Article
Environmental Sciences
Alberto Candela, Kevin Edelson, Michelle M. Gierach, David R. Thompson, Gail Woodward, David Wettergreen
Summary: Global mapping of coral reef condition requires a combination of remote sensing and in situ data to achieve accurate coverage on a worldwide scale. Utilizing new techniques in remote sensing analysis, probabilistic modeling, and decision theory for sample selection can refine information from remote sensing and extrapolate in situ features with increasing accuracy. Results from a proof of concept using spaceborne remote sensing and high-quality airborne data confirm the efficacy of this approach and the power of decision theory for sample selection.
FRONTIERS IN MARINE SCIENCE
(2021)
Article
Computer Science, Information Systems
Caleb Buffa, Vasit Sagan, Gregory Brunner, Zachary Phillips
Summary: This study predicts the presence or absence of terrorism in Europe using satellite imagery and socio-environmental data. It evaluates five machine learning models and conducts spatial statistics to improve the understanding of spatial processes among terror attacks. The results show a high accuracy in predicting terrorism and reveal spatial differences between separatists and other terrorist types.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Geochemistry & Geophysics
Yan-e Hou, Kang Yang, Lanxue Dang, Yang Liu
Summary: Convolutional neural networks have achieved remarkable results in remote sensing scene classification. However, existing methods often ignore object-level information in shallow features. This paper proposes an end-to-end contextual spatial-channel attention network (CSCANet) to fully utilize shallow features and improve classification performance.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Remote Sensing
Wenxuan Wang, Leiming Liu, Tianxiang Zhang, Jiachen Shen, Jing Wang, Jiangyun Li
Summary: Convolutional neural networks have been dominating the downstream tasks on hyperspectral remote sensing images with their strong local feature extraction capability. However, they fail to effectively capture long-range dependencies, which the Transformer architecture can handle. This paper introduces a dual-branch Transformer architecture called Hyper-ES2T, which effectively utilizes spatial information and spectral correlations in hyperspectral images. The design also includes an efficient multi-head self-attention block to balance model accuracy and efficiency.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Geochemistry & Geophysics
Haozhe Huang, Zhongfeng Mou, Yunying Li, Qiujun Li, Jie Chen, Haifeng Li
Summary: This paper introduces a spatial-temporal invariant contrastive learning (STICL) framework for learning spatial-temporal invariant representations from unlabeled images containing a large number of space-temporal scenes. By utilizing optimal transport on unlabeled remote sensing images, our method achieves better performance on unseen spatial-temporal scenes, demonstrating the importance of spatial-temporal invariance.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Ecology
Ramin Papi, A. A. Kakroodi, Masoud Soleimani, Leyla Karami, Fatemeh Amiri, Seyed Kazem Alavipanah
Summary: Sand and dust storms are common in central Iran, with sandy sources being the largest contributors. The frequency and severity of these storms have increased over the last two decades due to population growth and mismanagement of resources. Human activities have a direct impact on the occurrence and extent of dust storms in lakes and alluvial sources. Severe droughts intensify the frequency of dust storms.
ECOLOGICAL INFORMATICS
(2022)
Article
Environmental Sciences
Xinran Ji, Liang Huang, Bo-Hui Tang, Guokun Chen, Feifei Cheng
Summary: This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm for pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. The algorithm utilizes superpixel segmentation to obtain local spatial information, constructs a superpixel spatial intuitionistic fuzzy membership matrix, and uses spectral features and local relations between adjacent superpixels for classification. The results show that the proposed SSIFCM algorithm achieves the highest accuracy among fifteen existing unsupervised classification algorithms, demonstrating its effectiveness in improving the classification accuracy of HSRRS images.
Article
Environmental Sciences
Di Wang, Jinhui Lan
Summary: A deformable convolutional neural network is proposed in this paper to address the issues in extracting remote sensing scene features. Experimental results demonstrate that the method achieves competitive performance on three remote sensing scene classification datasets compared to state-of-the-art methods.
Article
Environmental Sciences
S. Andrefouet, M. Paul
Summary: The Millennium Coral Reef Mapping Project aimed to map coral reefs worldwide using Landsat satellite images. It identified 598 atolls and provided a quantitative database of their surface areas. This global database can be used for further research on coral reef classifications and geomorphic trends.
MARINE POLLUTION BULLETIN
(2023)
Article
Geochemistry & Geophysics
Guoming Gao, Baisen Liu, Xiangrong Zhang, Xudong Jin, Yanfeng Gu
Summary: A new method of multitemporal intrinsic image decomposition (MIID) is proposed in this article, which can effectively extract the common spectral reflectance from multitemporal images, leading to more accurate and easier multitemporal classification, change detection, and index extraction. The MIID methods not only achieve better results in spectral reflectance extraction, but also show good performance in multitemporal classification and change detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Anjali Madhu, Anil Kumar, Peng Jia
Summary: The study introduced three new PCM-based local spatial information algorithms and conducted experiments that showed these algorithms outperformed traditional ones in soft classification, with better handling of untrained classes and noise.
Article
Environmental Sciences
Giovanni Frati, Patrick Launeau, Marc Robin, Manuel Giraud, Martin Juigner, Francoise Debaine, Cyril Michon
Summary: This study utilizes hyperspectral imaging and full-waveform LiDAR technology to monitor sandy dunes in Pays-de-la-Loire, France, aiming to improve the accuracy of digital terrain models and implement a supervised hierarchic classification of foredune vegetation. By combining different technologies and data sources, as well as precise calibration and classification methods, it has been successfully applied to monitoring and analyzing coastlines.
