Single Core Research Articles

Mechanical characteristics of kenaf-glass fiber reinforced hybrid composites by varying the stacking sequences

Fiber composite materials are preferred for their lightweight, low-cost, and commercial uses. As part of this study, laminate materials consisting of two different fiber materials as their reinforcement materials are produced using the hand layup method. This study investigates the mechanical properties of hybrid composite laminates fabricated using kenaf and glass fibers. Six stacking arrangements of the fibers are examined, alongside two reference laminates with individual reinforcements. Epoxy resins HY951 and LY556 serve as matrix materials. ASTM standards guide the mechanical testing of the composites. Results indicate varied tensile strengths based on stacking sequence, with laminate L2 (KKGKK) featuring a single glass fiber core at 75 MPa, and increasing strengths in laminates with additional glass layers: L1 (GKKKG) at 123 MPa, L5 (KGKGK) at 110 MPa, L3 (GKGKG) at 150 MPa, L6 (KGGGK) at 118 MPa, and L4 (GGKGG) at 159 MPa, the highest among all. It was observed that adding one layer of glass fiber with kenaf fiber boosts strength and modulus by 9.52% and 12.19% respectively, compared to pure kenaf fiber composites. Morphological analysis via Scanning Electron Microscopy (SEM) confirms failure due to initial crack propagation in the matrix and fibers. This study offers insights into hybrid composite laminate behavior, pertinent for various industrial applications.

Schlieren Image Velocimetry and Modal Decomposition Study of Preheated Isothermal Flow From a Generic Multi-Swirl Burner

Abstract This study presents an experimental investigation into the turbulent flow characteristics of an unconfined counter-rotating dual swirl burner under external acoustic excitation. Utilizing Schlieren image velocimetry (SIV), we capture the velocity field of the swirling jets. Mean velocity field analysis reveals the upstream propagation of the central recirculation zone within the burner passages. Through proper orthogonal decomposition (POD) analysis on instantaneous axial velocity fields, coherent structures are identified and the impact of different actuation methods on spatial modes is illustrated. Spatial modes of the unforced (natural) flow show the presence of a single and double helical precessing vortex core (PVC) modes at St = 0.53. Low-frequency acoustic actuation (St = 0.46) effectively suppresses the PVC mode, while high-frequency (St = 2) actuation stabilizes it. Broadband excitation of the flow field, however, induces the excitation of both single and double helical PVC modes.

SLOPE: Safety LOg PEripherals implementation and software drivers for a safe RISC-V microcontroller unit

The focus of this manuscript is related to the main safety issues regarding a mixed criticality system running multiple concurrent tasks. Our concerns are related to the guarantee of Freedom of Interference between concurrent partitions, and to the respect of the Worst Case Execution Time for tasks. Moreover, we are interested in the evaluation of resources budgeting and the study of system behavior in case of occurring random hardware failures. In this paper we present a set of Safety LOg PEripherals (SLOPE): Performance Monitoring Unit (PMU), Execution Tracing Unit (ETU), Error Management Unit (EMU), Time Management Unit (TMU) and Data Log Unit (DLU); then, an implementation of SLOPE on a single core RISC-V architecture is proposed. Such peripherals are able to collect software and hardware information about execution, and eventually trigger recovery actions to mitigate a possible dangerous misbehavior. We show results of the hardware implementation and software testing of the units with a dedicated software library. For the PMU we standardized the software layer according to embedded Performance Application Programming Interface (ePAPI), and compared its functionality with a bare-metal use of the library. To test the ETU we compared the hardware simulation results with software ones, to understand if overflow may occur in internal hardware buffers during tracing. In conclusion, designed devices introduce new instruments for system investigation for RISC-V technologies and can generate an execution profile for safety related tasks.

