Search Results (183)

Accurate classification of individual tree types is a key component in forest inventory, biodiversity monitoring, and ecological modeling. This study evaluates and compares multiple Machine Learning (ML) and Deep Learning (DL) approaches for tree type classification based on Airborne Laser Scanning (ALS) data. A mixed-species forest in southeastern Austria, Europe, served as the test site, with spruce, pine, and a grouped class of broadleaf species as target categories. To examine the impact of data representation, ALS point clouds were transformed into four distinct structures: 1D feature vectors, 2D raster profiles, 3D voxel grids, and unstructured 3D point clouds. A comprehensive dataset, combining field measurements and manually annotated aerial data, was used to train and validate 45 ML and DL models. Results show that DL models based on 3D point clouds achieved the highest overall accuracy (up to 88.1%), followed by multi-view 2D raster and voxel-based methods. Traditional ML models performed well on 1D data but struggled with high-dimensional inputs. Spruce trees were classified most reliably, while confusion between pine and broadleaf species remained challenging across methods. The study highlights the importance of selecting suitable data structures and model types for operational tree classification and outlines potential directions for improving accuracy through multimodal and temporal data fusion. Full article

Sirex noctilio is an invasive pest that contributes to pine tree decline, leading to visual symptoms such as needle discoloration, crown thinning, and eventual tree death. Detecting these visible phenotypic signs from drone imagery is challenging due to elongated or irregular crown shapes, weak color differences, and occlusion within dense forests. This study introduces YOLO-PTHD, a lightweight deep learning model designed for detecting visible signs of pine decline in UAV images. The model integrates three customized components: Strip-based convolution to capture elongated tree structures, Channel-Aware Attention to enhance weak visual cues, and a scale-sensitive dynamic loss function to improve detection of minority classes and small targets. A UAV-based dataset, the Sirex Woodwasp dataset, was constructed with annotated images of weakened, and dead pine trees. YOLO-PTHD achieved an mAP of 0.923 and an F1-score of 0.866 on this dataset. To evaluate the model’s generalization capability, it was further tested on the Real Pine Wilt Disease dataset from South Korea. Despite differences in tree symptoms and imaging conditions, the model maintained strong performance, demonstrating its robustness across different forest health scenarios. Field investigations targeting Sirex woodwasp in outbreak areas confirmed that the model could reliably detect damaged trees in real-world forest environments. This work demonstrates the potential of UAV-based visual analysis for large-scale phenotypic surveillance of pine health in forest management. Full article

Forests are a key terrestrial carbon sink, storing carbon in biomass, the forest floor, and the mineral soil (SOC). Since Pinus radiata D. Don is the most widely planted forest species in Chile, it is important to understand how environmental and soil factors influence these carbon pools. Our objective was to evaluate the effects of climate and site variables on carbon stocks in adult radiata pine plantations across contrasting water and nutrient conditions. Three 1000 m² plots were installed at 20 sites with sandy, granitic, recent ash, and metamorphic soils, which were selected along a productivity gradient. Biomass carbon stocks were estimated using allometric equations, and carbon stocks in the forest floor and mineral soil (up to 1 m deep) were assessed. SOC varied significantly, from 139.9 Mg ha⁻¹ in sandy soils to 382.4 Mg ha⁻¹ in metamorphic soils. Total carbon stocks (TCS) per site ranged from 331.0 Mg ha⁻¹ in sandy soils to 552.9 Mg ha⁻¹ in metamorphic soils. Across all soil types, the forest floor held the lowest carbon stock. Correlation analyses and linear models revealed that variables related to soil water availability, nitrogen content, precipitation, and stand productivity positively increased SOC and TCS stocks. In contrast, temperature, evapotranspiration, and sand content had a negative effect. The developed models will allow more accurate estimation estimates of C stocks at SOC and in the total stand. Full article

