Article
Environmental Sciences
Shiwei Cheng, Baozhu Li, Le Sun, Yuwen Chen
Summary: Semantic segmentation of high-resolution remote sensing images is crucial in practical applications such as precision agriculture and natural disaster assessment. This article proposes a hierarchical refinement residual network (HRRNet) that utilizes attention blocks and decoders to improve the segmentation results by exploiting contextual dependencies. Experimental results show that HRRNet achieves superior segmentation results compared to state-of-the-art networks on Vaihingen and Potsdam datasets.
Article
Geography, Physical
Xue Yang, Xiang Fan, Mingjun Peng, Qingfeng Guan, Luliang Tang
Summary: This study proposes a new model, AD-HRNet, for semantic segmentation of remote sensing images. It addresses challenges such as unbalanced category weight, rich context leading to recognition difficulties, and blurred boundaries of multi-scale objects. The model combines HRNet with attention mechanisms and dilated convolution, and achieves improved performance in terms of mIoUs on different datasets.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2022)
Article
Geochemistry & Geophysics
Zhen Wang, Shanwen Zhang, Chuanlei Zhang, Buhong Wang
Summary: This article proposes a novel hidden feature-guided semantic segmentation network (HFGNet) for accurate semantic segmentation of remote sensing images. It introduces a hidden feature extraction module (HFE-M) to mine more valuable hidden features and a multifeature interactive fusion module (MIF-M) to establish correlation between different features. A multiscale feature calibration module (MSFC) and a local-channel attention mechanism (LCA-M) are also designed to enhance the diversity and refinement representation of hierarchical fusion features. Experimental results show that the proposed HFGNet outperforms several state-of-the-art methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Xudong Yao, Qing Guo, An Li
Summary: CD-AttDLV3+ is a lightweight cloud detection network based on deep learning, using only red-green-blue and near-infrared bands, and shows excellent performance in terms of efficiency and accuracy.
Article
Environmental Sciences
Xichen Meng, Liqun Zhu, Yilong Han, Hanchao Zhang
Summary: Traditional models using CNNs as encoders fail to effectively combine high-level features and low-level features. To address this issue, we propose CMA and CSA modules to enhance the interaction and fusion of different feature levels. Experimental results on the ISPRS Vaihingen and Potsdam datasets demonstrate that CANet achieves superior performance with mean F1-scores of 89.61% and 92.60% respectively in the semantic segmentation task of remote sensing images.
Article
Engineering, Marine
Huixuan Fu, Dan Meng, Wenhui Li, Yuchao Wang
Summary: The study proposed a crack detection method based on an improved DeepLabv3+ algorithm utilizing deep learning technology. Experimental results demonstrated that the method achieved higher accuracy in crack segmentation, showing improved ability to accurately identify crack details, thereby proving the effectiveness of the algorithm.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Environmental Sciences
Zhonggui Tong, Yuxia Li, Jinglin Zhang, Lei He, Yushu Gong
Summary: In this study, a Multiscale Fusion Attention Network (MSFANet) is proposed for road extraction, addressing the issues of discontinuous outputs caused by similar spectral signatures and the lack of spectral information in previous methods. Compared with traditional frameworks, MSFANet fuses information from different spectra at multiple scales, using multispectral remote sensing data alongside RGB data. Evaluation results on the SpaceNet dataset and self-annotated dataset demonstrate the superior performance of MSFANet compared to other methods.
