Search NASA⌕ Search

SEARCH · Search NASA

Results for “operator regression”

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 235 records · Page 13

Development and Evaluation of Ensemble Learning-based Environmental Methane Detection and Intensity Prediction Models

The environmental impacts of global warming driven by methane (CH 4 ) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH 4 . Several data-driven machine learning (ML) models were tested to determine how well they identified fugitive CH 4 and its related intensity in the affected areas. Various meteorological characteristics, including wind speed, temperature, pressure, relative humidity, water vapor, and heat flux, were included in the simulation. We used the ensemble learning method to determine the best-performing weighted ensemble ML models built upon several weaker lower-layer ML models to (i) detect the presence of CH 4 as a classification problem and (ii) predict the intensity of CH 4 as a regression problem. The classification model performance for CH 4 detection was evaluated using accuracy, F1 score, Matthew’s Correlation Coefficient (MCC), and the area under the receiver operating characteristic curve (AUC ROC), with the top-performing model being 97.2%, 0.972, 0.945 and 0.995, respectively. The R 2 score was used to evaluate the regression model performance for CH 4 intensity prediction, with the R 2 score of the best-performing model being 0.858. The ML models developed in this study for fugitive CH 4 detection and intensity prediction can be used with fixed environmental sensors deployed on the ground or with sensors mounted on unmanned aerial vehicles (UAVs) for mobile detection.

Majumder, Reek↗

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Revenue estimation for integrated renewable energy and energy storage systems is important to support plant owners or operators’ decisions in battery sizing selection that leads to maximized financial performances. A common approach to optimizing revenues of a hybrid hydro and energy storage system is using mixed-integer linear programming (MILP). Although MILP models can provide accurate production cost estimations, they are typically very computationally expensive. To provide a fast yet accurate first-step information to hydropower plant owners or operators who consider integrating energy storage systems, we propose an innovative approach to predicting optimal revenues of an integrated energy generation and storage system. In this study, we examined the performance of two prediction techniques: Generalized Additive Models (GAMs) and machine learning (ML) models developed based on artificial neural networks (ANN). Predictive equations and models are generated based on optimized solutions from a market participation optimization model, the Conventional Hydropower Energy and Environmental Resource System (CHEERS) model. The two predicting techniques reduce the computational time to evaluate annual revenue for one set of battery configurations from 3 h to 1 to 4 min per run while also being implementable with significantly less data. The model validation prediction errors of developed GAMs and ML models are generally below 5%; for model testing predictions, the ML models consistently outperform the regression equations in terms of root mean square errors. This new approach allows plant owners, operators, or potential investors to quickly access multiple battery configurations under different energy generation and market scenarios. This new revenue prediction method will therefore help reduce the barriers, and thereby promoting the deployment of battery hybridization with existing renewable energy sources.