Deep learning has demonstrated significant success in hyperspectral image (HSI) classification by effectively leveraging spatial–spectral feature learning. However, current approaches encounter three challenges: (1) high spectral redundancy and the presence of noisy bands, which impair the extraction of discriminative features; (2) limited spatial receptive fields inherent in convolutional operations; and (3) unidirectional context modeling that inadequately captures bidirectional dependencies in non-causal HSI data. To address these challenges, this paper proposes HG-Mamba, a novel hybrid geometry-aware bidirectional Mamba network for HSI classification. The proposed HG-Mamba synergistically integrates convolutional operations, geometry-aware filtering, and bidirectional state-space models (SSMs) to achieve robust spectral–spatial representation learning. The proposed framework comprises two stages. The first stage, termed spectral compression and discrimination enhancement, employs multi-scale spectral convolutions alongside a spectral bidirectional Mamba (SeBM) module to suppress redundant bands while modeling long-range spectral dependencies. The second stage, designated spatial structure perception and context modeling, incorporates a Gaussian Distance Decay (GDD) mechanism to adaptively reweight spatial neighbors based on geometric distances, coupled with a spatial bidirectional Mamba (SaBM) module for comprehensive global context modeling. The GDD mechanism facilitates boundary-aware feature extraction by prioritizing spatially proximate pixels, while the bidirectional SSMs mitigate unidirectional bias through parallel forward–backward state transitions. Extensiveexperiments on the Indian Pines, Houston2013, and WHU-Hi-LongKou datasets demonstrate the superior performance of HG-Mamba, achieving overall accuracies of 94.91%, 98.41%, and 98.67%, respectively. Full article

Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. To address these limitations, we propose MRFP-Mamba, a novel Multi-Receptive-Field Parallel Mamba architecture that integrates hierarchical spatial feature extraction with efficient modeling of spatial–spectral dependencies. The proposed MRFP-Mamba introduces two key innovation modules: (1) A multi-receptive-field convolutional module employing parallel $1\times 1$, $3\times 3$, $5\times 5$, and $7\times 7$ kernels to capture fine-to-coarse spatial features, thereby improving discriminability for multi-scale objects; and (2) a parameter-optimized Vision Mamba branch that models global spatial–spectral relationships through structured state space mechanisms. Experimental results demonstrate that the proposed MRFP-Mamba consistently surpasses existing CNN-, Transformer-, and state space model (SSM)-based approaches across four widely used hyperspectral image (HSI) benchmark datasets: PaviaU, Indian Pines, Houston 2013, and WHU-Hi-LongKou. Compared with MambaHSI, our MRFP-Mamba achieves improvements in Overall Accuracy (OA) by 0.69%, 0.30%, 0.40%, and 0.97%, respectively, thereby validating its superior classification capability and robustness. Full article

Pine wilt disease has caused severe damage to China’s forest ecosystems. Utilizing the rich information from very-high-resolution (VHR) satellite imagery for large-scale and accurate monitoring of pine wilt disease is a crucial approach to curbing its spread. However, current research on identifying infected trees using VHR satellite imagery and deep learning remains extremely limited. This study introduces several advanced self-attention algorithms into the task of satellite-based monitoring of pine wilt disease to enhance detection performance. We constructed a dataset of discolored pine trees affected by pine wilt disease using imagery from the Gaofen-2 and Gaofen-7 satellites. Within the unified semantic segmentation framework MMSegmentation, we implemented four single-head attention models—NLNet, CCNet, DANet, and GCNet—and two multi-head attention models—Swin Transformer and SegFormer—for the accurate semantic segmentation of infected trees. The model predictions were further analyzed through visualization. The results demonstrate that introducing appropriate self-attention algorithms significantly improves detection accuracy for pine wilt disease. Among the single-head attention models, DANet achieved the highest accuracy, reaching 73.35%. The multi-head attention models exhibited an excellent performance, with SegFormer-b2 achieving an accuracy of 76.39%, learning the features of discolored pine trees at the earliest stage and converging faster. The visualization of model inference results indicates that DANet, which integrates convolutional neural networks (CNNs) with self-attention mechanisms, achieved the highest overall accuracy at 94.43%. The use of self-attention algorithms enables models to extract more precise morphological features of discolored pine trees, enhancing user accuracy while potentially reducing production accuracy. Full article