Article
Computer Science, Artificial Intelligence
Junxiao Wang, Zhixi Feng, Yao Jiang, Shuyuan Yang, Huixiao Meng
Summary: In this paper, an Orientation Attention Network (OANet) is proposed to learn both orientation features and global semantic features of ground objects for accurate segmentation. An Asymmetrical Convolution (AC) is constructed to explore the directional anisotropy of objects, and an Orientation Attention Module (OAM) is advanced to enhance the intrinsic geometric features of objects. The proposed OANet combines OAM with a Global Feature Module (GFM) for both structural and semantic sensitive representations of images. Extensive experiments demonstrate the effectiveness of the OANet.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Qiaolin Zeng, Jingxiang Zhou, Xuerui Niu
Summary: This manuscript introduces a novel network called CFPNet, which achieves fast and effective extraction of multiscale semantic information in remote sensing images by introducing modules such as multiscale convolution, attention upsample, and feature semantic enhancement.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Environmental Sciences
Jinglin Zhang, Yuxia Li, Bowei Zhang, Lei He, Yuan He, Wantao Deng, Yu Si, Zhonggui Tong, Yushu Gong, Kunwei Liao
Summary: Multi-objective semantic segmentation is a crucial task in computer vision, attracting widespread attention and research in remote sensing image analysis. In this study, a CD-MQANet network structure is proposed to fully exploit and utilize the spatial and spectral dimensions of remote sensing images, achieving multi-objective semantic segmentation of complex remote sensing images.
Article
Computer Science, Information Systems
Jintong Jia, Jiarui Song, Qingqiang Kong, Huan Yang, Yunhe Teng, Xuan Song
Summary: This paper proposes a multi-attention-based semantic segmentation network for remote sensing images, addressing the challenges of multiple targets and large feature differences in such images. The model achieves improved extraction capability for fine-grained features by using a coordinate attention-based residual network in the encoder, replaces traditional upsampling operator with a content-aware reorganization module in the decoder to enhance network information extraction, and introduces a fused attention module for feature map fusion to solve the multi-scale problem. Experimental results show superior performance of the proposed model on both WHDLD dataset and self-labeled Lu County dataset, surpassing commonly used benchmark models.
Article
Environmental Sciences
Yuxia Li, Yu Si, Zhonggui Tong, Lei He, Jinglin Zhang, Shiyu Luo, Yushu Gong
Summary: This paper introduces a Multi-task Quadruple Attention Network (MQANet) to address the challenges of multi-object semantic segmentation in remote sensing images. By incorporating four attention modules and a multi-tasking mechanism, the MQANet is able to capture global features and improve the identification of similar objects. Experimental results demonstrate the superior performance of the MQANet compared to baseline methods.
Article
Environmental Sciences
Yonghong Zhang, Huanyu Lu, Guangyi Ma, Huajun Zhao, Donglin Xie, Sutong Geng, Wei Tian, Kenny Thiam Choy Lim Kam Sian
Summary: This paper proposes a novel method called MU-Net, which combines CNN and MixFormer, for automatically extracting water bodies. The method improves the network's ability to capture semantic features of the water body, thereby improving the accuracy of water body extraction.
Article
Environmental Sciences
Chao Zhang, Liguo Weng, Li Ding, Min Xia, Haifeng Lin
Summary: A new cloud detection method is proposed in this paper, which can accurately and efficiently detect smaller clouds and obtain finer edge segmentation. By using ResNet-18 as the backbone, and combining the Multi-scale Global Attention Module and Strip Pyramid Channel Attention Module, the detection accuracy of clouds is improved. The Hierarchical Feature Aggregation Module fuses high-dimensional and low-dimensional features, and the final segmentation effect is obtained by layer-by-layer upsampling. The proposed model achieves excellent results on the Cloud and Cloud Shadow Dataset and the public dataset CSWV.
Article
Geochemistry & Geophysics
Xudong Hu, Penglin Zhang, Qi Zhang, Feng Yuan
Summary: In this letter, the authors propose a network called GLSANet, which utilizes a global-local self-attention mechanism to consider both global and local contexts for image segmentation. Experimental results demonstrate that GLSANet significantly improves semantic segmentation accuracy and outperforms other competing methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Chemistry, Multidisciplinary
Laigang Hu, Wenhao Wu, Li Gong, Hongxia Zhu, Ling Jiang, Min Hu, Daohui Lin, Kun Yang
Summary: In this study, a novel metal-organic framework (MOF) called ZJU-620(Al) was synthesized using low toxic aluminum (Al) as the metal. ZJU-620(Al) has a uniform micropore size of 8.37 +/- 0.73 angstrom and a specific surface area of 1347 m(2) g(-1). It shows excellent chemical-thermal stability and adsorption for trace BTEX.
