fan case acoustic panel was replaced with a unperforated (hardwall) panel. No other modifications to any other acoustic treatment areas were made. The left hand (port side) engine was a production engine and was flown at idle thrust for all measurements in order to isolate the effects of the inlet liners to the right hand engine. As described in Ref. 1, the NASA inlet treatment consists of laterally cut slots (cut perpendicular to the flow direction) which are designed to reduce excrescence drag while maintaining or exceeding the liner acoustic noise reduction capabilities. The NASA inlet liner consists of a Multi-Degree of Freedom (MDOF) design with two breathable septum layers inserted into each honeycomb cell [1]. The aircraft noise measurements were acquired for both takeoff (flaps 1 setting, gear up) and approach (flaps 30 gear up and gear down) configurations. The inlet and flight test configurations are summarized in Table 1. Table 1: Inlet Treatment and Flight Configurations Inlet Forward Fan Case Aircraft Production Hardwall Flaps 1, gear up; flaps 30 gear up; flaps 30 gear down NASA Hardwall Flaps 1, gear up; flaps 30 gear up; flaps 30 gear down Hardwall Hardwall Flaps 1, gear up; flaps 30 gear up; flaps 30 gear down III.Test Description and Hardware The flight testing was conducted at the Grant County airport in Moses Lake, WA, between 27 July and 6 August 2018. The noise measurement instrumentation included 8 flush dish microphones arranged in a noise certification configuration as well as an 840 microphone phased array. The flush dish microphones were used to quantify the levels and differences in levels between the various inlet treatments. The phased array was used to separate and quantify the narrowband (tonal) and broadband noise component levels from the engine inlet/exhaust and from the airframe. Phased array extraction of the broadband component was critical to this study because it allowed for the separation of the inlet component from the total airplane level noise even when it was significantly below the total level. Figure 1 provides an overview of the phased array microphone layout as well as a detailed image of an individual phased array microphone mounted in a plate holder (the microphone sensor is the dot in the center of the plate). The ground plane ensemble array microphones (referred to as “ensemble array” in this paper) were mounted in plates with “flower petal” edges designed to minimize edge scattering effects. Fig. 1 Flyover test microphone layout. The phased array configuration was the result of a progressive development of concepts originally implemented in Ref. 2 and refined over the following years, consisting namely of multiple multi-arm logarithmic spiral subarrays designed to cover overlapping frequency ranges and optimized for various aircraft emission angles. For the present case, the signals from all 840 microphones were acquired on a single system. The 840 microphones were parsed into 11 primary subarray sets spanning from smallest to largest aperture size and labeled accordingly as “a, b, …, k”, where “a” corresponds to the smallest fielded subarray and “k” corresponds to the largest aperture subarray. The apertures ranged from approximately 10 ft to 427 ft in size (in the flight direction) with the subarrays consisting of between 215 and 312 microphones. Figure 2 shows three such subarrays, k, h and a. As done in Ref. 2, microphones were shared between subarrays in order to reduce total channel count. Fig. 2 Sample subarray sizes (20° from overhead – refer to Figure 3a discussion). In addition to the above, each of the 11 primary subarray sets consisted of four subarrays optimized to provide near equivalent array spatial resolution in both the flight and lateral directions within 30 degrees of overhead (i.e., airplane directly above the center of the array), namely, at angles  of 0, ±10, ±20 and ±30 degrees relative to overhead where angle  is defined as shown in Figure 3a. This allowed for optimized aircraft noise measurements from 60 to 120 degree emission angle.6 An example of this pletharray design is shown in Figure 3b for the k subarray. When the aircraft is at overhead, the microphones indicated by the blue markers are used for beamforming. When the aircraft is at angles ±10 degrees from overhead, both the blue and red colored microphones are used, and so on for the ±20 and ±30 degree aircraft locations. See Ref. 3 for extensive details on pletharray design for aeroacoustic phased array testing. 6 In the discussions that follow, emission angle values are used. These are the angles at the time sound is emitted relative to the engine axis and are calculated based on flight path angle, body aircraft body angle with respect to the relative wind direction, and engine axis angle relative to aircraft body angle.

