Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Portability”

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 775 records · Page 43
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

A physiological signal derived from sun-induced chlorophyll fluorescence quantifies crop physiological response to environmental stresses in the U.S. Corn Belt

Sun-induced chlorophyll fluorescence (SIF) measurements have shown unique potential for quantifying plant physiological stress. However, recent investigations found canopy structure and radiation largely control SIF, and physiological relevance of SIF remains yet to be fully understood. This study aims to evaluate whether the SIF-derived physiological signal improves quantification of crop responses to environmental stresses, by analyzing data at three different spatial scales within the U.S. Corn Belt, i.e. experiment plot, field, and regional scales, where ground-based portable, stationary and space-borne hyperspectral sensing systems are used, respectively. We found that, when controlling for variations in incoming radiation and canopy structure, crop SIF signals can be decomposed into non-physiological (i.e. canopy structure and radiation, 60% ~ 82%) and physiological information (i.e. physiological SIF yield, Φ F , 17% ~ 31%), which confirms the contribution of physiological variation to SIF. We further evaluated whether Φ F indicated plant responses under high-temperature and high vapor pressure deficit (VPD) stresses. The plot-scale data showed that Φ F responded to the proxy for physiological stress (partial correlation coefficient, r p = 0.40, p < 0.001) while non-physiological signals of SIF did not respond ( p > 0.1). The field-scale Φ F data showed water deficit stress from the comparison between irrigated and rainfed fields, and Φ F was positively correlated with canopy-scale stomatal conductance, a reliable indicator of plant physiological condition (correlation coefficient r = 0.60 and 0.56 for an irrigated and rainfed sites, respectively). The regional-scale data showed Φ F was more strongly correlated spatially with air temperature and VPD ( r = 0.23 and 0.39) than SIF ( r = 0.11 and 0.34) for the U.S. Corn Belt. The lines of evidence suggested that Φ F reflects crop physiological responses to environmental stresses with greater sensitivity to stress factors than SIF, and the stress quantification capability of Φ F is spatially scalable. Utilizing Φ F for physiological investigations will contribute to improve our understanding of vegetation responses to high-temperature and high-VPD stresses.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Robust and scalable uncertainty estimation with conformal prediction for machine-learned interatomic potentials

Abstract Uncertainty quantification (UQ) is important to machine learning (ML) force fields to assess the level of confidence during prediction, as ML models are not inherently physical and can therefore yield catastrophically incorrect predictions. Established a-posteriori UQ methods, including ensemble methods, the dropout method, the delta method, and various heuristic distance metrics, have limitations such as being computationally challenging for large models due to model re-training. In addition, the uncertainty estimates are often not rigorously calibrated. In this work, we propose combining the distribution-free UQ method, known as conformal prediction (CP), with the distances in the neural network’s latent space to estimate the uncertainty of energies predicted by neural network force fields. We evaluate this method (CP+latent) along with other UQ methods on two essential aspects, calibration, and sharpness, and find this method to be both calibrated and sharp under the assumption of independent and identically-distributed (i.i.d.) data. We show that the method is relatively insensitive to hyperparameters selected, and test the limitations of the method when the i.i.d. assumption is violated. Finally, we demonstrate that this method can be readily applied to trained neural network force fields with traditional and graph neural network architectures to obtain estimates of uncertainty with low computational costs on a training dataset of 1 million images to showcase its scalability and portability. Incorporating the CP method with latent distances offers a calibrated, sharp and efficient strategy to estimate the uncertainty of neural network force fields. In addition, the CP approach can also function as a promising strategy for calibrating uncertainty estimated by other approaches.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2023

FAIR AI models in high energy physics

Abstract The findable, accessible, interoperable, and reusable (FAIR) data principles provide a framework for examining, evaluating, and improving how data is shared to facilitate scientific discovery. Generalizing these principles to research software and other digital products is an active area of research. Machine learning models—algorithms that have been trained on data without being explicitly programmed—and more generally, artificial intelligence (AI) models, are an important target for this because of the ever-increasing pace with which AI is transforming scientific domains, such as experimental high energy physics (HEP). In this paper, we propose a practical definition of FAIR principles for AI models in HEP and describe a template for the application of these principles. We demonstrate the template’s use with an example AI model applied to HEP, in which a graph neural network is used to identify Higgs bosons decaying to two bottom quarks. We report on the robustness of this FAIR AI model, its portability across hardware architectures and software frameworks, and its interpretability.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Scaling neural simulations in STACS