13 HYDRO ENERGY↗

Demonstration of a Fiber Optic Regression Probe

The capability to provide localized, real-time monitoring of material regression rates in various applications has the potential to provide a new stream of data for development testing of various components and systems, as well as serving as a monitoring tool in flight applications. These applications include, but are not limited to, the regression of a combusting solid fuel surface, the ablation of the throat in a chemical rocket or the heat shield of an aeroshell, and the monitoring of erosion in long-life plasma thrusters. The rate of regression in the first application is very fast, while the second and third are increasingly slower. A recent fundamental sensor development effort has led to a novel regression, erosion, and ablation sensor technology (REAST). The REAST sensor allows for measurement of real-time surface erosion rates at a discrete surface location. The sensor is optical, using two different, co-located fiber-optics to perform the regression measurement. The disparate optical transmission properties of the two fiber-optics makes it possible to measure the regression rate by monitoring the relative light attenuation through the fibers. As the fibers regress along with the parent material in which they are embedded, the relative light intensities through the two fibers changes, providing a measure of the regression rate. The optical nature of the system makes it relatively easy to use in a variety of harsh, high temperature environments, and it is also unaffected by the presence of electric and magnetic fields. In addition, the sensor could be used to perform optical spectroscopy on the light emitted by a process and collected by fibers, giving localized measurements of various properties. The capability to perform an in-situ measurement of material regression rates is useful in addressing a variety of physical issues in various applications. An in-situ measurement allows for real-time data regarding the erosion rates, providing a quick method for empirically anchoring any analysis geared towards lifetime qualification. Erosion rate data over an operating envelope could also be useful in the modeling detailed physical processes. The sensor has been embedded in many regressing media for the purposes of proof-of-concept testing. A gross demonstration of its capabilities was performed using a sanding wheel to remove layers of metal. A longer-term demonstration measurement involved the placement of the sensor in a brake pad, monitoring the removal of pad material associated with the normal wear-and-tear of driving. It was used to measure the regression rates of the combustable media in small model rocket motors and road flares. Finally, a test was performed using a sand blaster to remove small amounts of material at a time. This test was aimed at demonstrating the unit's present resolution, and is compared with laser profilometry data obtained simultaneously. At the lowest resolution levels, this unit should be useful in locally quantifying the erosion rates of the channel walls in plasma thrusters. .

Korman, Valentin↗

Demonstration of a Fiber Optic Regression Probe in a High-Temperature Flow

The capability to provide localized, real-time monitoring of material regression rates in various applications has the potential to provide a new stream of data for development testing of various components and systems, as well as serving as a monitoring tool in flight applications. These applications include, but are not limited to, the regression of a combusting solid fuel surface, the ablation of the throat in a chemical rocket or the heat shield of an aeroshell, and the monitoring of erosion in long-life plasma thrusters. The rate of regression in the first application is very fast, while the second and third are increasingly slower. A recent fundamental sensor development effort has led to a novel regression, erosion, and ablation sensor technology (REAST). The REAST sensor allows for measurement of real-time surface erosion rates at a discrete surface location. The sensor is optical, using two different, co-located fiber-optics to perform the regression measurement. The disparate optical transmission properties of the two fiber-optics makes it possible to measure the regression rate by monitoring the relative light attenuation through the fibers. As the fibers regress along with the parent material in which they are embedded, the relative light intensities through the two fibers changes, providing a measure of the regression rate. The optical nature of the system makes it relatively easy to use in a variety of harsh, high temperature environments, and it is also unaffected by the presence of electric and magnetic fields. In addition, the sensor could be used to perform optical spectroscopy on the light emitted by a process and collected by fibers, giving localized measurements of various properties. The capability to perform an in-situ measurement of material regression rates is useful in addressing a variety of physical issues in various applications. An in-situ measurement allows for real-time data regarding the erosion rates, providing a quick method for empirically anchoring any analysis geared towards lifetime qualification. Erosion rate data over an operating envelope could also be useful in the modeling detailed physical processes. The sensor has been embedded in many regressing media to demonstrate the capabilities in a number of regressing environments. In the present work, sensors were installed in the eroding/regressing throat region of a converging-diverging flow, with the working gas heated to high temperatures by means of a high-pressure arc discharge at steady-state discharge power levels up to 500 kW. The amount of regression observed in each material sample was quantified using a later profilometer, which was compared to the in-situ erosion measurements to demonstrate the efficacy of the measurement technique in very harsh, high-temperature environments.

Korman, Valentin↗

How Wrong Can the Operational AEP Uncertainty Estimate Be When We Ignore the Correlations Between the Uncertainty Components?