Brusniak, Leon↗

The Chesapeake Lighthouse and Aircraft Measurements for Satellites (CLAMS) Experiment

NASA has developed an Earth Observing System (EOS) consisting of a series of satellites designed to study global change from space. The EOS flagship is the EOS TERRA satellite, launched in December 1999, equipped with five unique sensors to monitor and study the Earth s heat budget and many of the key controlling variables governing the Earth's climate system. CLAMS, the Chesapeake Lighthouse and Aircraft Measurements for Satellites field campaign was conducted from NASA Wallops Flight Facility and successfully executed over the middle Atlantic eastern seaboard from July 10 August 2, 2001. CLAMS is primarily a shortwave closure experiment designed to validate and improve EOS TERRA satellite data products being derived from three sensors: CERES (Clouds and Earth's Radiant Energy System), MISR (Multi-angle Imaging Spectro-Radiometer) and MODIS (MODerate Resolution Imaging Spectroradiometer). CLAMS is jointly sponsored by the CERES, MISR and MODIS instrument teams and the NASA GEWEX Global Aerosol Climatology Project (GACP). CLAMS primary objectives are to validate satellite-based retrievals of aerosol properties and vertical profiles of radiative flux, temperature and water vapor. Central to CLAMS measurement strategy is the Chesapeake Lighthouse, a stable sea platform located in the Atlantic Ocean, 13 miles east of Virginia Beach near the mouth of the Chesapeake Bay and the site of an ongoing CERES Ocean Validation Experiment (COVE). Six research aircraft were deployed to make detailed measurements of the atmosphere and ocean surface in the vicinity of COVE, over the surrounding ocean, over nearby NOAA buoys and over a few land sites. The measurements are used to validate and provide ground truth for simultaneous products being derived from TERRA data, a key step toward an improved understanding and ability to predict changes in the Earth's climate. One of the two CERES instruments on-board TERRA was programmed for Rotating Azimuth Plane Scans (RAPS) during CLAMS, increasing the CERES coverage over COVE by a factor of 10. Nine coordinated aircraft missions and numerous additional sorties were flown under a variety of atmospheric conditions and aerosol loadings. On one golden day, July 17, all six aircraft flew coordinated patterns, vertically stacked between 100 ft and 65,000 ft over the COVE site as the TERRA satellite orbited overhead. A summary of CLAMS measurement campaign and a description of the platforms and measurements is given.

Smith, William L., Jr.↗

Planetary Rover Simulation for Lunar Exploration Missions

When planning planetary rover missions it is useful to develop intuition and skills driving in, quite literally, alien environments before incurring the cost of reaching said locales. Simulators make it possible to operate in environments that have the physical characteristics of target locations without the expense and overhead of extensive physical tests. To that end, NASA Ames and Open Robotics collaborated on a Lunar rover driving simulator based on the open source Gazebo simulation platform and leveraging ROS (Robotic Operating System) components. The simulator was integrated with research and mission software for rover driving, system monitoring, and science instrument simulation to constitute an end-to-end Lunar mission simulation capability. Although we expect our simulator to be applicable to arbitrary Lunar regions, we designed to a reference mission of prospecting in polar regions. The harsh lighting and low illumination angles at the Lunar poles combine with the unique reflectance properties of Lunar regolith to present a challenging visual environment for both human and computer perception. Our simulator placed an emphasis on high fidelity visual simulation in order to produce synthetic imagery suitable for evaluating human rover drivers with navigation tasks, as well as providing test data for computer vision software development.In this paper, we describe the software used to construct the simulated Lunar environment and the components of the driving simulation. Our synthetic terrain generation software artificially increases the resolution of Lunar digital elevation maps by fractal synthesis and inserts craters and rocks based on Lunar size-frequency distribution models. We describe the necessary enhancements to import large scale, high resolution terrains into Gazebo, as well as our approach to modeling the visual environment of the Lunar surface. An overview of the mission software system is provided, along with how ROS was used to emulate flight software components that had not been developed yet. Finally, we discuss the effect of using the high-fidelity synthetic Lunar images for visual odometry. We also characterize the wheel slip model, and find some inconsistencies in the produced wheel slip behaviour.