MEPO-ML: a robust graph attention network model for rapid generation of partial atomic charges in metal-organic frameworks

Accurate computation of the gas adsorption properties of MOFs is usually bottlenecked by the DFT calculations required to generate partial atomic charges. Therefore, large virtual screenings of MOFs often use the QEq method which is rapid, but of limited accuracy. Recently, machine learning (ML) models have been trained to generate charges in much better agreement with DFT-derived charges compared to the QEq models. Previous ML charge models for MOFs have all used training sets with less than 3000 MOFs obtained from the CoRE MOF database, which has recently been shown to have high structural error rates. In this work, we developed a graph attention network model for predicting DFT-derived charges in MOFs where the model was developed with the ARC-MOF database that contains 279,632 MOFs and over 40 million charges. This model, which we call MEPO-ML, predicts charges with a mean absolute error of 0.025e on our test set of over 27 K MOFs. Other ML models reported in the literature were also trained using the same dataset and descriptors, and MEPO-ML was shown to give the lowest errors. The gas adsorption properties evaluated using MEPO-ML charges are found to be in significantly better agreement with the reference DFT-derived charges compared to the empirical charges, for both polar and non-polar gases. Using only a single CPU core on our benchmark computer, MEPO-ML charges can be generated in less than two seconds on average (including all computations required to apply the model) for MOFs in the test set of 27 K MOFs.

Preparation of GaN Nanocrystals with Single Ag Cores

Preparation of GaN Nanocrystals with Single Ag Cores

Scalable CNN-based classification of selective sweeps using derived allele frequencies.

Selective sweeps can successfully be distinguished from neutral genetic data using summary statistics and likelihood-based methods that analyze single nucleotide polymorphisms (SNPs). However, these methods are sensitive to confounding factors, such as severe population bottlenecks and old migration. By virtue of machine learning, and specifically convolutional neural networks (CNNs), new accurate classification models that are robust to confounding factors have been recently proposed. However, such methods are more computationally expensive than summary-statistic-based ones, yielding them impractical for processing large-scale genomic data. Moreover, SNP data are frequently preprocessed to improve classification accuracy, further exacerbating the long analysis times. To this end, we propose a 1D CNN-based model, dubbed FAST-NN, that does not require any preprocessing while using only derived allele frequencies instead of summary statistics or raw SNP data, thereby yielding a sample-size-invariant, scalable solution. We evaluated several data fusion approaches to account for the variance of the density of genetic diversity across genomic regions (a selective sweep signature), and performed an extensive neural architecture search based on a state-of-the-art reference network architecture (SweepNet). The resulting model, FAST-NN, outperforms the reference architecture by up to 12% inference accuracy over all challenging evolutionary scenarios with confounding factors that were evaluated. Moreover, FAST-NN is between 30× and 259× faster on a single CPU core, and between 2.0× and 6.2× faster on a GPU, when processing sample sizes between 128 and 1000 samples. Our work paves the way for the practical use of CNNs in large-scale selective sweep detection. https://github.com/SjoerdvandenBelt/FAST-NN.

The Fundamental of Fiber Bragg Grating (FBG) Sensor

An optical sensor known as an FBG is produced by laterally exposing a single mode fiber core to a strong UV laser light pattern on a regular basis. The exposure causes a sustained increase in the refractive index (ncore) of the fiber's core, resulting in fixed index modulation called grating (λ). The grating inside the fiber optic core must reflect a certain wavelength of incoming light while transmitting all other wavelengths. This wavelength is referred to as the Bragg wavelength or Bragg linked to grating period. FBG functions as intended when a Bragg reflector is built on an optical fiber by taking use of the regular fluctuations in the refractive index of the single mode fiber core. When light travels through the FBG, certain wavelengths will be transmitted and others will be reflected. When the strain or temperature around the grating varies, a shift in the wavelength of the light reflected is observed.

Fast prediction of personalized abdominal organ doses from CT examinations by radiomics feature-based machine learning models

The X-rays emitted during CT scans can increase solid cancer risks by damaging DNA, with the risk tied to patient-specific organ doses. This study aims to establish a new method to predict patient specific abdominal organ doses from CT examinations using minimized computational resources at a fast speed. The CT data of 247 abdominal patients were selected and exported to the auto-segmentation software named DeepViewer to generate abdominal regions of interest (ROIs). Radiomics feature were extracted based on the selected CT data and ROIs. Reference organ doses were obtained by GPU-based Monte Carlo simulations. The support vector regression (SVR) model was trained based on the radiomics features and reference organ doses to predict abdominal organ doses from CT examinations. The prediction performance of the SVR model was tested and verified by changing the abdominal patients of the train and test sets randomly. For the abdominal organs, the maximal difference between the reference and the predicted dose was less than 1 mGy. For the body and bowel, the organ doses were predicted with a percentage error of less than 5.2%, and the coefficient of determination (R2) reached up to 0.9. For the left kidney, right kidney, liver, and spinal cord, the mean absolute percentage error ranged from 5.1 to 8.9%, and the R2 values were more than 0.74. The SVR model could be trained to achieve accurate prediction of personalized abdominal organ doses in less than one second using a single CPU core.

