Explore the vast range of titles available.

Remote-sensing images constitute an important means of obtaining geographic information. Image super-resolution reconstruction techniques are effective methods of improving the spatial resolution of remote-sensing images. Super-resolution reconstruction networks mainly improve the model performance by increasing the network depth. However, blindly increasing the network depth can easily lead to gradient disappearance or gradient explosion, increasing the difficulty of training. This report proposes a new pyramidal multi-scale residual network (PMSRN) that uses hierarchical residual-like connections and dilation convolution to form a multi-scale dilation residual block (MSDRB). The MSDRB enhances the ability to detect context information and fuses hierarchical features through the hierarchical feature fusion structure. Finally, a complementary block of global and local features is added to the reconstruction structure to alleviate the problem that useful original information is ignored. The experimental results showed that, compared with a basic multi-scale residual network, the PMSRN increased the peak signal-to-noise ratio by up to 0.44 dB and the structural similarity to 0.9776.

Multi-scale structures, as found in nature (e.g., bone and bamboo), hold the promise of achieving superior performance while being intrinsically lightweight, robust, and multi-functional. Recent years have seen a rapid development in topology optimization approaches for designing multi-scale structures, but the field actually dates back to the seminal paper by Bendsøe and Kikuchi from 1988 (Computer Methods in Applied Mechanics and Engineering 71(2): pp. 197–224). In this review, we intend to categorize existing approaches, explain the principles of each category, analyze their strengths and applicabilities, and discuss open research questions. The review and associated analyses will hopefully form a basis for future research and development in this exciting field.

Implementation of wildfire- and climate-adaptation strategies in seasonally dry forests of western North America is impeded by numerous constraints and uncertainties. After more than a century of resource and land use change, some question the need for proactive management, particularly given novel social, ecological, and climatic conditions. To address this question, we first provide a framework for assessing changes in landscape conditions and fire regimes. Using this framework, we then evaluate evidence of change in contemporary conditions relative to those maintained by active fire regimes, i.e., those uninterrupted by a century or more of human-induced fire exclusion. The cumulative results of more than a century of research document a persistent and substantial fire deficit and widespread alterations to ecological structures and functions. These changes are not necessarily apparent at all spatial scales or in all dimensions of fire regimes and forest and nonforest conditions. Nonetheless, loss of the once abundant influence of low- and moderate-severity fires suggests that even the least fire-prone ecosystems may be affected by alteration of the surrounding landscape and, consequently, ecosystem functions. Vegetation spatial patterns in fire-excluded forested landscapes no longer reflect the heterogeneity maintained by interacting fires of active fire regimes. Live and dead vegetation (surface and canopy fuels) is generally more abundant and continuous than before European colonization. As a result, current conditions are more vulnerable to the direct and indirect effects of seasonal and episodic increases in drought and fire, especially under a rapidly warming climate. Long-term fire exclusion and contemporaneous social-ecological influences continue to extensively modify seasonally dry forested landscapes. Management that realigns or adapts fire-excluded conditions to seasonal and episodic increases in drought and fire can moderate ecosystem transitions as forests and human communities adapt to changing climatic and disturbance regimes. As adaptation strategies are developed, evaluated, and implemented, objective scientific evaluation of ongoing research and monitoring can aid differentiation of warranted and unwarranted uncertainties.

Aiming at the problems of low efficiency and poor accuracy in the product surface defect detection. In this paper, an online surface defects detection method based on YOLOV3 is proposed. Firstly, using lightweight network MobileNetV2 to replace the original backbone as the feature extractor to improve network speed. Then, we propose an extended feature pyramid network (EFPN) to extend the detection layer for multi-size object detection and design a novel feature fusing module (FFM) embedded in the extend layer to super-resolve features and capture more regional details. In addition, we add an IoU loss function to solve the mismatch between classification and bounding box regression. The proposed method is used to train and test on the hot rolled steel open dataset NEU-DET, which contains six typical defects of a steel surface, namely rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. The experimental results show that our method achieves a satisfactory balance between performance and consumption and reaches 86.96% mAP with a speed of 80.96 FPS, which is more accurate and faster than many other algorithms and can realize real-time and high-precision inspection of product surface defects.

