Article
Green & Sustainable Science & Technology
Liang Guo, Xiaohuan Xi, Weijun Yang, Lei Liang
Summary: The study revealed a continuous increase in built-up area and a decrease in vegetation area in Guangzhou City, China from 1986 to 2018. There was a strong positive correlation between GDP and built-up area, while a strong negative correlation was found between GDP and vegetation area, suggesting that the expansion of built-up area came at the expense of reduced vegetation area.
Article
Engineering, Electrical & Electronic
Cheng Shang, Shan Jiang, Feng Ling, Xiaodong Li, Yadong Zhou, Yun Du
Summary: Super-resolution mapping (SRM) can predict land cover distribution in mixed pixels with higher spatial resolution using deep learning techniques. This study proposes an end-to-end SRM model, called spectral-spatial generative adversarial network (SGS), which effectively handles spectral-spatial errors. The SGS model reduces land cover fraction errors, reconstructs spatial details, removes unrealistic cover artifacts, and eliminates false recognition.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Environmental Sciences
Hongmiao Wang, Cheng Xing, Junjun Yin, Jian Yang
Summary: This paper proposes a classification method based on vision Transformer, which extracts features from the global range of images using self-attention block and pre-trains the model using Mask Autoencoder. Experimental results demonstrate the superiority of this method in PolSAR image classification.
Article
Geochemistry & Geophysics
Guoqing Zhou, Weiguang Liu, Qiang Zhu, Yanling Lu, Yu Liu
Summary: In recent years, models based on fully convolutional neural networks have been proposed to improve accuracy but ignored computational efficiency. This research presents an innovative deep learning model, ECA-MobileNetV3(large)+SegNet, which simultaneously considers both aspects. By modifying the encoder and decoder structures, the proposed model achieves significant improvement in performance and reduces the number of parameters.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Construction & Building Technology
Terence Darlington Mushore, Onisimo Mutanga, John Odindi
Summary: This study developed an algorithm based on spectral indices to accurately predict land surface temperature (LST) in urban areas. The algorithm showed a strong relationship with LST and performed better than individual indices, providing insight into the impact of city growth on the thermal environment.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Geochemistry & Geophysics
Zhiyong Lv, Pengfei Zhang, Weiwei Sun, Jon Atli Benediktsson, Junhuai Li, Wei Wang
Summary: In this article, two novel features, the Gaussian-weighting spectral (GWS) feature and the area shape index (ASI) feature, are proposed to improve land cover classification with high spatial resolution remotely sensed imagery. Experimental results show that the proposed features can enhance classification accuracies and complement each other to improve classification performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Ecology
Heng Wan, Daniel McLaughlin, Yang Shao, Brian van Eerden, Shyam Ranganathan, Xinwei Deng
Summary: Urban forests have higher evapotranspiration rates compared to other urban land covers, playing an important role in stormwater flood reduction. Wetland and upland forests have significantly higher ET rates than urban areas, with wetland forests contributing 40% of total landscape ET despite covering only 20% of the area.
LANDSCAPE AND URBAN PLANNING
(2021)
Article
Agronomy
Briana M. Wyatt, Tyson E. Ochsner, Chris B. Zou
Summary: The study successfully estimated root zone soil moisture for diverse land cover types using a water balance model driven by high-resolution remote sensing and meteorological data. The model performed better than measured data and NASA-USDA soil moisture product, demonstrating the potential of integrating in-situ meteorological data and remotely sensed vegetation indices for accurate soil moisture estimation.
AGRICULTURAL AND FOREST METEOROLOGY
(2021)
Article
Engineering, Electrical & Electronic
Zhuang Zhou, Shengyang Li, Wei Wu, Weilong Guo, Xuan Li, Guisong Xia, Zifei Zhao
Summary: This article introduces a large-scale dataset NaSC-TG2 built from Tiangong-2 remotely sensed imagery, which aims to expand and enrich annotated data for advancing remote sensing classification algorithms, especially for natural scene classification. The dataset contains 20,000 images equally divided into ten scene classes, with the advantages of large scale, intra-class differences, and inter-class similarity.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Shoubao Geng, Long Yang, Zhongyu Sun, Zhihui Wang, Junxi Qian, Chong Jiang, Meili Wen
Summary: This study evaluated diurnal and seasonal variations of regional heat island intensity in the Guangdong-Hong Kong-Macao Greater Bay Area urban agglomeration. The results showed that daytime RHII was mainly influenced by vegetation fraction and background temperature, while nighttime RHII was mainly influenced by anthropogenic heat emissions and vegetation activities.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Dilek Kucuk Matci, Ugur Avdan
Summary: This study proposes a method for automatically labeling images without a training phase. By using bands in the image and Corine data, a database is created by examining spectral characteristics of land classes from sample images. The unlabelled classes are evaluated using this database, and the relevant label is assigned. The developed approach is tested in several regions in Turkey and Greece and achieves high accuracy.
EARTH SCIENCE INFORMATICS
(2022)
Article
Agronomy
Jan Bryan M. Encabo, Marcos R. C. Cordeiro, Nasem Badreldin, Emma J. McGeough, David Walker
Summary: Land cover classification is a common application of remote sensing and can help achieve conservation and economic goals. This study assessed the accuracy of grassland classification in Canadian crown lands using a remotely sensed dataset and compared it with government records. The results showed low agreement between woody and grassy vegetation classes, indicating the need for improvements in sensor and ground data for better classification accuracy.
GRASS AND FORAGE SCIENCE
(2023)
Article
Environmental Sciences
Luisa Velasquez-Camacho, Adrian Cardil, Midhun Mohan, Maddi Etxegarai, Gabriel Anzaldi, Sergio de-Miguel
Summary: Urban trees and forests offer diverse ecosystem services, but assessing urban biodiversity and ecosystem services faces challenges with increasing urbanization globally. Remote sensing techniques show promise in expanding research frontiers on urban tree and forest characteristics.
Article
Environmental Sciences
Kai Ding, Yidu Huang, Chisheng Wang, Qingquan Li, Chao Yang, Xu Fang, Ming Tao, Renping Xie, Ming Dai
Summary: Shenzhen has undergone rapid urbanization since the establishment of the Special Economic Zone in 1978. This study used Landsat images to investigate land use and land cover changes in Shenzhen, finding that urban areas expanded while vegetation, water, and bare areas decreased. The study also identified transportation and population as key drivers of urban land development.
Article
Geochemistry & Geophysics
Li Wang, Yanjiang Wang, Yaqian Zhao, Baodi Liu
Summary: The proposed Enhanced Residual Neural Network (ERNet) aims to improve classification performance on remote sensing images by addressing issues such as insufficient learning of discriminative information in early layers, overfitting due to limited labeling data, and limitations of transfer learning alone. By modifying the network architecture and incorporating dropout layers, ERNet achieves superior results compared to baseline methods in remote sensing image recognition tasks.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)