Allan, Mark↗

High-Rate Data-Capture for an Airborne Lidar System

A high-rate data system was required to capture the data for an airborne lidar system. A data system was developed that achieved up to 22 million (64-bit) events per second sustained data rate (1408 million bits per second), as well as short bursts (less than 4 s) at higher rates. All hardware used for the system was off the shelf, but carefully selected to achieve these rates. The system was used to capture laser fire, single-photon detection, and GPS data for the Slope Imaging Multi-polarization Photo-counting Lidar (SIMPL). However, the system has applications for other laser altimeter systems (waveform-recording), mass spectroscopy, xray radiometry imaging, high-background- rate ranging lidar, and other similar areas where very high-speed data capture is needed. The data capture software was used for the SIMPL instrument that employs a micropulse, single-photon ranging measurement approach and has 16 data channels. The detected single photons are from two sources those reflected from the target and solar background photons. The instrument is non-gated, so background photons are acquired for a range window of 13 km and can comprise many times the number of target photons. The highest background rate occurs when the atmosphere is clear, the Sun is high, and the target is a highly reflective surface such as snow. Under these conditions, the total data rate for the 16 channels combined is expected to be approximately 22 million events per second. For each photon detection event, the data capture software reads the relative time of receipt, with respect to a one-per-second absolute time pulse from a GPS receiver, from an event timer card with 0.1-ns precision, and records that information to a RAID (Redundant Array of Independent Disks) storage device. The relative time of laser pulse firings must also be read and recorded with the same precision. Each of the four event timer cards handles the throughput from four of the channels. For each detection event, a flag is recorded that indicates the source channel. To accommodate the expected maximum count rate and also handle the other extreme of very low rates occurring during nighttime operations, the software requests a set amount of data from each of the event timer cards and buffers the data. The software notes if any of the cards did not return all the data requested and then accommodates that lower rate. The data is buffered to minimize the I/O overhead of writing the data to storage. Care was taken to optimize the reads from the cards, the speed of the I/O bus, and RAID configuration.

Valett, Susan↗

Simple, Scalable, Script-Based Science Processor (S4P)

The development and deployment of data processing systems to process Earth Observing System (EOS) data has proven to be costly and prone to technical and schedule risk. Integration of science algorithms into a robust operational system has been difficult. The core processing system, based on commercial tools, has demonstrated limitations at the rates needed to produce the several terabytes per day for EOS, primarily due to job management overhead. This has motivated an evolution in the EOS Data Information System toward a more distributed one incorporating Science Investigator-led Processing Systems (SIPS). As part of this evolution, the Goddard Earth Sciences Distributed Active Archive Center (GES DAAC) has developed a simplified processing system to accommodate the increased load expected with the advent of reprocessing and launch of a second satellite. This system, the Simple, Scalable, Script-based Science Processor (S42) may also serve as a resource for future SIPS. The current EOSDIS Core System was designed to be general, resulting in a large, complex mix of commercial and custom software. In contrast, many simpler systems, such as the EROS Data Center AVHRR IKM system, rely on a simple directory structure to drive processing, with directories representing different stages of production. The system passes input data to a directory, and the output data is placed in a "downstream" directory. The GES DAAC's Simple Scalable Script-based Science Processing System is based on the latter concept, but with modifications to allow varied science algorithms and improve portability. It uses a factory assembly-line paradigm: when work orders arrive at a station, an executable is run, and output work orders are sent to downstream stations. The stations are implemented as UNIX directories, while work orders are simple ASCII files. The core S4P infrastructure consists of a Perl program called stationmaster, which detects newly arrived work orders and forks a job to run the appropriate executable (registered in a configuration file for that station). Although S4P is written in Perl, the executables associated with a station can be any program that can be run from the command line, i.e., non-interactively. An S4P instance is typically monitored using a simple Graphical User Interface. However, the reliance of S4P on UNIX files and directories also allows visibility into the state of stations and jobs using standard operating system commands, permitting remote monitor/control over low-bandwidth connections. S4P is being used as the foundation for several small- to medium-size systems for data mining, on-demand subsetting, processing of direct broadcast Moderate Resolution Imaging Spectroradiometer (MODIS) data, and Quick-Response MODIS processing. It has also been used to implement a large-scale system to process MODIS Level 1 and Level 2 Standard Products, which will ultimately process close to 2 TB/day.

