Article
Geography, Physical
Yuekai Hu, Bo Tian, Lin Yuan, Xiuzhen Li, Ying Huang, Runhe Shi, Xiaoyi Jiang, Lihua Wang, Chao Sun
Summary: Salt marshes play crucial ecological roles but are facing losses and degradation, this study utilized Sentinel-1 SAR data and knowledge-based classifiers to produce a high-precision map in China coastal zones, proving the effectiveness of SAR data for salt marsh classification, with a total area of 127,477.37 ha predominantly distributed between Shandong and Zhejiang provinces.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Jana Breznik, Kristof Ostir, Matjaz Ivacic, Gasper Rak
Summary: Studying karst water dynamics is challenging due to unknown underground flows. This research paper assesses a water bodies dataset detected from Sentinel-1 imagery for karst flood research. Statistical analysis using Spearman's correlation coefficients and visual analysis utilizing heat maps and vegetation maps were conducted to evaluate the dataset's reliability and effectiveness.
Article
Environmental Sciences
Fernando Pech-May, Raul Aquino-Santos, Jorge Delgadillo-Partida
Summary: Floods are increasing in frequency and danger worldwide, with climate change and land use being major contributing factors. In Mexico, floods occur annually in various regions, causing significant losses and negative impacts on multiple industries. This paper presents a strategy using satellite imagery, the U-Net neural network, and ArcGIS platform to classify flooded areas in Tabasco, Mexico. Results demonstrate that U-Net performs well despite limited training samples, with increased precision as training data and epochs increase.
Article
Engineering, Electrical & Electronic
Hui Yang, Xiuguo Liu, Qihao Chen, Yuanye Cao
Summary: This study utilizes the capabilities of the Sentinel-1 satellite to construct time series similarity parameters and statistical texture parameters for more accurate classification of the Dongting Lake wetland. The results show that this method effectively utilizes dynamic information among different classes and can accurately identify different geomorphic features in wetlands.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Xiao Xiao, Yilong Lu, Xiaoman Huang, Ting Chen
Summary: This study investigates the use of temporal series SAR imagery for crop classification in rural areas of China. By analyzing temporal features, using the KNN algorithm, and other techniques, the study achieved a high overall accuracy of 98.2% in classifying ten different land cover types.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Mitchell Thomas, Elizabeth Tellman, Daniel E. Osgood, Ben DeVries, Akm Saiful Islam, Michael S. Steckler, Maxwell Goodman, Maruf Billah
Summary: In this study, we aim to strengthen the use of satellite data for flood index insurance by proposing a set of criteria for assessing algorithm performance and providing a framework for remote sensing application validation in data-poor environments. The results show that the adapted Sentinel-1 algorithm significantly outperforms previous algorithms on the validation criteria. The proposed validation criteria can be used to develop and validate better remote sensing products for index insurance and other flood applications in places with inadequate ground truth data.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
M. Lavalle, C. Telli, N. Pierdicca, U. Khati, O. Cartus, J. Kellndorfer
Summary: This letter presents a model-based algorithm that utilizes synthetic aperture radar (SAR) interferometric coherence and backscatter data, along with sparse lidar data, to estimate tree height and other bio-physical land parameters. The algorithm extends the random-motion-over-ground model (RMoG) to time series in order to capture the temporal coherence variability caused by motion of scatterers and changes in soil and canopy backscatter. By first estimating the slow-varying RMoG model parameters using lidar data and then estimating the fast-varying model parameters such as tree height, the algorithm demonstrates the potential for global, model-based land parameter estimation using the recently published global Sentinel-1 (S-1) interferometric coherence and backscatter data set and sparse spaceborne GEDI lidar data.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Tsitsi Bangira, Lorenzo Iannini, Massimo Menenti, Adriaan van Niekerk, Zoltan Vekerdy
Summary: The study evaluates the potential of Sentinel-1 satellite constellation for flood monitoring in vegetated environments and proposes a new algorithm for rapid flood monitoring. When applied to the Caprivi region, it was found that the flood maps generated by S1 and Landsat-8 showed a high spatial agreement during flood peak periods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Oceanography
Gabriel Matheus de Souza Moreno, Osmar Abilio de Carvalho Jr, Osmar Luiz Ferreira de Carvalho, Tarsila Cutrim Andrade
Summary: In this study, a deep learning mangrove dataset was developed using the U-net architecture and different backbones, considering the spatial, temporal, and polarization dimensions in the Southeast region of Brazil. The study also explored the use of radar time series for mangrove detection. The results showed that the combination of VV and VH polarizations, the maximum number of images in the time series, the U-net with the Efficient-net-B7 backbone, and the smallest stride value in the sliding windows approach yielded the best results for mangrove detection.
