Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Sensing”

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

Quantum Sensing for Energy Applications

Quantum sensing is creating potentially transformative opportunities to exploit intricate quantum mechanical phenomena in new ways to make ultrasensitive measurements of multiple parameters. A growing interest in quantum sensing has created opportunities for its deployment to improve processes pertaining to energy production, distribution, and consumption. NETL is leveraging experimental and computational quantum tools to enhance sensitivity of hybrid quantum-classical ultrasensitive sensors for the detection of hydrocarbons and rare earth elements (REEs).

Paudel, Hari P.↗

Graphene K‐Tape Meshes for Densely Distributed Human Motion Monitoring

Abstract Wearable sensors that measure parameters associated with physical activity and bodily motions have been regarded as an indispensable tool for assessing personal wellness. Recent advances in nanocomposite strain sensors have been successfully used for monitoring skin strains and other strain‐derived physiological parameters. This study complements the existing body of work and presents a flexible, self‐adhering, fabric‐based wearable sensor for measuring skin strains and human motions. Graphene nanosheet thin films are directly spray‐coated onto kinesiology tape (K‐Tape) to obtain a self‐adhering strain sensor of high sensitivity and linearity. Their stable sensing performance and high repeatability are verified, while human subject tests confirm that they adequately capture muscle engagement during functional movements. In addition, densely distributed strain monitoring can be achieved using an electrical impedance tomography measurement approach and algorithm. Spatial strain sensing is successfully demonstrated using a single strip of piezoresistive K‐Tape, as well as when a K‐Tape network or mesh pattern is formed. The results show promise for using graphene K‐Tape meshes to measure how specific major muscle groups engage during different physical activities.

Lin, Yun‐An↗

Coherent Phonon Dynamics in Plasmonic Gold Tetrahedral Nanoparticle Ensembles

Coherent phonon modes supported by plasmonic nanoparticles offer prospective applications in chemical and biological sensing. Whereas characterization of these phonon modes often requires single particle measurements, synthetic routes to narrow size distributions of nanoparticles permit ensemble investigations. Recently, the synthesis of highly monodisperse gold tetrahedral nanoparticles with tunable edge length and corner sharpness has been developed. Herein, we characterize a size series of these nanoparticles in colloidal dispersion via transient absorption spectroscopy to examine their mechanical and plasmonic responses upon photoexcitation. Oscillations of transient absorption signals are observed in the plasmon resonance and correspond to the lowest order radial breathing modes of the nanoparticles, the frequencies of which are affected by edge length and truncation of the corners. Furthermore, quality factor values ranging from 10 to 15 are observed for the oscillations that convey potential utility in mass-sensing and plasmon-exciton coupling photonics schemes. Finite-difference time domain and finite element analysis calculations establish the specific optically-relevant phonon modes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Editorial: Edge computation and digital distribution networks

The development of digital technologies is penetrating all areas of energy revolution. Based on the in-depth integration of advanced digital technologies, distribution networks are gradually transforming into digital distribution networks (DDNs) with tremendous changes from the structure to the operation mode. DDNs is the digitalized appearance of the physical distribution network, in which ubiquitous connections and massive data are the basic characteristics (Huo et al., 2022). It is an important task to utilize the massive data and propose novel operation modes to construct more efficient and intelligent distribution networks (Jian et al., 2022). Among the advanced digital technologies in DDNs, edge computing has received wide attention (Zhao et al., 2022). It has superior performance in local sensing and intelligent computation, which can effectively relieve huge communication pressure. However, the limited computing resources and the complex computing tasks at the edge side significantly challenge the collaboration of distribution network regulation and advanced digital technologies (Hu et al., 2022). It is necessary to find out proper methods to utilize advanced digital technology to construct DDNs. This Research Topic is organized to introduce the recent progress in the construction, operation and advanced computational methods for DDNs. Finally, seven papers have been accepted, which can be sorted into the following three categories: 1) Evolution and technical features of DDNs, 2) Intelligent operation control of DDNs, 3) Advanced simulation for large-scale DDNs. The three sections below respectively introduce the major research and contributions of the papers covered in each category.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Local conformational perturbations of the DNA molecule in the SG-model