Against the backdrop of global climate change and increasing ecological pressure, the refined monitoring of forest resources and accurate tree species identification have become essential tasks for sustainable forest management. Hyperspectral remote sensing, with its high spectral resolution, shows great promise in tree species classification. However, traditional methods face limitations in extracting joint spatial–spectral features, particularly in complex forest environments, due to the “curse of dimensionality” and the scarcity of labeled samples. To address these challenges, this study proposes a synergistic classification approach that combines the spatial feature extraction capabilities of deep learning with the generalization advantages of machine learning. Specifically, a 2D convolutional neural network (2DCNN) is integrated with a support vector machine (SVM) classifier to enhance classification accuracy and model robustness under limited sample conditions. Using UAV-based hyperspectral imagery collected from a typical plantation area in Fuzhou City, Jiangxi Province, and ground-truth data for labeling, a highly imbalanced sample split strategy (1:99) is adopted. The 2DCNN is further evaluated in conjunction with six classifiers—CatBoost, decision tree (DT), k-nearest neighbors (KNN), LightGBM, random forest (RF), and SVM—for comparison. The 2DCNN-SVM combination is identified as the optimal model. In the classification of Masson pine, Chinese fir, and eucalyptus, this method achieves an overall accuracy (OA) of 97.56%, average accuracy (AA) of 97.47%, and a Kappa coefficient of 0.9665, significantly outperforming traditional approaches. The results demonstrate that the 2DCNN-SVM model offers superior feature representation and generalization capabilities in high-dimensional, small-sample scenarios, markedly improving tree species classification accuracy in complex forest settings. This study validates the model’s potential for application in small-sample forest remote sensing and provides theoretical support and technical guidance for high-precision tree species identification and dynamic forest monitoring. Full article

Pine wilt disease (PWD) is a severe forest disease caused by the infestation of pine wood nematodes. Due to its short disease cycle and strong transmission ability, it has caused significant damage to China’s forestry resources. To achieve large-scale monitoring of PWD, this study utilized machine learning/deep learning algorithms with Sentinel-1/2 images in the Google Earth Engine cloud platform to implement province-wide PWD monitoring in Anhui Province, China. The study also analyzed the spatial distribution of PWD in Anhui Province from two perspectives—spatiotemporal patterns and influencing factors—aiming to investigate the spatiotemporal evolution patterns and the impact of influencing factors on the occurrence of PWD. The results show that (1) the random forest model exhibited the strongest performance, followed by the CNN model, while the DNN model performed the worst. Using the RF model to monitor PWD and calculate the affected area in Anhui Province from 2019 to 2024 yielded errors within 30% compared to official statistics. (2) PWD in Anhui Province showed a clear clustering trend, with global Moran’s indices all exceeding 0.79 from 2019 to 2024. The LISA map revealed a spread pattern from south to north and from west to east. (3) Topographic and temperature factors had the greatest influence on PWD distribution. SHAP analysis indicated that topographic and climatic factors were the primary drivers of PWD-affected areas, with slope and temperature being the two most significant contributing factors. This study helps to rapidly and accurately identify outbreak areas during epidemics and enables precise quarantine measures and targeted control efforts. Full article

Deep learning has recently achieved remarkable progress in hyperspectral image (HSI) classification. Among these advancements, the Transformer-based models have gained considerable attention due to their ability to establish long-range dependencies. However, the quadratic computational complexity of the self-attention mechanism limits its application in hyperspectral image classification (HSIC). Recently, the Mamba architecture has shown outstanding performance in 1D sequence modeling tasks owing to its lightweight linear sequence operations and efficient parallel scanning capabilities. Nevertheless, its application in HSI classification still faces challenges. Most existing Mamba-based approaches adopt various selective scanning strategies for HSI serialization, ensuring the adjacency of scanning sequences to enhance spatial continuity. However, these methods lead to substantially increased computational overhead. To overcome these challenges, this study proposes the Hyperspectral Spatial Mamba (HyperSMamba) model for HSIC, aiming to reduce computational complexity while improving classification performance. The suggested framework consists of the following key components: (1) a Multi-Scale Spatial Mamba (MS-Mamba) encoder, which refines the state-space model (SSM) computation by incorporating a Multi-Scale State Fusion Module (MSFM) after the state transition equations of original SSMs. This module aggregates adjacent state representations to reinforce spatial dependencies among local features; (2) our proposed Adaptive Fusion Attention Module (AFAttention) to dynamically fuse bidirectional Mamba outputs for optimizing feature representation. Experiments were performed on three HSI datasets, and the findings demonstrate that HyperSMamba attains overall accuracy of 94.86%, 97.72%, and 97.38% on the Indian Pines, Pavia University, and Salinas datasets, while maintaining low computational complexity. These results confirm the model’s effectiveness and potential for practical application in HSIC tasks. Full article

