Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptive learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 883 records · Page 49

MO-E-BRC-01: Online Adaptive MR-Guided RT: Workflow and Clinical Implementation

Online adaptive radiation therapy has the potential to ensure delivery of optimal treatment to the patient by accounting for anatomical and potentially functional changes that occur from one fraction to the next and over the course of treatment. While on-line adaptive RT (ART) has been a topic of many publications, discussions, and research, it has until very recently remained largely a concept and not a practical implementation. However, recent advances in on-table imaging, use of deformable image registration for contour generation and dose tracking, faster and more efficient plan optimization, as well as fast quality assurance method has enabled the implementation of ART in the clinic in the past couple of years. The introduction of these tools into routine clinical use requires many considerations and progressive knowledge to understand how processes that have historically taken hours/days to complete can now be done in less than 30 minutes. This session will discuss considerations to perform real time contouring, planning and patient specific QA, as well as a practical workflow and the required resources. Learning Objectives: To understand the difficulties, challenges and available technologies for online adaptive RT. To understand how to implement online adaptive therapy in a clinical environment and to understand the workflow and resources required. To understand the limitations and sources of uncertainty in the online adaptive process I have research funding from ViewRay Inc. and Philips Medical Systems.; R. Kashani, I have research funding from ViewRay Inc. and Philips Medical Systems.; X. Li, Research supported by Elekta Inc.

60 APPLIED LIFE SCIENCES↗

MO-E-BRC-02: MRI-Guided Online Adaptive Radiotherapy: The UCLA Approach to Quality Management

Online adaptive radiation therapy has the potential to ensure delivery of optimal treatment to the patient by accounting for anatomical and potentially functional changes that occur from one fraction to the next and over the course of treatment. While on-line adaptive RT (ART) has been a topic of many publications, discussions, and research, it has until very recently remained largely a concept and not a practical implementation. However, recent advances in on-table imaging, use of deformable image registration for contour generation and dose tracking, faster and more efficient plan optimization, as well as fast quality assurance method has enabled the implementation of ART in the clinic in the past couple of years. The introduction of these tools into routine clinical use requires many considerations and progressive knowledge to understand how processes that have historically taken hours/days to complete can now be done in less than 30 minutes. This session will discuss considerations to perform real time contouring, planning and patient specific QA, as well as a practical workflow and the required resources. Learning Objectives: To understand the difficulties, challenges and available technologies for online adaptive RT. To understand how to implement online adaptive therapy in a clinical environment and to understand the workflow and resources required. To understand the limitations and sources of uncertainty in the online adaptive process I have research funding from ViewRay Inc. and Philips Medical Systems.; R. Kashani, I have research funding from ViewRay Inc. and Philips Medical Systems.; X. Li, Research supported by Elekta Inc.

60 APPLIED LIFE SCIENCES↗

MO-E-BRC-03: Fast Online Replanning Techniques

Online adaptive radiation therapy has the potential to ensure delivery of optimal treatment to the patient by accounting for anatomical and potentially functional changes that occur from one fraction to the next and over the course of treatment. While on-line adaptive RT (ART) has been a topic of many publications, discussions, and research, it has until very recently remained largely a concept and not a practical implementation. However, recent advances in on-table imaging, use of deformable image registration for contour generation and dose tracking, faster and more efficient plan optimization, as well as fast quality assurance method has enabled the implementation of ART in the clinic in the past couple of years. The introduction of these tools into routine clinical use requires many considerations and progressive knowledge to understand how processes that have historically taken hours/days to complete can now be done in less than 30 minutes. This session will discuss considerations to perform real time contouring, planning and patient specific QA, as well as a practical workflow and the required resources. Learning Objectives: To understand the difficulties, challenges and available technologies for online adaptive RT. To understand how to implement online adaptive therapy in a clinical environment and to understand the workflow and resources required. To understand the limitations and sources of uncertainty in the online adaptive process I have research funding from ViewRay Inc. and Philips Medical Systems.; R. Kashani, I have research funding from ViewRay Inc. and Philips Medical Systems.; X. Li, Research supported by Elekta Inc.