Within the formalism of the Fokker–Planck equation, the influence of nonstationary external force, random force, and dissipation effects on dynamics local conformational perturbations (kink) propagating along the DNA molecule is investigated. Such waves have an important role in the regulation of important biological processes in living systems at the molecular level. As a dynamic model of DNA was used a modified sine-Gordon equation, simulating the rotational oscillations of bases in one of the chains DNA. The equation of evolution of the kink momentum is obtained in the form of the stochastic differential equation in the Stratonovich sense within the framework of the well-known McLaughlin and Scott energy approach. The corresponding Fokker–Planck equation for the momentum distribution function coincides with the equation describing the Ornstein–Uhlenbek process with a regular nonstationary external force. The influence of the nonlinear stochastic effects on the kink dynamics is considered with the help of the Fokker– Planck nonlinear equation with the shift coefficient dependent on the first moment of the kink momentum distribution function. Expressions are derived for average value and variance of the momentum. Examples are considered which demonstrate the influence of the external regular and random forces on the evolution of the average value and variance of the kink momentum. Within the formalism of the Fokker–Planck equation, the influence of nonstationary external force, random force, and dissipation effects on the kink dynamics is investigated in the sine–Gordon model. The equation of evolution of the kink momentum is obtained in the form of the stochastic differential equation in the Stratonovich sense within the framework of the well-known McLaughlin and Scott energy approach. The corresponding Fokker–Planck equation for the momentum distribution function coincides with the equation describing the Ornstein–Uhlenbek process with a regular nonstationary external force. The influence of the nonlinear stochastic effects on the kink dynamics is considered with the help of the Fokker–Planck nonlinear equation with the shift coefficient dependent on the first moment of the kink momentum distribution function. Expressions are derived for average value and variance of the momentum. Examples are considered which demonstrate the influence of the external regular and random forces on the evolution of the average value and variance of the kink momentum.

60 APPLIED LIFE SCIENCES↗

Alternative Approaches to Traditional Net Energy Metering

Most jurisdictions in the United States originally implemented net energy metering (NEM) tariffs to support the deployment and interconnection of distributed generation (DG) resources (e.g., rooftop solar photovoltaic systems). Since then, NEM has proven effective in promoting adoption of DG resources. Recently, due to concerns about sufficient recovery of utilities’ revenue requirements and cost-shifting, there is increasing interest in—or statutory requirements to pursue—alternative compensation approaches, especially in U.S. states and territories with robust growth in distributed solar. Recent increases in other forms of distributed energy resources (DERs) that can potentially send power to the distribution grid (e.g., distributed battery energy storage system (BESS)) are further driving compensation reforms. This brief provides an overview of design elements associated with alternative approaches to traditional NEM, summarizes common arguments for and against them, and identifies implementation issues that utilities may need to address. Although this brief may be most useful in jurisdictions that are interested in or required to move beyond NEM, it is also applicable to those jurisdictions that have already done so—and are looking to further implement reforms to their existing compensation mechanisms. In the broadest sense, there are three primary tariff-related components when interconnecting a DER onto the local utility’s distribution system (adapted from Zinaman et al., 2017): 1. Metering and Billing Arrangements: How utilities measure and bill electricity consumption and production. 2. DER Export Tariff Design: The structure under which utilities compensate customers for electricity they export to the grid. 3. Consumption Tariff Design: The structure under which customers pay for electricity they consume from the grid. When implementing changes to any of these primary tariff-related components, there are likely implications for a utility’s metering system, billing system, and other technology systems. Where applicable, this brief explicitly identifies such implementation challenges.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Size-Resolved Shape Evolution in Inorganic Nanocrystals Captured via High-Throughput Deep Learning-Driven Statistical Characterization

