Search Results (141)

This research presents DuSAFNet, a lightweight deep neural network for fine-grained bird audio classification. DuSAFNet combines dual-path feature fusion, spectral–temporal attention, and a multi-band ArcMarginProduct classifier to enhance inter-class separability and capture both local and global spectro–temporal cues. Unlike single-feature approaches, DuSAFNet captures both local spectral textures and long-range temporal dependencies in Mel-spectrogram inputs and explicitly enhances inter-class separability across low, mid, and high frequency bands. On a curated dataset of 17,653 three-second recordings spanning 18 species, DuSAFNet achieves 96.88% accuracy and a 96.83% F1 score using only 6.77 M parameters and 2.275 GFLOPs. Cross-dataset evaluation on Birdsdata yields 93.74% accuracy, demonstrating robust generalization to new recording conditions. Its lightweight design and high performance make DuSAFNet well-suited for edge-device deployment and real-time alerts for rare or threatened species. This work lays the foundation for scalable, automated acoustic monitoring to inform biodiversity assessments and conservation planning. Full article

Accurate, detailed, and up-to-date tree species distribution information is essential for effective forest management and environmental research. However, existing tree species maps face limitations in resolution and update cycle, making it difficult to meet modern demands. To overcome these limitations, this study proposes a novel framework that utilizes existing medium-resolution national tree species maps as ‘weak labels’ and fuses multi-temporal Sentinel-2 and PlanetScope satellite imagery data. Specifically, a super-resolution (SR) technique, using PlanetScope imagery as a reference, was first applied to Sentinel-2 data to enhance its resolution to 2.5 m. Then, these enhanced Sentinel-2 bands were combined with PlanetScope bands to construct the final multi-spectral, multi-temporal input data. Deep learning (DL) model training data was constructed by strategically sampling information-rich pixels from the national tree species map. Applying the proposed methodology to Sobaeksan and Jirisan National Parks in South Korea, the performance of various machine learning (ML) and deep learning (DL) models was compared, including traditional ML (linear regression, random forest) and DL architectures (multilayer perceptron (MLP), spectral encoder block (SEB)—linear, and SEB-transformer). The MLP model demonstrated optimal performance, achieving over 85% overall accuracy (OA) and more than 81% accuracy in classifying spectrally similar and difficult-to-distinguish species, specifically Quercus mongolica (QM) and Quercus variabilis (QV). Furthermore, while spectral and temporal information were confirmed to contribute significantly to tree species classification, the contribution of spatial (texture) information was experimentally found to be limited at the 2.5 m resolution level. This study presents a practical method for creating high-resolution tree species maps scalable to the national level by fusing existing tree species maps with Sentinel-2 and PlanetScope imagery without requiring costly separate field surveys. Its significance lies in establishing a foundation that can contribute to various fields such as forest resource management, biodiversity conservation, and climate change research. Full article

Structural characterization of natural products in complex herbal extracts remains a major challenge in phytochemical analysis. In this study, we present a novel post-acquisition data-processing strategy—key ion diagnostics–neutral loss filtering (KID-NLF)—combined with ultra-high-performance liquid chromatography–quadrupole time-of-flight mass spectrometry (UPLC-Q/TOF-MS) for systematic profiling of the medicinal plant Terminalia chebula. The strategy consists of four main steps. First, untargeted data are acquired in negative electrospray ionization (ESI⁻) mode. Second, a genus-specific diagnostic ion database is constructed by leveraging characteristic fragment ions (e.g., gallic acid, chebuloyl, and HHDP groups) and conserved substructures. Third, MS/MS data are high-resolution filtered using key ion diagnostics and neutral loss patterns (302 Da for HHDP; 320 Da for chebuloyl). Finally, structures are elucidated via detailed spectral analysis. The methanol extract of T. chebula was separated on a C18 column using a gradient of acetonitrile and 0.1% aqueous formic acid within 33 min. This separation enabled detection of 164 compounds, of which 47 were reported for the first time. Based on fragmentation pathways and diagnostic ions (e.g., m/z 169 for gallic acid, m/z 301 for ellagic acid, and neutral losses of 152, 302, and 320 Da), the compounds were classified into three major groups: gallic acid derivatives, ellagitannins (containing HHDP, chebuloyl, or neochebuloyl moieties), and triterpenoid glycosides. KID-NLF overcomes key limitations of conventional workflows—namely, isomer discrimination and detection of low-abundance compounds—by exploiting genus-specific structural signatures. This strategy demonstrates high efficiency in resolving complex polyphenolic and triterpenoid profiles and enables rapid annotation of both known and novel metabolites. This study highlights KID-NLF as a robust framework for phytochemical analysis in species with high chemical complexity. It also paves the way for applications in quality control, drug discovery, and mechanistic studies of medicinal plants. Full article