Pine wilt disease poses a significant threat to pine forests worldwide, necessitating efficient and accurate detection of dead pine wood for effective disease control and forest management. Traditional deep learning methods based on supervised closed-set paradigms often struggle to address unknown interfering objects, causing false positives, missed detection, and increased annotation burdens. To overcome these challenges, we propose SS-OPDet, a semi-supervised open-set detection framework that leverages a small amount of labeled data along with abundant unlabeled data. SS-OPDet integrates a Weighted Multi-scale Feature Fusion module to dynamically integrate global- and local-scale features, thereby significantly improving representational accuracy for dead pine wood. Additionally, a Dynamic Confidence Pseudo-Label Generation strategy categorizes predictions by confidence level, effectively reducing training noise and maximizing the use of reliable unlabeled data. Experimental results from 7733 UAV images demonstrate that SS-OPDet achieves an average precision (${AP}_K$) of 84.73%, a recall ($R_K$) of 94.48%, an Absolute Open-Set Error (AOSE) of 271 and a Wilderness Impact (WI) of 0.0917%. Cross-region validation further confirms the robustness and generalization capability of the proposed framework. The proposed method offers a cost-effective and accurate solution for timely detection of pine wilt disease, providing substantial benefits to forest monitoring and management. Full article

Hyperspectral imaging (HSI) is an advanced imaging technique that captures detailed spectral information across multiple fields. This review explores its applications in counterfeit detection, remote sensing, agriculture, medical imaging, cancer detection, environmental monitoring, mining, mineralogy, and food processing, specifically highlighting significant achievements from the past five years, providing a timely update across several fields. It also presents a cross-disciplinary classification framework to systematically categorize applications in medical, agriculture, environment, and industry. In counterfeit detection, HSI identified fake currency with high accuracy in the 400–500 nm range and achieved a 99.03% F1-score for counterfeit alcohol detection. Remote sensing applications include hyperspectral satellites, which improve forest classification accuracy by 50%, and soil organic matter, with the prediction reaching R² = 0.6. In agriculture, the HSI-TransUNet model achieved 86.05% accuracy for crop classification, and disease detection reached 98.09% accuracy. Medical imaging benefits from HSI’s non-invasive diagnostics, distinguishing skin cancer with 87% sensitivity and 88% specificity. In cancer detection, colorectal cancer identification reached 86% sensitivity and 95% specificity. Environmental applications include PM2.5 pollution detection with 85.93% accuracy and marine plastic waste detection with 70–80% accuracy. In food processing, egg freshness prediction achieved R² = 91%, and pine nut classification reached 100% accuracy. Despite its advantages, HSI faces challenges like high costs and complex data processing. Advances in artificial intelligence and miniaturization are expected to improve accessibility and real-time applications. Future advancements are anticipated to concentrate on the integration of deep learning models for automated feature extraction and decision-making in hyperspectral imaging analysis. The development of lightweight, portable HSI devices will enable more on-site applications in agriculture, healthcare, and environmental monitoring. Moreover, real-time processing methods will enhance efficiency for field deployment. These improvements seek to enhance the accessibility, practicality, and efficacy of HSI in both industrial and clinical environments. Full article

Deep learning-based hyperspectral image (HSI) classification methods, such as Transformers and Mambas, have attracted considerable attention. However, several challenges persist, e.g., (1) Transformers suffer from quadratic computational complexity due to the self-attention mechanism; and (2) both the local and global feature extraction capabilities of large kernel convolutional neural networks (LKCNNs) need to be enhanced. To address these limitations, we introduce a multi-scale large kernel asymmetric CNN (MSLKACNN) with the large kernel sizes as large as $1\times 17$ and $17\times 1$ for HSI classification. MSLKACNN comprises a spectral feature extraction module (SFEM) and a multi-scale large kernel asymmetric convolution (MSLKAC). Specifically, the SFEM is first utilized to suppress noise, reduce spectral bands, and capture spectral features. Then, MSLKAC, with a large receptive field, joins two parallel multi-scale asymmetric convolution components to extract both local and global spatial features: (C1) a multi-scale large kernel asymmetric depthwise convolution (MLKADC) is designed to capture short-range, middle-range, and long-range spatial features; and (C2) a multi-scale asymmetric dilated depthwise convolution (MADDC) is proposed to aggregate the spatial features between pixels across diverse distances. Extensive experimental results on four widely used HSI datasets show that the proposed MSLKACNN significantly outperforms ten state-of-the-art methods, with overall accuracy (OA) gains ranging from 4.93% to 17.80% on Indian Pines, 2.09% to 15.86% on Botswana, 0.67% to 13.33% on Houston 2013, and 2.20% to 24.33% on LongKou. These results validate the effectiveness of the proposed MSLKACNN. Full article

