Review
Geography, Physical
Xian Sun, Peijin Wang, Zhiyuan Yan, Feng Xu, Ruiping Wang, Wenhui Diao, Jin Chen, Jihao Li, Yingchao Feng, Tao Xu, Martin Weinmann, Stefan Hinz, Cheng Wang, Kun Fu
Summary: With the rapid development of deep learning, many deep learning-based approaches have achieved great success in object detection tasks. However, existing datasets have limitations in terms of scale, category, and image. To address the needs of high-resolution remote sensing images, we propose a novel benchmark dataset called FAIR1M, which includes over 1 million instances and more than 40,000 images for fine-grained object recognition. The FAIR1M dataset has several unique characteristics, such as being larger than other datasets, providing richer category information, containing geographic information, and having better image quality. We evaluate state-of-the-art methods on the FAIR1M dataset and propose improvements to the evaluation metrics and the incorporation of hierarchy detection. We believe that the FAIR1M dataset will contribute to the field of earth observation through fine-grained object detection in large-scale real-world scenes.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Wei Liu, Karoll Quijano, Melba M. Crawford
Summary: This paper proposes a tassel detection algorithm based on UAV imagery, which achieves better performance in small-size tassel detection. The algorithm adopts novel techniques such as the bidirectional feature pyramid network and the robust attention module.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geography, Physical
Libo Wang, Rui Li, Ce Zhang, Shenghui Fang, Chenxi Duan, Xiaoliang Meng, Peter M. Atkinson
Summary: This paper discusses the importance of semantic segmentation of remotely sensed urban scene images in practical applications, and highlights the advantages of using Transformer and the proposed UNetFormer model for real-time segmentation. Experimental results demonstrate that UNetFormer achieves faster inference speed and higher accuracy compared to state-of-the-art lightweight models.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Muhammad Ahmad, Sidrah Shabbir, Swalpa Kumar Roy, Danfeng Hong, Xin Wu, Jing Yao, Adil Mehmood Khan, Manuel Mazzara, Salvatore Distefano, Jocelyn Chanussot
Summary: Hyperspectral imaging (HSI) is widely used in various applications, but the complex characteristics of HSI data make accurate classification challenging for traditional methods. Recent research has shown that deep learning (DL) can effectively address these challenges. This survey provides an overview of DL for HSI classification and compares state-of-the-art strategies. The article also discusses strategies to improve the generalization performance of DL in the context of limited labeled training data.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Review
Geography, Physical
Qiqi Zhu, Xi Guo, Weihuan Deng, Sunan Shi, Qingfeng Guan, Yanfei Zhong, Liangpei Zhang, Deren Li
Summary: A novel semantic change detection framework called Siam-GL was proposed for HSR remote sensing images. The Siam-GL framework effectively extracts representative features of bi-temporal HSR remote sensing images through Siamese architecture and global hierarchical sampling mechanism. Experimental results demonstrated that the Siam-GL framework outperforms advanced semantic change detection methods in terms of both quantity and quality.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Ecology
Zihan Xu, Jian Peng, Jianquan Dong, Yanxu Liu, Qianyuan Liu, Danna Lyu, Ruilin Qiao, Zimo Zhang
Summary: This study quantitatively analyzed the spatiotemporal changes in ecosystem services (ES) supply and demand in Guangdong Province from 2000 to 2015. The results showed spatial heterogeneity in the changes, with ES supply being significantly affected by ES demand. Different zones also exhibited spatial correlation in ES supply and demand changes.
LANDSCAPE AND URBAN PLANNING
(2022)
Article
Geography, Physical
Alex R. Aves, Laura E. Revell, Sally Gaw, Helena Ruffell, Alex Schuddeboom, Ngaire E. Wotherspoon, Michelle LaRue, Adrian J. McDonald
Summary: Airborne microplastics have been identified in various remote environments, but there is a lack of data in the Southern Hemisphere, particularly in Antarctica. This study collected snow samples from 19 sites in the Ross Island region of Antarctica and confirmed the presence of microplastics using micro-Fourier transform infrared spectroscopy (mu FTIR). The results showed that all Antarctic snow samples contained microplastics, with an average concentration of 29 particles L-1. The most common type of microplastic was fibers, and the most common polymer was polyethylene terephthalate (PET). The study also found that the microplastics could have been transported over long distances of up to 6000 km and could have local sources from nearby research stations.
