Hyperspectral image (HSI) can provide rich spectral information which be helpful for accurate classification in many applications. Yet, incorporating spatial the process improve accuracy even further. Existing convolutional neural network (CNN) usually only focuses on local features hyperspectral cubes, whereas burgeoning vision transformer (ViT) is interested global HSIs. In this letter, we propose a deep aggregated framework HSI called convolution mixer (CTMixer) to combine advantages of...

Vegetation dynamics and their response to climate change is critical for determining the mechanisms of climate-derived variations in terrestrial ecosystems. Here, Normalized Difference Index (NDVI) monthly temperature precipitation data were employed examine spatiotemporal patterns vegetation investigate time-lag effects responses variables Yamzhog Yumco Basin, South Tibet, during 2000–2018. The results reveal that annual average growing season NDVI basin was 0.28, with lower values...

This study explores the influence of angle attack (AOA) on icing distribution characteristics asymmetric blade airfoil (DU97) surfaces for wind turbines under conditions by numerical simulation. The findings demonstrate a consistence between simulated ice shapes and experimental data. thickness lower surface leading edge exhibits trend first rising then declining along chord direction while showing gradually decreasing upper surface. range trailing is broader than that peak at rises...

Convolutional neural networks (CNNs) showed impressive performance for hyperspectral image (HSI) classification. Nevertheless, convolutional layers contain massive parameters, which restrict the deployment of CNNs on satellite and airborne platforms with limited storage computing resources. In this letter, we propose a lightweight spectral-spatial convolution module (LS <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CM) as an...

Convolutional neural networks (CNNs) have recently shown outstanding capability for hyperspectral image (HSI) classification. In this work, a novel CNN model is proposed, which wider than other existing deep learning-based HSI classification models. Based on the fact that very residual (ResNets) behave like ensembles of relatively shallow networks, our proposed network, called multipath ResNet (MPRN), employs multiple functions in blocks to make network wider, rather deeper. The consists...

The convolutional neural network (CNN) can automatically extract hierarchical feature representations from raw data and has recently achieved great success in the classification of hyperspectral images (HSIs). However, most CNN based methods used HSI neglect adequately utilizing strong complementary yet correlated information each layer only employ last features for classification. In this paper, we propose a novel fully dense multiscale fusion (FDMFN) that takes full advantage all layers...

A iodine radical mediated cascade [3 + 2] carbocyclization of ene-vinylidenecyclopropanes with thiols and selenols to provide sulfur- or selenium-containing derivatives has been disclosed.

Convolutional neural networks (CNNs) are the go-to model for hyperspectral image (HSI) classification because of excellent locally contextual modeling ability that is beneficial to spatial and spectral feature extraction. However, CNNs with a limited receptive field pose challenges long-range dependencies. To solve this issue, we introduce novel framework which regards input HSI as sequence data constructed exclusively multilayer perceptrons (MLPs). Specifically, propose spectral-spatial MLP...

Convolutional neural networks (CNNs) have achieved great results in hyperspectral image (HSI) classification recent years. However, convolution kernels are reused among different spatial locations, known as spatial-agnostic or weight-sharing kernels. Furthermore, the preference of compactness (typically, 3×3 kernel size) constrains receptive field and ability to capture long-range interactions. To mitigate above two issues, this article, we combine a novel operation called involution with...

Recently, with the extensive application of deep learning techniques in hyperspectral image (HSI) field, particularly convolutional neural network (CNN), research HSI classification has stepped into a new stage. To avoid problem that receptive field naive convolution is small, dilated introduced classification. However, usually generates blind spots resulting discontinuous spatial information obtained. In order to solve above problem, densely connected pyramidal (PDCNet) proposed this paper....

To learn discriminative features, hyperspectral image (HSI), containing 3-D cube data, is a preferable means of capturing multi-head self-attention from both spatial and spectral domains if the burden in model optimization computation low. In this paper, we design dual contextual (DMuCA) network for HSI classification with fewest possible parameters lower costs. effectively capture rich dependencies domains, decouple attention into two sub-blocks, SaMCA SeMCA, where depth-wise convolution...

As the largest terrestrial ecosystem globally, grasslands and their Gross Primary Productivity (GPP) play a critical role in global carbon cycle, influenced by environmental changes human activities. This study classifies into multiple types, uses trend analysis to investigate temporal spatial of GPP for various grassland types from 2010 2020, extracts approximately 940,000 pixel data identify evaluate factors using best prediction model PLS-PM structural equation model. The results indicate...

<title>Abstract</title> High-precision prediction of near-surface PM_2.5 concentration is an significant theoretical prerequisite for effective monitoring and prevention air pollution, also provides guiding suggestions health risk control. In view the fact that control variables existing models are mostly dependent on influencing factors at near-surface, it often difficult to fully explore continuous spatio-temporal characteristics in PM_2.5. this study, MODIS remote...

Absidia represents the most species-rich genus within family Cunninghamellaceae, with its members commonly isolated from diverse substrates, particularly rhizosphere soil. In this study, four novel species (A. irregularis sp. nov., A. multiformis ovoidospora and verticilliformis nov.) were discovered south southwestern Chinese soil samples through integrated morphological molecular phylogenetic analyses. Phylogenetic analyses based on concatenated ITS, SSU, LSU, Act, TEF1α sequence data...

LiDAR point clouds of reflective targets often contain significant noise, which severely impacts the feature extraction accuracy and performance object detection algorithms. These challenges present substantial obstacles to cloud processing its applications. In this paper, we propose a Unified Denoising Framework (UDF) aimed at removing noise restoring geometry targets. The proposed method consists three steps: veiling effect denoising using an improved pass-through filter, range anomalies...

Convolutional neural networks (CNNs) have improved the accuracy of hyperspectral image (HSI) classification significantly. However, CNN models usually generate a large number feature maps, which lead to high redundancy and cannot guarantee effectively extract discriminative features for well characterizing complex structures HSIs. In this article, two novel mixed link (MLNets) are proposed enhance representational ability CNNs HSI classification. Specifically, architectures integrate reusage...

A visible-light mediated fluorinated cyclization of ene-vinylidenecyclopropanes along with mechanistic investigations is presented.

Trio-based whole-exome sequencing (trio-WES) enables identification of pathogenic variants, including copy-number variants (CNVs), in children with unexplained neurodevelopmental delay (NDD) and comorbidities (NDCs), autism spectrum disorder (ASD), epilepsy, attention deficit hyperactivity disorder. Further phenotypic genetic analysis on trio-WES-tested NDD-NDCs cases may help to identify key factors related higher diagnostic yield using trio-WES novel risk genes associated NDCs clinical settings.