Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 1,135 records · Page 63

Custom data support for the FAst -physics System Testbed and Research (FASTER) Project

The multi-institution FAst -physics System Testbed and Research (FASTER) project, funded by the DOE Earth System Modeling program, aims to evaluate and improve the parameterizations of fast processes (those involving clouds, precipitation and aerosols) in global climate models, using a combination of numerical prediction models, single column models, cloud resolving models, large-eddy simulations, full global climate model output and ARM active and passive remote sensing and in-situ data. This poster presents the Custom Data Support effort for the FASTER project. The effort will provide tailored datasets, statistics, best estimates and quality control data, as needed and defined by FASTER participants, for use in evaluating and improving parameterizations of fast processes in GCMs. The data support will include custom gridding and averaging, for the model of interest, using high time resolution and pixel level data from continuous ARM observations and complementary datasets. In addition to the FASTER team, these datasets will be made available to the ARM Science Team. Initial efforts with respect to data product development, priorities, availability and distribution are summarized here with an emphasis on cloud, atmospheric state and aerosol properties as observed during the Spring 2000 Cloud IOP and the Spring 2003 Aerosol IOP at the ARM Southern Great Plains site.

54 ENVIRONMENTAL SCIENCES↗

Evaluation of Extreme Weather Impacts on Utility-scale Photovoltaic Plant Performance in the United States

The global energy system is undergoing significant changes, including a shift in energy generating technologies to more renewable energy sources. However, the dependence of renewable energy sources on local environmental conditions could also increase disruptions in service through exposures to compound, extreme weather events. By fusing three diverse datasets (operations and maintenance tickets, weather data, and production data), this analysis presents a novel methodology to identify and evaluate performance impacts arising from extreme weather events across diverse geographical regions. Text analysis of maintenance tickets identified snow, hurricanes, and storms as the leading extreme weather events affecting photovoltaic plants in the United States. Statistical techniques and machine learning were then implemented to identify the magnitude and variability of these extreme weather impacts on site performance. Impacts varied between event and non-event days, with snow events causing the greatest reductions in performance (54.5%), followed by hurricanes (12.6%) and storms (1.1%). Machine learning analysis identified key features in determining if a day is categorized as low performing, such as low irradiance, geographic location, weather features, and site size. The analysis improves our understanding of compound, extreme weather event impacts on photovoltaic systems, which can inform planning activities, especially as the industry continues to expand into new geographic and climatic regions around the world.

14 SOLAR ENERGY↗

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗

Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems

We consider a high-dimensional nonlinear computational model of a dynamical system, parameterized by a vector-valued control parameter, in the presence of uncertainties represented by an uncontrolled parameter modeled by a vector-valued random variable, and possibly with stochastic excitation. The objective is to construct a statistical surrogate model where the input is any deterministic value of the control parameter, and the output is a vector-valued observation of the computational model, which is a random vector whose probability measure is updated using a target dataset. To construct this statistical surrogate model, the stochastic response of the computational model must be built, which is a vector-valued time-discretized stochastic process in high dimension, depending on the control parameter. It is assumed that the computational cost of a single evaluation of the deterministic model is high. For the probabilistic updating, we consider a subset of the components of the observation of the computational model, defined as the “identification observation” of the computational model, for which a small target dataset is available. Therefore, the target dataset is associated with partial observability, corresponding to an incomplete data case. Given a prior probability model of the random control and uncontrolled parameters, a training dataset is constructed, consisting of realizations of the random triplet composed of the stochastic response, the random identification observation, and the random control parameter. Since the computational cost of a single evaluation of the deterministic model is assumed to be large, the training dataset is also of small size. The main challenges in this problem are the high dimensionality, partial observability leading to incomplete data in the target dataset for the identification observation of the computational model (which is not sufficient to identify the computational stochastic responses), and the availability of a small training dataset. To address these challenges, we propose a methodology based on statistical methods for constructing necessary reduced representations, direct probabilistic learning under constraints using probabilistic learning on manifolds (PLoM) constrained by the target dataset, and the use of a weak formulation of the Fourier transform of probability measures. Statistical conditioning is also employed to explore the learned dataset. The constructed predictive statistical surrogate model can be implemented in the context of online computation. Here, we apply this approach to a problem of nonlinear stochastic dynamics in high dimensions within the framework of deformable solids mechanics.

