Article
Geography, Physical
Bolin Fu, Hang Yao, Feiwu Lan, Sunzhe Li, Yiyin Liang, Hongchang He, Mingming Jia, Yeqiao Wang, Donglin Fan
Summary: This study proposes the detect-monitor-predict (DMP) framework to track spatio-temporal changes and predict future trends of mangroves in Beibu Gulf, China, using multiple detection change algorithms. The study develops a method for extracting mangroves from multi-source inter-annual time-series spectral indices images and confirms its accuracy. The study reveals historical changes and predicts future growth conditions of mangroves in the Beibu Gulf.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Mohammad Ahmadlou, Mohammad Karimi, Nadhir Al-Ansari
Summary: This study aims to present and develop novel strategies for sampling and building training datasets in order to enhance the performance of data-driven models in urban gain modeling (UGM). The maximum entropy (ME) and ecological niche factor analysis (ENFA) models were used to select pure non-change samples with minimal uncertainty for training datasets in Isfahan and Tabriz cities in Iran. The results showed that the ME model was able to identify relatively pure non-change samples and properly remove impure non-change samples from the training dataset.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Kushanav Bhuyan, Sansar Raj Meena, Lorenzo Nava, Cees van Westen, Mario Floris, Filippo Catani
Summary: Repeated temporal mapping of landslides is crucial for studying their movement patterns and triggers. However, traditional methods of visual interpretation from remote sensing images are time-consuming. Recent advancements in deep learning models provide a faster and more accurate way of mapping landslides, but have not been applied to multi-temporal mapping in the Himalayas. This study proposes a new strategy using separate training samples to create multi-temporal landslide inventories.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Lin Feng, Penglei Xu, Hong Tang, Zeping Liu, Peng Hou
Summary: This paper presents a simple yet effective approach to generate a national-scale map of building footprints using feature super-resolution semantic segmentation of Sentinel-2 images. The proposed method detects over 86.3 million individual buildings with a total rooftop area of approximately 58,719.43 km(2) in China. The density of buildings varies greatly across different regions, with a gradual increase in the number of buildings from west to east.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Taewook Kim, Hyangsun Han
Summary: On January 11, 2021, a magnitude 6.7 earthquake occurred in Lake Hovsgol, Mongolia, with a complex rupture mechanism. The 3-D coseismic surface displacement fields were measured using interferometric synthetic aperture radar (InSAR) pairs. The study revealed that the maximum coseismic surface displacement appeared east of the Northern Hovsgol Fault (NHF). The importance of this study is rated 6 out of 10.
GISCIENCE & REMOTE SENSING
(2023)
Article
Environmental Sciences
Max A. A. Schuchardt, Bernd J. J. Berauer, Justyna Giejsztowt, Andreas V. V. Hessberg, Yujie Niu, Michael Bahn, Anke Jentsch
Summary: Warming in mountain regions is projected to occur three times faster than the global average. Observational studies have shown species loss and colonization by novel species in mountain plant communities due to climatic change. This study monitored translocated mountain plant communities and found increasing species turnover and colonization by novel species under two future climate scenarios. The colonization of novel species is facilitated by direct environmental filtering, which is affected by interacting climate stressors. The study provides experimental evidence of local species loss in mountain plant communities and reveals abrupt threshold dynamics.
ARCTIC ANTARCTIC AND ALPINE RESEARCH
(2023)
Article
Environmental Sciences
Anton Komarov, Matthew Sturm
Summary: This study investigates the effects of vegetation, microtopography, and microclimatic variability on taiga snow near Fairbanks, Alaska. The results show that different vegetation and topography can alter the structure of the snow cover, leading to irregular snow layers. A conceptual framework is proposed to understand and model taiga snow variability in terms of vegetation and microtopography.