Precise size and shape control in nanocrystal synthesis is essential for utilizing nanocrystals in various industrial applications, such as catalysis, sensing, and energy conversion. However, traditional ensemble measurements often overlook the subtle size and shape distributions of individual nanocrystals, hindering the establishment of robust structure–property relationships. In this study, we uncover intricate shape evolutions and growth mechanisms in Co 3 O 4 nanocrystal synthesis at a subnanometer scale, enabled by deep-learning-assisted statistical characterization. By first controlling synthetic parameters such as cobalt precursor concentration and water amount then using high resolution electron microscopy imaging to identify the geometric features of individual nanocrystals, this study provides insights into the interplay between synthesis conditions and the sizedependent shape evolution in colloidal nanocrystals. Utilizing population-wide imaging data encompassing over 441,067 nanocrystals, we analyze their characteristics and elucidate previously unobserved size-resolved shape evolution. This high-throughput statistical analysis is essential for representing the entire population accurately and enables the study of the size dependency of growth regimes in shaping nanocrystals. Our findings provide experimental quantification of the growth regime transition based on the size of the crystals, specifically (i) for faceting and (ii) from thermodynamic to kinetic, as evidenced by transitions from convex to concave polyhedral crystals. Additionally, we introduce the concept of an “onset radius,” which describes the critical size thresholds at which these transitions occur. This discovery has implications beyond achieving nanocrystals with desired morphology; it enables finely tuned correlation between geometry and material properties, advancing the field of colloidal nanocrystal synthesis and its applications.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Global variation in the fraction of leaf nitrogen allocated to photosynthesis

Plants invest a considerable amount of leaf nitrogen in the photosynthetic enzyme ribulose-1,5-bisphosphate carboxylase-oxygenase (RuBisCO), forming a strong coupling of nitrogen and photosynthetic capacity. Variability in the nitrogen-photosynthesis relationship indicates different nitrogen use strategies of plants (i.e., the fraction nitrogen allocated to RuBisCO; fLNR), however, the reason for this remains unclear as widely different nitrogen use strategies are adopted in photosynthesis models. Here, we use a comprehensive database of in situ observations, a remote sensing product of leaf chlorophyll and ancillary climate and soil data, to examine the global distribution in fLNR using a random forest model. We find global fLNR is 18.2 ± 6.2%, with its variation largely driven by negative dependence on leaf mass per area and positive dependence on leaf phosphorus. Some climate and soil factors (i.e., light, atmospheric dryness, soil pH, and sand) have considerable positive influences on fLNR regionally. This study provides insight into the nitrogen-photosynthesis relationship of plants globally and an improved understanding of the global distribution of photosynthetic potential.

54 ENVIRONMENTAL SCIENCES↗

Measuring the giant radio galaxy length distribution with the LoTSS

Many massive galaxies launch jets from the accretion disk of their central black hole, but only ~10 3 instances are known in which the associated outflows form giant radio galaxies (GRGs, or giants): luminous structures of megaparsec extent that consist of atomic nuclei, relativistic electrons, and magnetic fields. Large samples are imperative to understanding the enigmatic growth of giants, and recent systematic searches in homogeneous surveys constitute a promising development. For the first time, it is possible to perform meaningful precision statistics with GRG lengths, but a framework to do so is missing. We measured the intrinsic GRG length distribution by combining a novel statistical framework with a LOFAR Two-metre Sky Survey (LoTSS) sample of freshly discovered giants. In turn, this allowed us to answer an array of questions on giants. For example, we can now assess how rare a 5 Mpc giant is compared with one of 1 Mpc, and how much larger – given a projected length – the corresponding intrinsic length is expected to be. Notably, we can now also infer the GRG number density in the Local Universe. We assumed the intrinsic GRG length distribution to be Paretian (i.e. of power-law form) with tail index ξ, and predicted the observed distribution by modelling projection and selection effects. To infer ξ, we also systematically searched the LoTSS for hitherto unknown giants and compiled the largest catalogue of giants to date. We show that if intrinsic GRG lengths are Pareto distributed with index ξ, then projected GRG lengths are also Pareto distributed with index ξ. Selection effects induce curvature in the observed projected GRG length distribution: angular length selection flattens it towards the lower end, while surface brightness selection steepens it towards the higher end. We explicitly derived a GRG’s posterior over intrinsic lengths given its projected length, laying bare the ξ dependence. We also discovered 2060 giants within LoTSS DR2 pipeline products; our sample more than doubles the known population. Spectacular discoveries include the largest, second-largest, and fourth-largest GRG known (l p = 5.1 Mpc, l p = 5.0 Mpc, and l p = 4.8 Mpc), the largest GRG known hosted by a spiral galaxy (l p = 2.5 Mpc), and the largest secure GRG known beyond redshift 1 (l p = 3.9 Mpc). We increase the number of known giants whose angular length exceeds that of the Moon from 10 to 23; among the discoveries is the angularly largest known radio galaxy in the Northern Sky, which is also the angularly largest known GRG ($\phi$ = 2°). Combining theory and data, we determined that intrinsic GRG lengths are well described by a Pareto distribution, and measured the index ξ = –3.5 ± 0.5. This implies that, given its projected length, a GRG’s intrinsic length is expected to be just 15% larger. Finally, we determined the comoving number density of giants in the Local Universe to be n GRG = 5 ± 2(100 Mpc) –3 . We developed a practical mathematical framework that elucidates the statistics of giant radio galaxy lengths. Through a LoTSS search, we also discovered 2060 new giants. By combining both advances, we determined that intrinsic GRG lengths are well described by a Pareto distribution with index ξ = –3.5 ± 0.5, and that giants are truly rare in a cosmological sense: most clusters and filaments of the Cosmic Web are not currently home to a giant. Thus, our work yields new observational constraints for analytical models and simulations featuring radio galaxy growth.

