Article
Engineering, Electrical & Electronic
Lipeng Gao, Jingyu Wang, Qixin Wang, Wenzhong Shi, Jiangbin Zheng, Hongping Gan, Zhiyong Lv, Honghai Qiao
Summary: The proposed DAD-LinkNet model adaptively integrates local road features with their global dependencies by joint using satellite image and floating vehicle trajectory data, outperforming existing road extraction methods in terms of accuracy and connectivity.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Chao Zhang, Shijie Zhang, Yue Liu, Ri'ang Cheng
Summary: This article investigates the problem of star identification in terms of searches and time. A novel star catalog and matching method are proposed, which have been shown to have strong anti-interference ability and greatly improved matching efficiency compared to existing algorithms.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Aerospace
Kenza Benamar
Summary: This paper explores a space mission concept in the geostationary orbit to build a catalog of space objects and provide satellite inspection services. The mission involves a mother satellite and two smallsats, and the catalog construction can be completed in about 7.5 months with a flexible mission profile.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Environmental Sciences
Ruifu Wang, Dongdong Teng, Wenqing Yu, Xi Zhang, Jinshan Zhu
Summary: This research proposes a generative adversarial network (GAN) model for time series satellite cloud image prediction. The model learns the data feature distribution of satellite cloud images and predicts future time series cloud images by considering the time series information. Through the integration of the Mish activation function and implementation of improvement measures such as using the Wasserstein distance, establishing a multiscale network structure, and combining image gradient difference loss, the model achieves better predictive performance. The experimental results demonstrate that the improved GDL-GAN model maintains good visualization effects while accurately capturing the overall changes and movement trends of the predicted cloud images, thereby enhancing the cooperation ability of satellite cloud images in disastrous weather forecasting and early warning.
Article
Multidisciplinary Sciences
Hannah C. Cubaynes, Peter T. Fretwell
Summary: Monitoring whales in remote areas is crucial for conservation, but using traditional survey platforms is difficult. Very high-resolution satellite imagery shows promise, but accurate automated whale detection systems are lacking. This study presents a dataset of 633 annotated whale objects detected in satellite images, creating a valuable resource for training and testing automatic detection systems. The dataset covers four species across various regions and was captured by different high-resolution satellites.
Article
Geochemistry & Geophysics
Thomas J. Vandal, Daniel McDuff, Weile Wang, Kate Duffy, Andrew Michaelis, Ramakrishna R. Nemani
Summary: This study focuses on generating synthetic spectral imagery for multispectral sensors using unsupervised learning methods such as variational autoencoder (VAE) and generative adversarial network (GAN). By introducing a novel shared spectral reconstruction loss, efficient cross-domain reconstruction is achieved, providing a basis for synchronizing remote sensing datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Ana-Maria Loghin, Johannes Otepka-Schremmer, Camillo Ressl, Norbert Pfeifer
Summary: This paper proposes an approach to detect and estimate the periodic distortions of Pleiades tri-stereo imagery caused by satellite attitude oscillations. By re-projecting ground points onto satellite images using RPCs, the systematic height errors of satellite-based elevation models are computed and corrected. Experimental results show that the proposed method successfully removes the systematic elevation discrepancies and improves the overall accuracy of the elevation models.
Article
Engineering, Aerospace
Tao Nie, Pini Gurfil
Summary: The study explores a new approach for low-thrust orbit control by creating artificial resonance to improve efficiency and save fuel. A resonant-control candidate for efficiently changing all mean orbital elements is proposed, along with four decoupling control laws designed for this purpose.
JOURNAL OF GUIDANCE CONTROL AND DYNAMICS
(2021)
Article
Environmental Sciences
Roya Narimani, Changhyun Jun, Saqib Shahzad, Jeill Oh, Kyoohong Park
Summary: This paper proposes a novel hybrid method for flood susceptibility mapping using AHP and ArcGIS with satellite images. Nine environmental controlling factors were considered for weight estimation and integrated using overlay weighted sum technique to create a flood susceptibility map in Seoul. The validation results showed high risk in 40% of the area, providing valuable information for planners to mitigate flood incidents.
Article
Computer Science, Artificial Intelligence
Kate Duffy, Thomas J. Vandal, Weile Wang, Ramakrishna R. Nemani, Auroop R. Ganguly
Summary: Numerical models based on physics are the best tools for generating insights and predictions in Earth system modeling. However, the need for higher model resolutions exceeds the capabilities of current computers, leading to the development of surrogate models. Recent successes of machine learning methods, particularly deep learning, suggest that they can capture the complex structures and processes in Earth systems.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Xu Chen, Haigang Sui, Jian Fang, Mingting Zhou, Chen Wu
Summary: Satellite videos have become a new data source for applications such as traffic management and military surveillance. Compared to ground surveillance videos, satellite videos have the advantage of wider coverage for large-scale monitoring. However, the presence of pseudomotion backgrounds and low-resolution targets in satellite videos presents challenges for moving vehicle detection. To address this, a novel approach that uses adaptive motion separation and difference accumulated trajectory is proposed, achieving better detection performance than existing methods in satellite videos.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Cell Biology
Tingfeng Chen, Tingting Ni, Lan Mu, Zhou Ying, Hanqun Zhang, Zi Wang
Summary: This study classified ovarian cancer into different molecular subtypes using cell differentiation trajectory analysis and developed a prognostic risk scoring model. By analyzing differentiation-related genes, the ovarian cancer samples were divided into four subtypes, showing significant differences in survival rates, clinical features, tumor microenvironment, and immune-related gene expression levels. The prognostic risk score model based on nine differentiation-related genes provided valuable insights into predicting prognosis in ovarian cancer patients.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2023)
Article
Ecology
Muamer Didelija, Nedim Kulo, Admir Mulahusic, Nedim Tuno, Jusuf Topoljak
Summary: Illegal waste dumping is considered a major cause of environmental damage, particularly in the form of illegal landfills. To better manage and control these landfills, it is important to have knowledge of their locations and contents. Remote sensing methods have proven to be effective in detecting illegal landfill sites, and this study explores the relationship between segmentation scale parameters and the accuracy of detection in urban areas without vegetation or buried waste.
ECOLOGICAL INFORMATICS
(2022)
Article
Environmental Sciences
E. M. O. Silveira, A. M. Pidgeon, L. S. Farwell, M. L. Hobi, E. Razenkova, B. Zuckerberg, N. C. Coops, V. C. Radeloff
Summary: The dynamic habitat indices (DHIs) derived from satellite data capture patterns of vegetative productivity and are a good predictor of bird species richness. Multi-grain habitat measures obtained from different satellite sensors and data resolutions have better predictive power for bird species richness than high-resolution data derived from resampling. This study highlights the value of DHIs derived from high-resolution satellite data and the potential of multi-resolution remotely-sensed vegetation productivity measures for quantifying biodiversity.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Remote Sensing
Vahid Nasiri, Pawel Hawrylo, Piotr Janiec, Jaros law Socha
Summary: This study investigates the use of PlanetScope satellite images and pixel-based and object-based image analysis for accurate mapping of forest cover and detection of tree cuttings. Machine learning models were trained and evaluated, and the results showed that the object-based random forest classifier performed the best in both forest cover mapping and tree-cutting detection.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