Engineering↗

BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]

The residential and commercial building stock in the United States is responsible for a significant percentage of energy consumption and greenhouse gas emissions. Electrification of end-uses, as well as decarbonizing the electrical grid through renewable energy sources such as solar and wind, constitutes the pathway to zero-emission buildings. Forecasting day-ahead building energy consumption is an integral part of this solution. Currently, specialized forecasting models are hand-made for each individual building, which is time-consuming, expensive, and leads to duplicated efforts. BuildingsBench is a Python software framework for training and comparing generalized machine learning models for universal building load forecasting. This challenge tasks a single foundational model to generalize its forecasts for a wide variety of buildings, across geographic regions, building types, weather patterns, and more. This software provide code for pre-training such models and subsequently evaluating their performance on a suite of hundreds of diverse real and synthetic buildings. BuildingsBench is a platform for: - Large-scale pretraining with the synthetic Buildings-900K dataset for short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock and is extracted from the NREL End-Use Load Profiles database. - Benchmarking on two tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. We provide an index-based PyTorch Dataset for large-scale pretraining, easy data loading for multiple real building energy consumption datasets as PyTorch Tensors or Pandas DataFrames, simple (persistence) to advanced (transformer) baselines, metrics management, and more.

Emami, Patrick↗

The South American Land Data Assimilation System (SALDAS) 5-Year Retrospective Atmospheric Forcing Datasets

The definition and derivation of a 5-year, 0.125deg, 3-hourly atmospheric forcing dataset for the South America continent is described which is appropriate for use in a Land Data Assimilation System and which, because of the limited surface observational networks available in this region, uses remotely sensed data merged with surface observations as the basis for the precipitation and downward shortwave radiation fields. The quality of this data set is evaluated against available surface observations. There are regional difference in the biases for all variables in the dataset, with biases in precipitation of the order 0-1 mm/day and RMSE of 5-15 mm/day, biases in surface solar radiation of the order 10 W/sq m and RMSE of 20 W/sq m, positive biases in temperature typically between 0 and 4 K, depending on region, and positive biases in specific humidity around 2-3 g/Kg in tropical regions and negative biases around 1-2 g/Kg further south.

deGoncalves, Luis Gustavo G.↗

From Escherichia coli mutant 13 C labeling data to a core kinetic model: A kinetic model parameterization pipeline

Kinetic models of metabolic networks offer the promise of quantitative phenotype prediction. The mechanistic characterization of enzyme catalyzed reactions allows for tracing the effect of perturbations in metabolite concentrations and reaction fluxes in response to genetic and environmental perturbation that are beyond the scope of stoichiometric models. In this study, we develop a two-step computational pipeline for the rapid parameterization of kinetic models of metabolic networks using a curated metabolic model and available 13 C-labeling distributions under multiple genetic and environmental perturbations. The first step involves the elucidation of all intracellular fluxes in a core model of E. coli containing 74 reactions and 61 metabolites using 13 C-Metabolic Flux Analysis ( 13 C-MFA). Here, fluxes corresponding to the mid-exponential growth phase are elucidated for seven single gene deletion mutants from upper glycolysis, pentose phosphate pathway and the Entner-Doudoroff pathway. The computed flux ranges are then used to parameterize the same (i.e., k-ecoli74) core kinetic model for E. coli with 55 substrate-level regulations using the newly developed K-FIT parameterization algorithm. The K-FIT algorithm employs a combination of equation decomposition and iterative solution techniques to evaluate steady-state fluxes in response to genetic perturbations. k-ecoli74 predicted 86% of flux values for strains used during fitting within a single standard deviation of 13 C-MFA estimated values. By performing both tasks using the same network, errors associated with lack of congruity between the two networks are avoided, allowing for seamless integration of data with model building. Product yield predictions and comparison with previously developed kinetic models indicate shifts in flux ranges and the presence or absence of mutant strains delivering flux towards pathways of interest from training data significantly impact predictive capabilities. Using this workflow, the impact of completeness of fluxomic datasets and the importance of specific genetic perturbations on uncertainties in kinetic parameter estimation are evaluated.