Experimental validation of the 3-D neutron kinetics algorithm of RAPID using the JSI TRIGA Mark-II reactor

The high-fidelity simulation of reactor kinetics, with the ability of calculating detailed 3-D time-dependent distributions of the nuclear quantities of interest, is an important challenge in the field of nuclear engineering. As the industry moves towards innovative reactor designs and the financing and licensing of prototypes becomes increasingly complex, there is an increasing need of best-estimate and high-fidelity codes that are capable of replacing the computational tools that have been fine-tuned for LWRs using years of operation data and validation against benchmark facilities. Traditional neutron transport software either has to rely on significant modeling approximations or requires an impractical amount of computer time to calculate accurate and detailed solutions to the transport problems, failing to meet the need of the industry to simulate numerous scenarios over a relatively small time. RAPID is a software that relies on the Multi-stage Response-function Transport (MRT) methodology to achieve high-fidelity accurate solutions to the neutron transport problem by pre-calculating a database of response functions or coefficients that are then combined and interpolated to calculate the nuclear quantities of interest in seconds to minutes on a single computer core. In this article, the recently developed algorithms for 3-D time-dependent simulation of reactor kinetics and for control rods movement in the reactor core are validated using experiments performed at the Jožef Stefan Institute (JSI) TRIGA Mark-II reactor. The experiments were designed and performed with the goal of RAPID’s validation. In particular, time-dependent responses from four fission chambers located in the TRIGA core were collected and compared to RAPID-calculated values. The comparison of RAPID’s predictions to measured data shows very good agreement, demonstrating the ability of RAPID of calculating detailed 3-D time-dependent fission source distributions for a reactor kinetic problem that would be impractical to model with traditional neutron transport codes. In addition, it is demonstrated how RAPID is capable of obtaining a high level of accuracy within seconds to minutes on a single computer core, with a significant speedup with respect to state-of-the-art neutron transport methods.

Revealing faint compact radio jets at redshifts above 5 with very long baseline interferometry

Over the past two decades, our knowledge of the high-redshift $(z>5)$ radio quasars has expanded, thanks to dedicated high-resolution very long baseline interferometry (VLBI) observations. Distant quasars provide unique information about the formation and evolution of the first galaxies and supermassive black holes in the Universe. Powerful relativistic jets are likely to have played an essential role in these processes. However, the sample of VLBI-observed radio quasars is still too small to allow meaningful statistical conclusions. We extend the list of the VLBI observed radio quasars to investigate how the source structure and physical parameters are related to radio loudness. We assembled a sample of ten faint radio quasars located at $5 < z < 6$ with their radio-loudness indices spanning between $0.9-76$. We observed the selected targets with the European VLBI Network (EVN) at 1.7 GHz. The milliarcsecond-scale resolution of VLBI at this frequency allowed us to probe the compact innermost parts of radio-emitting relativistic jets. In addition to the single-band VLBI observations, we collected single-dish and low-resolution radio interferometric data to investigate the spectral properties and variability of our sources. The detection rate of this high-redshift, low-flux-density sample is $90<!PCT!>$, with only one target (J0306$+$1853) remaining undetected. The other nine sources appear core-dominated and show a single, faint and compact radio core on this angular scale. The derived radio powers are typical of Fanaroff-Riley II radio galaxies and quasars. By extending our sample with other VLBI-detected $z > 5$ sources from the literature, we found that the core brightness temperatures and monochromatic radio powers tend to increase with radio loudness.

Transformer coupled toroidal wave-heated remote plasma sources operating in Ar/NF3 mixtures

Remote plasmas are used in semiconductor device manufacturing as sources of radicals for chamber cleaning and isotropic etching. In these applications, large fluxes of neutral radicals (e.g. F, O, Cl, H) are desired with there being negligible fluxes of potentially damaging ions and photons. One remote plasma source (RPS) design employs toroidal, transformer coupling using ferrite cores to dissociate high flows of moderately high pressure (up to several Torr) electronegative gases. In this paper, results are discussed from a computational investigation of moderate pressure, toroidal transformer coupled RPS sustained in Ar and Ar/NF3 mixtures. Operation of the RPS in 1 Torr (133 Pa) of argon with a power of 1.0 kW at 0.5 MHz and a single core produces a continuous toroidal plasma loop with current continuity being maintained dominantly by conduction current. Operation with dual cores introduces azimuthal asymmetries with local maxima in plasma density. Current continuity is maintained by a mix of conduction and displacement current. Operation in NF3 for the same conditions produces essentially complete NF3 dissociation. Electron depletion as a result of dissociative attachment of NF3 and NF x fragments significantly alters the discharge topology, confining the electron density to the downstream portion of the source where the NF x density has been lowered by this dissociation.

