Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 1,423 records · Page 79

Exploring Gradient-Based Multi-directional Controls in GANs

Generative Adversarial Networks (GANs) have been widely applied in modeling diverse image distributions. However, despite its impressive applications, the structure of the latent space in GANs largely remains as a black-box, leaving its controllable generation an open problem, especially when spurious correlations between different semantic attributes exist in the image distributions. To address this problem, previous methods typically learn linear directions or individual channels that control semantic attributes in the image space. However, they often suffer from imperfect disentanglement, or are unable to obtain multi-directional controls. Furthermore, in this work, in light of the above challenges, we propose a novel approach that discovers nonlinear controls, which enables multi-directional manipulation as well as effective disentanglement, based on gradient information in the learned GAN latent space. More specifically, we first learn interpolation directions by following the gradients from classification networks trained separately on the attributes, and then navigate the latent space by exclusively controlling channels activated for the target attribute in the learned directions. Empirically, with small training data, our approach is able to gain fine-grained controls over a diverse set of bi-directional and multi-directional attributes, and we showcase its ability to achieve disentanglement significantly better than state-of-the-art methods both qualitatively and quantitatively.

97 MATHEMATICS AND COMPUTING↗

Automated discovery of a robust interatomic potential for aluminum

Machine learning, trained on quantum mechanics (QM) calculations, is a powerful tool for modeling potential energy surfaces. A critical factor is the quality and diversity of the training dataset. Here we present a highly automated approach to dataset construction and demonstrate the method by building a potential for elemental aluminum (ANI-Al). In our active learning scheme, the ML potential under development is used to drive non-equilibrium molecular dynamics simulations with time-varying applied temperatures. Whenever a configuration is reached for which the ML uncertainty is large, new QM data is collected. The ML model is periodically retrained on all available QM data. The final ANI-Al potential makes very accurate predictions of radial distribution function in melt, liquid-solid coexistence curve, and crystal properties such as defect energies and barriers. We perform a 1.3M atom shock simulation and show that ANI-Al force predictions shine in their agreement with new reference DFT calculations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

B/PS bulges in DESI Legacy edge-on galaxies – I. Sample building

ABSTRACT We present the biggest up-to-date sample of edge-on galaxies with boxy/peanut-shaped (B/PS) bulges and X-structures. The sample was prepared using images from the Dark Energy Spectroscopic Instrument (DESI) Legacy catalogue and contains about 2000 galaxies. To find suitable candidates in catalogue, we made the assumption that the residues (original images minus model) of galaxies with B/PS bulges should exhibit a characteristic X-shape. Galaxies with such features were selected by eye and then used as input data for a neural network training, which was applied to a bigger sample of edge-on galaxies. Using the available data and the photometric models from the literature, we investigated the observational and statistical properties of the sample created. Comparing the B/D ratios for galaxies with and without B/PS bulges, we found that the B/D ratio for galaxies from our sample is statistically higher, with typical values in the range ≈0.2–0.5 depending on the decomposition procedure. We studied how the opening angles φ of the X-structure and the length of its rays are distributed in the formed sample and found them to be consistent with previous measurements and predictions from N-body models, e.g. $\varphi \gtrsim 25{^\circ }$, but measured here for a much larger number of galaxies. We found a sharp increase in the B/PS bulge fraction for stellar masses log M⋆ ≳ 10.4, but for edge-on galaxies, which complements the results of previous works. The sample can be used in future work to test various bar models and their relationship with B/PS bulges, as well as to study their stability and evolution.

79 ASTRONOMY AND ASTROPHYSICS↗

Machine learning-based interatomic potential development and phase transition analysis of ferroelectric hafnium dioxide

