Abstract:
Forecasting the formation and development of clouds is a central element of modern weather forecasting systems. Incorrect cloud forecasts can lead to major uncertainty in...Show MoreMetadata
Abstract:
Forecasting the formation and development of clouds is a central element of modern weather forecasting systems. Incorrect cloud forecasts can lead to major uncertainty in the overall accuracy of weather forecasts due to their intrinsic role in the Earth's climate system. Few studies have tackled this challenging problem from a machine learning point-of-view due to a shortage of high-resolution datasets with many historical observations globally. In this article, we present a novel satellite-based dataset called “CloudCast.” It consists of 70 080 images with 10 different cloud types for multiple layers of the atmosphere annotated on a pixel level. The spatial resolution of the dataset is 928 × 1530 pixels (3 × 3 km per pixel) with 15-min intervals between frames for the period January 1, 2017 to December 31, 2018. All frames are centered and projected over Europe. To supplement the dataset, we conduct an evaluation study with current state-of-the-art video prediction methods such as convolutional long short-term memory networks, generative adversarial networks, and optical flow-based extrapolation methods. As the evaluation of video prediction is difficult in practice, we aim for a thorough evaluation in the spatial and temporal domain. Our benchmark models show promising results but with ample room for improvement. This is the first publicly available global-scale dataset with high-resolution cloud types on a high temporal granularity to the authors' best knowledge.
Published in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ( Volume: 14)
Funding Agency:

Department of Engineering, Aarhus University, Aarhus N, Denmark
Andreas Holm Nielsen received the M.Sc. degree in finance from Aarhus University, Aarhus, Denmark, in 2017. He is currently working toward the Ph.D. degree at the Department of Engineering - Signal Processing Group, Aarhus University.
His research interests includes machine learning for time-series data, remote sensing, deep learning, atmospheric sciences, and meteorology.
Andreas Holm Nielsen received the M.Sc. degree in finance from Aarhus University, Aarhus, Denmark, in 2017. He is currently working toward the Ph.D. degree at the Department of Engineering - Signal Processing Group, Aarhus University.
His research interests includes machine learning for time-series data, remote sensing, deep learning, atmospheric sciences, and meteorology.View more

Department of Engineering, Aarhus University, Aarhus N, Denmark
Alexandros Iosifidis (Senior Member, IEEE) is an Associate Professor with Aarhus University, Aarhus, Denmark. He received the B.Sc. and M.Sc. degrees in electrical and computer engineering from Democritus University of Thrace, and a Ph.D. degree in computer science from Aristotle University of Thessaloniki, in 2008, 2010, and 2014, respectively. He has contributed in more than 20 R&D projects financed by EU, Finnish, and ...Show More
Alexandros Iosifidis (Senior Member, IEEE) is an Associate Professor with Aarhus University, Aarhus, Denmark. He received the B.Sc. and M.Sc. degrees in electrical and computer engineering from Democritus University of Thrace, and a Ph.D. degree in computer science from Aristotle University of Thessaloniki, in 2008, 2010, and 2014, respectively. He has contributed in more than 20 R&D projects financed by EU, Finnish, and ...View more

Department of Engineering, Aarhus University, Aarhus N, Denmark
Henrik Karstoft received the B.Sc. degree in physics and in computer science, in 1985, the M.Sc. degree in math in 1988, and the Ph.D. degree in mathematics in 1991 from the University of Aarhus, Aarhus, Denmark.
He has been a Professor (Docent) with Department of Engineering, Aarhus University, since 2007. He has past experiences from R&D projects in computer vision and machine learning in a professional R&D organization....Show More
Henrik Karstoft received the B.Sc. degree in physics and in computer science, in 1985, the M.Sc. degree in math in 1988, and the Ph.D. degree in mathematics in 1991 from the University of Aarhus, Aarhus, Denmark.
He has been a Professor (Docent) with Department of Engineering, Aarhus University, since 2007. He has past experiences from R&D projects in computer vision and machine learning in a professional R&D organization....View more

