Spectral Information Research Articles

Metabolites rapid-annotation in mice by comprehensive method of virtual polygons and Kendric mass loss filtering: A case study of Dendrobium nobile Lindl

With significant advancements in high-resolution mass spectrometry, there has been a substantial increase in the amount of chemical component data acquired from natural products. Therefore, the rapid and efficient extraction of valuable mass spectral information from large volumes of high-resolution mass spectrometry data holds crucial significance. This study illustrates a targeted annotation of the metabolic products of alkaloid and sesquiterpene components from Dendrobium nobile (D. nobile) aqueous extract in mice serum through the integration of an in-houses database, R programming, a virtual metabolic product library, polygonal mass defect filtering, and Kendrick mass defect strategies. The research process involved initially establishing a library of alkaloids and sesquiterpenes components and simulating 71 potential metabolic reactions within the organism using R programming, thus creating a virtual metabolic product database. Subsequently, employing the virtual metabolic product library allowed for polygonal mass defect filtering, rapidly screening 1705 potential metabolites of alkaloids and 3044 potential metabolites of sesquiterpenes in the serum. Furthermore, based on the chemical composition database of D. nobile and online mass spectrometry databases, 95 compounds, including alkaloids, sesquiterpenes, and endogenous components, were characterized. Finally, utilizing Kendrick mass defect analysis in conjunction with known alkaloids and sesquiterpenes targeted screening of 209 demethylation, methylation, and oxidation products in phase I metabolism, and 146 glucuronidation and glutathione conjugation products in phase II metabolism. This study provides valuable insights for the rapid and accurate annotation of chemical components and their metabolites in vivo within natural products.

Polarized Hyperspectral Microscopic Imaging for Zebrafish.

Zebrafish is a well-established animal model for developmental and disease studies. Its optical transparency at early developmental stages is ideal for tissue visualization. Interaction of light with zebrafish tissues provides information on their structure and properties. In this study, we developed a microscopic imaging system for improving the visualization of unstained zebrafish tissues on tissue slides, with two different setups: polarized light imaging and polarized hyperspectral imaging. Based on the polarized light imaging setup, we collected the RGB images of Stokes vector parameters (S0, S1, S2, and S3), and calculated the Stokes vector derived parameters: the degree of polarization (DOP), the degree of linear polarization (DOLP)). We also calculated Stokes vector data based on the polarized hyperspectral imaging setup. The preliminary results demonstrate that Stokes vector data in two imaging setups (polarized light imaging and polarized hyperspectral imaging) are capable of improving the visualization of different types of zebrafish tissues (brain, muscle, skin cells, blood vessels, and yolk). Using the images collected from larval zebrafish samples by polarized light imaging, we found that DOP and DOLP could show clearer structural information of the brain and of skin cells, muscle and blood vessels in the tail. Furthermore, DOP and DOLP parameters derived from images collected by polarized hyperspectral imaging could show clearer structural information of skin cells developing around yolk as well as the surrounding blood vessel network. In addition, polarized hyperspectral imaging could provide complementary spectral information to the spatial information on Stokes vector data of zebrafish tissues. The polarized light imaging & polarized hyperspectral imaging systems provide a better insight into the microstructures of zebrafish tissues.

Application of hyperspectral imaging for characterization of VOC-induced historical glass corrosion

Hyperspectral imaging (HSI) provides high-resolution recording of the spectral information at every spatial point (pixel) of an object throughout a contiguous range of wavelengths. This paper reports an attempt at exploring the application of HSI in transmittance mode for the identification and quantification of corrosion in transparent historical glass, which is difficult to identify by visual inspection. This was done using model glass samples mimicking historical composition and subjected to artificial ageing in the presence of volatile organic compounds. Hyperspectral images of unaged and aged glass samples were recorded with two cameras covering visible and near infrared (VNIR, 400–1000 nm) and short-wave infrared range (SWIR, 1000–2500 nm) using a custom-made HSI set-up in transmission mode. The HSI data were further processed to classify and visualize corrosion in different ageing environments and ageing periods. The results show that HSI can be employed as a valuable tool to assess glass corrosion at early stages, especially by analysing the SWIR spectral region—which shows the water absorption by the glass matrix due to corrosion.