Low-cost unmanned aerial vehicle (UAV) visible light remote sensing provides new opportunities for plant community monitoring, but its practical deployment in different ecosystems is still limited by the lack of standardized vegetation index (VI) optimization for multi-species coverage extraction. This study developed a universal method integrating four VIs—Excess Green Index (EXG), Visible Band Difference Vegetation Index (VDVI), Red-Green Ratio Index (RGRI), and Red-Green-Blue Vegetation Index (RGBVI)—to bridge UAV imagery with plant communities. By combining spectral separability analysis with machine learning (SVM), we established dynamic thresholds applicable to crops, trees, and shrubs, achieving cross-species compatibility without multispectral data. The results showed that all VIs achieved robust vegetation/non-vegetation discrimination (Kappa > 0.84), with VDVI being more suitable for distinguishing vegetation from non-vegetation. The overall classification accuracy for different vegetation types exceeded 92.68%, indicating that the accuracy is considerable. Crop coverage extraction showed a minimum segmentation error of 0.63, significantly lower than that of other vegetation types. These advances enable high-resolution vegetation monitoring, supporting biodiversity assessment and ecosystem service quantification. Our research findings track the impact of plant communities on the ecological environment and promote the application of UAVs in ecological restoration and precision agriculture. Full article

Food spoilage caused by microbial contamination remains a global challenge, driving demand for sustainable antibacterial packaging. Conventional photocatalytic materials suffer from limited spectral response, rapid charge recombination, and insufficient reactive oxygen species (ROS) generation under visible light. Here, a Z-scheme heterojunction was constructed by coupling zeolitic imidazolate framework-8 (ZIF-8) with Ag₃PO₄, achieving dual-spectral absorption and spatial charge separation. The directional electron transfer from Ag₃PO₄’s conduction band to ZIF-8 effectively suppresses electron-hole recombination, prolonging carrier lifetimes and amplifying ROS production (·O₂⁻/·OH). Synergy with Ag⁺ release further enhances bactericidal efficacy. Incorporated into a cellulose acetate matrix (CAM), the ZIF-8/Ag₃PO₄/CAM film demonstrates 99.06% antibacterial efficiency against meat surface microbiota under simulated sunlight, alongside high transparency. This study proposes a Z-scheme heterojunction strategy to maximize ROS generation efficiency and demonstrates a scalable fabrication approach for active food packaging materials, effectively targeting microbial contamination control and shelf-life prolongation. Full article

UAV LiDAR and digital aerial photogrammetry (DAP) have shown great performance in forest inventory due to their advantage in three-dimensional information extraction. Many studies have compared their performance in individual tree segmentation and structural parameters extraction (e.g. tree height). However, few studies have compared their performance in tree species classification. Therefore, we have compared the performance of UAV LiDAR and DAP-based point clouds in individual tree species classification with the following steps: (1) Point cloud data processing: Denoising, smoothing, and normalization were conducted on LiDAR and DAP-based point cloud data separately. (2) Feature extraction: Spectral, structural, and texture features were extracted from the pre-processed LiDAR and DAP-based point cloud data. (3) Individual tree segmentation: The marked watershed algorithm was used to segment individual trees on canopy height models (CHM) derived from LiDAR and DAP data, respectively. (4) Pixel-based tree species classification: The random forest classifier (RF) was used to classify urban tree species with features derived from LiDAR and DAP data separately. (5) Individual tree species classification: Based on the segmented individual tree boundaries and pixel-based classification results, the majority filtering method was implemented to obtain the final individual tree species classification results. (6) Fused with hyperspectral data: LiDAR-hyperspectral and DAP-hyperspectral fused data were used to conduct individual tree species classification. (7) Accuracy assessment and comparison: The accuracy of the above results were assessed and compared. The results indicate that LiDAR outperformed DAP in individual tree segmentation (F-score 0.83 vs. 0.79), while DAP achieved higher pixel-level classification accuracy (73.83% vs. 57.32%) due to spectral-textural features. Fusion with hyperspectral data narrowed the gap, with LiDAR reaching 95.98% accuracy in individual tree classification. Our findings suggest that DAP offers a cost-effective alternative for urban forest management, balancing accuracy and operational costs. Full article