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
(2023)
Article
Meteorology & Atmospheric Sciences
Xu Yuan, Kun Yang, Hui Lu, Yan Wang, Xiaogang Ma
Summary: This study clarifies the impacts of moisture transport between the lower layer and the upper layer through and over the Yarlung Tsangpo Grand Canyon (YTGC). The results show that moisture transport in the lower layer through the YTGC is critical to precipitation in the YTGC, while moisture transport in the upper layer over the YTGC is more important to precipitation in the eastern Tibetan Plateau (TP).
ATMOSPHERIC RESEARCH
(2023)
Article
Engineering, Environmental
Yanlong Wang, Jiang Xu, Kun Yang, Daohui Lin
Summary: In this study, a three-layer Fe-0@SiO2@CaO2 nanocomposite was developed, which achieved the removal of various water contaminants through oxidation, reduction, and flocculation. The removal rates of tetracycline, pentachlorophenol, cadmium, chromium, and phosphorus exceeded 99%. Additionally, the nanocomposite showed excellent performance in turbidity removal and water decolorization. This research provides a novel material for simultaneous removal of multiple contaminants in wastewater treatment.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Biophysics
Jun Liu, Yangyang Xu, Xiangyun Lin, Nan Ma, Qiongqiong Zhu, Kunlin Yang, Xinfei Li, Chang Liu, Ninghan Feng, Yuxia Zhao, Xuesong Li, Wei Zhang
Summary: Developing methods to prevent catheter-associated infections (CAIs) is in high demand worldwide. In this study, antimicrobial poly-L-lysine (PLL) brush was developed on the surface of silicone catheter to provide long-term antibacterial properties. The PLL-tethered catheter showed potent antibacterial activities against CAUTIs-related pathogens and retained its bactericidal properties even after immersion in simulated body fluid or incubation at high temperature. The PLL-tethered catheter also exhibited good anti-infection activity and biocompatibility in vivo, making it a promising approach in combating CAIs in clinical applications.
COLLOIDS AND SURFACES B-BIOINTERFACES
(2023)
Article
Biodiversity Conservation
Ruibo Yang, Xian Fan, Lei Zhao, Kun Yang
Summary: In lake ecosystems, regime shifts can change the composition and structure of phytoplankton communities. This study analyzed long-term observations in Erhai Lake, China, and found a distinct regime shift between 2001 and 2003. Before the shift, the lake was oligotrophic and dominated by Cyanophyta, Bacillariophyta, and Cryptophyta. After the shift, the community became eutrophic and dominated by Cyanophyta, Chlorophyta, and Bacillariophyta, with light becoming the primary driver for community succession.
ECOLOGICAL INDICATORS
(2023)
Article
Environmental Sciences
Xiaoming Tao, Jiang Xu, Kun Yang, Daohui Lin
Summary: The new paradigm in wastewater treatment focuses on resource recovery, especially for non-renewable phosphorus (P). Nanomaterial-based adsorption technology, such as oxymagnesite/green rust (OMGR) nanohybrids, offers high efficiency and selectivity for P recovery from wastewater. OMGR demonstrated excellent selectivity for phosphate removal, wide pH adaptability, and a high removal capacity of 141 mg P.g-1. Phosphate-loaded OMGR also acted as a slow-release P-fertilizer, providing a green and eco-friendly approach to P resource recovery and reuse.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Remote Sensing
Fengjie Ren, Hui Lu, Bin Wang, Kun Yang, Le Yu, Weiwei Gan, Tianjie Zhao
Summary: In this study, SMAP36 and SMAP09 products from the SMAP mission and the AMSR2 FT product were compared against surface soil temperature measurements in Russia. The results show that AMSR2 FT performs better than the SMAP products, particularly in the overall accuracy of the descending orbit. AMSR2 FT has high accuracy in inland areas but lower accuracy along coastal zones due to the presence of water bodies or lake ice. The study also highlights the need to improve the algorithm for wet snow detection in mixed forest areas.