59 BASIC BIOLOGICAL SCIENCES↗

Comparison of Different Global Information Sources Used in Surface Radiative Flux Calculation: Radiative Properties of the Surface

Direct estimates of surface radiative fluxes that resolve regional and weather-scale variabilty over the whole globe with reasonable accuracy have only become possible with the advent of extensive global, mostly satellite, datasets within the past couple of decades. The accuracy of these fluxes, estimated to be about 10-15 W per square meter is largely limited by the accuracy of the input datasets. The leading uncertainties in the surface fluxes are no longer predominantly induced by clouds but are now as much associated with uncertainties in the surface and near-surface atmospheric properties. This study presents a fuller, more quantitative evaluation of the uncertainties for the surface albedo and emissivity and surface skin temperatures by comparing the main available global datasets from the Moderate-Resolution Imaging Spectroradiometer product, the NASA Global Energy and Water Cycle Experiment Surface Radiation Budget project, the European Centre for Medium-Range Weather Forecasts, the National Aeronautics and Space Administration, the National Centers for Environmental Prediction, the International Satellite Cloud Climatology Project (ISCCP), the Laboratoire de Meteorologie Dynamique, NOAA/NASA Pathfinder Advanced Very High Resolution Radiometer project, NOAA Optimum Interpolation Sea Surface Temperature Analysis and the Tropical Rainfall Measuring Mission (TRMM) Microwave Image project. The datasets are, in practice, treated as an ensemble of realizations of the actual climate such that their differences represent an estimate of the uncertainty in their measurements because we do not possess global truth datasets for these quantities. The results are globally representative and may be taken as a generalization of our previous ISCCP-based uncertainty estimates for the input datasets. Surface properties have the primary role in determining the surface upward shortwave (SW) and longwave (LW) flux. From this study, the following conclusions are obtained. Although land surface albedos in the near near-infrared remain poorly constrained (highly uncertain), they do not cause too much error in total surface SW fluxes; the more subtle regional and seasonal variations associated with vegetation and snow are still on doubt. The uncertainty of the broadband black-sky SW albedo for land surface from this study is about 7%, which can easily induce 5-10 W per square meter uncertainty in (upwelling) surface SW flux estimates. Even though available surface (broadband) LW emissivity datasets differ significantly (3%-5% uncertainty), this disagreement is confined to wavelengths greater than 20 micrometers so that there is little practical effect (1-3 W per square meters) on the surface upwelling LW fluxes. The surface skin temperature is one of two leading factors that cause problems with surface LW fluxes. Even though the differences among the various datasets are generally only 2-4 K, this can easily cause 10-15 W per square meter uncertainty in calculated surface (upwelling) LW fluxes. Significant improvements could be obtained for surface LW flux calculations by improving the retrievals of (in order of decreasing importance): (1) surface skin temperature, (2) surface air and near-surface-layer temperature, (3) column precipitable water amount and (4) broadband emissivity. And for surface SW fluxes, improvements could be obtained (excluding improved cloud treatment) by improving the retrievals of (1) aerosols (from our sensitivity studies but not discussed in this work), and (2) surface (black-sky) albedo, of which, NIR part of the spectrum has much larger uncertainty.

Zhang, Yuanchong↗

An Evaluation of Database Solutions to Spatial Object Association

Object association is a common problem encountered in many applications. Spatial object association, also referred to as crossmatch of spatial datasets, is the problem of identifying and comparing objects in two datasets based on their positions in a common spatial coordinate system--one of the datasets may correspond to a catalog of objects observed over time in a multi-dimensional domain; the other dataset may consist of objects observed in a snapshot of the domain at a time point. The use of database management systems to the solve the object association problem provides portability across different platforms and also greater flexibility. Increasing dataset sizes in today's applications, however, have made object association a data/compute-intensive problem that requires targeted optimizations for efficient execution. In this work, we investigate how database-based crossmatch algorithms can be deployed on different database system architectures and evaluate the deployments to understand the impact of architectural choices on crossmatch performance and associated trade-offs. We investigate the execution of two crossmatch algorithms on (1) a parallel database system with active disk style processing capabilities, (2) a high-throughput network database (MySQL Cluster), and (3) shared-nothing databases with replication. We have conducted our study in the context of a large-scale astronomy application with real use-case scenarios.