Calculations of wind farm annual energy production (AEP) on operational data are essential for a variety of financial transactions during the life of wind plants. The AEP estimate is associated with an uncertainty value, which is calculated by combining contributions connected to on-site measurements, long-term reference measurements, losses, regression, windiness adjustment, and wind resource interannual variability. Although very limited documentation on the topic exists, the conventional approach currently used by the wind energy community to assess the uncertainty connected to the operational AEP estimate assume that the different uncertainty components are uncorrelated and therefore calculates the overall uncertainty with a sum of squares approach. In this analysis, we contrast the traditional technique to estimate the overall AEP uncertainty by ignoring the correlation between its different components with a novel Monte Carlo based approach, which can instead take into account the correlation between different uncertainty categories. We consider monthly operational data from 472 wind farms from the Energy Information Administration (EIA) 923 database to assess the difference between the two approaches. Long-term wind speed data needed for the AEP assessment are taken from three reanalysis products: the Modern-Era Retrospective analysis for Research and Applications v2 (MERRA-2), the European Reanalysis Interim (ERA-interim), and the National Centers for Environmental Prediction v2 (NCEP-2). The results of the Monte Carlo approach show that three pairs of AEP uncertainty components do show a statistically significant correlation: the uncertainty connected with wind resource inter-annual variability is positively correlated with the one related to the windiness correction and negatively correlated with the one due to the regression, and the wind measurement uncertainty is positively correlated with the regression uncertainty. All these correlations, which are found between uncertainty components which are not only part of an operational analysis, but also of a wind resource assessment, are currently ignored in the conventional techniques used as industry standard. We further investigate the causes of these correlations, in terms of common dependencies of different uncertainty components on wind resource variability, number of data points, and quality of the regression between wind speed and energy production data. Next, we quantify the error in the current industry standard technique, in terms of the percentage difference in total uncertainty calculated with the two considered approaches, for all the analyzed wind farms. We find a mean absolute percentage difference of about 6%, with the largest differences being greater than 20%. The data clearly confirm that ignoring the actual correlation between the uncertainty components can lead to large errors in the assessment of the operational AEP uncertainty, and the proposed Monte Carlo approach should be preferred.

Monte Carlo↗

Short-Term Load Forecasting Considering EV Charging Loads with Prediction Interval Evaluation

Short-term load forecasting plays a critical role in power system planning and operation. Along with the electrification of various loads, electricity demands are becoming increasingly hard to predict. Notably, the recent rise in electric vehicles (EVs) has further contributed to this unpredictability. To address this issue, this paper proposes a probabilistic load forecasting strategy utilizing Gaussian process regression, structured in a day-ahead manner. While many works focus on deterministic prediction, probabilistic forecasting offers additional insights into variability and uncertainty, enabling more flexible and reliable operation for power systems. To enhance the accuracy of the load forecasting model, the inputs include features related to EV charging habits as well as commonly used weather information. The load forecasting results are evaluated using various metrics, including conventional ones that assess the accuracy of point forecasts, as well as additional metrics that test the reliability of prediction intervals. The proposed load forecasting method is finally tested on real residential power consumption data and EV charging data sampled from real-world sources. The results prove that the new features can greatly improve the performance of the load forecasting method.

electrical vehicle↗

Dose-Volume Analysis of Predictors for Gastrointestinal Toxicity After Concurrent Full-Dose Gemcitabine and Radiotherapy for Locally Advanced Pancreatic Adenocarcinoma