Abstract As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on Simulation Tool for Asynchronous Cortical Streams (STACS), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Efficient DNA sequence compression with neural networks

Abstract Background The increasing production of genomic data has led to an intensified need for models that can cope efficiently with the lossless compression of DNA sequences. Important applications include long-term storage and compression-based data analysis. In the literature, only a few recent articles propose the use of neural networks for DNA sequence compression. However, they fall short when compared with specific DNA compression tools, such as GeCo2. This limitation is due to the absence of models specifically designed for DNA sequences. In this work, we combine the power of neural networks with specific DNA models. For this purpose, we created GeCo3, a new genomic sequence compressor that uses neural networks for mixing multiple context and substitution-tolerant context models. Findings We benchmark GeCo3 as a reference-free DNA compressor in 5 datasets, including a balanced and comprehensive dataset of DNA sequences, the Y-chromosome and human mitogenome, 2 compilations of archaeal and virus genomes, 4 whole genomes, and 2 collections of FASTQ data of a human virome and ancient DNA. GeCo3 achieves a solid improvement in compression over the previous version (GeCo2) of $2.4\%$, $7.1\%$, $6.1\%$, $5.8\%$, and $6.0\%$, respectively. To test its performance as a reference-based DNA compressor, we benchmark GeCo3 in 4 datasets constituted by the pairwise compression of the chromosomes of the genomes of several primates. GeCo3 improves the compression in $12.4\%$, $11.7\%$, $10.8\%$, and $10.1\%$ over the state of the art. The cost of this compression improvement is some additional computational time (1.7–3 times slower than GeCo2). The RAM use is constant, and the tool scales efficiently, independently of the sequence size. Overall, these values outperform the state of the art. Conclusions GeCo3 is a genomic sequence compressor with a neural network mixing approach that provides additional gains over top specific genomic compressors. The proposed mixing method is portable, requiring only the probabilities of the models as inputs, providing easy adaptation to other data compressors or compression-based data analysis tools. GeCo3 is released under GPLv3 and is available for free download at https://github.com/cobilab/geco3.

Silva, Milton↗
DOE OSTI2023

DSPS: Differentiable stellar population synthesis

ABSTRACT Models of stellar population synthesis (SPS) are the fundamental tool that relates the physical properties of a galaxy to its spectral energy distribution (SED). In this paper, we present DSPS: a python package for SPS. All of the functionality in DSPS is implemented natively in the JAX library for automatic differentiation, and so our predictions for galaxy photometry are fully differentiable, and directly inherit the performance benefits of JAX, including portability onto GPUs. DSPS also implements several novel features, such as i) a flexible empirical model for stellar metallicity that incorporates correlations with stellar age, ii) support for the Diffstar model that provides a physically-motivated connection between the star formation history of a galaxy (SFH) and the mass assembly of its underlying dark matter halo. We detail a set of theoretical techniques for using autodiff to calculate gradients of predictions for galaxy SEDs with respect to SPS parameters that control a range of physical effects, including SFH, stellar metallicity, nebular emission, and dust attenuation. When forward modelling the colours of a synthetic galaxy population, we find that DSPS can provide a factor of 5 speed-up over standard SPS codes on a CPU, and a factor of 300-400 on a modern GPU. When coupled with gradient-based techniques for optimization and inference, DSPS makes it practical to conduct expansive likelihood analyses of simulation-based models of the galaxy–halo connection that fully forward model galaxy spectra and photometry.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Optimizing infrasound observations for sample return capsule re-entry: Insights from OSIRIS-REx and Hayabusa2

The atmospheric entry of meteoroids presents a rare and unpredictable phenomenon, posing challenges for systematic observation and detailed characterization. Such events are nonetheless critical for advancing understanding of acoustic wave propagation, atmospheric structure, and entry dynamics. In contrast, sample return capsules (SRCs) from space missions follow well constrained re-entry trajectories, enabling planned observations of shock wave generation and propagation under controlled conditions. This study compares two SRC atmospheric entries, Hayabusa2 in 2020 and OSIRIS-REx in 2023, to assess how different infrasound array configurations influence shock wave detection and trajectory validation. Hayabusa2’s re-entry was monitored using a distributed network of 28 portable infrasound sensors across seven arrays in Woomera, Australia, permitting three-dimensional reconstruction of the trajectory and analysis of wave characteristics. For OSIRIS-REx, a compact four-sensor array deployed near Eureka Airport provided trajectory confirmation through arrival-time differences and back-azimuth estimates. Spectral and waveform analyses revealed differences in signal properties associated with variations in entry angle and velocity. The results illustrate both the strengths and the limitations of the deployed array configurations. The dense and distributed arrays during Hayabusa2’s re-entry enabled detailed trajectory reconstruction, whereas the compact array at Eureka primarily provided confirmation of signal coherence and back-azimuth consistency. These case studies highlight that even relatively small arrays, if located close to the predicted ground track, can still capture useful information on arrival direction and timing. Such insights provide practical guidance for planning future observational campaigns of SRC returns and other controlled atmospheric entries, and may also inform approaches to opportunistic observations of meteoroid events and other atmospheric acoustic phenomena.

