Article
Environmental Sciences
Peiyao Weng, Yu Tian, Hong Zhou, Ying Zheng, Yunzhong Jiang
Summary: This study proposes a real-time saltwater intrusion early warning framework based on timeseries clustering to improve the accuracy and lead time of predictions. By clustering previous observations, a comprehensive 24-h forecast of saltwater intrusion risk is obtained. The latest supervised clustering model, CAMELOT, outperforms traditional unsupervised clustering models and machine learning classifiers. The analysis reveals that the variation in saltwater intrusion length is strongly associated with tidal cycles and upstream discharge.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2024)
Article
Environmental Sciences
Chunzhu Wei, Qianying Zhao, Yang Lu, Dongjie Fu
Summary: The study compared different regression models for bathymetry mapping in the Pearl River Delta, demonstrating that random forest regression model outperformed others, and three-band combinations were superior to two-band combinations in all models. Despite differences in spatial resolution and band wavelength, Landsat 8 and Sentinel-2 performed similarly in bathymetry estimation.
Article
Biodiversity Conservation
Lei Zhang, Ming Zhang, Qian Wang
Summary: This study proposes a new method for subpixel time series impervious surface estimation based on optimal spectral-temporal features, which effectively distinguish impervious surfaces from pervious surfaces through feature optimization selection and improve the feature utilization performances, thereby obtaining high-precision impervious surface mapping.
ECOLOGICAL INDICATORS
(2023)
Article
Green & Sustainable Science & Technology
Wei Liu, Jinyan Zhan, Fen Zhao, Chao Wang, Fan Zhang, Yanmin Teng, Xi Chu, Michael Asiedu Kumi
Summary: This study evaluates the changes in ecosystem services in the Pearl River Delta and analyzes the drivers behind these changes from the perspectives of nature, society, and economy. The results show that the driving factors for different ecosystem services vary and the spatial distribution of these services is heterogeneous.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Remote Sensing
Vangelis Fotakidis, Irene Chrysafis, Giorgos Mallinis, Nikos Koutsias
Summary: This study evaluates the feasibility of using three spectral indices for continuous burned area monitoring and finds that using the differenced Normalized Burn Ratio (dNBR) and Relativized Burn Ratio (RBR) is more efficient than using the Normalized Burn Ratio (NBR).
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Remote Sensing
Xin Huang, Yihong Song, Jie Yang, Wenrui Wang, Huiqun Ren, Mengjie Dong, Yujin Feng, Haidan Yin, Jiayi Li
Summary: Accurate and long-term monitoring of global artificial impervious surface area (ISA) is crucial for biodiversity, water quality assessment, and urban heat island. However, existing datasets exhibit inconsistencies. Therefore, we proposed a new mapping method and generated a highly accurate ISA dataset (GISA 2.0).
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Remote Sensing
Sven Huettermann, Simon Jones, Mariela Soto-Berelov, Samuel Hislop
Summary: Passive and active spaceborne remote sensing technologies are crucial for monitoring forests, and this study explores the relationship between spectral and structural change following forest fire disturbance. The study found strong fire responses in spectral indices, but a more pronounced decline in structural change metrics. Canopy height showed a less substantial decline. Fire severity and forest type were found to impact the fire response of the metrics. The study demonstrates the potential of integrating GEDI observations into spectral forest change monitoring.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Environmental Sciences
Rui Chen, Xiaodong Li, Yihang Zhang, Pu Zhou, Yalan Wang, Lingfei Shi, Lai Jiang, Feng Ling, Yun Du
Summary: The monitoring of impervious surfaces in urban areas using remote sensing with fine spatial and temporal resolutions is crucial. A new Spatiotemporal Continuous Impervious Surface Mapping (STCISM) method was proposed to address challenges in fusing Landsat and Google Earth imagery, utilizing spectral mixture analysis and temporal consistency check to improve accuracy in impervious surface predictions.
Article
Environmental Sciences
Aoyang He, Jiangcheng Huang, Zhengbao Sun, Jingyi Zhou, Cheng Yang
Summary: We obtained and analyzed sixteen clear-sky remote sensing images of the Salween River Delta from 1973 to 2021. By using the Modified Normalized Difference Water Index (MNDWI) and visual interpretation correction, we extracted and evaluated the coastlines of both the continental and island areas. The analysis revealed that the overall coastline evolution was faster on the island and the Indian Ocean side, with significant changes in both area and length.