ARCTIC ANTARCTIC AND ALPINE RESEARCH
(2023)
Article
Geography, Physical
Luoan Yang, Baolei Zhang, Xiaobo Zhang, Shumin Zhang, Le Yin
Summary: Urban vibrancy is a crucial factor in assessing urban prosperity. This study focuses on the relationship between urban vibrancy and housing prices, considering both spatial and temporal characteristics. By optimizing the identification model of urban vibrancy centers, a novel model for evaluating the time-dynamic accessibility of these centers is proposed. Results from the case study in Chengdu reveal significant variations in the spatiotemporal distribution of urban vibrancy centers, with high-vibrancy areas concentrated near commercial complexes. The study emphasizes the importance of considering the temporal nature of urban vibrancy and accessibility, contributing to the improvement of research frameworks and urban planning.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Qing Ding, Zhenfeng Shao, Xiao Huang, Xiaoxiao Feng, Orhan Altan, Bin Hu
Summary: This study proposes a lightweight semi-supervised binary change detection method (Semi-LCD) that achieves the optimal balance between performance and model size by fully utilizing unlabeled samples. By employing data augmentation, consistency regularization, and pseudo-labeling, Semi-LCD enhances detection performance and generalization capability. Experimental results demonstrate that Semi-LCD outperforms competing methods in terms of quantitative and qualitative measures. Ablation experiments further validate the robustness and advantages of Semi-LCD in effectively utilizing unlabeled samples.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Yang Qichi, Wang Lihui, Huang Jinliang, Liu Linzhi, Li Xiaodong, Xiao Fei, Du Yun, Yan Xue, Ling Feng
Summary: In this study, a deep convolutional neural network (DCNN) in Google Earth Engine (GEE) was developed for large-scale mapping of alpine land cover types in the Yarlung Zangbo river basin on the Tibetan plateau using multi-source remote sensing data. A detailed land cover classification system was established and the accuracy of the DCNN algorithm was found to be higher than traditional classification algorithms. The spatial distribution of alpine land cover types in different gradient zones was analyzed, revealing clear altitudinal characteristics. The results of this study provide valuable land cover information to support alpine ecosystem conservation.
GISCIENCE & REMOTE SENSING
(2023)
Review
Geography, Physical
Weiwei Sun, Chao Chen, Weiwei Liu, Gang Yang, Xiangchao Meng, Lihua Wang, Kai Ren
Summary: Coastlines play a crucial role in geographic studies. Recent advancements in remote sensing have enabled more accurate extraction methods and the ability to analyze detailed ocean-land interaction changes. This review identifies key milestones in coastline extraction using remote sensing, and provides insights on future development and challenges in this field.
GISCIENCE & REMOTE SENSING
(2023)
Article
Geography, Physical
Junyi Wei, Hangbin Wu, Han Yue, Shoujun Jia, Jintao Li, Chun Liu
Summary: This study proposes an automatic and accurate method for reconstructing indoor models with semantics based on a weak Manhattan world assumption. The method extracts boundary primitives from semantic point clouds and optimizes the geometric relationships among features to reconstruct a high-accuracy 3D wireframe model of the indoor scene.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Shengqing Zhang, Xiaoyan Zhai, Peng Yang, Jun Xia, Sheng Hu, Libo Zhou, Cai Fu
Summary: Changes in wetland ecosystems in the middle Yangtze River basin were studied from 2001 to 2020. The study used a land use simulation model and a random forest method to predict and analyze future wetland changes under different scenarios. Results showed a decrease in overall wetland area, successful simulation of future ecological quality, and reductions in ecological index in certain regions. The study provides a basis for future regional ecosystem quality studies and supports wetland conservation and management.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Xichen Meng, Shuai Xie, Lin Sun, Liangyun Liu, Yilong Han
Summary: In this paper, four commonly used temporal compositing algorithms were evaluated for land cover classification using Landsat time series data. Weighted scoring-based algorithms showed the best spatial fidelity and superior classification accuracy compared to other algorithms. However, the median algorithm has a significant advantage in computational efficiency and its overall classification accuracy is only slightly lower than weighted scoring-based algorithms. The findings of this study provide insights into the performance difference between various compositing algorithms and have potential uses for land cover mapping based on Landsat time series data.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Minglu Che, Yanyun Nian, Siwen Chen, Hao Zhang, Tao Pei