Review
Geography, Physical
F. Nex, C. Armenakis, M. Cramer, D. A. Cucci, M. Gerke, E. Honkavaara, A. Kukko, C. Persello, J. Skaloud
Summary: This paper reviews best practices for the use of UAVs in remote sensing and mapping applications, emphasizes the need for interdisciplinary research, explores the future trends and impacts of UAVs in photogrammetry and remote sensing.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Bing Zhang, Yuanfeng Wu, Boya Zhao, Jocelyn Chanussot, Danfeng Hong, Jing Yao, Lianru Gao
Summary: Due to advances in remote sensing satellite imaging and image processing technologies, intelligent remote sensing satellites have the potential to provide personalized, real-time, and accurate remote sensing information services. However, there are technological breakthroughs and legal challenges in the design of intelligent remote sensing satellites.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geography, Physical
Faming Huang, Jiawu Chen, Weiping Liu, Jinsong Huang, Haoyuan Hong, Wei Chen
Summary: This study focuses on the rainfall-induced landslide hazard, using machine learning models to predict landslide susceptibility and proposing different critical rainfall threshold methods. The coupling of susceptibility maps and critical rainfall threshold values effectively predicts the rainfall-induced landslide hazards.
Article
Geography, Physical
Rashedul Islam, Boshir Ahmed, Ali Hossain
Summary: This study proposes a band grouping technique called BgMNF, which utilizes Normalized Mutual Information (NMI) for feature extraction from hyperspectral images (HSI). The technique combines kernel Support Vector Machine (SVM) for feature selection and analysis. Experimental results demonstrate significant improvement in classification accuracy and computational cost compared to existing methods.
JOURNAL OF SPATIAL SCIENCE
(2022)
Article
Engineering, Electrical & Electronic
Andreas Colliander, Rolf Reichle, Wade Crow, Michael Cosh, Fan Chen, Steven Chan, Narendra Narayan Das, Rajat Bindlish, J. Chaubell, Seungbum Kim, Qing Liu, Peggy OaNeill, Scott Dunbar, Land Dang, John S. Kimball, Thomas Jackson, Hala Al-Jassar, Jun Asanuma, Bimal Bhattacharya, Aaron Berg, David Bosch, Laura Bourgeau-Chavez, Todd Caldwell, Jean-Christophe Calvet, Chandra Collins, Karsten Jensen, Stan Livingston, Ernesto Lopez-Baeza, Jose Martinez-Fernandez, Heather McNairn, Mahta Moghaddam, Carsten Montzka, Claudia Notarnicola, Thierry Pellarin, Isabella Greimeister-Pfeil, Jouni Pulliainen, Judith Ramos, Judith Gpe. Ramos Hernandez, Mark Seyfried, Patrick Starks, Bob Su, R. van der Velde, Yijian Zeng, Marc Thibeault, Mariette Vreugdenhil, Jeffrey Walker, Mehrez Zribi, Dara Entekhabi, Simon Yueh
Summary: The National Aeronautics and Space Administration's Soil Moisture Active Passive (SMAP) mission has been validating its soil moisture products since 2015. The results show that the SMAP products meet the mission requirements and are generally consistent with other satellite products. The validation program will continue and plans to expand to forested and high-latitude regions.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Ecology
Carlos M. Duarte, Jean-Pierre Gattuso, Kasper Hancke, Hege Gundersen, Karen Filbee-Dexter, Morten F. Pedersen, Jack J. Middelburg, Michael T. Burrows, Kira A. Krumhansl, Thomas Wernberg, Pippa Moore, Albert Pessarrodona, Sarah B. Orberg, Isabel S. Pinto, Jorge Assis, Ana M. Queiros, Dan A. Smale, Trine Bekkby, Ester A. Serrao, Dorte Krause-Jensen
Summary: This study provides a data-driven assessment of the global extent and production of macroalgal habitats, revealing that macroalgal forests are a significant biome with a large area and high productivity. They are globally distributed as a thin strip along shorelines and their expansion in polar, subpolar, and tropical areas may increase their contribution to global carbon sequestration.