Article
Remote Sensing
Zhipeng Tang, Hari Adhikari, Petri K. E. Pellikka, Janne Heiskanen
Summary: A new method called MOPSTM is proposed to fill missing observations in Landsat data, which shows better performance in accurately predicting missing data compared to other algorithms, especially in nearly cloud-free conditions.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Environmental Sciences
Mengmeng Hu, Yafei Wang, Shuang Wang, Mengyu Jiao, Guohe Huang, Beicheng Xia
Summary: The study found that from 2006 to 2019, most air pollutant concentrations decreased, especially sulfur dioxide, while ozone concentrations increased. Winter had the most severe air pollution, with coastal areas having better air quality, and meteorological factors had a significant impact on air pollution.
ATMOSPHERIC ENVIRONMENT
(2021)
Article
Environmental Sciences
Yun Tang, Zhenfeng Shao, Xiao Huang, Bowen Cai
Summary: This study developed a new method for mapping impervious surface area percentage using Nighttime Light and MODIS products, and successfully monitored ISA% dynamics in the Guangdong-Hong Kong-Macao Greater Bay area. The results demonstrate the effectiveness of the proposed method in investigating ISA dynamics and the method's feasibility for large scale and high frequency mapping of ISA%.
Article
Environmental Sciences
Xinchuang Chen, Feng Li, Xiaoqian Li, Hongxiao Liu, Yinhong Hu, Panpan Hu
Summary: The study highlights the importance of identifying and managing ecological restoration areas for sustainable urban development, while also pointing out the lack of a scientific basis for the scope and scale of ecological restoration in current research. By proposing a transdisciplinary framework combining ecological quality, ecological health, and ecosystem services, priority restoration areas can be effectively identified and classified to achieve policy goals and fulfill public preferences.
Article
Geosciences, Multidisciplinary
Xinyi Hu, Yunpeng Wang
Summary: The study found significant changes in the Pearl River Estuary coastline over the past 40 years, especially in the western area where land reclamation and dam construction had a greater impact. Both natural factors and human activities have influenced the coastline variation in the region.
Article
Environmental Sciences
Yue Xu, Zhongwen Hu, Yinghui Zhang, Jingzhe Wang, Yumeng Yin, Guofeng Wu
Summary: A novel approach based on multi-source spectral and texture features was proposed to map simultaneously inland and marine aquaculture areas. In a case study in the Pearl River Basin of China, the proposed approach achieved an overall accuracy of 89.5% for aquaculture mapping.
Article
Geography, Physical
Chunhong Zhao, Qihao Weng, Yige Wang, Zhongmin Hu, Chaoyang Wu
Summary: Phenological changes caused by urbanization provide evidence of vegetation response to global warming. This study explores the spatiotemporal variations in urban vegetation phenology in the Austin metropolitan area by using Local Climate Zones (LCZs) and MODIS data. The results show an advancement in the start and end of the growing season, while the length of the growing season remains unchanged. Statistical analysis reveals significant differences in phenology metrics among different LCZs, but not along Urban-Rural Gradients (URGs).
GISCIENCE & REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Yang Chen, Qihao Weng, Luliang Tang, Qinhuo Liu, Rongshuang Fan
Summary: Cloud detection is crucial in remote sensing, but challenging in cloud-snow coexisting areas. The proposed ACD net integrates remote sensing imagery and geospatial data to improve accuracy in cloud detection under cloud-snow coexistence.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Lei Zhang, Ming Zhang
Summary: This study proposes a 3-D spatiotemporal interpolation method to address the low coverage issue of MODIS aerosol optical depth (AOD) products. The method is applied to analyze the dynamics of AOD in Beijing-Tianjin-Hebei urban agglomeration, and compared with ordinary Kriging interpolation. The results demonstrate that the 3-D spatiotemporal interpolation outperforms the traditional method in predicting missing data of AOD products. This proposed method provides a feasible solution for establishing long-term MODIS aerosol products with temporal and spatial consistency, and offers effective data support for studying urban environmental changes.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Yang Chen, Qihao Weng, Luliang Tang, Xia Zhang, Muhammad Bilal, Qingquan Li
Summary: Landsat images are widely used in Earth observation and geoinformatics. However, cloud cover often affects the usability of these images. In this study, a spatiotemporal neural network with four modules was proposed to reconstruct Landsat images, achieving better results compared to existing methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Remote Sensing
Mohammad Kazemi Garajeh, Qihao Weng, Vahid Hossein Haghi, Zhenlong Li, Ali Kazemi Garajeh, Behnam Salmani
Summary: This study investigates the impact of shallow flood spreading on vegetation density using various machine learning algorithms. The analysis shows significant changes in NDVI values and soil properties following flood occurrence.
CANADIAN JOURNAL OF REMOTE SENSING
(2022)
Article
Remote Sensing
Mohammad Kazemi Garajeh, Thomas Blaschke, Vahid Hossein Haghi, Qihao Weng, Khalil Valizadeh Kamran, Zhenlong Li
Summary: This paper compares the suitability of Sentinel-2 and Landsat 8 OLI images for detecting and mapping soil salinity distribution using a deep learning convolutional neural network approach. The results show that Sentinel-2 is more suitable than Landsat 8 OLI for this purpose, and the DL-CNN approach supports fast and reliable image analysis and classification.