60 APPLIED LIFE SCIENCES↗

Monitoring Fracture Hydromechanical Evolution in the Lab and Field Using Unsupervised Metric Learning

Fractures evolve in time through thermal‐hydraulic‐mechanical‐chemical (THMC) processes that alter their long‐range hydraulic transport properties and modify subsurface behavior and activities. The location of subsurface fractures makes it necessary to use remote sensing techniques such as passive or active seismic monitoring for fracture characterization. In this paper, we develop a machine learning approach to monitor the evolution of fracture properties using passive seismic sources in a laboratory setting and using active seismic monitoring from the Sanford Underground Research Facility in Lead, South Dakota, at a depth of 1.25 km in amphibolite rock during stimulation of natural fractures as well as during induced fracturing. The unsupervised metric learning technique applies tandem neural networks (twin (Siamese) or triplet) with contrastive loss and adaptive margins to track slowly varying systems for which class or similarity labels are not available. The approach adopts locality‐sensitive hashing to divide time‐ordered contiguous data into an arbitrary number of pseudo‐classes. Contrastive‐loss training with many hash bins generates an evolving latent‐space trajectory. This approach enables unsupervised metric learning for seismic data stacks under the condition of contiguous state sampling and slowly varying fracture properties. The displacement discontinuity theory provides a mechanistic foundation for the fracture‐dependent trajectories that are related to relaxation of fractures with time‐dependent specific stiffness responding to changes in stress or fluid saturation.

02 PETROLEUM↗

Single-Net Continual Learning with Progressive Segmented Training

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference. Different from previous approaches with dynamic structures, this work focuses on a single network and model segmentation to prevent catastrophic forgetting. Leveraging the redundant capacity of a single network, model parameters for each task are separated into two groups: one important group which is frozen to preserve current knowledge, and secondary group to be saved (not pruned) for a future learning. A fixed-size memory containing a small amount of previously seen data is further adopted to assist the training. Without additional regularization, the simple yet effective approach of Progressive Segmented Training (PST) successfully incorporates multiple tasks and achieves the state-of-the-art accuracy in the single-head evaluation on CIFAR-10 and CIFAR-100 datasets. Moreover, the segmented training significantly improves computation efficiency in continual learning at the edge.

Du, Xiaocong↗

Integrated Multi Scale Data Analytics and Machine Learning for the Grid; Benchmarking Algorithms and Data Quality Analysis

Machine Learning and Data Analytics are terms which are utilized now ubiquitously throughout grid analytics forums, as a potential solution to the growing big data challenges for the distribution grid. As sensors become inexpensive and common, and communication networks grow, the analytics themselves must adapt and enable consumers and providers to visualize and utilize the data provided effectively. Machine learning is one of the techniques proposed in order to manage this data deluge. This report is a subset of the work in this activity, funded through the DOE Grid Modernization Initiative, to summarize the benchmarking and review of data quality impact on the algorithm sets being developed within each use case area.

42 ENGINEERING↗

Putting Priors in Mixture Density Mercer Kernels

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly infinite dimensional feature space. We describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using predefined kernels. These data adaptive kernels can en- code prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS). The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains template for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic- algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code. The results show that the Mixture Density Mercer-Kernel described here outperforms tree-based classification in distinguishing high-redshift galaxies from low- redshift galaxies by approximately 16% on test data, bagged trees by approximately 7%, and bagged trees built on a much larger sample of data by approximately 2%.

Srivastava, Ashok N.↗

ESM data downscaling: a comparison of super-resolution deep learning models

Abstract Climate projections at fine spatial resolutions are required to conduct accurate risk assessment for critical infrastructure and design adaptation planning. Generating these projections using advanced Earth system models (ESM) requires significant computational resources. To address this issue, various statistical downscaling techniques have been introduced to generate fine-resolution data from coarse-resolution simulations. In this study, we evaluate and compare five deep learning-based downscaling techniques, namely, super-resolution convolutional neural networks, fast super-resolution convolutional neural network ESM, efficient sub-pixel convolutional neural network, enhanced deep residual network (EDRN), and super-resolution generative adversarial network (SRGAN). These techniques are applied to a dataset generated by the Energy Exascale Earth System Model (E3SM), focusing on key surface variables such as surface temperature, shortwave heat flux, and longwave heat flux. Models are trained and validated using paired fine-resolution (0.25 $$^{\circ }$$ ∘ ) and coarse-resolution (1 $$^{\circ }$$ ∘ ) monthly data obtained from a 9-year simulation. Next, blind testing is performed using monthly data obtained from two different years outside of the training and validation set. To evaluate the efficiency of each technique, different statistical metrics are used, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS). The results show that EDRN outperforms other algorithms in terms of PSNR, SSIM, and MSE, but struggles to capture fine-scale features in the data. In contrast, SRGAN, a generative model that uses perceptual loss, excels in capturing fine details at boundaries and internal structures, resulting in lower LPIPS than other methods.