Birds are significant bioindicators in the assessment of habitat biodiversity, ecological impacts and ecosystem health. Against the backdrop of easier bird vocalization data acquisition, and with deep learning and machine learning technologies as the technical support, exploring recognition and classification networks suitable for bird calls has become the focus of bioacoustics research. Due to the fact that the spectral differences among various bird calls are much greater than the differences between human languages, constructing birdsong classification networks based on human speech recognition networks does not yield satisfactory results. Effectively capturing the differences in birdsong across species is a crucial factor in improving recognition accuracy. To address the differences in features, this study proposes multi-scale deep features. At the same time, we separate the classification part from the deep network by using machine learning to adapt to classification with distinct feature differences in birdsong. We validate the effectiveness of multi-scale deep features on a publicly available dataset of 20 bird species. The experimental results show that the accuracy of the multi-scale deep features on a log-wavelet spectrum, log-Mel spectrum and log-power spectrum reaches 94.04%, 97.81% and 95.89%, respectively, achieving an improvement over single-scale deep features on these three spectrograms. Comparative experimental results show that the proposed multi-scale deep feature method is superior to five state-of-the-art birdsong identification methods, which provides new perspectives and tools for birdsong identification research, and is of great significance for ecological monitoring, biodiversity conservation and forest research. Full article

The objectives of this work are (i) to classify soybean cultivars under different irrigation managements using hyperspectral data, looking for the best machine-learning algorithm for the classification and the input that improves the performance of the models. The experiment was implemented in the 2023/24 harvest in the experimental area of the Federal University of Mato Grosso do Sul, Câmpus Chapadão do Sul, Mato Grosso do Sul, and it was conducted in a strip scheme with seven cultivars subjected to irrigated and rainfed management. Sixty days after crop emergence, three leaves per plot were collected for evaluation by the hyperspectral sensor. The spectral data was then separated into 28 bands to reduce dimensionality. In this way, two databases were generated: one with all the spectral information provided by the sensor (WL) and one with the 28 spectral bands (SB). Each database was subjected to different machine-learning models to ascertain the improved accuracy of the models in distinguishing the different eucalyptus species. The models tested were artificial neural networks (ANN), decision trees (DT), linear regression (LR), M5P algorithm, random forest (RF), and support vector machine (SVM). The results demonstrate the effectiveness of machine-learning models in differentiating soybean management under rainfed and irrigated conditions, highlighting the advantage of hyperspectral data (WL) over selected spectral bands (SB). Models such as the support vector machine (SVM) showed the best levels of accuracy when using the entire available spectrum. On the other hand, artificial neural networks (ANN) performed well with spectral band data, demonstrating their ability to work with smaller data sets without compromising the classification. Full article

Panicum maximum cultivars have distinct characteristics, especially morphological ones related to the leaf structure and coloration, and there may be differences in the spectral behavior captured by sensors. These differences can be used in classification using machine learning (ML) algorithms to differentiate biodiversity within the same species. The objectives of this study were to identify ML models able to differentiate P. maximum cultivars and determine which is the best spectral input for these algorithms and whether reducing the sample size improves the response of the algorithms. The experiment was carried out at the experimental area of the Forage Sector of the School Farm belonging to the Federal University of Mato Grosso do Sul (UFMS). The leaf samples of the cultivars Massai, Mombaça, Tamani, Quênia, and Zuri were collected from experimental plots in the field. Analysis was carried out on 120 leaf samples from the P. maximum cultivars using a VIS/NIR hyperspectral sensor. After obtaining the spectral data and separating them into bands, the data were submitted for ML analysis to classify the cultivars based on the spectral variables. The algorithms tested were artificial neural networks (ANNs), REPTree and J48 decision trees, random forest (RF), and support vector machine (SVM). A logistic regression (LR) was used as a traditional classification method. Two input models were evaluated in the algorithms: the entire spectrum band provided by the sensor (ALL) and another input configuration using the calculated bands. The reflectances from the P. maximum cultivars showed different behavior, especially in the green and NIR regions. RL and ANN algorithms using all information in the spectrum are able to accurately classify the cultivars, reaching accuracies above 70 for CC and above 0.6 for kappa and F-score. VIS/NIR leaf reflectance can be a powerful tool for low-cost, non-destructive, and high-performance analysis to distinguish P. maximum cultivars. Here, we achieved better model accuracy using only 40 leaf samples. In the present study, the J48 decision tree model proved to have good classification performance regardless of the sample size used, which makes it a strategic model for forage cultivar classification studies in smaller or larger datasets. Full article