In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the HSIC task, such as the lack of labeled training samples, which constrains the classification accuracy and generalization ability of CNNs. To address this problem, a deep multi-scale attention fusion network (DMAF-NET) is proposed in this paper. This network is based on multi-scale features and fully exploits the deep features of samples from multiple levels and different perspectives with an aim to enhance HSIC results using limited samples. The innovation of this article is mainly reflected in three aspects: Firstly, a novel baseline network for multi-scale feature extraction is designed with a pyramid structure and densely connected 3D octave convolutional network enabling the extraction of deep-level information from features at different granularities. Secondly, a multi-scale spatial–spectral attention module and a pyramidal multi-scale channel attention module are designed, respectively. This allows modeling of the comprehensive dependencies of coordinates and directions, local and global, in four dimensions. Finally, a multi-attention fusion module is designed to effectively combine feature mappings extracted from multiple branches. Extensive experiments on four popular datasets demonstrate that the proposed method can achieve high classification accuracy even with fewer labeled samples.

MXenes as an emerging two‐dimensional (2D) material have attracted tremendous interest in electrochemical energy‐storage systems such as supercapacitors. Nevertheless, 2D MXene flakes intrinsically tend to lie flat on the substrate when self‐assembling as electrodes, leading to the highly tortuous ion pathways orthogonal to the current collector and hindering ion accessibility. Herein, a facile strategy toward multi‐scale structural engineering is proposed to fabricate high‐performance MXene hydrogel supercapacitor electrodes. By unidirectional freezing of the MXene slurry followed by a designed thawing process in the sulfuric acid electrolyte, the hydrogel electrode is endowed with a three‐dimensional (3D) open macrostructure impregnated with sufficient electrolyte and H+‐intercalated microstructure, which provide abundant active sites for ion storage. Meanwhile, the ordered channels bring through‐electrode ion and electron transportation pathways that facilitate electrolyte infiltration and mass exchange between electrolyte and electrode. Furthermore, this strategy can also be extended to the fabrication of a 3D‐printed all‐MXene micro‐supercapacitor (MSC), delivering an ultrahigh areal capacitance of 2.0 F cm–2 at 1.2 mA cm–2 and retaining 1.2 F cm–2 at 60 mA cm–2 together with record‐high energy density (0.1 mWh cm–2 at 0.38 mW cm–2). A strategy of multi‐scale structural engineering is proposed to fabricate high‐performance MXene hydrogel supercapacitor electrode with both vertically ordered macrostructure and the proton‐intercalated microstructure. This strategy also can be extended to the fabrication of 3D‐printed all‐MXene micro‐supercapacitor, delivering an ultrahigh areal capacitance together with record‐high energy density.

Many species distribution models (SDMs) are built with precise but geographically restricted presence–absence data sets (e.g., a country) where only a subset of the environmental conditions experienced by a species across its range is considered (i.e., spatial niche truncation). This type of truncation is worrisome because it can lead to incorrect predictions e.g., when projecting to future climatic conditions belonging to the species niche but unavailable in the calibration area. Data from citizen-science programs, species range maps or atlases covering the full species range can be used to capture those parts of the species’ niche that are missing regionally. However, these data usually are too coarse or too biased to support regional management. Here, we aim to (1) demonstrate how varying degrees of spatial niche truncation affect SDMs projections when calibrated with climatically truncated regional data sets and (2) test the performance of different methods to harness information from larger-scale data sets presenting different spatial resolutions to solve the spatial niche truncation problem. We used simulations to compare the performance of the different methods, and applied them to a real data set to predict the future distribution of a plant species (Potentilla aurea) in Switzerland. SDMs calibrated with geographically restricted data sets expectedly provided biased predictions when projected outside the calibration area or time period. Approaches integrating information from larger-scale data sets using hierarchical data integration methods usually reduced this bias. However, their performance varied depending on the level of spatial niche truncation and how data were combined. Interestingly, while some methods (e.g., data pooling, downscaling) performed well on both simulated and real data, others (e.g., those based on a Poisson point process) performed better on real data, indicating a dependency of model performance on the simulation process (e.g., shape of simulated response curves). Based on our results, we recommend to use different data integration methods and, whenever possible, to make a choice depending on model performance. In any case, an ensemble modeling approach can be used to account for uncertainty in how niche truncation is accounted for and identify areas where similarities/dissimilarities exist across methods.