Department of Engineering, Aarhus University, Aarhus N, Denmark
Andreas Holm Nielsen received the M.Sc. degree in finance from Aarhus University, Aarhus, Denmark, in 2017. He is currently working toward the Ph.D. degree at the Department of Engineering - Signal Processing Group, Aarhus University.
His research interests includes machine learning for time-series data, remote sensing, deep learning, atmospheric sciences, and meteorology.
Andreas Holm Nielsen received the M.Sc. degree in finance from Aarhus University, Aarhus, Denmark, in 2017. He is currently working toward the Ph.D. degree at the Department of Engineering - Signal Processing Group, Aarhus University.
His research interests includes machine learning for time-series data, remote sensing, deep learning, atmospheric sciences, and meteorology.View more

Department of Engineering, Aarhus University, Aarhus N, Denmark
Alexandros Iosifidis (Senior Member, IEEE) is an Associate Professor with Aarhus University, Aarhus, Denmark. He received the B.Sc. and M.Sc. degrees in electrical and computer engineering from Democritus University of Thrace, and a Ph.D. degree in computer science from Aristotle University of Thessaloniki, in 2008, 2010, and 2014, respectively. He has contributed in more than 20 R&D projects financed by EU, Finnish, and Danish funding agencies and companies. He has authored or coauthored 72 journal articles and 88 conference papers proposing novel machine learning techniques, and their application in a variety of problems.
Dr. Iosifidis served as an Officer of the Finnish IEEE Signal Processing-Circuits and Systems Chapter in 2016–2018. He is currently an Associate/Academic/Area Editor for Neurocomputing, Signal Processing: Image Communication, IEEE Access, and BMC Bioinformatics Journals.
Alexandros Iosifidis (Senior Member, IEEE) is an Associate Professor with Aarhus University, Aarhus, Denmark. He received the B.Sc. and M.Sc. degrees in electrical and computer engineering from Democritus University of Thrace, and a Ph.D. degree in computer science from Aristotle University of Thessaloniki, in 2008, 2010, and 2014, respectively. He has contributed in more than 20 R&D projects financed by EU, Finnish, and Danish funding agencies and companies. He has authored or coauthored 72 journal articles and 88 conference papers proposing novel machine learning techniques, and their application in a variety of problems.
Dr. Iosifidis served as an Officer of the Finnish IEEE Signal Processing-Circuits and Systems Chapter in 2016–2018. He is currently an Associate/Academic/Area Editor for Neurocomputing, Signal Processing: Image Communication, IEEE Access, and BMC Bioinformatics Journals.View more

Department of Engineering, Aarhus University, Aarhus N, Denmark
Henrik Karstoft received the B.Sc. degree in physics and in computer science, in 1985, the M.Sc. degree in math in 1988, and the Ph.D. degree in mathematics in 1991 from the University of Aarhus, Aarhus, Denmark.
He has been a Professor (Docent) with Department of Engineering, Aarhus University, since 2007. He has past experiences from R&D projects in computer vision and machine learning in a professional R&D organization. His main research interests include applications of computer vision and machine learning in various domains. He has authored or coauthored more than 77 peer reviewed scientific paper on computer vision, machine learning, and mathematics. He has supervised three Postdocs, eight Ph.D. students, more than 60 students in their M.Sc. thesis projects, and more than 65 bachelor students’ final project. He is a member of the external examiner corps in engineering and mathematics in Denmark. He is heading the master's program in electrical engineering at Aarhus University.
Henrik Karstoft received the B.Sc. degree in physics and in computer science, in 1985, the M.Sc. degree in math in 1988, and the Ph.D. degree in mathematics in 1991 from the University of Aarhus, Aarhus, Denmark.
He has been a Professor (Docent) with Department of Engineering, Aarhus University, since 2007. He has past experiences from R&D projects in computer vision and machine learning in a professional R&D organization. His main research interests include applications of computer vision and machine learning in various domains. He has authored or coauthored more than 77 peer reviewed scientific paper on computer vision, machine learning, and mathematics. He has supervised three Postdocs, eight Ph.D. students, more than 60 students in their M.Sc. thesis projects, and more than 65 bachelor students’ final project. He is a member of the external examiner corps in engineering and mathematics in Denmark. He is heading the master's program in electrical engineering at Aarhus University.View more