Pawar, Nikhil M. (ORCID:0000000211613289)↗

Unveiling mesoscopic structures in distorted lamellar phases through deep learning-based small angle neutron scattering analysis

Hypothesis: The formation of distorted lamellar phases, distinguished by their arrangement of crumpled, stacked layers, is frequently accompanied by the disruption of long-range order, leading to the formation of interconnected network structures commonly observed in the sponge phase. Nevertheless, traditional scattering functions grounded in deterministic modeling fall short of fully representing these intricate structural characteristics. Our hypothesis posits that a deep learning method, in conjunction with the generalized leveled wave approach used for describing structural features of distorted lamellar phases, can quantitatively unveil the inherent spatial correlations within these phases. Experiments and Simulations: This report outlines a novel strategy that integrates convolutional neural networks and variational autoencoders, supported by stochastically generated density fluctuations, into a regression analysis framework for extracting structural features of distorted lamellar phases from small angle neutron scattering data. To evaluate the efficacy of our proposed approach, we conducted computational accuracy assessments and applied it to the analysis of experimentally measured small angle neutron scattering spectra of AOT surfactant solutions, a frequently studied lamellar system. Findings: The findings unambiguously demonstrate that deep learning provides a dependable and quantitative approach for investigating the morphology of wide variations of distorted lamellar phases. It is adaptable for deciphering structures from the lamellar to sponge phase including intermediate structures exhibiting fused topological features. In conclusion, this research highlights the effectiveness of deep learning methods in tackling complex issues in the field of soft matter structural analysis and beyond.

36 MATERIALS SCIENCE↗

LENS: Learning Enabled Network Synthesis

RTRC and UMD have developed novel machine learning based methods under the ARPA-E DIFFERENTIATE program for rapid acceleration of hypothesis generation in complex architecture design spaces involving both discrete choices of component inclusion and interconnection and continuous parametric decisions. The project named Learning Enabled Network Synthesis (LENS) further demonstrated the developed methods on challenging electrical power converter design problems by identifying the most suitable circuit topologies and simultaneously selecting the most appropriate components to achieve optimized design of power converter with improved performances. We demonstrated that LENS could enable exploration of very large design space of circuit topologies and components by addressing the limitations of conventional design process in non-linear, high switching speed, multi-dimensional power converter design and optimization. The key innovation developed in LENS is the seamless integration of statistical learning and logical reasoning techniques and building on the individual strengths of these techniques for rapid hypothesis discovery. The main component of LENS comprises of: 1) Graph Reasoning Engine (GRE) to enforce composition rules that rapidly reject all discrete architectures that are composed incorrectly and generates an adaptive database of feasible designs which can be used by ML modules, 2) Graph Generative Learning module which is a deep neural network based generative model for graph architectures which can enable design space exploration beyond the dataset generated by the GRE, 3) Graph Reduced Order Model (ROM) for graph domains for accelerating computation of output metrics, and 4) Active learning and Rule Discovery module for sample efficient learning and extracting logical rules from the learned ML models which will be integrated in the GRE to enhance the filtering effectiveness. LENS approach can be applied to any design domains where designs can be represented as multi-attribute graphs. The LENS team integrated the various technical innovations listed above into an optimization pipeline and exercised the optimization pipeline on the converter design problem. The LENS project demonstrated that the developed AI/ML technologies can be used to generate novel converter circuits >45x faster than experts on chosen use-cases. This can enable faster design space exploration and identification of new designs which are not considered by experts due to the increasing design space complexity. This has significant potential impact on the public and energy needs of the country. It is currently estimated that 30% of all electrical powers generated passes through power converters. The future estimate is that 80% of all power generated would be passing through converters. LENS fills a critical gap in this space since by accelerating the design process the designers would be able to generate more efficient converters which can lead to significant energy savings for the country.