Experimental Investigation on the Influence of Observation Angle on the Spectral Characteristics of Minerals in the Visible-Near Infrared Range

The analysis of the factors affecting the spectral characteristics of rock minerals is the basis of improving the accuracy of quantitative inversion of spectral minerals. Hyperspectral remote sensing has advantages and development potential in the quantitative inversion of minerals, but it is limited by many constraints and influencing factors in the process of remote sensing recognition of rock and mineral spectral information. In practical application, satellite earth observation is affected by terrain fluctuation, which leads to some deviation of observation Angle. At the same time, vertical samples are often used in the experiment to reduce the spectral experimental error. Therefore, the spectral observation Angle plays an important role in determining the composition of rock and ore. In order to study the effect of different observation angles on the reflectance spectra of minerals, the spectral reflectance spectra were analyzed in the visible near-infrared (0.4-2.5μm) band to explore the variation rules. First, common quartz, orthoclase and plagioclase minerals were sliced and polished to make block samples with fixed roughness values. The incident Angle of light source was fixed, and the influence of different observation angles on the visible near-infrared spectral characteristics of minerals was analyzed by changing the Angle of emergence and azimuth. Secondly, through the qualitative and quantitative analysis of the results and the mechanism analysis, it can be concluded that the effect of zenith Angle on spectral reflectance is the same under different observation azimuth angles. The observed zenith Angle has a great influence on the spectral reflectance, which is reflected in the fact that the reflectance of mineral samples gradually increases with the increasing of the zenith Angle to reach the peak value within 30°~50°, and then gradually decreases. The spectral reflectance at 0°-360° azimuth is symmetrical, and the spectral reflectance is oscillatory, and the reflectance at 180° azimuth is the highest. The overall situation gradually increases from 0°-180° spectral reflectance, and gradually decreases from 180°-360° spectral reflectance. With the change of observation Angle, the peak and trough of the reflectance of the sample are basically located in the same band position. It is of great significance to realize the accurate division of rock mining area and to exploit mineral resources reasonably and efficiently.

Stability of periodic waves for the defocusing fractional cubic nonlinear Schrödinger equation

In this paper, we determine the spectral instability of periodic odd waves for the defocusing fractional cubic nonlinear Schrödinger equation. Our approach is based on periodic perturbations that have the same period as the standing wave solution, and we construct real periodic waves by minimizing a suitable constrained problem. The odd solution generates three negative simple eigenvalues for the associated linearized operator, and we obtain all this spectral information by using tools related to the oscillation theorem for fractional Hill operators. Newton’s iteration method is presented to generate the odd periodic standing wave solutions and numerical results have been used to apply the spectral stability theory via Krein signature as established in Kapitula et al. (2004) and Kapitula et al. (2005).

Estimating Winter Wheat Plant Nitrogen Content by Combining Spectral and Texture Features Based on a Low-Cost UAV RGB System throughout the Growing Season