PCA-constrained multi-core matrix fusion network: A novel approach for cancer subtype identification.

Cancer subtyping refers to categorizing a particular cancer type into distinct subtypes or subgroups based on a range of molecular characteristics, clinical manifestations, histological features, and other relevant factors. The identification of cancer subtypes can significantly enhance precision in clinical practice and facilitate personalized diagnosis and treatment strategies. Recent advancements in the field have witnessed the emergence of numerous network fusion methods aimed at identifying cancer subtypes. The majority of these fusion algorithms, however, solely rely on the fusion network of a single core matrix for the identification of cancer subtypes and fail to comprehensively capture similarity. To tackle this issue, in this study, we propose a novel cancer subtype recognition method, referred to as PCA-constrained multi-core matrix fusion network (PCA-MM-FN). The PCA-MM-FN algorithm initially employs three distinct methods to obtain three core matrices. Subsequently, the obtained core matrices are projected into a shared subspace using principal component analysis, followed by a weighted network fusion. Lastly, spectral clustering is conducted on the fused network. The results obtained from conducting experiments on the mRNA expression, DNA methylation, and miRNA expression of five TCGA datasets and three multi-omics benchmark datasets demonstrate that the proposed PCA-MM-FN approach exhibits superior accuracy in identifying cancer subtypes compared to the existing methods.

A new single magnetic core coupled-inductor based active switched Quasi Z-source inverter

This paper presents a novel topology for Z-source inverters (ZSI). The new Z-Source network is based on the coupled-inductors and active switched boost. Features of the topology include high voltage boost ability, single magnetic-core, low voltage stress on the active switch, and capacitors. The principles of operation, analysis, voltage and current equations of each component, and the converter voltage gain in the steady-state are presented. A comparison with other topologies has also been performed to determine the advantages and disadvantages of the proposed ZSI. Finally, experimental results of the laboratory prototype are presented to confirm the performance of the proposed topology.

Ultracompact 3D Splitter for Single‐Core to Multi‐Core Optical Fiber Connections Fabricated Through Direct Laser Writing in Polymer

AbstractThe deployment and advancement of high‐bandwidth communication networks, quantum information systems, and sensing platforms relying on multi‐core optical fibers (MCFs) are challenged by the scarcity of cost‐effective, compact, and efficient optical interfacing components. This study introduces an unprecedented 3D‐printed 1 × 4 splitter for MCFs fabricated with 2‐photon polymerization‐based direct laser writing. The pivotal element is a triangular cross‐section 3D multimode interference (MMI) coupler, supplemented with S‐bends and adiabatic tapers to facilitate the splitting of a signal from a single core of a single‐mode fiber into four cores of a multi‐core fiber. All components are initially designed and assessed to minimize loss and polarization dependence across the C‐ and L‐bands using optical simulation. Subsequently, a proof‐of‐concept model of the splitter, compactly integrated within the fiber volume, featuring a remarkably short length of 180 µm and insertion loss of ≈−3 dB, is fabricated. The manufacturing speed, minimal loss, component compactness, and flexibility of the approach, collectively present promising avenues for pioneering developments in MCF‐coupling components.

Features of the part-speech composition of terms of international air law in English and Russian languages

The work reveals a problem of the part-of-speech composition in terms of the English and Russian languages in international air law. The study presents an analysis of the parts of speech included in the term structure in international air law according to the criterion of certain terminological field. The purpose of the study is to determine the most characteristic part-of-speech composition for the terms of several groups, identified on the basis of a common field in terminological systems Russian and English. This principle of analysis helps to compare terminological groups in different language systems. The objectives of the study were to identify the frequency of a certain part-ofspeech structure for the terms of the Russian and English languages. The work presents an empirical study, which prove that the proposed version of the analysis makes it possible to compare each lexical and semantic group in the English language with the Russian language in terms of the frequency of a certain part-of-speech structure; to identify the main dynamics in certain part-ofspeech structures in the English and Russian terminological systems of international air law. Based on the results of the study, the following conclusions were made: comparative analysis of the partof-speech structure based on the criterion of a single semantic core within the branch of international air law is the most objective criterion that allows the comparison of terms from two different language systems within the framework of cross-linguistic research; part-of-speech structures of terms are directly related to the structural features of the Russian and English languages.