42 ENGINEERING↗

Integrating HPC, AI, and Workflows for Scientific Data Analysis: Report from Dagstuhl Seminar 23352

The Dagstuhl Seminar 23352, titled “Integrating HPC, AI, and Workflows for Scientific Data Analysis,” held from August 27 to September 1, 2023, was a significant event focusing on the synergy between High-Performance Computing (HPC), Artificial Intelligence (AI), and scientific workflow technologies. The seminar recognized that modern Big Data analysis in science rests on three pillars: workflow technologies for reproducibility and steering, AI and Machine Learning (ML) for versatile analysis, and HPC for handling large data sets. These elements, while crucial, have traditionally been researched separately, leading to gaps in their integration. The seminar aimed to bridge these gaps, acknowledging the challenges and opportunities at the intersection of these technologies. The event highlighted the complex interplay between HPC, workflows, and ML, noting how ML has increasingly been integrated into scientific workflows, thereby enhancing resource demands and bringing new requirements to HPC architectures, like support for GPUs and iterative computations. The seminar also addressed the challenges in adapting HPC for large-scale ML tasks, including in areas like deep learning, and the need for workflow systems to evolve to leverage ML in data analysis fully. Moreover, the seminar explored how ML could optimize scientific workflow systems and HPC operations, such as through improved scheduling and fault tolerance. A key focus was on identifying prestigious use cases of ML in HPC and understanding their unique, unmet requirements. The stochastic nature of ML and its impact on the reproducibility of data analysis on HPC systems was also a topic of discussion.

97 MATHEMATICS AND COMPUTING↗

Machine learning-based observation-constrained projections reveal elevated global socioeconomic risks from wildfire

Reliable projections of wildfire and associated socioeconomic risks are crucial for the development of efficient and effective adaptation and mitigation strategies. The lack of or limited observational constraints for modeling outputs impairs the credibility of wildfire projections. Here, we present a machine learning framework to constrain the future fire carbon emissions simulated by 13 Earth system models from the Coupled Model Intercomparison Project phase 6 (CMIP6), using historical, observed joint states of fire-relevant variables. During the twenty-first century, the observation-constrained ensemble indicates a weaker increase in global fire carbon emissions but higher increase in global wildfire exposure in population, gross domestic production, and agricultural area, compared with the default ensemble. Such elevated socioeconomic risks are primarily caused by the compound regional enhancement of future wildfire activity and socioeconomic development in the western and central African countries, necessitating an emergent strategic preparedness to wildfires in these countries.

54 ENVIRONMENTAL SCIENCES↗

Contrasting advantages of learning with random weights and backpropagation in non-volatile memory neural networks

Recently, a Cambrian explosion of novel, non-volatile memory (NVM) devices known as memristive devices have inspired effort in building hardware neural networks that learn like the brain. Early experimental prototypes built simple perceptrons from nanosynapses, and recently, fully-connected multi-layer perceptron (MLP) learning systems have been realized. However, while backpropagating learning systems pair well with high-precision computer memories and achieve state-of-the-art performances, this typically comes with a massive energy budget. For future Internet of Things/peripheral use cases, system energy footprint will be a major constraint, and emerging NVM devices may fill the gap by sacrificing high bit precision for lower energy. In this work, we contrast the well known MLP approach with the Extreme Learning Machine (ELM) or NoProp approach, which uses a large layer of random weights to improve the separability of high-dimensional tasks, and is usually considered inferior in a software context. However, we find that when taking device non-linearity into account, NoProp manages to equal hardware MLP system in terms of accuracy. While also using a sign-based adaptation of the delta rule for energy-savings, we find that NoProp can learn effectively with four to six ’bits’ of device analog capacity, while MLP requires eight bit capacity with the same rule. This may allow the requirements for memristive devices to be relaxed in the context of online learning. By comparing the energy footprint of these systems for several candidate nanosynapses, as well as realistic peripherals, we confirm that memristive NoProp systems save energy compared to MLP systems. Lastly, we show that ELM/NoProp systems can achieve better generalization abilities than nanosynaptic MLP systems when paired with pre-processing layers (which do not require backpropagated error). Collectively, these advantages make such systems worthy of consideration in future accelerators or embedded hardware.

97 MATHEMATICS AND COMPUTING↗

Direct Imaging of Extra-Solar Planets in Star Forming Regions: Lessons Learned from a False Positive Around IM Lup