As prior information for precise nitrogen fertilization management, plant nitrogen content (PNC), which is obtained timely and accurately through a low-cost method, is of great significance for national grain security and sustainable social development. In this study, the potential of the low-cost unmanned aerial vehicle (UAV) RGB system was investigated for the rapid and accurate estimation of winter wheat PNC across the growing season. Specifically, texture features were utilized as complements to the commonly used spectral information. Five machine learning regression algorithms, including support vector machines (SVMs), classification and regression trees, artificial neural networks, K-nearest neighbors, and random forests, were employed to establish the bridge between UAV RGB image-derived features and ground-truth PNC, with multivariate linear regression serving as the reference. The results show that both spectral and texture features had significant correlations with ground-truth PNC, indicating the potential of low-cost UAV RGB images to estimate winter wheat PNC. The H channel, S4O6, and R_SE and R_EN had the highest correlation among the spectral indices, Gabor texture features, and grey level co-occurrence matrix texture features, with absolute Pearson’s correlation coefficient values of 0.63, 0.54, and 0.69, respectively. When the texture features were used together with spectral indices, the PNC estimation accuracy was enhanced, with the root mean square error (RMSE) decreasing from 2.56 to 2.24 g/kg, for instance, when using the SVM regression algorithm. The SVM regression algorithm with validation achieved the highest estimation accuracy, with a coefficient of determination (R2) of 0.62 and an RMSE of 2.15 g/kg based on the optimal feature combination of B_CON, B_M, G_DIS, H, NGBDI, R_EN, R_M, R_SE, S3O7, and VEG. Overall, this study demonstrated that the low-cost UAV RGB system could be successfully used to map the PNC of winter wheat across the growing season.

A novel framework combining band selection algorithm and improved 3D prototypical network for tree species classification using airborne hyperspectral images

Fine-grained identification of forest types and tree species represents a critical aspect of forest resource inventory and monitoring. The use of airborne hyperspectral remote sensing imagery stands out for its ability to finely differentiate among tree species, leveraging its exceptional spatial resolution and rich spectral details. However, this approach is limited by several challenges (e.g., high spectral correlation and information redundancy). In accordance, the adoption of a lightweight deep learning approach in the form of a few-shot learning model can effectively resolve the challenges of multi-forest tree species classification. Therefore, integrating a data dimensionality reduction algorithm with a few-shot classification model presents a promising avenue for resolving the fine-grained classification of forest tree species. In this study, we propose the innovative classification framework FAST 3D-CNN P-Net. This framework utilizes CNN for band selection, enhances the fine-grained identification process in hyperspectral data, and integrates an optimized FAST 3D-CNN into the P-Net classifier (a few-shot classifier). First, a CNN-based band selection method is employed to learn the nonlinear dependencies between spectral bands, assign weights to rank the bands, and reconstruct the global spectral information using the most informative bands. It then constructs a novel classification model, designated FAST 3D-CNN P-Net, through the integration of an optimal 3D-CNN with a prototypical network. To enhance classification performance, the FAST 3D-CNN P-Net utilizes reconstructed hyperspectral images derived from the band selection results as input. The effectiveness of the proposed framework was assessed with the airborne GFF dataset and the widely accessible medium-resolution hyperspectral datasets, Indian Pines (IP) and Kennedy Space Center (KSC). The overall classification accuracy reached 98.33 % for the GFF dataset and 97.21 % and 99.43 % for the IP and KSC, respectively, exhibiting performance superiority compared to the standalone 3D-CNN classification network. This classification framework demonstrates efficiency in selecting a subset of hyperspectral bands with minimal redundancy, empowering the rapid and accurate classification and mapping of tree species in complicated, multi-species forest stands, even with a limited quantity of labeled samples.

Granite Extraction Based on the SDGSAT-1 Satellite Thermal Infrared Spectrometer Imagery.

Earth observation by remote sensing plays a crucial role in granite extraction, and many current studies use thermal infrared data from sensors such as ASTER. The challenge lies in the low spatial resolution of these satellites, hindering precise rock type identification. A breakthrough emerges with the Thermal Infrared Spectrometer (TIS) on the Sustainable Development Science Satellite 1 (SDGSAT-1) launched by the Chinese Academy of Sciences. With an exceptional 30 m spatial resolution, SDGSAT-1 TIS opens avenues for accurate granite extraction using remote sensing. This study, exemplified in Xinjiang's Karamay region, introduces the BR-ISauvola method, leveraging SDGSAT-1 TIS data. The approach combines band ratio with adaptive k-value selection using local grayscale statistical features for Sauvola thresholding. Focused on large-scale granite extraction, results show F1 scores above 70% for Otsu, Sauvola, and BR-ISauvola. Notably, BR-ISauvola achieves the highest accuracy at 82.11%, surpassing Otsu and Sauvola by 9.62% and 0.34%, respectively. This underscores the potential of SDGSAT-1 TIS data as a valuable resource for granite extraction. The proposed method efficiently utilizes spectral information, presenting a novel approach for rapid granite extraction using remote sensing TIS imagery, even in scenarios with low spectral resolution and a single data source.