celestial mechanics: orbit determination↗
DOE OSTI2025

StarDICE III: characterization of the photometric instrument with a collimated beam projector

The measurement of Type Ia supernovae magnitudes provides cosmological distances, which constrain dark energy parameters. Current and upcoming large photometric surveys require improved photometric calibration precision to reduce systematic uncertainties in cosmological constraints. The StarDICE experiment aims to establish accurate broad-band flux references for these surveys, targeting sub-percent precision in magnitude measurements. Achieving this requires precise filter bandpass measurements for both StarDICE and survey instruments with sub-nanometre accuracy. To this end, we developed the Collimated Beam Projector (CBP), an optical device for calibrating the throughput of astronomical telescopes and their filters. The CBP uses a tunable laser source and a reversed telescope to emit a parallel monochromatic light beam, continuously monitored in flux and wavelength. The CBP output flux is measured with a large-area photodiode calibrated relative to a NIST photodiode. Using CBP measurements, we derive the StarDICE telescope throughput and filter transmissions, anchoring them to NIST’s absolute calibration. After analysing systematic uncertainties, we achieved sub-nanometre accuracy for filter central wavelengths, measured filter transmission with ~0.5 per cent precision per 1 nm bin, and detected out-of-band leakages at a relative level of 10 –4 ⁠. Furthermore, we synthesized equivalent transmission for full pupil illumination from four sampled positions in the StarDICE telescope mirror, with ~0.2 nm accuracy for central wavelengths and 7 mmag for broad-band fluxes. This demonstrates our ability to characterize telescope throughput down to the millimagnitude, paving the way for future developments, such as the Rubin-CBP for measuring the LSST at Vera Rubin Observatory, and a portable CBP version for in-situ transmission monitoring.

Calibration↗
DOE OSTI2026

Efficient many-jet event generation with flow matching

We apply for the first time, to the best of our knowledge, the flow matching method to the problem of phase-space sampling for event generation in high-energy collider physics. By training the model to remap the random numbers used to generate the momenta and helicities of the scattering matrix elements as implemented in the portable partonic event generator pepper, we find substantial efficiency improvements in the studied processes. We focus our study on the highest final-state multiplicities in Drell-Yan and top-antitop pair production used in simulated samples for the Large Hadron Collider, which computationally are the most relevant ones. We find that the unweighting efficiencies improve by factors of 184 and 25, respectively, when compared to the standard approach of using a vegas-based optimization. We also compare continuous normalizing flows trained with flow matching against the previously studied normalizing flows based on coupling layers and find that the former leads to better results, faster training and a better scaling behavior across the studied multiplicity range, while the latter evaluate faster. When combining the advantages of both methods using the regflow approach, we find parton-level unweighted event generation walltime gains of about a factor of 10 at the highest final-state multiplicities.

Bothmann, E. [CERN; Gottingen U.] (ORCID:000000016↗
DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗
DOE OSTI2020

YbH + formation in an ytterbium ion trap

The trapped 171 Yb + ion is a promising candidate for portable atomic clock applications. However, with buffer-gas cooled ytterbium ions, the ions can be pumped into a low-lying 2 F 7 / 2 state or form YbH + molecules. These dark states reduce the fluorescence signal from the ions and can degrade the clock stability. In this work, we study the dynamics of the populations of the 2 F 7 / 2 state and YbH + molecules under different operating conditions of our 171 Yb + ion system. Our study indicates that 2 F 7 / 2 -state ions can form YbH + molecules through interactions with hydrogen gas. As observed previously, dissociation of YbH + is observed at wavelengths around 369 nm. We also demonstrate YbH+ dissociation using 405 nm light. Moreover, we show that the population in the dark states can be limited by using a single repump laser at 935 nm. Our study provides insights into the molecular formation in a trapped ion system.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2022