The modern analytical technique of Fourier-transform mid-infrared spectroscopy (FT-MIR) has found its place in routine wine quality control. It allows rapid and nondestructive analysis, with easy sample preparation and without the need for chemical pretreatment or expensive reagents. The objective of this research was to apply these advantages to fruit wines in order to create a tool for the authentication of fruit wines produced from different fruit species (chokeberry, blackberry, and raspberry). The aim of this work was to establish a chemometric model from FT-MIR spectra and to find a “fingerprint” of specific fruit wines, enabling the classification of fruit wines by plant species. Physicochemical analysis of 111 Croatian fruit wine samples (38 liqueur fruit wines and 73 fruit wines) revealed content levels of the following parameters: alcoholic strength (5.0–15.2% vol.), total dry extract (60.4–253.3 g/L), total sugars (1.2–229.9 g/L), pH (3.13–4.98), total acidity (4.2–18.3 g/L) and volatile acidity (0.2–1.5 g/L). For statistical data processing, spectral ranges between 926 and 1450 cm⁻¹ and between 1801 and 2951 cm⁻¹ were used. The first principal component (PC1) explained 70.4% of the observed variation, and the second component (PC2) explained 16.7%, clearly separating chokeberry fruit wines from blackberry and raspberry fruit wines. Soft Independent Modeling Class Analogy (SIMCA) was performed following the development of a PCA model showing that the chokeberry and blackberry wine samples form clearly separated clusters. Key discriminators for classifying chokeberry vs. blackberry wines were identified at 1157, 1304, and 1435 cm⁻¹, demonstrating high discrimination power (DP 26, 17, and 14, respectively). FT-MIR spectroscopy, in combination with chemometric methods, has shown promising potential for the authenticity assessment of fruit wines. Full article

Synthetic biology has advanced in creating artificial microbial and algal communities, but technical and evolutionary complexities still pose significant challenges. Traditional methods, like microscopy and pigment analysis, are limited in throughput and resolution. In contrast, advancements in full-spectrum cytometry enabled high-throughput, multidimensional analysis of single cells based on size, complexity, and spectral fingerprints, offering more precision and flexibility than conventional flow cytometry. This study uses full-spectrum cytometry to analyze synthetic algal–microbial communities, enabling rapid species identification and enumeration. The workflow involves recording individual spectral signatures from monocultures, using autofluorescence to capture populations of interest, and creating a spectral library for further analysis. This spectral library was used for the analysis of the synthetic phytoplankton communities, revealing differences in spectral signatures. Moreover, the synthetic consortium experiment monitored algal growth, comparing results from different instruments, highlighting the advantages of the spectral virtual filter system for precise population separation and abundance tracking. By capturing the entire emission spectrum of each cell, this method enhances understanding of algal–microbial community dynamics and responses to environmental stressors. The development of standardized spectral libraries would improve the characterization of algal communities, further advancing synthetic biology and phytoplankton ecology research. Full article

The ability to differentiate species is not adequate for modern forage breeding programs. The measurement of persistence is currently a bottleneck in the breeding system that limits the throughput of cultivars to the marketplace and prevents it from being selected as a trait. The use of hyperspectral data obtained through remote sensing offers the potential to reduce guesswork by identifying the distribution of pasture species, but only if such data alone can distinguish the subtle differences within species, i.e., cultivars. The implementation of this technology faces many challenges due to the spectral and temporal variability of species. To understand the spectral variability between and within species groups, differentiation using hyperspectral data from monoculture plots of turf species was utilized. Spectral data were collected over a year using an ASD FieldSpec^® and canopy pasture probe (CAPP). The plots consisted of monocultures of various species, and cultivars (a total of 10 plots). Linear discriminant analysis (LDA) was conducted on the full spectrum and reduced band data. This technique successfully differentiated the species with high accuracy (>98%). We demonstrate the potential of hyperspectral data and analysis techniques to accurately separate differences down to cultivar level. We also show that diurnal variation is measurable in the spectra but does not preclude differentiation. Full article