79 ASTRONOMY AND ASTROPHYSICS↗

High-resolution absolute frequency referenced fiber optic sensor for quasi-static strain sensing

We present a quasi-static fiber optic strain sensing system capable of resolving signals below nanostrain from 20 mHz. A telecom-grade distributed feedback CW diode laser is locked to a fiber Fabry-Perot sensor, transferring the detected signals onto the laser. An H{sup 13}C{sup 14}N absorption line is then used as a frequency reference to extract accurate low-frequency strain signals from the locked system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Flow-turbulence interaction in magnetic reconnection

Roles of turbulence in the context of magnetic reconnection are investigated with special emphasis on the mutual interaction between flow (large-scale inhomogeneous structure) and turbulence. In order to evaluate the effective transport due to turbulence, in addition to the intensity information of turbulence represented by the turbulent energy, the structure information represented by pseudoscalar statistical quantities (helicities) is important. On the basis of the evolution equation, mechanisms that provide turbulence with cross helicity are presented. Magnetic-flux freezing in highly turbulent media is considered with special emphasis on the spatial distribution of the turbulent cross helicity. The cross-helicity effects in the context of magnetic reconnection are also investigated. It is shown that the large-scale flow and magnetic-field configurations favorable for the cross-helicity generation is compatible with the fast reconnection. Difference between the spatial distributions of the turbulent MHD energy and cross helicity plays an essential role for localizing the reconnection region. In this sense, turbulence and large-scale structures promote magnetic reconnection mediated by the turbulent cross helicity.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Ultrafast Fiber Bragg Grating Interrogation for Sensing in Detonation and Shock Wave Experiments

Chirped fiber Bragg grating (CFBG) sensors coupled to high speed interrogation systems are described as robust diagnostic approaches to monitoring shock wave and detonation front propagation tracking events for use in high energy density shock physics applications. Taking advantage of the linear distributed spatial encoding of the spectral band in single-mode CFBGs, embedded fiber systems and associated photonic interrogation methodologies are shown as an effective approach to sensing shock and detonation-driven loading processes along the CFBG length. Two approaches, one that detects spectral changes in the integrated spectrum of the CFBG and another coherent pulse interrogation approach that fully resolves its spectral response, shows that 100-MHz–1-GHz interrogation rates are possible with spatial resolution along the CFBG in the 50 µm to sub-millimeter range depending on the combination of CFBG parameters (i.e., length, chirp rate, spectrum) and interrogator design specifics. In conclusion, results from several dynamic tests are used to demonstrate the performance of these high speed systems for shock and detonation propagation tracking under strong and weak shock pressure loading: (1) linear detonation front tracking in the plastic bonded explosive (PBX) PBX-9501; (2) tracking of radial decaying shock with crossover to non-destructive CFBG response; (3) shock wave tracking along an aluminum cylinder wall under weak loading accompanied by dynamic strain effects in the CFBG sensor.