The ferroelectric phase (𝑃⁢𝑐⁢𝑎⁢2 1 , which is in orthorhombic symmetry) of hafnium dioxide (HfO 2 ) has gained much attention due to its potential applications in nanoelectronics and advanced memory devices. However, its complex phase behavior under external stimuli, such as pressure and temperature, remains a subject of intense investigation. This study focuses on developing a machine learning-based interatomic potential (MLIP) that is trained with data from density-functional theory (DFT) calculations to simulate phase transitions and mechanical properties of HfO 2 . The developed MLIP predicts lattice parameters, equations of state, bulk and shear moduli, and elastic constants that closely align with DFT predictions for several phases and at various pressures. Once validated, the MLIP is used to investigate the phase transitions of ferroelectric HfO 2 (𝑃⁢𝑐⁢𝑎⁢2 1 ) under both isobaric and constant stress conditions at elevated temperatures ranging from 200 to 2500 K. We used several complementary methods, including local symmetry identification, radial distribution function, and x-ray diffraction characterization, to identify interesting phase transitions among several competitive hafnia phases predicted from our simulations. The suggested methods uniformly reveal that under pure deviatoric condition, the system favors a transition from the orthorhombic 𝑃⁢𝑐⁢𝑎⁢2 1 phase to a tetragonal (𝑃⁢4 2 /𝑛⁢𝑚⁢𝑐) phase, whereas a zero stress condition drives the system from the 𝑃⁢𝑐⁢𝑎⁢2 1 phase to another orthorhombic (𝑃⁢𝑏⁢𝑐⁢𝑛) phase. These findings provide crucial insights into stress and temperature-induced phase behavior of hafnia, guiding future experimental and theoretical studies for optimizing hafnia-based ferroelectric devices.

Ferroelectric HfO2↗

Normalizing Flows for Microscopic Many-Body Calculations: An Application to the Nuclear Equation of State

We report that normalizing flows are a class of machine learning models used to construct a complex distribution through a bijective mapping of a simple base distribution. We demonstrate that normalizing flows are particularly well suited as a Monte Carlo integration framework for quantum many-body calculations that require the repeated evaluation of high-dimensional integrals across smoothly varying integrands and integration regions. As an example, we consider the finite-temperature nuclear equation of state. An important advantage of normalizing flows is the ability to build highly expressive models of the target integrand, which we demonstrate enables precise evaluations of the nuclear free energy and its derivatives. Furthermore, we show that a normalizing flow model trained on one target integrand can be used to efficiently calculate related integrals when the temperature, density, or nuclear force is varied. This work will support future efforts to build microscopic equations of state for numerical simulations of supernovae and neutron star mergers that employ state-of-the-art nuclear forces and many-body methods.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Poisson Log-Normal Process for Count Data Prediction

Modeling count data is important in physics and other scientific disciplines, where measurements often involve discrete, non-negative quantities such as photon or neutrino detection events. Traditional parametric approaches can be trained to generate integer-count predictions but may struggle with capturing complex, non-linear dependencies often observed in the data. Gaussian process (GP) regression provides a robust non-parametric alternative to modeling continuous data; however, it cannot generate integer outputs. We propose the Poisson Log-Normal (PoLoN) process, a framework that employs GP to model Poisson log-rates. As in GP regression, our approach relies on the correlations between data points captured via GP kernel structure rather than explicit functional parameterizations. We demonstrate that the PoLoN predictive distribution is Poisson-LogNormal and provide an algorithm for optimizing kernel hyperparameters. Furthermore, we adapt the PoLoN approach to the problem of detecting weak localized signals superimposed on a smoothly varying background - a task of considerable interest in many areas of science and engineering. Our framework allows us to predict the strength, location and width of the detected signals. We evaluate PoLoN's performance using both synthetic and real-world datasets, including the open dataset from CERN which was used to detect the Higgs boson at the Large Hadron Collider. Our results indicate that the PoLoN process can be used as a non-parametric alternative for analyzing, predicting, and extracting signals from integer-valued data.

Saha, Anushka [Rutgers U., Piscataway]↗

Knowledge management: Role of the the Radiation Safety Information Computational Center (RSICC)

The Radiation Safety Information Computational Center (RSICC) at Oak Ridge National Laboratory (ORNL) is an information analysis center that collects, archives, evaluates, synthesizes and distributes information, data and codes that are used in various nuclear technology applications. RSICC retains more than 2,000 software packages that have been provided by code developers from various federal and international agencies. RSICC’s customers (scientists, engineers, and students from around the world) obtain access to such computing codes (source and/or executable versions) and processed nuclear data files to promote on-going research, to ensure nuclear and radiological safety, and to advance nuclear technology. The role of such information analysis centers is critical for supporting and sustaining nuclear education and training programs both domestically and internationally, as the majority of RSICC’s customers are students attending U.S. universities. Additionally, RSICC operates a secure CLOUD computing system to provide access to sensitive export-controlled modeling and simulation (M&S) tools that support both domestic and international activities. This presentation will provide a general review of RSICC’s activities, services, and systems that support knowledge management and education and training in the nuclear field.