REMOTE SENSING LETTERS
(2023)
Article
Engineering, Civil
Yanbin Lei, Tandong Yao, Yongwei Sheng, Kun Yang, Wei Yang, Shenghai Li, Jing Zhou, Yaozhi Jiang, Yifan Yu
Summary: Extreme events on the Tibetan Plateau, such as unprecedented lake expansion, have become more frequent and severe due to climate warming and moistening. This expansion, attributed to abnormally high precipitation, poses a substantial threat to regional ecosystems, infrastructure, and habitats. Therefore, it is necessary to identify threatened areas using satellite images and conduct real-time observations of lake level changes.
JOURNAL OF HYDROLOGY
(2023)
Article
Medicine, General & Internal
Bing Wang, Wenzhi Gao, Kunlin Yang, Honglei Liu, Yangjun Han, Mingxin Diao, Chao Zuo, Minghua Zhang, Yingzhi Diao, Zhihua Li, Xinfei Li, Gang Wang, Peng Zhang, Chunji Wang, Chunjuan Xiao, Chen Huang, Yaming Gu, Xuesong Li
Summary: This study aimed to investigate the efficacy of balloon dilation in ureteral stricture and analyze the risk factors for its failure. A retrospective analysis of 196 patients who underwent balloon dilation was conducted, with 127 patients having complete data. The success rates of balloon dilation and balloon dilation combined with endoureterotomy for lower ureteral stricture were higher compared to other cases. Balloon circumference and multiple ureteral strictures were identified as risk factors for balloon dilation failure.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Environmental Sciences
Fang Li, Yishui Shui, Jiayao Liang, Kun Yang, Junyi Yu
Summary: By modeling the measured data of marine wireless channels and creating sea surface morphology models under multiple wind speeds, this paper calculates the radio propagation characteristics of the Pearl River estuary and estimates the path loss in the same area under different conditions using the Monte Carlo method. The simulation results show that the electric wave propagation gradually changes from the round earth loss (REL) model to the free space model with increasing wind speed. The distribution of the shadow fading varies with distance. The findings provide references for the network planning of marine communication.
FRONTIERS IN MARINE SCIENCE
(2023)
Article
Engineering, Marine
Yang Shi, Shuwen Wang, Fan Yang, Kunde Yang
Summary: In this paper, the statistical distribution of atmospheric ducts over the northern South China Sea is analyzed, and the propagation characteristics of microwaves near the sea surface in the presence of both surface and evaporation ducts are studied using the parabolic equation model. It is found that a hybrid atmospheric duct structure can capture more microwave energy at a lower receiving height compared to considering only one type of atmospheric duct.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Oncology
Fangyuan Zhou, You Qin, Xixi Liu, Jing Huang, Bian Wu, Zhanjie Zhang, Zhongyuan Yin, Jinsong Yang, Sheng Zhang, Ke Jiang, Kunyu Yang
Summary: This study evaluates the efficacy and safety of thoracic radiotherapy in patients with stage IV non-small-cell lung cancer (NSCLC) treated with epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs). The findings show that the combination of EGFR inhibitors and thoracic radiotherapy significantly improves overall survival but not progression-free survival. Therefore, preemptive thoracic radiotherapy during EGFR-TKI treatment could be considered as a competitive first-line therapeutic option with superior progression-free survival and a lower incidence of side effects.
THERAPEUTIC ADVANCES IN MEDICAL ONCOLOGY
(2023)
Article
Geosciences, Multidisciplinary
Yaozhi Jiang, Kun Yang, Youcun Qi, Xu Zhou, Jie He, Hui Lu, Xin Li, Yingying Chen, Xiaodong Li, Bingrong Zhou, Ali Mamtimin, Changkun Shao, Xiaogang Ma, Jiaxin Tian, Jianhong Zhou
Summary: This study produced a high-resolution long-term precipitation dataset (TPHiPr) for the Third Pole region by merging atmospheric simulation-based ERA5_CNN and gauge observations. The dataset showed higher accuracy and better detection of precipitation extremes compared to widely used datasets. It has broad applications in meteorological, hydrological, and ecological studies.