A novel graph-attention based multimodal fusion network for joint classification of hyperspectral image and LiDAR data

The joint classification of hyperspectral image (HSI) and Light Detection and Ranging (LiDAR) data can provide complementary information for each other, which has become a prominent topic in the field of remote sensing. Nevertheless, the common CNN-based fusion techniques still suffer from the following drawbacks. (1) Most of these models omit the correlation and complementarity between different data sources and always fail to model the long-distance dependencies of spectral information well. (2) Simply splicing the multi-source feature embeddings overlooks the deep semantic relationships among them. To tackle these issues, we propose a novel graph-attention based multimodal fusion network (GAMF). Specifically, it employs three major components, including an HSI–LiDAR feature extractor, a graph-attention based fusion module and a classification module. In the feature extraction module, we consider the correlation and complementarity between multi-sensor data by parameter sharing and employ Gaussian tokenization for feature transformation additionally. To address the problem of long-distance dependencies, the deep fusion module utilizes modality-specific tokens to construct an undirected weighted graph, which is essentially a heterogeneous graph. And the deep semantic relationships between them are exploited utilizing a graph-attention based fusion framework. At the end, two fully connected layers classify the fused embeddings. Experiment evaluations on several benchmark HSI–LiDAR datasets (Trento, University of Houston 2013 and MUUFL) show that GAMF achieves more accurate prediction results than some state-of-the-art baselines. The code is available at https://github.com/tyust-dayu/GAMF.

A high resolution prism-grating panoramic imaging spectrometer based on occultation observations

Occultation observation is an important technique for shadow region detection and a significant complement to the illuminated region detection method. This technology will significantly reduce the impact of background light pollution and provide clearer occultation signals. In order to achieve high-resolution all-round detection in the shadow region, this paper introduces a proposal for a prism-grating panoramic imaging spectrometer based on occultation observations. It utilizes a panoramic annular lens to enable 360-degree occultation observations within the shadow region, combines a grating for spectral separation to obtain spectral information, and achieves an overall straight-line design for the system by adjusting the prism-grating surface's deflection angle. This paper, by analyzing the non-uniformity of light rays from different fields of view after dispersion by the grating, obtains the coordinate information of the spectrum on the image plane, significantly improving the accuracy of subsequent spectral calibration. The design results indicate that the optical system of this imaging spectrometer achieves a spectral resolution of 0.67 nm in the wavelength range of 365–770 nm. At a Nyquist frequency of 37.04lp/mm, the MTF across the entire bandwidth exceeds 0.6. The RMS of the point spread function is less than 9 μm across the full field of view, and aberration correction is excellent. This imaging spectrometer utilizes stellar occultations to achieve real-time 360-degree observations in the shadow region, and at the same time obtains total information on atmospheric components and contour information that varies with occultation height. This scheme offers a more comprehensive information for scientists in related fields.