Valentine, Timothy↗

The Dark Energy Survey supernova programme: modelling selection efficiency and observed core-collapse supernova contamination

ABSTRACT The analysis of current and future cosmological surveys of Type Ia supernovae (SNe Ia) at high redshift depends on the accurate photometric classification of the SN events detected. Generating realistic simulations of photometric SN surveys constitutes an essential step for training and testing photometric classification algorithms, and for correcting biases introduced by selection effects and contamination arising from core-collapse SNe in the photometric SN Ia samples. We use published SN time-series spectrophotometric templates, rates, luminosity functions, and empirical relationships between SNe and their host galaxies to construct a framework for simulating photometric SN surveys. We present this framework in the context of the Dark Energy Survey (DES) 5-yr photometric SN sample, comparing our simulations of DES with the observed DES transient populations. We demonstrate excellent agreement in many distributions, including Hubble residuals, between our simulations and data. We estimate the core collapse fraction expected in the DES SN sample after selection requirements are applied and before photometric classification. After testing different modelling choices and astrophysical assumptions underlying our simulation, we find that the predicted contamination varies from 7.2 to 11.7 per cent, with an average of 8.8 per cent and an r.m.s. of 1.1 per cent. Our simulations are the first to reproduce the observed photometric SN and host galaxy properties in high-redshift surveys without fine-tuning the input parameters. The simulation methods presented here will be a critical component of the cosmology analysis of the DES photometric SN Ia sample: correcting for biases arising from contamination, and evaluating the associated systematic uncertainty.

79 ASTRONOMY AND ASTROPHYSICS↗

Data Driven Temperature Control of Heat Exchangers

The following poster presents a couple of approaches for temperature control at heat exchanger’s exit. One of the approaches is based on using n-step ahead neural network while the other approach utilizes a combination of control + learning module for temperature control. Designing robust controllers for typical heat exchangers is very challenging primarily because of complexities associated with the synthesis of dynamics of industrial heat exchangers. Even if a dynamics model is synthesized, the accuracy of it would be called into question as there can be lot of unmodeled system dynamics and random noise in input parameters. In many situations, the degree of uncertainty in the model of system being controlled limits the utility of optimal control design. Controller can be manually tuned on the field but it is very difficult to determine manual adjustments that result in overall improvement. These practical challenges call for learning based approaches for temperature control that would result in optimal heat exchanger performance. We utilize the existing mathematical model for air-water system synthesized by Underwood and Crawford for testing our algorithms. Underwood and Crawford developed a model of heating coil by fitting a second-order non-linear equations to measurements of air and water temperature and flow rates obtained from the actual coil. The uncertainties in the model include air and water inlet temperatures and air-flow rate. These uncertainties are modeled as random variables that are sampled from a uniform distribution. The control variable is the water flow rate which is controlled for regulating the air-outlet temperature. Neural networks are frequently used in various literatures for learning time-series. We propose a modified version of neural networks known as n-step ahead neural network that take the state variables and output at time t as input to successfully predict output at time t+n. The variable n is a hyper-parameter which can be optimized based on performance constraints. The n-step ahead neural network was then trained on training data generated from experimental model to high training accuracies. This trained model performed appreciably in its objective to regulate outlet temperature of a heat exchanger. The second approach uses a combination of control and learning module for temperature regulation. The control module used is a proportional controller while the learning module used is steady state neural network. The steady state neural network is used to learn the controller output as a function of random variables and temperature set-point. The proportional controller is then used to compensate for transient behavior of linearized system around various operating points. The algorithm works effectively for temperature regulation as neural network captures the non-linear input-output behavior of closed loop system leaving proportional controller to compensate for steady state errors of a linearized plant. The proposed algorithm’s performances were evaluated against the performance of a PI controller. Further, the robustness of the algorithms were also studied in great detail under small perturbations around tuned parameters of the proposed algorithms.