Summary: Human activities have a significant impact on the environment, making it crucial to understand their patterns and distribution for ecological protection. With advancements in location-based technology, big data such as location and trajectory data can be utilized to analyze human activities at finer temporal and spatial scales than traditional remote sensing data. This study focuses on Qilian Mountain National Park (QMNP) and utilizes Tencent location data to construct time series data. By analyzing the spatio-temporal distribution characteristics of human activities in QMNP, two distinct patterns were identified, one representing residents and the other representing tourists. The study also discovered seasonal variations in human activities and conducted an analysis of human activities in different counties within QMNP.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Ying Liang, Shisong Cao, Mingyi Du, Linlin Lu, Jie Jiang, Jinling Quan, Meizi Yang
Summary: In this study, a novel LCZ mapping method utilizing space-borne multi-view and diurnal observations was proposed. Land cover classification was performed using multiple machine learning methods and various features. The use of NTL data improved the classification accuracy of certain LCZs. The refined LCZ classification achieved through this study will contribute to more accurate regional climate modeling and provide valuable guidance for urban planning.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Xuefei Zhang, Min Feng, Jinhao Xu, Dezhao Yan, Jing Wang, Xiaoqing Zhou, Tao Li, Xiang Zhang
Summary: Rock glaciers are typical periglacial landforms that can be monitored for deformation using MT-InSAR technology. However, existing methods face challenges due to complex topography and snow cover. In this study, we developed a quadtree segmentation and parallel computing-based MT-InSAR method to improve the quality and efficiency of deformation measurement of rock glaciers. Applying this method to the Nyainqentanglha Range in China, we found strong correlations between rock glacier activities and various factors, demonstrating the effectiveness of the method for monitoring rock glacier deformation over a large region.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Pingheng Li, Aqil Tariq, Qingting Li, Bushra Ghaffar, Muhammad Farhan, Ahsan Jamil, Walid Soufan, Ayman El Sabagh, Mohamed Freeshah
Summary: In this study, the Revised Universal Soil Loss Equation (RUSLE) and Geographical Information System (GIS) were used to predict the annual rate of soil loss in District Chakwal, Pakistan. The parameters of the RUSLE model were estimated using remote sensing data, and GIS was used to determine erosion probability zones. The results show that the estimated total annual potential soil loss is comparable to the measured sediment loss, and the predicted soil erosion rate due to an increase in agricultural area is also significant. Integrating GIS and remote sensing with the RUSLE model helped achieve the objectives of the study.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Zhengli Yang, Heng Lu, Zhijie Zhang, Chao Liu, Ruihua Nie, Wanchang Zhang, Gang Fan, Chen Chen, Lei Ma, Xiaoai Dai, Min Zhang, Donghui Zhang
Summary: In recent years, RS and GIS technologies have played an increasingly important role in rainfall induced landslide research. This paper conducted an extensive analysis of 1,161 documents collected from the WOS data platform, using quantitative and qualitative methods and various visualization analysis technologies, to understand the application situation. The study focused on sub domain analysis in four aspects: landslide detection and monitoring, prediction models, sensitivity mapping, and risk assessment. It was found that the number of literature in this field has steadily increased and is expected to continue rising. This study can provide valuable insights for researchers in this field and contribute to landslide prevention and control decision-making and achieving sustainable development goals.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Geography, Physical
Mengmeng Cao, Xuyan Li, Tingwei Cui, Xinliang Pan, Yan Li, Yanlong Chen, Ning Wang, Yanfang Xiao, Xingai Song, Yuzhu Xu, A. Runa, Bing Mu, Song Qing, Rongjie Liu, Wenjing Zhao, Yuhai Bao, Jie Zhang, Lan Wei
Summary: Green macroalgae bloom (GMB), dominated by Ulva prolifera, has been occurring regularly along the China coast since 2007. The satellite-observed GMB annual maximum coverage (AMC) rebounded sharply in 2021 to an unprecedented level, which raises questions about the reasons for this rebound and the significant interannual variability. Through the analysis of long-term satellite observations, meteorological data, and water quality statistics, two key determinants for AMC were identified as the macroalgae distribution in a key area and nutrient availability. A novel model for AMC prediction was proposed and validated, which can explain the significant interannual variability and align well with the latest observation in 2022.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