FASO-C: A rapid visualization technique based on optimized fusion with crossover-based atom search for multi-band imagery

Multi-band image fusion is a vital image processing technique used to combine data from multiple images or sensor bands, particularly in scenarios where a wide range of spectral information is available. Its primary objective is to create a single, comprehensive image that not only visually enhances the scene but also preserves critical details and characteristics present in each source. This paper proposes a novel image fusion technique that combines the useful features from a set of source images to provide a quick visualization of the scene. The approach is highly beneficial for multi-band images, including a large number of bands acquired by sampling the wavelength spectrum at narrow intervals. The fusion process depends on a multi-objective cost function, which optimizes the resultant fused image according to specific desired characteristics. By solving this optimization framework, an optimal set of weights is obtained using a novel Fusion-Driven Atom Search Optimization with Crossover (FASO-C) algorithm for the fusion of the image bands. Crossover operation enhances the exploitation capability of ASO, enabling the global optimal solution to be achieved quickly. To further validate the effectiveness of the proposed fusion model, various experiments were conducted to assess its performance using both subjective and objective metrics, as well as analyze its convergence.

Improving the performance of a spectral model to estimate total nitrogen content with small soil samples sizes

The application of near-infrared spectroscopy (NIRS) for rapid quantitative analysis of soil total nitrogen (STN) is of great significance to recycling nitrogen in the ecosystem and crops growth. However, collecting thousands of soil samples and chemical analysis are impracticable, more importantly a deviation from NIRS advantages of rapid, inexpensive and nondestructive. To more efficiently improve the estimation performance and reduce uncertainty of the model when working with small sample sizes (less than 100), solutions from soil particle size decomposition and model fusion were investigated. Elaborately, 123 Latosols samples were collected and decomposed them according to particle sizes to extend limited data at multiple scales. Based on all soil groups decomposed, a hyperspectral data recapture and model decision fusion method were implemented. The results demonstrated that the proposed method increased the scale of spectral data, extracted more STN-related spectral information, improved estimation accuracy, and reduced uncertainty. The fused model based on data from all decomposed groups yielded the best estimated results (root mean square error (RMSE)=0.075g.kg-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(RMSE) = 0.075g.kg^{-1}$$\\end{document}, R2=0.784\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2 = 0.784$$\\end{document}, and a ratio of performance to inter-quartile distance (RPIQ)=3.787\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(RPIQ) = 3.787$$\\end{document}) on the validation set. Through a tenfold cross-validation, the weighted fusion model with six groups of particle sizes data showed an improvement of 0.307 in Rc2v\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2_cv$$\\end{document} and an improved RPIQ of 1.015 compared to models constructed using conventional machine learning (ML) techniques and limited pristine data (Rc2v=0.442,RMSE=0.119\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2_cv = 0.442, RMSE = 0.119$$\\end{document}). Therefore, when utilizing NIRS to build rapid and accurate STN predictive models, the proposed method demonstrates great potential in improving the reliability of soil spectral models under small sample sizes.Graphical

MMDL-Net: Multi-Band Multi-Label Remote Sensing Image Classification Model

High-resolution remote sensing imagery comprises spatial structure features of multispectral bands varying in scale, color, and shape. These heterogeneous geographical features introduce grave challenges to the fine segmentation required for classification applications in remote sensing imagery, where direct application of traditional image classification models fails to deliver optimal results. To overcome these challenges, a multispectral, multi-label model, MMDL-Net, has been developed. This model is integrated with the multi-label BigEarthNet dataset, primarily employed for land cover classification research in remote sensing imagery, with each image composed of 13 spectral bands and spatial resolutions of 10 m, 20 m, and 60 m. To effectively utilize the information across these bands, a multispectral stacking module has been introduced to concatenate this spectral information. To proficiently process three distinct large-scale remote sensing image datasets, a multi-label classification module has been incorporated for training and inference. To better learn and represent the intricate features within the images, a twin-number residual structure has been proposed. The results demonstrate that the MMDL-Net model achieves a top accuracy of 83.52% and an F1 score of 77.97%, surpassing other deep learning models and conventional methods, thereby exhibiting exceptional performance in the task of multispectral multi-label classification of remote sensing imagery.