A feasible method to prepare yolk@shell nanoreactor with multiple cores and enhanced Fenton-like performance by confinement effect

At present, yolk@shell nanoreactor has drawn much attention in Fenton reaction, since the degradation rate could be accelerated by confinement effect, and metal leaching could be suppressed under the shell protection. To further improve the performance of traditional yolk@shell nanoreactor with single core, in this work, a yolk@shell nanoreactor with multiple CoFe nanoparticles as cores and nitrogen-atom doped carbon (NC) as shell was prepared. In peroxymonosulfate (PMS)-based Fenton-like reaction, 93.8 % of degradation efficiency was realized within 30 min over CoFe@NC, much better than the reference broken CoFe@NC (B-CoFe@NC), confirming the positive function of integrated yolk@shell structure. Based on the radical trapping experiment, 1O2 was the most important reactive oxygen species in CoFe@NC, while SO4•- played a dominated role in B-CoFe@NC, reflecting the different catalytic mechanism in these two catalysts. To reveal the confinement effect, electron paramagnetic resonance analysis was carried out to trace the 1O2 source. And they were originated from SO4•- and •OH with high concentrations inside the yolk@shell CoFe@NC nanoreactor. This study provided a novel method to construct yolk@shell nanoreactor with multiple cores and gave a novel insight on enhanced Fenton-like performance via confinement effect.

Latitudinal patterns of shifts in cladoceran communities throughout the Holocene: A paleoecological case study of northwestern Russia

Paleolimnology is a rapidly expanding field within the natural sciences. To date, many scientific papers have been published focusing on studies of remains from single sediment cores in specific lakes, or a few cores from the same water body. However, few previous publications have provided a comprehensive comparative analysis of taphocenosis (and maternal community) changes in different water bodies from a large geographical region during whole Holocene using multivariate statistical methods. We conducted a joined statistical analysis of data obtained as a result of the cladoceran analysis of the sediment samples from six cores taken along the North-South transect from the Kola Peninsula to the Karelian Region (North-West Russia). Our aim was to identify, based on quantitative statistical methods, general whole-Holocene patterns in cladoceran taphocenosis changes. All taphocenoses in all cores from six lakes can be classified into six clusters based on their species composition. Our unexpected conclusion is that different taphocoenoses are formed by the same set of species, but their proportions vary significantly. This suggests that the same species may play different functional roles in different maternal communities. During whole Holocene, we observed a single taphocenosis cluster in the Holocene core from Lake Antyukh-Lambina, and four taphocenosis clusters in the Lake Medvedevskoe, with an intermediate number of clusters in the lakes between them. Furthermore, it can be asserted that the potential for cluster changes in the core is greater for the more southern studied water bodies (0–3 clusters for northern lakes vs. 4 clusters for southern lakes). Based on our data, we hypothesize that the diversity of cladoceran associations during the Holocene was lower in Arctic/Subarctic lakes, possibly due to their formation by ubiquitous species. Our study suggests that at least some Arctic lake ecosystems have remained unchanged since deglaciation times. Further studies are necessary to determine if this is a general rule.

Enhancing Prostate Cancer Diagnosis: Artificial Intelligence–Driven Virtual Biopsy for Optimal Magnetic Resonance Imaging-Targeted Biopsy Approach and Gleason Grading Strategy

