Astrid Veronig, Werner Pötzi, Tatiana Podladchikova

In recent years deep learning had a major impact in various disciplines. New state-of-the-art results have been achieved in image processing, voice recognition, decision making and many other domains. Deep learning has proven to be robust and capable of solving complex tasks. In contrast to other algorithms deep learning benefits from large amounts of data and the inference times are typically short. Under these aspects deep learning is also of interest for tasks within the SOLARNET H2020 project. We will discuss the potential benefits and applications of deep learning for SPRING. Adequate data filtering and merging of simultaneous observations from multiple observation sites need suitable measure for single-site image quality. Recent approaches with neural networks have proven to perform well on image quality assessment. For full-disk solar observations additional effects, like local atmospheric and seeing conditions, complicate the situation. We propose a customized neural network, to account for the image quality assessment. As a baseline we use the currently operating quality estimation of the Kanzelhöhe Observatory for Solar and Environmental Research (KSO), which is based on a combination of parameters that describe local and global properties extracted from each recorded image. The dataset will consist of manually annotated H-alpha images between 2008 and 2019, covering a wide range of solar activity conditions. The advantage of this approach is that additional observation sites can be included with reduced effort by reusing the pre-trained neural network. Additionally, we are investigating reconstruction and homogenization methods to compensate for local seeing conditions. This can be accomplished by a neural network which translates between high- and low-quality images. The architecture is based on generative adversarial networks (GANs). We use high quality images as conditional input for generating a neural network to create realistic low quality solar images. In parallel a second generator is trained to reproduce the original image. With this approach a dataset of paired ground-truth and degraded images is created. This will be of further use for artificial scenarios of multi-site observation with mixed qualities and for performance estimation of the reconstruction algorithms. To enforce the generation of artificial low-quality images a discriminating network is used to identify the differences between low- and high-quality images. With further training on the full augmented dataset, this network serves as an image quality classifier.

Martina Exnerová

In the first part, an overview of solar full-disc observations made at the Ondřejov Observatory is presented. These observations may serve as test data sets for the SPRING data calibration and merging. In the second part, a method of cloud detection in full-disc solar images is outlined. This method is used for a classification of an effect of cloud shadows on the usability of full-disc images.

This is an overview of the objectives and tasks in Solarnet WP8: SPRING.

Berrilli F., Jefferies S., Oliviero M., Del Moro D., Forte R., Giovannelli L., Magrì M., Murphy N., Pietropaolo E., Terranegra L., Viavattene G.

The Magneto Optical Filters at Two Heights (MOTH) experiment consists of two Doppler-magnetographs that each measure the Line-of-Sight (LoS) Doppler velocity and magnetic fields over the full solar disk at a given (different) height in the Sun's atmosphere. The MOTH uses magneto-optical filters (MOFs) at 589 nm (Na D2-line) and 770 nm (K D1-line) and looks at the photosphere low chromosphere region of the Sun's atmosphere (between 400 km and 700 km). The Tor Vergata Solar Synoptic Telescope (TSST) project started in 2011 in collaboration with people involved in MOTH experiment (IfA-University of Hawaii, Georgia State University and JPL) and uses a double telescope for full disk solar images, a MOF-based telescope operating at 770 nm (K D1-line) and a Hα Daystar SR-127 0.4A telescope. Real-time information about Hα structures and LoS velocity and magnetic maps at different solar layers will be the output of a MOF-based network of telescopes (MOTH, VAMOS, TSST and similar MOF-based instruments) to investigate and automatically detect flare location and associated velocity and magnetic features, an essential input to space weather prediction.

Overview of the coronagraphs planned for GBSON and COSMO/ChroMag

This presentation describes the facilities and instruments used in Catania to carry out observations of the solar photosphere and chromosphere.

Data homogenization between different stations.

Brief secription of past and current INAF programs of solar observations and of the INAF instrumentation and data that will be available to the project.

Sanjay Gosain, Markus Roth

Some telescope design considerations are presented

Sanjay Gosain, Markus Roth

Status and activities at KIS are presented

Ideas and description of work for WP 8.3.1, Lucky Imaging

A presentation on the concept for the Ground-Based Solar Observatory Network

Juan P Cobos

Toward real-time inversion of SPRING Stokes observations