Robust domain decomposition methods for high-contrast multiscale problems on irregular domains with virtual element discretizations

Our research focuses on the development of domain decomposition preconditioners tailored for second-order elliptic partial differential equations. Our approach addresses two major challenges simultaneously: i) effectively handling coefficients with high-contrast and multiscale properties, and ii) accommodating irregular domains in the original problem, the coarse mesh, and the subdomain partition. The robustness of our preconditioners is crucial for real-world applications, such as the efficient and accurate modeling of subsurface flow in porous media and other important domains.The core of our method lies in the construction of a suitable partition of unity functions and coarse spaces utilizing local spectral information. Leveraging these components, we implement a two-level additive Schwarz preconditioner. We demonstrate that the condition number of the preconditioned systems is bounded with a bound that is independent of the contrast. Our claims are further substantiated through selected numerical experiments, which confirm the robustness of our preconditioners.

Distinction and quantification of Panax polysaccharide extracts via attenuated total reflectance-Fourier transform infrared spectroscopy with first-order derivative processing

Derivative spectroscopy is used to separate the small absorption peaks superimposed on the main absorption band, which is widely adopted in modern spectral analysis to increase both the valid spectral information and the identification accuracy. In this study, a method based on attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) with first-order derivative (FD) processing combined with chemometrics is proposed for rapid qualitative and quantitative analysis of Panax ginseng polysaccharides (PGP), Panax notoginseng polysaccharides (PNP), and Panax quinquefolius polysaccharides (PQP). First, ATR-FTIR with FD processing was used to establish the discriminant model combined with principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA). After that, two-dimensional ATR-FTIR based on single-characteristic temperature as external interference (2D-sATR-FTIR) was established using ATR-FTIR with FD processing. Then, ATR-FTIR with FD processing was combined with PLS to establish and optimize the quantitative regression model. Finally, the established discriminant model and 2D-sATR-FTIR successfully distinguished PGP, PNP and PQP, and the optimal PLS regression model had a good prediction ability for the Panax polysaccharide extracts content. This strategy provides an efficient, economical and nondestructive method for the distinction and quantification of PGP, PNP and PQP in a short detection time.

Beam hardening correction based on image noise statistics

Beam hardening artefacts in x-ray computed tomography (CT) result from energy-dependent attenuation of x-rays in matter and cause inaccuracies in reconstructed 3D volume data. Effects due to beam hardening can easily be corrected if the detected spectrum of x-rays is known after having passed through an object. Conventional scintillator x-ray detectors, however, are incapable of measuring spectral information directly. The innovative idea of this paper is to extract information about the detected spectrum from image noise statistics and to estimate the spectrum using a new semi-empirical model function for a partially absorbed x-ray spectrum depending on a single unknown variable. The beam hardening correction factor is thus determined for each image pixel prior to the 3D reconstruction, does not require knowledge of the material of the CT-scanned object and is determined by modelling physical effects directly, without relying on an iterative approach or elaborate image processing.

First Constraints on the Photon Coupling of Axionlike Particles from Multimessenger Studies of the Neutron Star Merger GW170817.

We use multimessenger observations of the neutron star merger event GW170817 to derive new constraints on axionlike particles (ALPs) coupling to photons. ALPs are produced via Primakoff and photon coalescence processes in the merger, escape the remnant, and decay back into two photons, giving rise to a photon signal approximately along the line of sight to the merger. We analyze the spectral and temporal information of the ALP-induced photon signal and use the Fermi Large Area Telescope (Fermi-LAT) observations of GW170817 to derive our new ALP constraints. We also show the improved prospects with future MeV γ-ray missions, taking the spectral and temporal coverage of Fermi-LAT as an example.