An optimal approach to magnetic resonance imaging fusion targeted prostate biopsy (PBx) remains unclear (number of cores, intercore distance, Gleason grading [GG] principle). The aim of this study was to develop a precise pixel-wise segmentation diagnostic artificial intelligence (AI) algorithm for tumor detection and GG as well as an algorithm for virtual prostate biopsy that are used together to systematically investigate and find an optimal approach to targeted PBx. Pixel-wise AI algorithms for tumor detection and GG were developed using a high-quality, manually annotated data set (slides n = 442) after fast-track annotation transfer into segmentation style. To this end, a virtual biopsy algorithm was developed that can perform random biopsies from tumor regions in whole-mount whole-slide images with predefined parameters. A cohort of 115 radical prostatectomy (RP) patient cases with clinically significant, magnetic resonance imaging-visible tumors (n = 121) was used for systematic studies of the optimal biopsy approach. Three expert genitourinary (GU) pathologists (Y.T., A.P., A.Q.) participated in the validation. The tumor detection algorithm (aware version sensitivity/specificity 0.99/0.90, balanced version 0.97/0.97) and GG algorithm (quadratic kappa range vs pathologists 0.77-0.78) perform on par with expert GU pathologists. In total, 65,340 virtual biopsies were performed to study different biopsy approaches with the following results: (1) 4 biopsy cores is the optimal number for a targeted PBx, (2) cumulative GG strategy is superior to using maximal Gleason score for single cores, (3) controlling for minimal intercore distance does not improve the predictive accuracy for the RP Gleason score, (4) using tertiary Gleason pattern principle (for AI tool) in cumulative GG strategy might allow better predictions of final RP Gleason score. The AI algorithm (based on cumulative GG strategy) predicted the RP Gleason score of the tumor better than 2 of the 3 expert GU pathologists. In this study, using an original approach of virtual prostate biopsy on the real cohort of patient cases, we find the optimal approach to the biopsy procedure and the subsequent GG of a targeted PBx. We publicly release 2 large data sets with associated expert pathologists’ GG and our virtual biopsy algorithm.

Optimizing and Implementing Fischlin's Transform for UC-Secure Zero Knowledge

Fischlin's transform (CRYPTO 2005) is an alternative to the Fiat-Shamir transform that enables straight-line extraction when proving knowledge. In this work we focus on the problem of using the Fischlin transform to construct UC-secure zero-knowledge from Sigma protocols, since UC security – that guarantees security under general concurrent composition – requires straight-line (non-rewinding) simulators. We provide a slightly simplified transform that is much easier to understand, and present algorithmic and implementation optimizations that significantly improve the running time. It appears that the main obstacles to the use of Fischlin in practice is its computational cost and implementation complexity (with multiple parameters that need to be chosen). We provide clear guidelines and a simple methodology for choosing parameters, and show that with our optimizations the running-time is far lower than expected. For just one example, on a 2023 MacBook, the cost of proving the knowledge of discrete log with Fischlin is only 0.41ms (on a single core). This is 15 times slower than plain Fiat-Shamir on the same machine, which is a significant multiple but objectively not significant in many applications. We also extend the transform so that it can be applied to batch proofs, and show how this can be much more efficient than individually proving each statement. We hope that this paper will both encourage and help practitioners implement the Fischlin transform where relevant.

Coarse to superfine: can hyperspectral soil organic carbon models predict higher-resolution information?

Introduction: Modeling and mapping of soil organic carbon concentration and distribution at the pedon scale is a current knowledge gap that can be addressed by laboratory-based hyperspectral imaging and chemometric analysis of soil cores. Despite the advancements in soil organic carbon models based on hyperspectral images, it is not clear how these models will perform upon input with images at higher resolutions than those of their training sets. This study aims to measure the generalizability of a soil organic carbon model based on a test set with higher resolution hyperspectral images than that of its training set.Methods: Organic carbon contents were measured at 10 cm intervals on eight soil cores for use as the training set and at 1 cm intervals on a single core for use as the test set. Three regression models, namely, multilayer perceptron, partial least-squares, and support vector regressions, were trained and tested with the median of each hyperspectral image for each of these intervals as the training and test predictors. Permutation importance analysis was performed to explain the models.Results: The results show that although all three models had the same validation R2 of 0.92 for cross-validation on the 10 cm data, multilayer perceptron regression allowed the best generalization with a test R2 of 0.96 compared to the partial least-squares regression (0.81) and support vector regression (0.86). It was demonstrated that the multilayer perceptron model is more robust to soil surface anomalies and that it predicts soil organic carbon on the test set by learning the spectral features related to soil organic matter chromophore activity in the 950–1,150 nm region along with clay mineralogy derived from peaks at 1,400, 1,900, 2,200, 2,250, and 2,350 nm.Conclusions: This study shows that while the regression models based on hyperspectral images perform well at the 10-cm-resolution cross validation, multilayer perceptron regression shows superior generalization and robustness for a higher 1-cm-resolution test set without much loss of prediction power.