High-Fidelity Ion State Detection Using Trap-Integrated Avalanche Photodiodes

Integrated technologies greatly enhance the prospects for practical quantum information processing and sensing devices based on trapped ions. High-speed and high-fidelity ion state readout is critical for any such application. Integrated detectors offer significant advantages for system portability and can also greatly facilitate parallel operations if a separate detector can be incorporated at each ion-trapping location. Here, we demonstrate ion quantum state detection at room temperature utilizing single-photon avalanche diodes (SPADs) integrated directly into the substrate of silicon ion trapping chips. Furthermore, we detect the state of a trapped Sr + ion via fluorescence collection with the SPAD, achieving 99.92(1)% average fidelity in 450 μs, opening the door to the application of integrated state detection to quantum computing and sensing utilizing arrays of trapped ions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Environmental cell for in situ X-ray synchrotron micro-CT imaging with simultaneous acoustic measurements

Synchrotron radiation provides the necessary spatial and temporal resolution for non-invasive operando studies of dynamic processes under complex environmental conditions. Here a new environmental cell for simultaneous in situ dynamic X-ray imaging and measuring acoustic properties of geological samples is presented. The primary purpose of this cell is to study gas-hydrate formation in porous geo-materials and its influence on their acoustic properties. The cell is designed for cylindrical samples of 9 mm in diameter, confining and pore pressures up to 12 MPa, and temperatures from –20°C to room temperature. The cell is portable and can be easily assembled and operated at different X-ray sources. This cell enables a wide range of experiments studying physical/chemical processes in the Earth subsurface that change the mechanical properties of rocks (geochemical reactions, phase transitions, etc.).

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

On-Chip Batteries as Distributed Energy Sources in Heterogeneous 2.5D/3D Integrated Circuits

Energy efficiency in digital systems faces challenges due to the constraints imposed by small-scale transistors. Moreover, the growing demand for portable consumer electronics necessitates the use of compact energy sources. To address these challenges, heterogeneous 3D IC technology has emerged as a promising solution for the former. Regarding the latter, we propose the concept of distributed batteries within a heterogeneous 3D IC. This approach involves utilizing multiple smaller batteries with different specifications among different modules of 3D ICs. This approach optimizes performance and overcomes limitations associated with both 3D ICs and conventional power delivery methods. Distributed batteries play a vital role in effectively managing the heat generated by energy sources and modules within a 3D IC. Furthermore, they contribute to achieving a uniform distribution of heat throughout the entire structure, which ultimately ensures the optimal performance of the batteries and modules. The simulation results indicate a 40 percent enhancement in achieving a more even distribution of generated heat. Additionally, the proposed distributed battery techniques improve power delivery, enhance reliability, and enable optimized voltage regulation while improving efficiency. In addition to the primary benefits, alternative configurations of the proposed approach can offer extra energy storage capacity and act as efficient electromagnetic shields, resulting in an impressive reduction of external electromagnetic noises by 60 dB.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

TRIM: AI Guided Random Number Generation for Resource-Constrained IoT Systems

Random numbers often serve as the backbone for many security solutions in diverse domains such as cryptography, side channel leakage prevention, and moving target defense. However, generating true random numbers requires a physical source of entropy (e.g. hardware, quantum, environmental phenomenon) making it difficult to realize at a large scale and at a low cost. On the flip side, pseudorandom number generators (easy to implement) following a specific distribution (e.g. Gaussian) can be easily compromised given a sufficient amount of traces. In this work, we have developed a machine learning-guided generative approach that can be used to create portable, resource-efficient, and cost-effective random number generators with high throughput and true randomness characteristics. We implement the proposed approach as a highly parameterized framework and perform extensive evaluation for different settings. The framework was able to learn from true random sources such as irrational numbers and environmental audio noise and imitate those sources towards generating new good quality random numbers on demand. We have generated more than 1 billion bits and observed robust performance in terms of true randomness metrics obtained from NIST SP 800-22 and FIPS 140-1 randomness test suites achieving a throughput of up to 142.85 Mbps. Compared to the state-of-the-art (SOTA) technique, the iso-cost setup of our framework can achieve more than 500 Mbps in a distributed setting. We have evaluated the efficacy of running the true randomness imitation AI models on target edge devices such as Raspberry Pi 4 (Model B), Nvidia Jetson Nano, Nvidia Jetson Orin Nano and Nvidia Jetson Xavier. We have also looked at the security of the TRIM framework itself against different adversarial threat models.