Lynnes, Christopher↗

A Multi-Season Study of the Effects of MODIS Sea-Surface Temperatures on Operational WRF Forecasts at NWS Miami, FL

Studies at the Short-term Prediction Research and Transition (SPORT) Center have suggested that the use of Moderate Resolution Imaging Spectroradiometer (MODIS) sea-surface temperature (SST) composites in regional weather forecast models can have a significant positive impact on short-term numerical weather prediction in coastal regions. Recent work by LaCasse et al (2007, Monthly Weather Review) highlights lower atmospheric differences in regional numerical simulations over the Florida offshore waters using 2-km SST composites derived from the MODIS instrument aboard the polar-orbiting Aqua and Terra Earth Observing System satellites. To help quantify the value of this impact on NWS Weather Forecast Offices (WFOs), the SPORT Center and the NWS WFO at Miami, FL (MIA) are collaborating on a project to investigate the impact of using the high-resolution MODIS SST fields within the Weather Research and Forecasting (WRF) prediction system. The project's goal is to determine whether more accurate specification of the lower-boundary forcing within WRF will result in improved land/sea fluxes and hence, more accurate evolution of coastal mesoscale circulations and the associated sensible weather elements. The NWS MIA is currently running WRF in real-time to support daily forecast operations, using the National Centers for Environmental Prediction Nonhydrostatic Mesoscale Model dynamical core within the NWS Science and Training Resource Center's Environmental Modeling System (EMS) software. Twenty-seven hour forecasts are run dally initialized at 0300, 0900, 1500, and 2100 UTC on a domain with 4-km grid spacing covering the southern half of Florida and adjacent waters of the Gulf of Mexico and Atlantic Ocean. Each model run is initialized using the Local Analysis and Prediction System (LAPS) analyses available in AWIPS. The SSTs are initialized with the NCEP Real-Time Global (RTG) analyses at 1/12deg resolution (approx.9 km); however, the RTG product does not exhibit fine-scale details consistent with its grid resolution. SPORT is conducting parallel WRF EMS runs identical to the operational runs at NWS MIA except for the use of MODIS SST composites in place of the RTG product as the initial and boundary conditions over water, The MODIS SST composites for initializing the SPORT WRF runs are generated on a 2-km grid four times daily at 0400, 0700, 1600, and 1900 UTC, based on the times of the overhead passes of the Aqua and Terra satellites. The incorporation of the MODIS SST data into the SPORT WRF runs is staggered such that SSTs are updated with a new composite every six hours in each of the WRF runs. From mid-February to July 2007, over 500 parallel WRF simulations have been collected for analysis and verification. This paper will present verification results comparing the NWS MIA operational WRF runs to the SPORT experimental runs, and highlight any substantial differences noted in the predicted mesoscale phenomena for specific cases.

Case, Jonathan L.↗

Celestial Mapping System for Lunar Surface Mapping and Analytics

Celestial Mapping System (CMS) is a software platform to generate virtual 3D globe for celestial bodies within our solar system. Various layers are built on top of the virtual globe to provide visualization of high resolution imagery, enable precise measurements, build analytical capabilities and broad range of functionalities to assist planetary scientists and mission planners. CMS is built using OpenJDK 11 and will run on a wide variety of platforms such as Linux, Windows, OSX, etc. It has a thick client with less overhead to access hardware resources. This allows features such as terrain profiling and distance calculations to be performed on the client and on the fly. The present focus of CMS is on developing lunar mapping tool kits to provide features such as - 3D first person view with zoom and navigational capabilities, realistic terrain visualization based on LRO data, measurement tools, Apollo landing site annotations, stereoscopic view, elevation profiles, line of sight analysis and many more. The application is developed to provide situational and domain awareness on Lunar surface, planning capabilities for equipment placements and traverse path optimization. As data becomes available, CMS has the capabilities to integrate data sets that change dynamically in real-time, which will be useful for monitoring satellites and remotely-sensed data on Lunar surface. CMS utilizes NASA WorldWind Java library and OpenGL to achieve high-performance rendering of data and measurements, and also adheres to OGC standards. CMS supports importing synthetic features in a variety of 3D, 2D, vector and raster formats. Nomenclature is pulled from USGS Moon IAU2000 database, and lunar parameters are based of the standardized IAU2000 Moon ellipsoid. GDAL (Geospatial Data Abstraction Library) was used to modify and test the accuracy of datasets before integrating into the application. Our high-resolution global elevation model was compared with the LRO LOLA DEM elevation values and tested to ensure accuracy. Celestial Mapping System has several potential use cases for NASA including subsurface lava tubes visualization and analysis, soil analysis, resource visualization and representation on 3D globe.