Purpose: To identify dosimetric predictors for the development of gastrointestinal (GI) toxicity in patients with locally advanced pancreatic adenocarcinoma (LAPC) treated with concurrent full-dose gemcitabine and radiotherapy (GemRT). Methods and Materials: From June 2002 to June 2009, 46 LAPC patients treated with definitive GemRT were retrospectively analyzed. The stomach and duodenum were retrospectively contoured separately to determine their dose-volume histogram (DVH) parameters. GI toxicity was defined as Grade 3 or higher GI toxicity. The follow-up time was calculated from the start of RT to the date of death or last contact. Univariate analysis (UVA) and multivariate analysis (MVA) using Kaplan-Meier and Cox regression models were performed to identify risk factors associated with GI toxicity. The receiver operating characteristic curve and the area under the receiver operating characteristic curve (AUC) were used to determine the best DVH parameter to predict for GI toxicity. Results: Of the patients, 28 (61%) received concurrent gemcitabine alone, and 18 (39%) had concurrent gemcitabine with daily erlotinib. On UVA, only the V{sub 20Gy} to V{sub 35Gy} of duodenum were significantly associated with GI toxicity (all p {<=} 0.05). On MVA, the V{sub 25Gy} of duodenum and the use of erlotinib were independent risk factors for GI toxicity (p = 0.006 and 0.02, respectively). For the entire cohort, the V{sub 25Gy} of duodenum is the best predictor for GI toxicity (AUC = 0.717), and the 12-month GI toxicity rate was 8% vs. 48% for V{sub 25Gy} {<=} 45% and V{sub 25Gy} > 45%, respectively (p = 0.03). However, excluding the erlotinib group, the V{sub 35Gy} is the best predictor (AUC = 0.725), and the 12-month GI toxicity rate was 0% vs. 41% for V{sub 35Gy} {<=} 20% and V{sub 35Gy} > 20%, respectively (p = 0.04). Conclusions: DVH parameters of duodenum may predict Grade 3 GI toxicity after GemRT for LAPC. Concurrent use of erlotinib during GemRT may increase GI toxicity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Discrete generative diffusion models without stochastic differential equations: A tensor network approach

Diffusion models (DMs) are a class of generative machine learning methods that sample a target distribution by transforming samples of a trivial (often Gaussian) distribution using a learned stochastic differential equation. In standard DMs, this is done by learning a “score function” that reverses the effect of adding diffusive noise to the distribution of interest. Here we consider the generalisation of DMs to lattice systems with discrete degrees of freedom, and where noise is added via Markov chain jump dynamics. We show how to use tensor networks (TNs) to efficiently define and sample such “discrete diffusion models” (DDMs) without explicitly having to solve a stochastic differential equation. We show the following: (i) by parametrising the data and evolution operators as TNs, the denoising dynamics can be represented exactly; (ii) the auto-regressive nature of TNs allows to generate samples efficiently and without bias; (iii) for sampling Boltzmann-like distributions, TNs allow to construct an efficient learning scheme that integrates well with Monte Carlo. We illustrate this approach to study the equilibrium of two models with non-trivial thermodynamics, the d = 1 constrained Fredkin chain and the d = 2 Ising model. Published by the American Physical Society 2025

Causer, Luke (ORCID:0000000194243473)↗

Control-Oriented Modeling of Cycle-to-Cycle Combustion Variability at the Misfire Limit in SI Engines

A control-oriented model is presented that can capture the prior-cycle correlation of combustion cycles during conditions with high levels of exhaust gas recirculation (EGR). Combustion events are modeled in discrete time and the dynamic evolution is captured by the residual air, fuel, and inert gas trapped in the combustion chamber. The mathematical formulation of the model is presented together with the calibration procedure to emulate a particular engine operating condition. A cycle-to-cycle system identification methodology is described which allows regressing model parameters from experimental data. Simulations are presented and compared to real engine measurements to show the modeling potential for analysis and control of combustion events.

Maldonado Puente, Bryan↗

Transient Unsaturated Zone Modeling of Radioactive Waste Pits at Los Alamos National Laboratory - 87544 - 18432