Learning information from a single or a few samples is called few-shot learning. This learning method will solve deep learning’s dependence on a large sample. Deep learning achieves few-shot learning through meta-learning: “how to learn by using previous experience”. Therefore, this paper considers how the deep learning method uses meta-learning to learn and generalize from a small sample size in image classification. The main contents are as follows. Practicing learning in a wide range of tasks enables deep learning methods to use previous empirical knowledge. However, this method is subject to the quality of feature extraction and the selection of measurement methods supports set and the target set. Therefore, this paper designs a multi-scale relational network (MSRN) aiming at the above problems. The experimental results show that the simple design of the MSRN can achieve higher performance. Furthermore, it improves the accuracy of the datasets within fewer samples and alleviates the overfitting situation. However, to ensure that uniform measurement applies to all tasks, the few-shot classification based on metric learning must ensure the task set’s homologous distribution.

Mountain ecosystems have been less adversely affected by invasions of nonnative plants than most other ecosystems, partially because most invasive plants in the lowlands are limited by climate and cannot grow under harsher high‐elevation conditions. However, with ongoing climate change, invasive species may rapidly move upwards and threaten mid‐, and then high‐elevation mountain ecosystems. We evaluated this threat by modeling the current and future habitat suitability for 48 invasive plant species in Switzerland and New South Wales, Australia. Both regions had contrasting climate interactions with elevation, resulting in possible different responses of species distributions to climate change. Using a species distribution modeling approach that combines data from two spatial scales, we built high‐resolution species distribution models (≤250 m) that account for the global climatic niche of species and also finer variables depicting local climate and disturbances. We found that different environmental drivers limit the elevation range of invasive species in each of the two regions, leading to region‐specific species responses to climate change. The optimal suitability for plant invaders is predicted to markedly shift from the lowland to the montane or subalpine zone in Switzerland, whereas the upward shift is far less pronounced in New South Wales where montane and subalpine elevations are already suitable. The results suggest that species most likely to invade high elevations in Switzerland will be cold‐tolerant, whereas species with an affinity to moist soils are most likely to invade higher elevations in Australia. Other plant traits were only marginally associated with elevation limits. These results demonstrate that a more systematic consideration of future distributions of invasive species is required in conservation plans of not yet invaded mountainous ecosystems.

The precise building extraction from high-resolution remote sensing images holds significant application for urban planning, resource management, and environmental conservation. In recent years, deep neural networks (DNNs) have garnered substantial attention for their adeptness in learning and extracting features, becoming integral to building extraction methodologies and yielding noteworthy performance outcomes. Nonetheless, prevailing DNN-based models for building extraction often overlook spatial information during the feature extraction phase. Additionally, many existing models employ a simplistic and direct approach in the feature fusion stage, potentially leading to spurious target detection and the amplification of internal noise. To address these concerns, we present a multi-scale attention network (MSANet) tailored for building extraction from high-resolution remote sensing images. In our approach, we initially extracted multi-scale building feature information, leveraging the multi-scale channel attention mechanism and multi-scale spatial attention mechanism. Subsequently, we employed adaptive hierarchical weighting processes on the extracted building features. Concurrently, we introduced a gating mechanism to facilitate the effective fusion of multi-scale features. The efficacy of the proposed MSANet was evaluated using the WHU aerial image dataset and the WHU satellite image dataset. The experimental results demonstrate compelling performance metrics, with the F1 scores registering at 93.76% and 77.64% on the WHU aerial imagery dataset and WHU satellite dataset II, respectively. Furthermore, the intersection over union (IoU) values stood at 88.25% and 63.46%, surpassing benchmarks set by DeepLabV3 and GSMC.