Satellite Production
Satellite production research currently focuses on enhancing data acquisition, processing, and analysis capabilities. Key areas include developing satellite-agnostic datasets for training advanced machine learning models (e.g., deep diffusion models, variational autoencoders), improving the accuracy and efficiency of algorithms for tasks like cloud type identification, and enabling on-board processing and model training for real-time applications such as orbit determination and collision avoidance. These advancements are crucial for improving various fields, including weather forecasting, environmental monitoring, traffic management, and space situational awareness.
Papers
A knowledge-based data-driven (KBDD) framework for all-day identification of cloud types using satellite remote sensing
Longfeng Nie, Yuntian Chen, Mengge Du, Changqi Sun, Dongxiao Zhang
QIENet: Quantitative irradiance estimation network using recurrent neural network based on satellite remote sensing data
Longfeng Nie, Yuntian Chen, Dongxiao Zhang, Xinyue Liu, Wentian Yuan
Autonomous Local Catalog Maintenance of Close Proximity Satellite Systems on Closed Natural Motion Trajectories
Christopher W. Hays, Kristina Miller, Alexander Soderlund, Sean Phillips, Troy Henderson
Data level and decision level fusion of satellite multi-sensor AOD retrievals for improving PM2.5 estimations, a study on Tehran
Ali Mirzaei, Hossein Bagheri, Mehran Sattari