Waste disposals at Material Disposal Area G (MDA G) at Los Alamos National Laboratory (LANL) occur primarily in a series of long, rectangular pits into which layers of waste have been emplaced beginning in the late 1950's. MDA G is situated in north-central New Mexico on top of Mesita del Buey, a narrow 3 km long mesa in the Parajito Plateau. The mesa is composed primarily of volcanic tuff from two principle volcanic eruptions in the Jemez Mountains which deposited the Otowi and Tshirege Members of the Bandelier Tuff. The Cerros del Rio Basalt underlay the tuff units and extends down for approximately 200 meters. The water table lies within the basalts at around 300 m below the surface of the mesa. The local climate is temperate and semiarid, averaging around 34 cm of precipitation per year. Ambient subsurface moisture conditions are dry, with water content typically below 10%. During disposal operations, open pits are subject to enhanced infiltration compared to the final covered configuration due to the unvegetated disturbed surface and precipitation events. Additionally, water added to the pits during disposal operations for tasks like waste compaction and dust suppression introduces additional moisture to the system during disposal operations that could potentially provide a pathway for contaminants in the waste zone to migrate through the unsaturated zone. Modeling was conducted using the HYDRUS-2D/3D software to evaluate the spatial extent of saturation changes and fluxes across geologic layer interfaces in the unsaturated zone throughout the life cycle of a waste pit. A general 2-dimensional framework was developed that included a cross section of a waste pit and the underlying geologic units. Several geological layerings were developed to represent the variation across the mesa at Area G. The model was run stochastically for hundreds of realizations to understand how variations in hydraulic parameters (e.g., porosity, saturated hydraulic conductivity, Van Genuchten parameters, etc.) and operational parameters (e.g., pit open period duration, pit depth, initial saturation of the waste zone, etc.) affect the extent of saturation changes and fluxes in the deep unsaturated zone. Distributions for these parameters were developed based on available site data. Results of the unsaturated zone modeling indicate that a significant amount of water can reach the lower unsaturated zone under some circumstances, particularly when the amount of water introduced during pit operations is high. A statistical study of modeling results was performed to develop a regression that describes the variations of water flux in time at the geological layer interfaces. These statistical model results will be used to evaluate solute transport in a future effort. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

The Influence of Land Use and Land Cover Change on Landslide Susceptibility in the Lower Mekong River Basin

The Lower Mekong River Basin in Southeast Asia experiences frequent rainfall-triggered landslides especially during the monsoon season. In this study, the influence of land use and land cover change and other causative factors on landslide susceptibility is evaluated in the Lower Mekong Basin. Frequency ratio analysis is performed to quantify the relationship between LULC change and susceptibility. Detailed landslide inventory maps are used for analysis with yearly LULC maps. The LULC change is used as a contributing variable in a logistic regression-based susceptibility model with other variables including distance to roads, slope, aspect, forest loss, and soil properties. The Receiver Operating Characteristic (ROC) curve and Area Under the Curve are estimated for the model trained by each landslide inventory. The models show good performance, with AUC values ranging from 0.697 to 0.958 and an average AUC equal to 0.820. Both the Frequency Ratio analysis and the Logistic Regression models indicate LULC change from agricultural land to forest has a positive correlation with landslide occurrence. The most significant factors in the models are found to be distance to roads, slope, and aspect. A better understanding of the effects of LULC on landslide susceptibility can be useful for local land and disaster management and for the implementation of LULC as a factor in future susceptibility models. Using datasets that are unique to the Lower Mekong region, this study provides additional insights into the relationship between causative factors and landslide activity to better inform regional and global landslide susceptibility modeling.

River Basin↗

Adaptive Online Multivariate Signal Extraction With Locally Weighted Robust Polynomial Regression

High-frequency, multivariate data collected in real-time and used to control or make decisions regarding a process’ operation often contain some noise and outliers. Thus, a method to extract the signal is needed in order to reduce the number and magnitude of control-based adjustments that are implemented. Such a method must be (i) online, depending only on past and current observations; (ii) fast, producing a smooth value more quickly than the measurement frequency; (iii) robust, ignoring brief bursts of erroneously measured values; (iv) multivariate, ignoring observations that are jointly unusual; (v) adaptive, adjusting to periods of rapid fluctuation in the signal versus periods of stability; and (vi) purely data-driven, not incorporating any information about the process from which the data are collected. Most existing methods are only able to address a subset of these six features. Furthermore, we also require the method to be nonlinear, providing a local nonlinear estimate of the signal. In this work, we propose a novel, real-time signal extraction method based on a local, robust polynomial fit. We demonstrate the performance of our method compared to a state-of-the-art competitor through simulation. For illustration, the methodology is applied to data collected from a reverse osmosis water treatment process.

