Related references
Note: Only part of the references are listed.
Article
Environmental Sciences
Rui Lu et al.
Summary: This paper proposes a deep learning-based approach for extracting agricultural fields from remote sensing images. The approach, called DASFNet, utilizes a dual attention mechanism and multi-scale feature fusion to achieve automated and accurate field extraction. The experimental results demonstrate the effectiveness and advantages of the proposed method.
Article
Environmental Sciences
Jie Yu et al.
Summary: The classification of urban land-use information is crucial for applications such as urban planning and administration. This paper presents a combined convolutional neural network named DUA-Net for complex and diverse urban land-use classification. By using GIS data, a well-tagged and high-resolution urban land-use image dataset is created, and the DUA-Net effectively fuses multi-source semantic information using channel attention. The proposed method achieves high-precision urban land-use classification, which is valuable for urban planning and national land resource surveying.
Article
Environmental Sciences
Mojtaba Saboori et al.
Summary: This paper proposes a comprehensive analysis for optimum feature selection and the most efficient classifier for accurate urban area mapping. The experiments reveal that RF, PSO, and NCA are the most efficient classifiers, and wrapper-based and filter-based methods are the most efficient feature selection methods. Dissimilarity, contrast, and correlation features play the greatest contributing role in the classification performance.
Article
Environmental Sciences
Fabrice Dubertret et al.
Summary: This article introduces how to monitor the land use and land cover changes in the Tucson metropolitan area of Arizona, USA, using various data and techniques. It also shows that policies to reduce urban sprawl in the area have limited effects. Additionally, an automated tool is provided for future monitoring of changes.
Article
Environmental Sciences
Vahid Nasiri et al.
Summary: Accurate and real-time LULC maps are crucial for dynamic Earth monitoring, planning, and management. This study explored the impact of spectral-temporal metrics and composition methods on machine learning classifiers for accurate LULC mapping, finding that seasonal composites outperformed percentile metrics in providing phenological variation information for different LULC classes. This methodology can produce precise LULC maps efficiently through cloud computing platforms and is beneficial for large-scale mapping projects.
Article
Environmental Sciences
Alejandro-Martin Simon Sanchez et al.
Summary: Land use classification (LUC) is the process of providing information on land cover and the types of human activity involved in land use. This study uses multispectral reflectance Sentinel-2 images to perform agricultural LUC, achieving high accuracy by arranging pixel information as 2D yearly fingerprints and utilizing CNN for modeling and capturing multispectral temporal patterns. This operational tool shows promising potential for monitoring crops and water use over large areas.
Article
Environmental Sciences
Dadirai Matarira et al.
Summary: This study utilizes the cloud computing capabilities of Google Earth Engine platform to accurately extract the location and spatial extent of informal settlements in Durban, South Africa, by integrating spectral and textural features. The results show that the classification based on spectral bands + textural information achieves the highest accuracy in identifying informal settlements.
Article
Environmental Sciences
Senyao Feng et al.
Summary: In this study, new LULC products with a spatial resolution of 10m were generated using Sentinel-2 imagery, the Google Earth Engine platform, and the random forest method. The study focused on monitoring changes in ecosystem types in the upper Yellow River basin over the Tibetan Plateau. The results provided information on the areas and trends of different ecosystem type changes, serving as a basis for basin-scale ecosystem monitoring and analysis with more detailed categories and reliable accuracy.
Article
Environmental Sciences
Eya Cherif et al.
Summary: This study aims to develop automated methods for land use and land cover classification in the Amazon basin using deep learning techniques. By fusing multi-spectral and radar data, the proposed networks achieve high overall accuracy and outperform state-of-the-art models in handling underrepresented classes.
Article
Environmental Sciences
Pegah Mohammadpour et al.
Summary: This study used Sentinel-2 data to map vegetation in the complex and mixed vegetation cover of the Lousa district in Portugal. By incorporating GLCM texture features and vegetation indices, the classification accuracy can be increased.
Article
Green & Sustainable Science & Technology
Zhe Zhao et al.
Summary: This study quantitatively explores the impact of urbanization on agricultural technical efficiency in the Northeast China region. The results show that overall agricultural technical efficiency is relatively low in the region, with differences in urbanization levels across different cities. Population urbanization and land urbanization are relatively high in most cities, and overall urbanization, land urbanization, and economic urbanization all have a significant positive effect on agricultural technical efficiency.
Article
Environmental Sciences
Oliver Sefrin et al.
Summary: Land cover and its change play a crucial role in various environmental applications. This study focuses on utilizing multitemporal and multispectral Sentinel-2 satellite data for land cover classification and change detection using deep learning architectures. Pre-processing methods and two different deep learning models were employed to enhance the accuracy of detecting actual land cover changes and misclassifications.
Article
Environmental Sciences
James Magidi et al.
Summary: This study utilized random forest algorithm on Google Earth Engine platform to process and classify irrigated areas in Mpumalanga Province, Africa using NDVI to differentiate between irrigated and rainfed areas. Assessment of irrigated areas in 2019 and 2020, along with the impact of Covid-19 pandemic on agriculture, helped in evaluating changes in irrigated areas in smallholder farming areas.
Article
Environmental Sciences
Andrea Tassi et al.
Summary: This research aimed to produce a 2018-2020 Land Use/Land Cover (LULC) map of the Maiella National Park, central Italy using Landsat 8 (L8) data and Google Earth Engine (GEE). The study compared pixel-based and object-based approaches, successfully generating a 15m resolution LULC map incorporating spectral indices and textural information.
Article
Environmental Sciences
Thanh Noi Phan et al.
Article
Environmental Sciences
Johanna Buchner et al.
REMOTE SENSING OF ENVIRONMENT
(2020)
Editorial Material
Environmental Sciences
Le Wang et al.
REMOTE SENSING OF ENVIRONMENT
(2020)
Article
Environmental Sciences
Dakota Aaron McCarty et al.
Article
Environmental Sciences
Lalit Kumar et al.
Article
Environmental Sciences
Steve Foga et al.
REMOTE SENSING OF ENVIRONMENT
(2017)
Article
Environmental Sciences
Jun Xiong et al.
Article
Environmental Sciences
XM Xiao et al.
REMOTE SENSING OF ENVIRONMENT
(2005)