36 MATERIALS SCIENCE↗

Controllable 3D Manufacturing System

Next generation Small Modular Reactor (SMR) requires new and improved techniques, instrumentations and strategies to deal with the anticipated high radiation and high temperature environment (esp. in reactors). Component manufacturing technologies will be required that take full advantage of the new 3-D printing methods employed by additive manufacturing technologies. These manufacturing methods must be capable of producing components or sub components on a limited production basis and with nuclear quality. Based on our success in developing a variety of award-winning high energy and high power ultrafast fiber lasers and our pioneered work in fs laser 3D manufacturing (US patents, 9643361 and 9770760), PolarOnyx proposes to use tunable fiber lasers to develop smart AM & SM system to make nuclear quality components for SMR. In Phase I, we have achieved critical milestones and experimentally demonstrated the most critical functions of the proposed controllable laser AM: • Developed and investigated a series of NDI sensing technologies. Combination of IR thermal image and high resolution visible camera provides a powerful tool to characterize thermal distribution and defects. • Built an in-line laser induced breakdown spectroscopy (LIBS) to real time detect compositions of powder and parts, and melting temperature of the melting pool. It proves the LIBS is a very powerful tool to precisely guide the process. • Filed a patent (Application number 16378485) for integrating IR and visible images and LIBS for intelligent AM system. • Developed control algorithm and proved it works well for overhang experiment. • Achieved high density (>99%) and excellent mechanical properties. • Succeeded in developing a working and reliable calibration method to extract true temperature distribution during AM process. • Demonstrated spatial and temporal pulse shaping methods, and impact on microstructures. • Filed one utility patent • Laid out a solid path for phase II to work on controllable 3D manufacturing system development and optimization and to make components with nuclear quality. Our proprietary fs fiber laser based AM processing offers an ultimate solution for manufacturing high temperature components with high strength for nuclear systems. The 3D AM system in conjunction with the intelligent sensing and control is energy efficient and cost effective for the growing nuclear industries. Successful development of the proposed AM technology will provide a vital tool to solve existing and potential issues. This technology will be directly applied in the 3D printing area with combined market share of $10(s) of billions. The achievement in this research will have significant and wide social, scientific, and economic impacts by providing affordable low cost intelligent AM/SM systems, laser micromachining systems, improving energy efficiency, and reducing fabrication and operational cost. Having demonstrated the proof of concept in Phase I, we will prototype the controllable AM/SM system and investigate the efficiency and qualification of fabricating various nuclear quality components in Phase II.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

UNMANNED AERIAL VEHICLE (UAV) HYPERSPECTRAL REMOTE SENSING FOR DRYLAND VEGETATION MONITORING

UAV-based hyperspectral remote sensing capabilities developed by the Idaho National Lab and Idaho State University, Boise Center Aerospace Lab, were recently tested via demonstration flights that explored the influence of altitude on geometric error, image mosaicking, and dryland vegetation classification. The test flights successfully acquired usable flightline data capable of supporting classifiable composite images. Unsupervised classification results support vegetation management objectives that rely on mapping shrub cover and distribution patterns. Overall, supervised classifications performed poorly despite spectral separability in the image-derived endmember pixels. Future mapping efforts that leverage ground reference data, ultra-high spatial resolution photos and time series analysis should be able to effectively distinguish native grasses such as Sandberg bluegrass (Poa secunda), from invasives such as burr buttercup (Ranunculus testiculatus) and cheatgrass (Bromus tectorum).

54 ENVIRONMENTAL SCIENCES↗

Automated Identification of Characteristic Droplet Size Distributions in Stratocumulus Clouds Utilizing a Data Clustering Algorithm