97 MATHEMATICS AND COMPUTING↗

Comparison of Nodal Risk Formula and MR Lymphography for Predicting Lymph Node Involvement in Prostate Cancer

Purpose: To compare the nodal risk formula (NRF) as a predictor for lymph node (LN) metastasis in patients with prostate cancer with magnetic resonance lymphography (MRL) using Ultrasmall Super-Paramagnetic particles of Iron Oxide (USPIO) and with histology as gold standard. Methods and Materials: Logistic regression analysis was performed with the results of histopathological evaluation of the LN as dependent variable and the nodal risk according to the NRF and the result of MRL as independent input variables. Receiver operating characteristic (ROC) analysis was performed to assess the performance of the models. Results: The analysis included 375 patients. In the single-predictor regression models, the NRF and MRL results were both significantly (p <0.001) predictive of the presence of LN metastasis. In the models with both predictors included, NRF was nonsignificant (p = 0.126), but MRL remained significant (p <0.001). For NRF, sensitivity was 0.79 and specificity was 0.38; for MRL, sensitivity was 0.82 and specificity was 0.93. After a negative MRL result, the probability of LN metastasis is 4% regardless of the NRF result. After a positive MRL, the probability of having LN metastasis is 68%. Conclusions: MRL is a better predictor of the presence of LN metastasis than NRF. Using only the NRF can lead to a significant overtreatment on the pelvic LN by radiation therapy. When the MRL result is available, the NRF is no longer of added value.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

SU-E-J-251: Incorporation of Pre-Therapy 18F-FDG Uptake with CT Texture Features in a Predictive Model for Radiation Pneumonitis Development

Purpose: To determine whether the addition of standardized uptake value (SUV) statistical variables to CT lung texture features can improve a predictive model of radiation pneumonitis (RP) development in patients undergoing radiation therapy. Methods: Anonymized data from 96 esophageal cancer patients (18 RP-positive cases of Grade ≥ 2) were retrospectively collected including pre-therapy PET/CT scans, pre-/posttherapy diagnostic CT scans and RP status. Twenty texture features (firstorder, fractal, Laws’ filter and gray-level co-occurrence matrix) were calculated from diagnostic CT scans and compared in anatomically matched regions of the lung. The mean, maximum, standard deviation, and 50th–95th percentiles of the SUV values for all lung voxels in the corresponding PET scans were acquired. For each texture feature, a logistic regression-based classifier consisting of (1) the average change in that texture feature value between the pre- and post-therapy CT scans and (2) the pre-therapy SUV standard deviation (SUV{sub SD}) was created. The RP-classification performance of each logistic regression model was compared to the performance of its texture feature alone by computing areas under the receiver operating characteristic curves (AUCs). T-tests were performed to determine whether the mean AUC across texture features changed significantly when SUV{sub SD} was added to the classifier. Results: The AUC for single-texturefeature classifiers ranged from 0.58–0.81 in high-dose (≥ 30 Gy) regions of the lungs and from 0.53–0.71 in low-dose (< 10 Gy) regions. Adding SUVSD in a logistic regression model using a 50/50 data partition for training and testing significantly increased the mean AUC by 0.08, 0.06 and 0.04 in the low-, medium- and high-dose regions, respectively. Conclusion: Addition of SUVSD from a pre-therapy PET scan to a single CT-based texture feature improves RP-classification performance on average. These findings demonstrate the potential for more accurate prediction of RP using information from multiple imaging modalities. Supported, in part, by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under grant number T32 EB002103; SGA receives royalties and licensing fees through the University of Chicago for computer-aided diagnosis technology. HA receives royalties through the University of Chicago for computer-aided diagnosis technology.