99 GENERAL AND MISCELLANEOUS↗

Evaluation of the Potential of NASA Multi-satellite Precipitation Analysis in Global Landslide Hazard Assessment

Landslides are one of the most widespread natural hazards on Earth, responsible for thousands of deaths and billions of dollars in property damage every year. In the U.S. alone landslides occur in every state, causing an estimated $2 billion in damage and 25- 50 deaths each year. Annual average loss of life from landslide hazards in Japan is 170. The situation is much worse in developing countries and remote mountainous regions due to lack of financial resources and inadequate disaster management ability. Recently, a landslide buried an entire village on the Philippines Island of Leyte on Feb 17,2006, with at least 1800 reported deaths and only 3 houses left standing of the original 300. Intense storms with high-intensity , long-duration rainfall have great potential to trigger rapidly moving landslides, resulting in casualties and property damage across the world. In recent years, through the availability of remotely sensed datasets, it has become possible to conduct global-scale landslide hazard assessment. This paper evaluates the potential of the real-time NASA TRMM-based Multi-satellite Precipitation Analysis (TMPA) system to advance our understanding of and predictive ability for rainfall-triggered landslides. Early results show that the landslide occurrences are closely associated with the spatial patterns and temporal distribution of rainfall characteristics. Particularly, the number of landslide occurrences and the relative importance of rainfall in triggering landslides rely on the influence of rainfall attributes [e.g. rainfall climatology, antecedent rainfall accumulation, and intensity-duration of rainstorms). TMPA precipitation data are available in both real-time and post-real-time versions, which are useful to assess the location and timing of rainfall-triggered landslide hazards by monitoring landslide-prone areas while receiving heavy rainfall. For the purpose of identifying rainfall-triggered landslides, an empirical global rainfall intensity-duration threshold is developed by examining a number of landslide occurrences and their corresponding TMPA precipitation characteristics across the world. These early results , in combination with TRMM real-time precipitation estimation system, may form a starting point for developing an operational early warning system for rainfall-triggered landslides around the globe.

Hong, Yang↗

SU-G-BRA-15: Dosimetric Evaluation of Dynamic Tumor Tracking Radiation Therapy Using Digital Phantom: A Study On Margin and Desired Accuracy of Tracking

Purpose: Dynamic tumor tracking radiation therapy can potentially reduce internal margin without prolongation of irradiation time. However, dynamic tumor tracking technique requires an extra margin (tracking margin, TM) for the uncertainty of tumor localization, prediction, and beam repositioning. The purpose of this study was to evaluate a dosimetric impact caused by TM. Methods: We used 4D XCAT to create 9 digital phantom datasets of different tumor size and motion range: tumor diameter TD=(1, 3, 5) cm and motion range MR=(1, 2, 3) cm. For each dataset, respiratory gating (30%–70% phase) and tumor tracking treatment plans were created using 8-field 3D-CRT by 4D dose calculation implemented in RayStation. The dose constraint was based on RTOG0618. For the tracking plan, TMs of (0, 2.5, 5) mm were considered by surrounding a normal setup margin: SM=5 mm. We calculated V20 of normal lung to evaluate the dosimetric impact for each case, and estimated an equivalent TM that affects the same impact on V20 obtained by the gated plan. Results: The equivalent TMs for (TD=1 cm, MR=2 cm), (TD=1 cm, MR=3 cm), (TD=5 cm, MR=2 cm), and (TD=5 cm, MR=3 cm) were estimated as 1.47 mm, 3.95 mm, 1.04 mm, and 2.13 mm, respectively. The larger the tumor size, the equivalent TM became smaller. On the other hand, the larger the motion range, the equivalent TM was found to be increased. Conclusion: Our results showed the equivalent TM changes depending on tumor size and motion range. The tracking plan with TM less than the equivalent TM achieves a dosimetric impact better than the gated plan in less treatment time. This study was partially supported by JSPS Kakenhi and Varian Medical Systems.

60 APPLIED LIFE SCIENCES↗

MINERALIZATION OF RADIOACTIVE WASTES BY FLUIDIZED BED STEAM REFORMING (FBSR): COMPARISONS TO VITREOUS WASTE FORMS, AND PERTINENT DURABILITY TESTING