Sundar, Sreenath↗

An Updated Review of the Solar PV Installation Workforce Literature

In order to develop a well-trained, equitable, and inclusive workforce with high quality jobs, the DOE Solar Energy Technologies Office (SETO) identified a need for analytical context around different PV project characteristics and labor aspects, and how they might impact workforce wellbeing and PV industry growth. To determine the most valuable novel analytical contributions, this work reviews existing literature on solar workforce topics to identify what areas have been studied previously and where gaps remain. Focus areas included the following topics: (1) metrics for solar workforce, deployment, costs, and associated studies capturing aspects such as demographics and regional distribution, (2) solar workforce wellbeing, including employee contracting mechanisms, compensation, occupational safety and health, and community impacts, (3) national and state policies most relevant to the U.S. solar workforce, and (4) ongoing efforts to expand solar workforce participation, including local staffing dynamics, challenges, and relevant strategies.

14 SOLAR ENERGY↗

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗

Quantitative Encapsulation and Homogeneity Assessment of Sol–Gel Based Nuclear Explosive Debris Simulants

Nuclear explosive debris simulants are an important material in training and validating aspects of post-detonation nuclear forensic processes. Realistic simulants should replicate several aspects of nuclear explosive debris such as the size, shape, color, density, and chemical and radiological properties. Silica particles produced via sol-gel synthesis have recently been found to successfully reproduce many of these parameters including the controllable incorporation of radionuclide content. However, to be useful as a benchmarking material for validation and verification of laboratory methodologies, radionuclide content from batch-to-batch must be reproducible. Here, in this work, we explore the variance in radionuclide distribution incorporated into sol-gel benchmarking materials with respect to sample subdivision. Results will help inform the sample sizes required to minimize variance between samples.

36 - MATERIALS SCIENCE↗

Creating ground truth for nanocrystal morphology: a fully automated pipeline for unbiased transmission electron microscopy analysis

Control over colloidal nanocrystal morphology (size, size distribution, and shape) is important for tailoring the functionality of individual nanocrystals and their ensemble behavior. Despite this, traditional methods to quantify nanocrystal morphology are laborious. New developments in automated morphology classification will accelerate these analyses but the assessment of machine learning models is limited by human accuracy for ground truth, causing even unsupervised machine learning models to have inherent bias. Herein, we introduce synthetic image rendering to solve the ground truth problem of nanocrystal morphology classification. By simulating 2D images of nanocrystal shapes via a function of high-dimensional parameter space, we trained a convolutional neural network to link unique morphologies to their simulated parameters, defining nanocrystal morphology quantitatively rather than qualitatively. An automated pipeline then processes, quantitatively defines, and classifies nanocrystal morphology from experimental transmission electron microscopy (TEM) images. Using improved computer vision techniques, 42,650 nanocrystals were identified, assessed, and labeled with quantitative parameters, offering a 600-fold improvement in efficiency over best-practice manual measurements. Further, a classification algorithm was trained with a prediction accuracy of 99.5%, which can successfully analyze a range of concave, convex, and irregular nanocrystal shapes. The resulting pipeline was applied to differentiating two syntheses of nominally cuboidal CsPbBr 3 nanocrystals and uniquely classifying binary nickel sulfide nanocrystal phase based on morphology. This pipeline provides a simple, efficient, and unbiased method to quantify nanocrystal morphology and represents a practical route to construct large datasets with an absolute ground truth for training unbiased morphology-based machine learning algorithms.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

WE-E-BRE-11: New Method to Simulate DNA Damage Using Ionization Cross-Sections and a Geometrical Nucleosome Model