Abstract Droplet-level interactions in clouds are often parameterized by a modified gamma fitted to a “global” droplet size distribution. Do “local” droplet size distributions of relevance to microphysical processes look like these average distributions? This paper describes an algorithm to search and classify characteristic size distributions within a cloud. The approach combines hypothesis testing, specifically, the Kolmogorov–Smirnov (KS) test, and a widely used class of machine learning algorithms for identifying clusters of samples with similar properties: density-based spatial clustering of applications with noise (DBSCAN) is used as the specific example for illustration. The two-sample KS test does not presume any specific distribution, is parameter free, and avoids biases from binning. Importantly, the number of clusters is not an input parameter of the DBSCAN-type algorithms but is independently determined in an unsupervised fashion. As implemented, it works on an abstract space from the KS test results, and hence spatial correlation is not required for a cluster. The method is explored using data obtained from the Holographic Detector for Clouds (HOLODEC) deployed during the Aerosol and Cloud Experiments in the Eastern North Atlantic (ACE-ENA) field campaign. The algorithm identifies evidence of the existence of clusters of nearly identical local size distributions. It is found that cloud segments have as few as one and as many as seven characteristic size distributions. To validate the algorithm’s robustness, it is tested on a synthetic dataset and successfully identifies the predefined distributions at plausible noise levels. The algorithm is general and is expected to be useful in other applications, such as remote sensing of cloud and rain properties. Significance Statement A typical cloud can have billions of drops spread over tens or hundreds of kilometers in space. Keeping track of the sizes, positions, and interactions of all of these droplets is impractical, and, as such, information about the relative abundance of large and small drops is typically quantified with a “size distribution.” Droplets in a cloud interact locally, however, so this work is motivated by the question of whether the cloud droplet size distribution is different in different parts of a cloud. A new method, based on hypothesis testing and machine learning, determines how many different size distributions are contained in a given cloud. This is important because the size distribution describes processes such as cloud droplet growth and light transmission through clouds.

54 ENVIRONMENTAL SCIENCES↗

Green and Cost Effective Synthesis of Fluorescent Carbon Quantum Dots for Dopamine Detection

Carbon quantum dots (CQDs) due to its high fluorescent output is evolving as novel sensing material and is considered as future building blocks for nano sensing devices. Hence, in this investigation we report microwave assisted preparation and multi sensing application of CQDs. The microwave derived CQDs are characterized by Dynamic Light Scattering (DLS) experiment and Fourier Infrared spectra (FTIR) to investigate the size distribution and chemical purity respectively. Fluorescent emission spectra recorded at varying pH shows varying fluorescence emission intensities. Further, emission spectra recorded at different temperatures shows that fluorescence emission of CQDs greatly depends on temperature. Therefore, we demonstrate the pH and temperature sensing characteristics of CQDs by fluorescence quenching behaviour. In addition, the interaction and sensing behaviour of CQDs for dopamine is also presented in this work with a detection limit of 0.2 mM. The steady state and time-resolved methods have been employed in fluorescence quenching methods for sensing dopamine through CQDs at room temperature. The bimolecular quenching rate constants for different concentration have been measured. The interaction between CQDs and dopamine indicates fluorescence quenching method is an elegant process for detecting dopamine through CQDs.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Using automated machine learning for the upscaling of gross primary productivity

Estimating gross primary productivity (GPP) over space and time is fundamental for understanding the response of the terrestrial biosphere to climate change. Eddy covariance flux towers provide in situ estimates of GPP at the ecosystem scale, but their sparse geographical distribution limits larger-scale inference. Machine learning (ML) techniques have been used to address this problem by extrapolating local GPP measurements over space using satellite remote sensing data. However, the accuracy of the regression model can be affected by uncertainties introduced by model selection, parameterization, and choice of explanatory features, among others. Recent advances in automated ML (AutoML) provide a novel automated way to select and synthesize different ML models. In this work, we explore the potential of AutoML by training three major AutoML frameworks on eddy covariance measurements of GPP at 243 globally distributed sites. We compared their ability to predict GPP and its spatial and temporal variability based on different sets of remote sensing explanatory variables. Explanatory variables from only Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance data and photosynthetically active radiation explained over 70 % of the monthly variability in GPP, while satellite-derived proxies for canopy structure, photosynthetic activity, environmental stressors, and meteorological variables from reanalysis (ERA5-Land) further improved the frameworks' predictive ability. We found that the AutoML framework Auto-sklearn consistently outperformed other AutoML frameworks as well as a classical random forest regressor in predicting GPP but with small performance differences, reaching an r 2 of up to 0.75. We deployed the best-performing framework to generate global wall-to-wall maps highlighting GPP patterns in good agreement with satellite-derived reference data. This research benchmarks the application of AutoML in GPP estimation and assesses its potential and limitations in quantifying global photosynthetic activity.

54 ENVIRONMENTAL SCIENCES↗