The outbreak of Pine Shoot Beetle (PSB, Tomicus spp.) posed a significant threat to the health of Yunnan pine forests, necessitating the development of an efficient and accurate remote sensing monitoring method. The integration of unmanned aerial vehicle (UAV) imagery and deep learning algorithms shows great potential for monitoring forest-damaged trees. Previous studies have utilized various deep learning semantic segmentation models for identifying damaged trees in forested areas; however, these approaches were constrained by limited accuracy and misclassification issues, particularly in complex forest backgrounds. This study evaluated the performance of five semantic segmentation models in identifying PSB-damaged trees (UNet, UNet++, PAN, DeepLabV3+ and FPN). Experimental results showed that the FPN model outperformed the others in terms of segmentation precision (0.8341), F1 score (0.8352), IoU (0.7239), mIoU (0.7185) and validation accuracy (0.9687). Under the pure Yunnan pine background, the FPN model demonstrated the best segmentation performance, followed by mixed grassland-Yunnan pine backgrounds. Its performance was the poorest in mixed bare soil-Yunnan pine background. Notably, even under this challenging background, FPN still effectively identified diseased trees, with only a 1.7% reduction in precision compared to the pure Yunnan pine background (0.9892). The proposed method in this study contributed to the rapid and accurate monitoring of PSB-damaged trees, providing valuable technical support for the prevention and management of PSB. Full article

Hyperspectral image classification (HSIC) represents a significant area of research within the domain of remote sensing. Given the intricate nature of hyperspectral images and the substantial volume of data they generate, it is essential to introduce innovative methodologies to effectively address the data pre-processing challenges encountered in HSIC. In this paper, we draw inspiration from the Segment Anything Model (SAM) within the realm of large language models to propose its application for HSIC, aiming to achieve significant advancements and breakthroughs in this field. Initially, we constructed the SAM and labeled a limited number of samples as segmentation prompts for the model. We conducted HSIC experiments utilizing three publicly available hyperspectral image datasets: Indian Pines (IP), Salinas (SA), and Pavia University (PU). Furthermore, a voting strategy was implemented during these experiments, with only five samples selected from each land type. The classification results obtained from the SAM-based hyperspectral images were compared with those derived from eight distinct machine learning, deep learning, and Transformer models. The findings indicate that the SAM requires only a limited number of samples to effectively perform hyperspectral image classification, achieving higher accuracy than the other models discussed in this paper. Building on this foundation, a voting strategy was implemented, leading to significant enhancements in the overall accuracy (OA) of HSIC across three datasets. The improvements were quantified at 66.76%, 74.66%, and 70.53%, respectively, culminating in final accuracies of 80.29%, 90.66%, and 86.51%. In this study, the SAM is utilized for unsupervised classification, thereby reducing the need for sample labeling while attaining effective classification outcomes. Full article

Hyperspectral image classification faces significant challenges in effectively extracting and integrating spectral-spatial features from high-dimensional data. Recent deep learning (DL) methods combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have demonstrated exceptional performance. However, two critical challenges may cause degradation in the classification accuracy of these methods: interference from irrelevant information within the observed region, and the potential loss of useful information due to local spectral variability within the same class. To address these issues, we propose a central pixel-based dual-branch network (CPDB-Net) that synergistically integrates CNN and ViT for robust feature extraction. Specifically, the central spectral feature extraction branch based on CNN serves as a strong prior to reinforce the importance of central pixel features in classification. Additionally, the spatial branch based on ViT incorporates a novel frequency-aware HiLo attention, which can effectively separate high and low frequencies, alleviating the problem of local spectral variability and enhancing the ability to extract global features. Extensive experiments on widely used HSI datasets demonstrate the superiority of our method. Our CPDB-Net achieves the highest overall accuracies of 92.67%, 97.48%, and 95.02% on the Indian Pines, Pavia University, and Houston 2013 datasets, respectively, outperforming recent representative methods and confirming its effectiveness. Full article