60 APPLIED LIFE SCIENCES↗

Gaussian process regression constrained by boundary value problems

We develop a framework for Gaussian processes regression constrained by boundary value problems. The framework may be applied to infer the solution of a well-posed boundary value problem with a known second-order differential operator and boundary conditions, but for which only scattered observations of the source term are available. Scattered observations of the solution may also be used in the regression. The framework combines co-kriging with the linear transformation of a Gaussian process together with the use of kernels given by spectral expansions in eigenfunctions of the boundary value problem. Furthermore, it benefits from a reduced-rank property of covariance matrices. We demonstrate that the resulting framework yields more accurate and stable solution inference as compared to physics-informed Gaussian process regression without boundary condition constraints.

42 ENGINEERING↗

Deterministic symbolic regression with derivative information: General methodology and application to equations of state

Symbolic regression methods simultaneously determine the model functional form and the regression parameter values by generating expression trees. Symbolic regression can capture the complexity of real–world phenomena but the use of deterministic optimization for symbolic regression has been limited due to the complexity of the search space of existing formulations. Herein we present a novel deterministic mixed–integer nonlinear programming formulation for symbolic regression that incorporates derivative constraints through auxiliary expression trees. By applying the chain rule to mathematical operations, binary expression trees are capable of representing the calculation of first and second derivatives. We apply this formulation to illustrative examples using derivative information to show increased model discrimination capability. In addition, we perform a case study of a thermodynamic equation of state to gain insight on valid functional forms with thermodynamics–based constraints on the first and second derivatives.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Modern deep neural networks for Direct Normal Irradiance forecasting: A classification approach

The escalating energy demand and the adverse environmental impacts of fossil-fuel use necessitate a shift towards cleaner and renewable alternatives. Concentrated Solar Power (CSP) technology emerges as a promising solution, offering a carbon-free alternative for power generation. The efficiency and profitability of CSP depend on the Direct Normal Irradiance (DNI) component of solar radiation; hence, accurate DNI forecasting can help optimize CSP plants’ operations and performance. The unpredictable nature of weather phenomena, particularly cloud cover, introduces uncertainty into DNI projections. Existing DNI forecasting models use meteorological factors, which are both challenging to estimate numerically over short prediction windows and expensive to model through data at a sufficiently high spatial and temporal resolution. This research addresses the challenge by presenting a novel approach that formulates DNI prediction as a multi-class classification problem, departing from conventional regression-based methods. The primary objective of this classification framework is to identify optimal periods aligning with specific operational thresholds for CSP plants, contributing to enhanced dispatch optimization strategies. We model the DNI classification problem using four advanced deep neural networks – rectified linear unit (ReLU) networks, 1D residual networks (ResNets), bidirectional long short-term memory (BiLSTM) networks, and transformers – achieving accuracies up to 93.5% without requiring meteorological parameters.

14 SOLAR ENERGY↗

"Hidden" hydrothermal technical potential & technoeconomics: Revealing permeability & fluids with more data

Historical hydrothermal estimates have largely relied on temperature or heat flow estimates ignoring the need for natural flowing fluids. More accurate hydrothermal estimates require some indication of permeability and fluids that naturally exist in the subsurface. This paper describes a novel approach that includes proxies of permeability and fluids in hydrothermal estimates by leveraging the relatively data-rich Great Basin. Specifically, nameplate capacities (megawatts) of operating geothermal plants, negative (0 megawatt) locations and 48 geophysical and geologic features are used to used in eXtreme Gradient Boosting (XGBoost) regression to make hydrothermal capacity predictions. Additionally, this work inputs the XGBoost-based hydrothermal predictions into the Renewable Energy Potential (reV) model to quantify technical capacity, its uncertainty and techno-economics. Compared to historical hydrothermal estimates, these predictions adhere to the 37 operating geothermal plants and negative locations. We present a method for subsampling the negative sites to bring the labels into balance that uses the geologic domain knowledge to proportionally represent negatives. Overall, the distributions of the hydrothermal technical capacity and the site levelized cost of energy are respectively much tighter, lower and more accurate than the previous estimates for the Great Basin, as they include geological and geophysical surrogates for permeability and fluids. Percentile (50th and 90th, median and high estimate, respectively) models provide bookends for these metrics.

13 HYDRO ENERGY↗