Context. Most exoplanet imagers consist of ground-based adaptive optics coronagraphic cameras which are currently limited in contrast, sensitivity and astrometric precision, but advantageously observe in the near-infrared window (1 5 m). Because of these practical limitations, our current observational aim at detecting and characterizing planets puts heavy constraints on target selection, observing strategies, data reduction, and follow-up. Most surveys so far have thus targeted young systems (1 100 Myr) to catch the putative remnant thermal radiation of giant planets, which peaks in the near-infrared. They also favor systems in the solar neighborhood (d less than 80 pc), which eases angular resolution requirements but also ensures a good knowledge of the distance and proper motion, which are critical to secure the planet status, and enable subsequent characterization. Aims. Because of their youth, it is very tempting to target the nearby star forming regions, which are typically twice as far as the bulk of objects usually combed for planets by direct imaging. Probing these interesting reservoirs sets additional constraints that we review in this paper by presenting the planet search that we initiated in 2008 around the disk-bearing T Tauri star IM Lup, which is part of the Lupus star forming region (140-190 pc). Methods. We show and discuss why age determination, the choice of evolutionary model for both the central star and the planet, precise knowledge of the host star proper motion, relative or absolute (between different instruments) astrometric accuracy (including plate scale calibration), and patience are the key ingredients for exoplanet searches around more distant young stars. Results. Unfortunately, most of the time, precision and perseverance are not paying off: we discovered a candidate companion around IM Lup in 2008, which we report here to be an unbound background object. We nevertheless review in details the lessons learned from our endeavor, and additionally present the best detection limits ever calculated for IM Lup. We also accessorily report on the successful use of innovative data reduction techniques, such as the damped-LOCI and iterative roll subtraction.

D Mawet↗

Learning and tuning fuzzy logic controllers through reinforcements

This paper presents a new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system. In particular, our generalized approximate reasoning-based intelligent control (GARIC) architecture (1) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward neural network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto et al. (1983) to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.

Berenji, Hamid R.↗

FIRE: A Failure-Adaptive RL Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated between edge servers due to user mobility. Reinforcement Learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like AR/VR and real- time obstacle detection. These rare failures, being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. We introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose FIRE-ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove FIRE-ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (FIRE-ImDQL) and actor critic (FIRE-ImACRE) versions of our algorithm to enhance scalability. Here, we extend our framework to accommodate users with varying risk tolerances of rare failure events. Through trace-driven experiments, we show that FIRE reduces edge computing costs compared to vanilla RL and the greedy baseline in the event of failures.

Edge computing↗

Experiments in Neural-Network Control of a Free-Flying Space Robot

Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.

NEURAL NETS↗

HAIMOS Ensemble Forecasts for Intra-day and Day- Ahead GHI, DNI and Ramps

The objective of this research is to develop a hybrid physics-based/data-driven forecast model to improve direct normal and global horizontal irradiance (DNI and GHI) prediction for horizons ranging from 1 to 72 hours. Project objectives also address key gaps in state-of-the-art solar forecasting: accurate probabilistic solar forecasts and the forecasting of large irradiance ramps (ramp onset and magnitude). The proposed model ensembles Numerical Weather Prediction (NWP) forecasts, determinist physics-based algorithms, and new-generation cloud cover products (high-resolution rapid refresh satellite images and Large Eddy Simulations). The result is the Hybrid Adaptive Input Model Objective Selection (HAIMOS) ensemble model. HAIMOS blends state of the art machine learning methodologies with physics-based models for cloud cover and cloud optical depth forecasts. The technical activities followed a two-pronged strategy. First, the preprocessing of data, the selection of inputs to the nonlinear approximators, the type of approximator and objective functions, and post-processing ensembling techniques included in HAIMOS were all optimized adaptively to find the best model for a specific goal (reduce DNI/GHI forecast error, improve the prediction of ramp onset, etc.). Second, a large effort was put in improving cloud identification and the forecast of cloud cover and cloud optical depth. To this end, new-generation cloud parametrization products were developed in this work. These include improved algorithms to assist in cloud identification, cloud classification and cloud parametrization from satellite images – three key factors in the accuracy of 1 to 6-hours irradiance forecasts and prediction of ramp onset. Furthermore, we also included cloud information extracted from high resolution rapid refresh satellite images (GOES-16) and Large Eddy Simulations (LES). LES was used to model the atmosphere in detail over locations of interest and produce cloud optical depth forecasts. Once these data streams were validated, they were used as input data to the HAIMOS forecast. The model was developed using data from several climatologically distinct locations with potential for high solar penetration. In the last year of the project, we conducted a validation campaign according to the guidelines stipulated by the Topic Area 1 project as described in the FOA. This effort brings, for the first time, proven machine-learning methodologies for generating state-of-the-art solar forecasts interweaved with detailed physics-based models for cloud detection, and cloud optical depth forecasts. HAIMOS will generate accurate irradiance probabilistic forecast to assist in reducing solar generation prediction error. Globally optimized solar forecast models are more likely to impact solar energy stakeholders. The goal of this project was to increase the state-of-the-art forecast skill from their present values of 10 to 35%. At the end of the project, we achieved between 30% and 50% forecast skill across a wide range of horizons for both GHI and DNI.

14 SOLAR ENERGY↗