The Savannah River National Laboratory (SRNL) was requested to generate a document for the Washington State Department of Ecology and the U.S. Environmental Protection Agency that would cover the following topics: (1) A description of the mineral structures produced by Fluidized Bed Steam Reforming (FBSR) of Hanford type Low Activity Waste (LAW including LAWR which is LAW melter recycle waste) waste, especially the cage structured minerals and how they are formed. (2) How the cage structured minerals contain some contaminants, while others become part of the mineral structure (Note that all contaminants become part of the mineral structure and this will be described in the subsequent sections of this report). (3) Possible contaminant release mechanisms from the mineral structures. (4) Appropriate analyses to evaluate these release mechanisms. (5) Why the appropriate analyses are comparable to the existing Hanford glass dataset. In order to discuss the mineral structures and how they bond contaminants a brief description of the structures of both mineral (ceramic) and vitreous waste forms will be given to show their similarities. By demonstrating the similarities of mineral and vitreous waste forms on atomic level, the contaminant release mechanisms of the crystalline (mineral) and amorphous (glass) waste forms can be compared. This will then logically lead to the discussion of why many of the analyses used to evaluate vitreous waste forms and glass-ceramics (also known as glass composite materials) are appropriate for determining the release mechanisms of LAW/LAWR mineral waste forms and how the durability data on LAW/LAWR mineral waste forms relate to the durability data for LAW/LAWR glasses. The text will discuss the LAW mineral waste form made by FBSR. The nanoscale mechanism by which the minerals form will be also be described in the text. The appropriate analyses to evaluate contaminant release mechanisms will be discussed, as will the FBSR test results to date and how they compare to testing performed on LAW glasses. Other details about vitreous waste form durability and impacts of REDuction/OXidation (REDOX) on durability are given in Appendix A. Details about the FBSR process, various pilot scale demonstrations, and applications are given in Appendix B. Details describing all the different leach tests that need to be used jointly to determine the leaching mechanisms of a waste form are given in Appendix C. Cautions regarding the way in which the waste form surface area is measured and in the choice of leachant buffers (if used) are given in Appendix D.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Structure-aware graph neural network based deep transfer learning framework for enhanced predictive analytics on diverse materials datasets

Abstract Modern data mining methods have demonstrated effectiveness in comprehending and predicting materials properties. An essential component in the process of materials discovery is to know which material(s) will possess desirable properties. For many materials properties, performing experiments and density functional theory computations are costly and time-consuming. Hence, it is challenging to build accurate predictive models for such properties using conventional data mining methods due to the small amount of available data. Here we present a framework for materials property prediction tasks using structure information that leverages graph neural network-based architecture along with deep-transfer-learning techniques to drastically improve the model’s predictive ability on diverse materials (3D/2D, inorganic/organic, computational/experimental) data. We evaluated the proposed framework in cross-property and cross-materials class scenarios using 115 datasets to find that transfer learning models outperform the models trained from scratch in 104 cases, i.e., ≈90%, with additional benefits in performance for extrapolation problems. We believe the proposed framework can be widely useful in accelerating materials discovery in materials science.

Chemistry↗

Techno-Economic Simulation Results Using dGeo for EGS-Based District Heating in the Northeastern United States

This dataset presents the results of techno-economic simulations performed using the Distributed Geothermal Market Demand Model (dGeo) to evaluate the feasibility of Enhanced Geothermal Systems (EGS)-based district heating in the Northeastern United States. Developed by the National Renewable Energy Laboratory (NREL), dGeo is a geospatially resolved, bottom-up modeling framework designed to explore the deployment potential of geothermal distributed energy resources. The dataset, created as part of the Cornell EGS Ground-Truthing Project, provides census tract-level data that includes inputs and outputs such as thermal demand, road length, energy prices, geothermal system sizing, annual energy contributions from geothermal and natural gas peaking boilers, system capital costs (CAPEX), operation and maintenance costs (OPEX), and the levelized cost of heat (LCOH). Key simulation parameters include geothermal gradients, measured well depths, production temperatures, and district heating piping lengths based on S1400 neighborhood road lengths. The simulations assume a target bottom hole temperature of 80C and the development of new district heating networks in each census tract.

15 GEOTHERMAL ENERGY↗

Climatological Characteristics of Typical Daily Precipitation

Precipitation is often quantified by the amount that falls over a given period of time but not the rate at which most of it falls or the rate associated with the most frequent events. Here, three metrics are introduced to distill salient characteristics of typical daily precipitation accumulation based on the full distribution of rainfall: rain amount peak (the rain rate at which the most rain falls), rain frequency peak (the most frequent nonzero rain rate), and rain amount width (a measure of the variability of typical precipitation accumulation). These metrics are applied to two observational datasets to describe the climatology of typical daily precipitation accumulation: GPCP 1° daily (October 1996–October 2015) and TMPA 3B42 (January 1998–October 2015). Results show that the rain frequency peak is similar to total rainfall in terms of geographical pattern and seasonal cycle and varies inversely with rain amount width. In contrast, the rain amount peak varies distinctly, reaching maxima on the outer edges of the regions of high total precipitation, and with less seasonal variation. Despite that GPCP and TMPA 3B42 are both merged satellite–gauge precipitation products, they show substantial differences. In particular, the rain amount peak and rain amount width are uniformly greater in TMPA 3B42 compared to GPCP, and there are large discrepancies in their rain frequency distributions (peak and width). Issues relating to model evaluation are highlighted using CESM1 as an illustrative example and underscore the need for observational datasets incorporating measurements of light rain.