Article
Chemistry, Analytical
Xudong Guan, Chong Huang, Juan Yang, Ainong Li
Summary: This paper implements a classification scheme utilizing knowledge graphs to improve remote sensing image classification by considering neighborhood relationships. Experimental results show that this method has the ability to correct misclassified patches using spatial relationships. However, two issues must be considered when applying spatial relationships to image classification: the siphonic effect produced by neighborhood patches, and the loss of local spatial relationship information due to global spatial relationships derived from pre-trained graphs.
Review
Environmental Sciences
Xinglu Cheng, Yonghua Sun, Wangkuan Zhang, Yihan Wang, Xuyue Cao, Yanzhao Wang
Summary: The rapid advancement of remote sensing technology has enhanced the temporal resolution of remote sensing data, leading to the emergence of multitemporal remote sensing image classification. Deep learning methods have become prevalent in this field due to their ability to handle massive datasets. This paper provides a review and discussion on the research status and trends in multitemporal images, including retrieval statistics, dataset preparation, model overview, and application status. It also identifies current problems and proposes future prospects, aiming to help readers understand the research process and application status of this field.
Article
Computer Science, Artificial Intelligence
Huseyin Firat, Mehmet Emin Asker, Mehmet Ilyas Bayindir, Davut Hanbay
Summary: Hyperspectral remote sensing images (HRSI) are 3D image cubes containing multiple spectral bands. This study proposes a deep learning method, called 3D-RSSCN, for feature extraction and classification of HRSI. The proposed method achieves the best classification accuracy compared to various deep learning-based methods on multiple datasets.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Environmental Sciences
Eric J. Hochberg, Dar A. Roberts, Philip E. Dennison, Glynn C. Hulley
REMOTE SENSING OF ENVIRONMENT
(2015)
Article
Environmental Sciences
Chuanmin Hu, Lian Feng, Robert F. Hardy, Eric J. Hochberg
REMOTE SENSING OF ENVIRONMENT
(2015)
Article
Environmental Sciences
David R. Thompson, Eric J. Hochberg, Gregory P. Asner, Robert O. Green, David E. Knapp, Bo-Cai Gao, Rodrigo Garcia, Michelle Gierach, Zhongping Lee, Stephane Maritorena, Ronald Fick
REMOTE SENSING OF ENVIRONMENT
(2017)
Article
Geochemistry & Geophysics
C. Giardino, V. E. Brando, P. Gege, N. Pinnel, E. Hochberg, E. Knaeps, I Reusen, R. Doerffer, M. Bresciani, F. Braga, S. Foerster, N. Champollion, A. Dekker
SURVEYS IN GEOPHYSICS
(2019)
Article
Environmental Sciences
Rodrigo A. Garcia, Zhongping Lee, Eric J. Hochberg
Article
Ecology
Samuel E. Kahng, Eric J. Hochberg, Amy Apprill, Daniel Wagner, Daniel G. Luck, Denise Perez, Robert R. Bidigare
MARINE ECOLOGY PROGRESS SERIES
(2012)
Article
Multidisciplinary Sciences
Yvonne Sawall, Eric J. Hochberg
Article
Environmental Sciences
Brandon J. Russell, Heidi M. Dierssen, Eric J. Hochberg
Article
Environmental Sciences
Tom W. Bel, Gregory S. Okin, Kyle C. Cavanaugh, Eric J. Hochberg
REMOTE SENSING OF ENVIRONMENT
(2020)
Article
Marine & Freshwater Biology
Eric J. Hochberg, Stacy A. Peltier, Stephane Maritorena
Review
Environmental Sciences
Eric J. Hochberg, Michelle M. Gierach
Summary: Many coral reefs worldwide are in decline, risking ecosystem goods and services for millions of people. However, our understanding of the relationship between coral reefs and their environments is lacking, underscoring the need for uniform, high-density data for modeling and predicting their future.
FRONTIERS IN MARINE SCIENCE
(2021)
Article
Environmental Sciences
Rodrigo A. Garcia, Zhongping Lee, Brian B. Barnes, Chuanmin Hu, Heidi M. Dierssen, Eric J. Hochberg
REMOTE SENSING OF ENVIRONMENT
(2020)
Article
Environmental Sciences
Chiara Pisapiai, Eric Jeremy Hochberg, Robert Carpenter
FRONTIERS IN MARINE SCIENCE
(2019)
Proceedings Paper
Geosciences, Multidisciplinary
Kevin Turpie, Steven Ackleson, Thomas Bell, Heidi Dierssen, James Goodman, Robert Green, Liane Guild, Eric Hochberg, Victor V. Klemas, Samantha Lavender, Christine Lee, Tiffany Moisan, Frank Muller-Karger, Joseph Ortiz, Sherry Palacios, David R. Thompson, Richard Zimmerman
2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)
(2017)
Article
Environmental Sciences
Travis A. Courtney, Andreas J. Andersson, Nicholas R. Bates, Andrew Collins, Tyler Cyronak, Samantha J. de Putron, Bradley D. Eyre, Rebecca Garley, Eric J. Hochberg, Rodney Johnson, Sylvia Musielewicz, Tim J. Noyes, Christopher L. Sabine, Adrienne J. Sutton, Jessy Toncin, Aline Tribollet
FRONTIERS IN MARINE SCIENCE
(2016)