OCEAN & COASTAL MANAGEMENT
(2023)
Article
Geochemistry & Geophysics
Congyu Li, Jiaqi Liu, Xinxin Liu, Xudong Kang, Shutao Li
Summary: This study proposes a novel flood detection model based on time-series variation analysis and integrates it with fuzzy-based methods to develop an unsupervised flood-mapping framework. The framework also includes a flooded short vegetation activation model to improve accuracy in complex regions. Experimental results show that the proposed method outperforms other methods in terms of quantitative evaluation and visual performance, demonstrating its effectiveness, stability, and universality.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Meteorology & Atmospheric Sciences
Qing Yang, Xinyi Shen, Emmanouil N. Anagnostou, Chongxun Mo, Jack R. Eggleston, Albert J. Kettner
Summary: This research successfully generated a high-resolution flood inundation dataset for most of the United States using SAR data and an automated RAPID system. Comparisons showed the dataset had a high accuracy of 99% and demonstrated strong automated processing capabilities.
BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY
(2021)
Article
Environmental Sciences
David Frantz, Franz Schug, Akpona Okujeni, Claudio Navacchi, Wolfgang Wagner, Sebastian van der Linden, Patrick Hostert
Summary: This study mapped building heights for entire Germany using Sentinel-1A/B and Sentinel-2A/B time series, achieving good results in training machine learning models. The synergistic combination of radar and optical models led to superior prediction results, and there were significant differences in average building heights across different regions in Germany.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Ignacio Borlaf-Mena, Ovidiu Badea, Mihai Andrei Tanase
Summary: This study examined the ability of Sentinel-1 C-band to distinguish between forests and other common land use classes in two different sites, and found that adding coherence features can improve the accuracy of temperate forest classification.
Article
Environmental Sciences
Sophie Reinermann, Ursula Gessner, Sarah Asam, Tobias Ullmann, Anne Schucknecht, Claudia Kuenzer
Summary: Grasslands cover a significant portion of agricultural areas in Germany, providing economic value and ecosystem services. Varied management practices across different regions and time periods can be analyzed using remote sensing data to understand the spatiotemporal dynamics of grasslands.
Article
Engineering, Electrical & Electronic
O. Charfi Marrakchi, C. Masmoudi Charfi, M. Hamzaoui, H. Habaieb
Summary: This study proposes a new approach for data resource processing by utilizing PCA and DWT methods on Sentinel-1 radar satellite's polarized images to achieve better classification results. The application of DWT method on VV and VH images yielded the best classification outcome with the highest Kappa Precision Coefficient.
JOURNAL OF SENSORS
(2021)
Article
Computer Science, Software Engineering
M. Weinmann, S. Urban, S. Hinz, B. Jutzi, C. Mallet
COMPUTERS & GRAPHICS-UK
(2015)
Article
Engineering, Electrical & Electronic
Devis Tuia, Jan Dirk Wegner, Clement Mallet, Michael Ying Yang
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2016)
Article
Geochemistry & Geophysics
Yunsheng Wang, Juha Hyyppa, Xinlian Liang, Harri Kaartinen, Xiaowei Yu, Eva Lindberg, Johan Holmgren, Yuchu Qin, Clement Mallet, Antonio Ferraz, Hossein Torabzadeh, Felix Morsdorf, Lingli Zhu, Jingbin Liu, Petteri Alho
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2016)
Article
Geography, Physical
Antonio Ferraz, Clement Mallet, Nesrine Chehata
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2016)
Article
Environmental Sciences
Antonio Ferraz, Sassan Saatchi, Clement Mallet, Victoria Meyer
REMOTE SENSING OF ENVIRONMENT
(2016)
Article
Environmental Sciences
Minh-Tan Pham, Gregoire Mercier, Oliver Regniers, Julien Michel
Article
Environmental Sciences
Antonio Ferraz, Sassan Saatchi, Clement Mallet, Stephane Jacquemoud, Gil Goncalves, Carlos Alberto Silva, Paula Soares, Margarida Tome, Luisa Pereira
Article
Environmental Sciences
Martin Weinmann, Michael Weinmann, Clement Mallet, Mathieu Bredif
Article
Environmental Sciences
Pierre-Louis Frison, Benedicte Fruneau, Syrine Kmiha, Kamel Soudani, Eric Dufrene, Thuy Le Toan, Thierry Koleck, Ludovic Villard, Eric Mougin, Jean-Paul Rudant
Article
Environmental Sciences
Luc Baudoux, Jordi Inglada, Clement Mallet
Summary: The study focuses on translating a national scale remote sensed map into CORINE Land Cover using a Convolution Neural Network with positional encoding. The results show that this method achieves a superior performance compared to traditional semantic-based translation approach, with an accuracy of 81% overall in France, close to the targeted 85% accuracy of CLC.
Proceedings Paper
Computer Science, Artificial Intelligence
Joseph Chazalon, Edwin Carlinet, Yizi Chen, Julien Perret, Bertrand Dumenieu, Clement Mallet, Thierry Geraud, Vincent Nguyen, Nam Nguyen, Josef Baloun, Ladislav Lenc, Pavel Kral
Summary: This paper presents the final results of the ICDAR 2021 MapSeg competition, which focuses on historical map segmentation of a series of historical atlases of Paris, France. The winning teams used different network structures and methods for each task. The research outcomes have a positive impact on the development of historical map segmentation technology.
DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT IV
(2021)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Clement Dechesne, Clement Mallet, Arnaud Le Bris, Valerie Gouet, Alexandre Hervieu
XXIII ISPRS CONGRESS, COMMISSION III
(2016)