Meteorology & Atmospheric Sciences↗

Evaluation and comparison of benchmark QSAR models to predict a relevant REACH endpoint: The bioconcentration factor (BCF)

The bioconcentration factor (BCF) is an important bioaccumulation hazard assessment metric in many regulatory contexts. Its assessment is required by the REACH regulation (Registration, Evaluation, Authorization and Restriction of Chemicals) and by CLP (Classification, Labeling and Packaging). We challenged nine well-known and widely used BCF QSAR models against 851 compounds stored in an ad-hoc created database. The goodness of the regression analysis was assessed by considering the determination coefficient (R{sup 2}) and the Root Mean Square Error (RMSE); Cooper's statistics and Matthew's Correlation Coefficient (MCC) were calculated for all the thresholds relevant for regulatory purposes (i.e. 100 L/kg for Chemical Safety Assessment; 500 L/kg for Classification and Labeling; 2000 and 5000 L/kg for Persistent, Bioaccumulative and Toxic (PBT) and very Persistent, very Bioaccumulative (vPvB) assessment) to assess the classification, with particular attention to the models' ability to control the occurrence of false negatives. As a first step, statistical analysis was performed for the predictions of the entire dataset; R{sup 2}>0.70 was obtained using CORAL, T.E.S.T. and EPISuite Arnot–Gobas models. As classifiers, ACD and log P-based equations were the best in terms of sensitivity, ranging from 0.75 to 0.94. External compound predictions were carried out for the models that had their own training sets. CORAL model returned the best performance (R{sup 2}{sub ext}=0.59), followed by the EPISuite Meylan model (R{sup 2}{sub ext}=0.58). The latter gave also the highest sensitivity on external compounds with values from 0.55 to 0.85, depending on the thresholds. Statistics were also compiled for compounds falling into the models Applicability Domain (AD), giving better performances. In this respect, VEGA CAESAR was the best model in terms of regression (R{sup 2}=0.94) and classification (average sensitivity>0.80). This model also showed the best regression (R{sup 2}=0.85) and sensitivity (average>0.70) for new compounds in the AD but not present in the training set. However, no single optimal model exists and, thus, it would be wise a case-by-case assessment. Yet, integrating the wealth of information from multiple models remains the winner approach. - Highlights: • REACH encourages the use of in silico methods in the assessment of chemicals safety. • The performances of nine BCF models were evaluated on a benchmark database of 851 chemicals. • We compared the models on the basis of both regression and classification performance. • Statistics on chemicals out of the training set and/or within the applicability domain were compiled. • The results show that QSAR models are useful as weight-of-evidence in support to other methods.

54 ENVIRONMENTAL SCIENCES↗

Evaluation of the potential for wake steering for U.S. land-based wind power plants

The wind power plant-wide control strategy known as wake steering involves the misalignment of upstream turbines with the wind direction to deflect wakes away from downstream turbines, increasing net wind plant power production. In this paper, we evaluate the potential of wake steering for U.S. land-based wind power plants. First, we outline a method for simulating and optimizing wake steering control for existing wind plants by combining the flow redirection and induction in steady state wake steering engineering model with the U.S. Wind Turbine Database and Wind Integration National Dataset Toolkit wind resource dataset. Next, to better understand the potential benefits of wake steering beyond those for existing wind plants, we evaluate the relative impacts of turbine specific power, turbine spacing, and mean wind speed on energy gain and levelized cost of energy (LCOE) using a model land-based wind power plant. For a subset of 60 existing wind plants, assuming a constant turbulence intensity of 8%, wake steering was found to yield an average annual energy production (AEP) gain of 0.80%, equivalent to recovering 13.85% of baseline wake losses. Further, we present a linear approximation between baseline wake losses and AEP gains that can be used to estimate wake steering gains for other wind power plants. Highlighting additional benefits of wake steering, for the model wind power plant we found that energy gains from wake steering enabled an approximate 30% reduction in turbine spacing while keeping LCOE constant.

17 WIND ENERGY↗