Cybersecurity↗
DOE OSTI2026

A Survey on the Expanding Scope and Interdisciplinary Opportunities for Processing-in-Memory Techniques

Processing-in-Memory (PIM) is emerging as a practical path to overcome the limitations of traditional von Neumann architectures. At its core, PIM systems implement computing primitives such as logic operations and multiply-accumulate acceleration through compute-in-memory, near-memory processing, or hybrid designs. The role of memory cells varies widely across technologies, acting as inputs, outputs, or analog accumulators through bit-lines and sense amplifiers. This diversity creates trade-offs in precision, bandwidth, latency, and programmability, making it difficult to build a unified understanding on the progress of the field. In this survey, we organize recent advances of PIM into three areas. First, we discuss the progress on the architectural optimizations of PIM and its integration with both DRAM and emerging non-volatile memories. Second, we examine how PIM is being used to accelerate key computing domains, including generative AI workloads and high-performance kernels, along with new approaches. Third, we highlight the growing adoption of PIM in computational sciences, where it is being applied to solve interdisciplinary problems such as genome analysis, mRNA quantification, mass spectrometry, quantum circuit simulation, wave modeling, and secure computation. Finally, we synthesize the major challenges that continue to slow PIM adoption, including manufacturing constraints, power delivery, thermal reliability, data consistency, runtime and memory-management coordination, and the difficulty of building portable software abstractions without sacrificing commercial viability. This work provides an updated, structured perspective on PIM’s potential across computing and computational sciences and the barriers that must be solved for it to reach its full impact.

Asifuzzaman, Kazi [Oak Ridge National Laboratory (↗
DOE OSTI2021

Addressing Load Imbalance in Bioinformatics and Biomedical Applications: Efficient Scheduling across Multiple GPUs

Computational bioinformatics and biomedical applications frequently contain heterogeneously sized units of work or tasks, for instance due to variability in the sizes of biological sequences and molecules. Variable-sized workloads lead to load imbalances in parallel implementations which detract from efficiency and performance. Many modern computing resources now have multiple graphics processing units(GPUs) per computer for acceleration. These multiple GPU resources need to be used efficiently through balancing of workloads across the GPUs. OpenMP is a portable directive-based parallel programming API used ubiquitously in bioscience applications to program CPUs; recently, the use of OpenMP directives for GPU acceleration has become possible. Here, motivated by experiences with imbalanced loads in GPU-accelerated bioinformatics applications, we address the load balancing problem using OpenMP task-to-GPU scheduling combined with OpenMP GPU offloading for multiply heterogeneous workloads – loads with both variable input sizes, and simultaneously, variable convergence rates for algorithms with a stochastic component – scheduled across multiple GPUs. We aim to develop strategies which are both easy to use and have lower overheads, and may be incorporated incrementally in existing programs which already make use of OpenMP for CPU-based threading in order to make use of multi-GPU computers. We test different combinations of input size variability and convergence rate variability, and characterize the effects of these different scenarios on the performance of scheduling strategies across multiple GPUs with OpenMP. We present several dynamic scheduling solutions for different parallel patterns, explore optimizations, and provide publicly available example computational kernels to make these strategies easy to use in programs. This work will enable application developers to efficiently and easily use multiple GPUs for imbalanced workloads found in bioinformatics and biomedical applications.

Thavappiragasam, Mathialakan↗
DOE OSTI2023

Intra-hour Solar Irradiance Forecast in Multiple Locations using Deep Transfer Learning

In recent years, solar power system installation imposes several challenges on the operations of local and regional power grids due to the inherent variability of ground-level solar irradiance. This work proposes a novel real-time solar forecast methodology for intra-hour solar irradiance based on deep transfer learning from ground-based sky imager for time horizons ranging from 5-15 min. There are three unique aspects of the proposed methodology: (1) a Deep Learning based algorithm development which is modeled as a classification approach rather than a traditional regression approach; (2) the use of the Transfer Learning technique to show generalization capability, robustness, and portability of baseline model in the newly deployed location where availability of enough data for training is typically scarce, and (3) redefinition of point-based irradiation forecast error estimation technique with a window-based one that is more intuitive and user-friendly. The system is developed using multiple years of irradiance and sky image recording in New Jersey and one-year data from Colorado, USA. The method is validated against ground telemetry from these two locations of diverse geographic and climatic conditions. Results show that the forecasting method proposed in this work is robust and highly accurate (8% MAPE error) for multiple locations deployment.

Deep Learning, Convolution Neural Networks, transf↗