Purpose: To obtain probability distributions of various DNA damage types as a function of the incident electron kinetic energy. Methods: Using Geant4-DNA electron ionization cross-sections, we calculated path length distributions for electrons of energies between 10 eV and 1 MeV, defined as the length between two subsequent interactions. These path lengths were then convolved with probability distributions for the creation of same-strand damage, opposite-strand damage, clustered damage, isolated damage, and same DNA strand target damage. These probability distributions of DNA damage were obtained by a Monte Carlo routine calculating probabilities of interaction in DNA targets inside a nucleosome geometrical model. Results represent the probability of a secondary electron, initially created inside a DNA strand target, of undergoing its next interaction: (1) in the opposite strand (DSB), (2) in the same strand (SSB+), (3) in either the opposite or same-strand (clustered), (4) in the same DNA target (multiple-hit) or (5) more than 10 base pairs away (isolated). Results: Electrons with kinetic energy between 50 and 250 eV have a maximal probability of creating DSB, SSB+, clustered damage and multiple-hits in the same target The probabilities for these damage patterns have values of 2.5%, 4.3%, 6.7% and 5.4%, respectively. Isolated damage is most probable between 700 eV to 900 eV with a probability of 0.2%. Conclusion: We obtained DNA damage probability distributions as a function of electron incident energy. We showed that electrons with kinetic energies between 50 and 250 eV have the highest probability of producing complex forms of DNA damage (DSB, SSB+). We also showed that a double ionization within the same DNA target is the most frequent outcome occurring 5% of the time. It is expected that electron slowing down spectra can be convolved with our formalism to calculate source specific DNA damage patterns. Research grants from governments of Canada and Quebec. PP acknowledges partial support by the CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290)

74 ATOMIC AND MOLECULAR PHYSICS↗

Data from: 'Abiotic influences on continuous conifer forest structure across a subalpine watershed'

This package archives the core data used for analysis and inference in 'Abiotic influences on continuous conifer forest structure across a subalpine watershed' (Worsham et al., 2025). All data were collected in the East River, Washington Gulch, Slate River, and Coal Creek watersheds of Colorado. In the paper, we quantified the relative influence of climate, topographic, edaphic, and geologic factors on conifer stand structure and composition, and their functional relationships, at the watershed scale. We used waveform LiDAR data to derive spatially continuous stand structure metrics. We fused these with a species-level classification map to estimate tree species abundance. We applied generalized additive and generalized boosted models to evaluate the covariability of structural and compositional metrics with abiotic variables. The package contains the essential products required for reproducing our analysis and the tables and figures reported in the publication. The products comprise four classes: (1) geospatial data, (2) tabular data used for inferential analysis, (3) tabular data describing analytical results and performance statistics, and (4) a data user guide. (1) includes discretized waveform LiDAR data, locations and attributes of individual tree crowns, sampling locations and domain boundaries, a canopy height model, and raster files of estimated forest structural and compositional metrics at 100 m grid scale. (2) includes all response and explanatory variable values applied in inferential models. Response variables include conifer forest stand density, basal area, 95th percentile height, quadratic mean diameter, and others. Explanatory variables include climatic water deficit, actual evapotranspiration, elevation, heat load, soil available water content, and others. (3) includes results of training and testing several individual tree detection (ITD) algorithms, as well as inferential modeling results. (4) is a PDF user guide for this data package, including detailed descriptions and data dictionaries for all files. The data package root contains 17 assets: 8 compressed tape archive (.tar.gz) files, 5 comma-separated values (.csv) files, 3 Geographic Tagged Image File Format (GeoTIFF) (.tif) files, and 1 Portable Document Format (.pdf) file. The compressed .tar.gz archives contain ESRI shapefiles (.shp) .tif, compressed LASer (.laz), and .csv files. The archives must first be decompressed using the widely distributed command-line software utility TAR. All other files, including constituent files within the .tar.gz archives, can be opened in the open-source R statistical computing environment. Alternatively, .csv files may also be read in any simple text editor software or Microsoft Excel. Geospatial files including .shp and .tif files can also be opened in GIS software, such as QGIS (open-source) or ESRI ArcGIS (proprietary). The .pdf Data User Guide can be read with Adobe Acrobat Reader or other compatible readers.