Enhancing detection of volcanic ash clouds from space with convolutional neural networks

Volcanic ash cloud detection is a crucial component of volcano monitoring and a valuable tool for investigating ash cloud dispersion, which is paramount for enhancing the safety of human settlements and air traffic. The latest generation of high-resolution satellite sensors (e.g., EUMETSAT MSG Spinning Enhanced Visible and InfraRed Imager, SEVIRI) provides radiometric estimates for monitoring volcanic clouds on a global scale efficiently and timely. However, these radiometric intensities are not always discriminative enough to detect volcanic ash clouds due to the spectral limitations of these instruments and the complex nature of some volcanic clouds, such as low concentration resulting in an averaged detected radiometric estimate comparable to the background. Here, we evaluate the ability of a Convolutional Neural Network (CNN) to detect and track the dispersion of volcanic ash clouds into the atmosphere, exploiting a variety of spatial and spectral intensity information mainly coming from SEVIRI Ash RGB images. We train a deep CNN model through transfer learning, and demonstrate that the trained models overcome the limitations of algorithms based solely on pixel intensity, whether traditional or machine learning, resulting in increased performance compared to other methods. We illustrate the operation of this model using the paroxysmal explosive events that occurred at Mt. Etna between 2020 and 2022.

Machine learning in the classification of asian rust severity in soybean using hyperspectral sensor

Traditional monitoring of asian soybean rust severity is a time- and labor-intensive task, as it requires visual assessments by skilled professionals in the field. Thus, the use of remote sensing and machine learning (ML) techniques in data processing has emerged as an approach that can increase efficiency in disease monitoring, enabling faster, more accurate and time- and labor-saving evaluations. The aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels; (iii) which spectral input provides the highest classification accuracy for the algorithms; (iv) to determine a sample size of leaves that guarantees the best accuracy for the algorithms. A field experiment was carried out in the 2022/2023 harvest in a randomized block design with a 6x3 factorial scheme (ML algorithms x severity levels) and four replications. Disease severity levels assessed were: healthy leaves, 25 % severity, and 50 % severity. Leaf hyperspectral analysis was carried out over a wide range from 350 to 2500 nm. From this analysis, 28 spectral bands were extracted, seeking to distinguish the spectral signature for each severity level with the least input dataset. Data was subjected to machine learning analysis using Artificial Neural Network (ANN), REPTree (DT) and J48 decision trees, Random Forest (RF), and Support Vector Machine (SVM) algorithms, as well as a traditional classification method (Logistic Regression - LR). Two different input datasets were tested for each algorithm: the full spectrum (ALL) provided by the sensor and the 28 spectral bands (SB). Tests with different sample sizes were also conducted to investigate the algorithms' ability to detect severity levels with a reduced sample size. Our findings indicate differences between the spectral curves for the severity levels assessed, which makes it possible to differentiate between healthy plants with low and high severity using hyperspectral sensing. SVM was the most accurate algorithm for classifying severity levels by using all the spectral information as input. This algorithm also provided high classification accuracy when using smaller leaf samples. This study reveals that hyperspectral sensing and the use of ML algorithms provide an accurate classification of different levels of Asian rust severity, and can be powerful tools for a more efficient disease monitoring process.

PyM2aia: Python interface for mass spectrometry imaging with focus on deep learning.

Python is the most commonly used language for deep learning (DL). Existing Python packages for mass spectrometry imaging (MSI) data are not optimized for DL tasks. We, therefore, introduce pyM2aia, a Python package for MSI data analysis with a focus on memory-efficient handling, processing and convenient data-access for DL applications. pyM2aia provides interfaces to its parent application M2aia, which offers interactive capabilities for exploring and annotating MSI data in imzML format. pyM2aia utilizes the image input and output routines, data formats, and processing functions of M2aia, ensures data interchangeability, and enables the writing of readable and easy-to-maintain DL pipelines by providing batch generators for typical MSI data access strategies. We showcase the package in several examples, including imzML metadata parsing, signal processing, ion-image generation, and, in particular, DL model training and inference for spectrum-wise approaches, ion-image-based approaches, and approaches that use spectral and spatial information simultaneously. Python package, code and examples are available at (https://m2aia.github.io/m2aia).