CANADIAN JOURNAL OF REMOTE SENSING
(2022)
Editorial Material
Geography, Physical
Qihao Weng, Clement Mallet
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Geography, Physical
Zhiwei Li, Huanfeng Shen, Qihao Weng, Yuzhuo Zhang, Peng Dou, Liangpei Zhang
Summary: This review discusses the methods and progress in cloud and cloud shadow detection in optical satellite images, analyzes the trends and existing problems in this field, and provides prospects for future development. It highlights the importance of addressing cloud contamination issues in remote sensing and offers guidance and resources for researchers in this area.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Ecology
Mohammad Kazemi Garajeh, Bakhtiar Feizizadeh, Qihao Weng, Mohammad Hossein Rezaei Moghaddam, Ali Kazemi Garajeh
Summary: In this study, a semi-automated object-based image analysis approach was proposed for detecting and mapping desert landforms. By utilizing Sentinel-2 imagery and a digital elevation model, relevant features were selected and appropriate segmentation scales were defined for different landform categories. The results demonstrated the effectiveness and accuracy of using this approach for detecting and classifying saline domes, barchans, playas, and dunes in the desert environment. The fuzzy synthetic evaluation technique was applied to validate the classification results.
JOURNAL OF ARID ENVIRONMENTS
(2022)
Article
Computer Science, Interdisciplinary Applications
Morteza Khazaei, Saeid Hamzeh, Najmeh Neysani Samani, Arnab Muhuri, Kalifa Goita, Qihao Weng
Summary: Nowadays, there is a demand for high spatial resolution near-real-time Surface Soil Moisture (SSM) data. However, existing passive microwave systems can only provide such information at a relatively coarse resolution. To address this issue, we developed a Satellite-based Hydrological Monitoring System (SHMS), which combines different data sources to generate high-resolution SSM maps.
COMPUTERS & GEOSCIENCES
(2023)
Article
Geography, Physical
Yang Chen, Qihao Weng, Luliang Tang, Lei Wang, Hanfa Xing, Qinhuo Liu
Summary: Urban green spaces (UGS) are important for understanding urban ecosystems, climate, environment, and public health. Satellite-derived UGS maps are an efficient tool for urban studies and contribute to global sustainable development goals. However, cloud contamination poses challenges for UGS mapping. In this study, an automatic UGS mapping method using satellite images and crowdsourced geospatial data is proposed to reduce uncertainty caused by clouds. Results show a high-quality global UGS map with average overall accuracy of 92.96%, even with cloud coverage ranging from 0% to 50%.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Geography, Physical
Qiming Zheng, Karen C. Seto, Yuyu Zhou, Shixue You, Qihao Weng
Summary: Nighttime light (NTL) remote sensing data have been extensively used to understand urbanization. A literature review of 688 papers published between 1992 and 2022 identified the trends and challenges in NTL-based urban applications. Future research directions include understanding scale effects and variations in NTL data, integrating multi-source NTL data with other geospatial data, focusing on the Global South, and developing new urban applications with new NTL data products. Addressing research gaps in these areas will provide new insights into urbanization under different settings.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Engineering, Electrical & Electronic
Dehui Dong, Dongping Ming, Qihao Weng, Yi Yang, Kun Fang, Lu Xu, Tongyao Du, Yu Zhang, Ran Liu
Summary: This study proposes a framework for extracting structures by combining region-line feature fusion with object-based convolutional neural networks to solve the problem of broken and inaccurate building edges extracted using existing techniques in complex suburban and rural areas.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Lei Zhang, Ming Zhang, Jiejun Huang, Chuan Zhang, Fawang Ye, Wei Pan
Summary: This letter discusses the application of hyperspectral remote sensing technology in geological fields and proposes a new approach called graph convolutional neural networks-SAM (GCNNSAM) to improve the accuracy of mineral mapping using drill-core hyperspectral images. By comparing different mapping methods, the study verifies the reliability of the proposed method and provides a new idea for mineral information acquisition in geological research.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Geochemistry & Geophysics
Wenzhuo Liu, Lei Zhang
Summary: As impervious surface plays a crucial role in indicating urbanization level and ecological environment, understanding its spatiotemporal differentiation is essential for urban sustainable development. This study proposes a new method to analyze the annual changes of impervious surface in the Beijing-Tianjin-Hebei urban agglomeration from 2000 to 2019. The results reveal a steady increase of impervious surface in the region, primarily due to outward expansion centered on urban areas. Furthermore, significant variations in impervious surface expansion are observed among cities within the region.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)