2018 NEON and 2025 CHESS Campaigns↗

Framework for Developing Management goals for Species at Risk and Application to Military Installations in the United States

A decision framework for setting management goals for species at risk is presented. Species at risk are those whose potential future rarity is of concern. Listing these species as threatened or endangered could potentially result in significant restrictions to activities in resource management areas in order to maintain those species. The decision framework, designed to foster proactive management, has nine steps: identify species at risk on and near the management area, describe available information and potential information gaps for each species, determine the potential distribution of species and their habitat, select metrics for describing species status, assess the status of local population or metapopulation, conduct threat assessment, set and prioritize management goals, develop species management plans, and develop criteria for ending special species management where possible. This framework will aid resource managers in setting management goals that minimally impact human activities while reducing the likelihood that species at risk will become rare in the near future. The management areas in many of the examples are United States (US) military installations, which are concerned about potential restrictions to military training capacity if species at risk become regulated under the US Endangered Species Act. The benefits of the proactive management set forth in this formal decision framework are that it is impartial, provides a clear procedure, calls for identification of causal relationships that may not be obvious, provides a way to target the most urgent needs, reduces costs, enhances public confidence, and, most importantly, decreases the chance of species becoming more rare.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Data-Driven Machine Learning for Wind Plant Flow Modeling

In this study, we introduce a data-driven machine learning framework for improving the accuracy of wind plant flow models by learning turbulence model corrections based on data from higher-fidelity simulations. First, a high-dimensional PDE-constrained optimization problem is solved using gradient-based optimization with adjoints to determine optimal eddy viscosity fields that improve the agreement of a medium-fidelity Reynolds-Averaged Navier Stokes (RANS) model with large eddy simulations (LES). A supervised learning problem is then constructed to find general, predictive representations of the optimal turbulence closure. A machine learning technique using Gaussian process regression is trained to predict the eddy viscosity field based on local RANS flow field information like velocities, pressures, and their gradients. The Gaussian process is trained on LES simulations of a single turbine and implemented in a wind plant simulation with 36 turbines. We show improvement over the baseline RANS model with the machine learning correction, and demonstrate the ability to provide accurate confidence levels for the corrections that enable future uncertainty quantification studies.

17 WIND ENERGY↗

Aleutian Pribilof Islands Wind Energy Feasibility Study

Under this project, the Aleutian Pribilof Islands Association (APIA) conducted wind feasibility studies for Adak, False Pass, Nikolski, Sand Point and St. George. The DOE funds were also be used to continue APIA's role as project coordinator, to expand the communication network quality between all participants and with other wind interest groups in the state and to provide continued education and training opportunities for regional participants. This DOE project began 09/01/2005. We completed the economic and technical feasibility studies for Adak. These were funded by the Alaska Energy Authority. Both wind and hydro appear to be viable renewable energy options for Adak. In False Pass the wind resource is generally good but the site has high turbulence. This would require special care with turbine selection and operations. False Pass may be more suitable for a tidal project. APIA is funded to complete a False Pass tidal feasibility study in 2012. Nikolski has superb potential for wind power development with Class 7 wind power density, moderate wind shear, bi-directional winds and low turbulence. APIA secured nearly $\$$1M from the United States Department of Agriculture Rural Utilities Service Assistance to Rural Communities with Extremely High Energy Costs to install a 65kW wind turbine. The measured average power density and wind speed at Sand Point measured at 20m (66ft), are 424 W/m2 and 6.7 m/s (14.9 mph) respectively. Two 500kW Vestas turbines were installed and when fully integrated in 2012 are expected to provide a cost effective and clean source of electricity, reduce overall diesel fuel consumption estimated at 130,000 gallons/year and decrease air emissions associated with the consumption of diesel fuel. St. George Island has a Class 7 wind resource, which is superior for wind power development. The current strategy, led by Alaska Energy Authority, is to upgrade the St. George electrical distribution system and power plant. Avian studies in Nikolski and Sand Point have allowed for proper wind turbine siting without killing birds, especially endangered species and bald eagles. APIA continues coordinating and looking for funding opportunities for regional renewable energy projects. An important goal for APIA has been, and will continue to be, to involve community members with renewable energy projects and energy conservation efforts.

17 WIND ENERGY↗