GIS system↗

Fast Query-Optimized Kernel-Machine Classification

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Mazzoni, Dominic↗

Impact of MODIS High-Resolution Sea-Surface Temperatures on WRF Forecasts at NWS Miami, FL

Over the past few years,studies at the Short-term Prediction Research and Transition (SPoRT) Center have suggested that the use of Moderate Resolution Imaging Spectroradiometer (MODIS) composite sea-surface temperature (SST) products in regional weather forecast models can have a significant positive impact on short-term numerical weather prediction in coastal regions. The recent paper by LaCasse et al. (2007, Monthly Weather Review) highlights lower atmospheric differences in regional numerical simulations over the Florida offshore waters using 2-km SST composites derived from the MODIS instrument aboard the polar-orbiting Aqua and Terra Earth Observing System satellites. To help quantify the value of this impact on NWS Weather Forecast Offices (WFOs), the SPoRT Center and the NWS WFO at Miami, FL (MIA) are collaborating on a project to investigate the impact of using the high-resolution MODIS SST fields within the Weather Research and Forecasting (WRF) prediction system. The scientific hypothesis being tested is: More accurate specification of the lower-boundary forcing within WRF will result in improved land/sea fluxes and hence, more accurate evolution of coastal mesoscale circulations and the associated sensible weather elements. The NWS MIA is currently running the WRF system in real-time to support daily forecast operations, using the National Centers for Environmental Prediction Nonhydrostatic Mesoscale Model dynamical core within the NWS Science and Training Resource Center's Environmental Modeling System (EMS) software; The EMS is a standalone modeling system capable of downloading the necessary daily datasets, and initializing, running and displaying WRF forecasts in the NWS Advanced Weather Interactive Processing System (AWIPS) with little intervention required by forecasters. Twenty-seven hour forecasts are run daily with start times of 0300,0900, 1500, and 2100 UTC on a domain with 4-km grid spacing covering the southern half of Florida and the far western portions of the Bahamas, the Florida Keys, the Straights of Florida, and adjacent waters of the Gulf of Mexico and Atlantic Ocean. Each model run is initialized using the Local Analysis and Prediction System (LAPS) analyses available in AWIPS, invoking the diabatic. "hot-start" capability. In this WRF model "hot-start", the LAPS-analyzed cloud and precipitation features are converted into model microphysics fields with enhanced vertical velocity profiles, effectively reducing the model spin-up time required to predict precipitation systems. The SSTs are initialized with the NCEP Real-Time Global (RTG) analyses at l/12 degree resolution (approx. 9 km); however, the RTG product does not exhibit fine-scale details consistent with its grid resolution. SPoRT is conducting parallel WRF EMS runs identical to the operational runs at NWS MIA in every respect except for the use of MODIS SST composites in place of the RTG product as the initial and boundary conditions over water. The MODIS SST composites for initializing the SPoRT WRF runs are generated on a 2-km grid four times daily at 0400, 0700, 1600, and 1900 UTC, based on the times of the overhead passes of the Aqua and Terra satellites. The incorporation of the MODIS SST composites into the SPoRTWRF runs is staggered such that the 0400UTC composite initializes the 0900 UTC WRF, the 0700 UTC composite initializes the 1500 UTC WRF, the 1600 UTC composite initializes the 2100 UTC WRF, and the 1900 UTC composite initializes the 0300 UTC WRF. A comparison of the SPoRT and Miami forecasts is underway in 2007, and includes quantitative verification of near-surface temperature, dewpoint, and wind forecasts at surface observation locations. In addition, particular days of interest are being analyzed to determine the impact of the MODIS SST data on the development and evolution of predicted sea/land-breeze circulations, clouds, and precipitation. This paper will present verification results comparing the NWS MIA forecasts the SPoRT experimental WRF forecasts, and highlight any substantial differences noted in the predicted mesoscale phenomena.

Case, Jonathan L.↗