GLOBAL ECOLOGY AND BIOGEOGRAPHY
(2022)
Review
Ecology
Matthew H. E. M. Browning, Alessandro Rigolon, Olivia McAnirlin, Hyunseo (Violet) Yoon
Summary: Greenspace in urban areas may have greater protective health effects than elsewhere. Urban dwellers experience more environmental harmful exposures, attentional demands, and stressors than their suburban/rural counterparts. Stronger greenspace-health associations in more urban areas might be explained in part by the mechanistic pathways underlying these associations.
LANDSCAPE AND URBAN PLANNING
(2022)
Article
Geography, Physical
Shaojian Wang, Zitian Cui, Jingjie Lin, Jinyan Xie, Kun Su
Summary: Urban resilience is an emerging research topic in urban studies, which refers to the ability of cities to withstand, recover from, and adapt to uncertain disruptions. This paper constructs an urban ecological resilience evaluation system based on Size, Density, and Morphology, and measures the degree of coupling coordination between urbanization and ecological resilience in the Pearl River Delta from 2000 to 2015. The results show that the urbanization level increased while the ecological resilience decreased during this period, and the coupling coordination degree between the two systems shifted from basic coordination to basic imbalance. The spatial distribution of coupling coordination degree exhibited a circular pattern, with higher coordination degree towards the periphery from the cities at the estuary of the Pearl River. The different sub-systems of ecological resilience played varying roles in the coupling coordination process.
JOURNAL OF GEOGRAPHICAL SCIENCES
(2022)
Article
Ecology
Haowei Mu, Xuecao Li, Haijiao Ma, Xiaoping Du, Jianxi Huang, Wei Su, Zhen Yu, Chen Xu, Hualiang Liu, Dongqin Yin, Baoguo Li
Summary: This study evaluated the ecological network in the Three-North Shelterbelt (TNS) region in China from a policy-driven perspective. The research found that the ecological network is denser in humid regions and identified vulnerable areas in the southern part of the Qilian Mountains and the northern part of Shaanxi. Additionally, the study observed a consistent decrease in human activities and species numbers with increasing distance to the ecological network.
LANDSCAPE AND URBAN PLANNING
(2022)
Article
Geography, Physical
Haonan Guo, Bo Du, Liangpei Zhang, Xin Su
Summary: This study proposes a novel boundary refinement network (CBR-Net) for accurately extracting building footprints from remote sensing imagery. The CBR-Net progressively refines building predictions in a coarse-to-fine manner, while enhancing the model's ability to perceive and refine building edges. Experimental results demonstrate that CBR-Net outperforms other algorithms on various building datasets.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Geography, Physical
Pan Chen, Bing Zhang, Danfeng Hong, Zhengchao Chen, Xuan Yang, Baipeng Li
Summary: This paper introduces a feature-constrained change detection network (FCCDN) that utilizes deep learning techniques and constrains features in both bitemporal feature extraction and feature fusion. By building a dual encoder-decoder network backbone and a nonlocal feature pyramid network, as well as a dense connection-based feature fusion module, the network achieves state-of-the-art performance on the change detection task. Moreover, accurate bitemporal semantic segmentation results are achieved for the first time without using semantic segmentation labels, which is crucial for cost-saving in change detection applications.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Mengxi Liu, Zhuoqun Chai, Haojun Deng, Rong Liu
Summary: Nonagriculturalization incidents are serious threats to local agricultural ecosystem and global food security. The proposed MSCANet combines the merits of CNN and transformer to fulfill efficient and effective cropland change detection. The article also provides a new cropland change detection dataset.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Ecology
Karel Mokany, Chris Ware, Skipton N. C. Woolley, Simon Ferrier, Matthew C. Fitzpatrick
Summary: This article presents a working guide to Generalized Dissimilarity Modelling (GDM) for characterizing and predicting beta diversity. It provides guidance on various aspects of GDM, including data preparation, model fitting, refinement, and assessment. The article also highlights the potential of GDM for spatial biodiversity analyses and suggests priority areas for future research and development.
GLOBAL ECOLOGY AND BIOGEOGRAPHY
(2022)