EARTH SYSTEM SCIENCE DATA
(2023)
Article
Urology & Nephrology
Zhihua Li, Xiang Wang, Yicen Ying, Xinfei Li, Weijie Zhu, Chang Meng, Guanpeng Han, Jing Liu, Jie Wang, Yanbo Huang, Kunlin Yang, Peng Zhang, Hongjian Zhu, Hua Guan, Xuesong Li, Liqun Zhou
Summary: This study evaluated the health-related quality of life, anxiety, and depression levels in patients with ureteral stricture (US) and identified independent factors affecting these outcomes. The results showed that patients with US had poor quality of life and emotional well-being. Factors such as increased age, female gender, and higher education level were associated with worse health-related quality of life. Additionally, iatrogenic US, nephrostomy tube placement, urinary symptoms, and high levels of anxiety and depression independently predicted poorer quality of life.
WORLD JOURNAL OF UROLOGY
(2023)
Article
Urology & Nephrology
Shubo Fan, Zhihua Li, Chang Meng, Yicen Ying, Guanpeng Han, Jingjing Gao, Xinfei Li, Jie Wang, Changwei Yuan, Shengwei Xiong, Peng Zhang, Kunlin Yang, Ninghan Feng, Hongjian Zhu, Xuesong Li
Summary: Robotic and laparoscopic ureteroplasty using a lingual mucosa graft (RU-LMG and LU-LMG, respectively) are both feasible, effective, and safe for repairing complex ureteral strictures. RU-LMG has a shorter operative time and length of post-operative stay, but incurs higher hospital costs.
INTERNATIONAL UROLOGY AND NEPHROLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Yapo Abole Serge Innocent Oboue, Yunfeng Chen, Sergey Fomel, Wei Zhong, Yangkang Chen
Summary: Strong noise can disrupt the recorded seismic waves and negatively impact subsequent seismological processes. To improve the signal-to-noise ratio (S/N) of seismological data, we introduce MATamf, an open-source MATLAB code package based on an advanced median filter (AMF) that simultaneously attenuates various types of noise and improves S/N. Experimental results demonstrate the usefulness and advantages of the proposed AMF workflow in enhancing the S/N of a wide range of seismological applications.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Upkar Singh, P. N. Vinayachandran, Vijay Natarajan
Summary: The Bay of Bengal maintains its salinity distribution due to the cyclic flow of high salinity water and the mixing with freshwater. This paper introduces an advection-based feature definition and algorithms to track the movement of high salinity water, validated through comparison with observed data.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Bijal Chudasama, Nikolas Ovaskainen, Jonne Tamminen, Nicklas Nordback, Jon Engstro, Ismo Aaltonen
Summary: This contribution presents a novel U-Net convolutional neural network (CNN)-based workflow for automated mapping of bedrock fracture traces from aerial photographs acquired by unmanned aerial vehicles (UAV). The workflow includes training a U-Net CNN using a small subset of photographs with manually traced fractures, semantic segmentation of input images, pixel-wise identification of fracture traces, ridge detection algorithm and vectorization. The results show the effectiveness and accuracy of the workflow in automated mapping of bedrock fracture traces.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Ruizhen Wang, Siyang Wan, Weitao Chen, Xuwen Qin, Guo Zhang, Lizhe Wang
Summary: This paper proposes a novel framework to generate a finer soil strength map based on RCI, which uses ensemble learning models to obtain USCS soil classification and predict soil moisture, in order to improve the resolution and reliability of existing soil strength maps.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhanlong Chen, Xiaochuan Ma, Houpu Li, Xuwei Xu, Xiaoyi Han
Summary: Simulated terrains are important for landform and terrain research, disaster prediction, rescue and disaster relief, and national security. This study proposes a deep learning method, IGPN, that integrates global information and pattern features of the local terrain to generate accurate simulated terrains quickly.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Daniele Secci, Vanessa A. Godoy, J. Jaime Gomez-Hernandez
Summary: Neural networks excel in various machine learning applications, but lack physical interpretability and constraints, limiting their accuracy and reliability in predicting complex physical systems' behavior. Physics-Informed Neural Networks (PINNs) integrate neural networks with physical laws, providing an effective tool for solving physical problems. This article explores recent developments in PINNs, emphasizing their application in solving unconfined groundwater flow, and discusses challenges and opportunities in this field.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Renguang Zuo, Ying Xu
Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.
COMPUTERS & GEOSCIENCES
(2024)