In this study, we propose a scalable deep learning approach to automated phenotyping using UAV multispectral imagery, exemplified by yellow rust detection in winter wheat. We adopt a high-granularity scoring method (1 to 9 scale) to align with international standards and plant breeders’ needs. Using a lower spatial resolution (60 m flight height at 2.5 cm GSD), we reduce the data volume by a factor of 3.4, making large-scale phenotyping faster and more cost-effective while obtaining results comparable to those of the state-of-the-art. Our model incorporates explainability components to optimise spectral bands and flight schedules, achieving top-three accuracies of 0.87 for validation and 0.67 and 0.70 on two separate test sets. We demonstrate that a minimal set of bands (EVI, Red, and GNDVI) can achieve results comparable to more complex setups, highlighting the potential for cost-effective solutions. Additionally, we show that high performance can be maintained with fewer time steps, reducing operational complexity. Our interpretable model components improve performance through regularisation and provide actionable insights for agronomists and plant breeders. This scalable and explainable approach offers an efficient solution for yellow rust phenotyping and can be adapted for other phenotypes and species, with future work focusing on optimising the balance between spatial, spectral, and temporal resolutions. Full article

Photosystem I (PSI) serves as a model system for studying fundamental processes such as electron transfer (ET) and energy conversion, which are not only central to photosynthesis but also have broader implications for bioenergy production and biomimetic device design. In this study, we employed electron paramagnetic resonance (EPR) spectroscopy to investigate key light-induced charge separation steps in PSI isolated from several green algal and cyanobacterial species. Following photoexcitation, rapid sequential ET occurs through either of two quasi-symmetric branches of donor/acceptor cofactors embedded within the protein core, termed the A and B branches. Using high-frequency (130 GHz) time-resolved EPR (TR-EPR) and deuteration techniques to enhance spectral resolution, we observed that at low temperatures prokaryotic PSI exhibits reversible ET in the A branch and irreversible ET in the B branch, while PSI from eukaryotic counterparts displays either reversible ET in both branches or exclusively in the B branch. Furthermore, we observed a notable correlation between low-temperature charge separation to the terminal [4Fe-4S] clusters of PSI, termed F_A and F_B, as reflected in the measured F_A/F_B ratio. These findings enhance our understanding of the mechanistic diversity of PSI’s ET across different species and underscore the importance of experimental design in resolving these differences. Though further research is necessary to elucidate the underlying mechanisms and the evolutionary significance of these variations in PSI charge separation, this study sets the stage for future investigations into the complex interplay between protein structure, ET pathways, and the environmental adaptations of photosynthetic organisms. Full article

Invasive species have historically disrupted environments by outcompeting, displacing, and extirpating native species, resulting in significant environmental and economic damage. Developing approaches to detect the presence of invasive species, favorable habitats for their establishment, and predicting their potential spread are underutilized management strategies to effectively protect the environment and the economy. Spotted lanternfly (SLF, Lycorma delicatula) is a phloem-feeding planthopper native to China that poses a severe threat to horticultural and forest products in the United States. Tools are being developed to contain the spread and damage caused by SLF; however, methods to rapidly detect novel infestations or low-density populations are lacking. Vegetation spectroscopy is an approach that can represent vegetation health through changes in the reflectance and absorption of radiation based on plant physiochemical status. Here, we hypothesize that SLF infestations change the spectral and chemical characteristics of tree canopies. To test this hypothesis, we used a full range spectroradiometer to sample canopy foliage of silver maple (Acer saccharinum) and red maple (Acer rubrum) trees in a common garden in Berks County, Pennsylvania that were exposed to varying levels of SLF infestation. Foliar spectral profiles separated between SLF infestation levels, and the magnitude of separation was greater for the zero-SLF control compared with higher infestation levels. We found the red-edge and portions of the NIR and SWIR regions were most strongly related to SLF infestation densities and that corresponding changes in vegetation indexes related to levels of chlorophyll were influenced by SLF infestations, although we found no change in foliar levels of chlorophyll. We found no influence of SLF densities on levels of primary metabolites (i.e., pigments, nonstructural carbohydrates, carbon, and nitrogen), but did find an increase in the phenolic compound ferulic acid in response to increasing SLF infestations; this response was only in red maple, suggesting a possible species-specific response related to SLF feeding. By identifying changes in spectral and chemical properties of canopy leaves in response to SLF infestation, we can link them together to potentially better understand how trees respond to SLF feeding pressure and more rapidly identify SLF infestations. Full article