A large-scale solar dynamics observatory image dataset for computer vision applications

Küçük, Ahmet; Banda, Juan M.; Angryk, Rafal A.

doi:10.1038/sdata.2017.96

Cited by 25 publications

(14 citation statements)

References 22 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While heliophysics researchers are likely aware of corrections that must be applied to this data, and the fact that AIA measurements have heterogenous exposure times, it is unrealistic to expect the same from researchers in other fields (e.g. the data set of Kucuk et al 2017, were compiled from quicklook JPEG2000 images that have compressed dynamic range and do not account for instrumental degradation). We therefore process these corrections by identifying and removing corrupt observations (e.g., images taken during instrument anomalies), adjust detected intensities for heterogeneous exposure times, and fix instrument artifacts that introduce spurious trends.…”

Section: Examination Of Raw Data Productsmentioning

confidence: 99%

A Machine-learning Data Set Prepared from the NASA Solar Dynamics Observatory Mission

Galvez¹,

Fouhey²,

Jin³

et al. 2019

ApJS

View full text Add to dashboard Cite

In this paper we present a curated dataset from the NASA Solar Dynamics Observatory (SDO) mission in a format suitable for machine learning research. Beginning from level 1 scientific products we have processed various instrumental corrections, downsampled to manageable spatial and temporal resolutions, and synchronized observations spatially and temporally. We illustrate the use of this dataset with two example applications: forecasting future EVE irradiance from present EVE irradiance and translating HMI observations into AIA observations. For each application we provide metrics and baselines for future model comparison. We anticipate this curated dataset will facilitate machine learning research in heliophysics and the physical sciences generally, increasing the scientific return of the SDO mission. This work is a direct result of the 2018 NASA Frontier Development Laboratory Program. Please see the appendix for access to the dataset.

show abstract

Section: Examination Of Raw Data Productsmentioning

confidence: 99%

A Machine-learning Data Set Prepared from the NASA Solar Dynamics Observatory Mission

Galvez¹,

Fouhey²,

Jin³

et al. 2019

ApJS

View full text Add to dashboard Cite

show abstract

“…Our SDO AIA image data is collected in two steps: first, event records are downloaded and filtered, second: from the filtered event records, solar images are downloaded or extracted from [22] and annotation files are created.…”

Section: Dataset Usedmentioning

confidence: 99%

Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation

Sarker

Banda

2019

2019 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

With the advent of deep learning for computer vision tasks, the need for accurately labeled data in large volumes is vital for any application. The increasingly available large amounts of solar image data generated by the Solar Dynamic Observatory (SDO) mission make this domain particularly interesting for the development and testing of deep learning systems. The currently available labeled solar data is generated by the SDO mission's Feature Finding Team's (FFT) specialized detection modules. The major drawback of these modules is that detection and labeling is performed with a cadence of every 4 to 12 hours, depending on the module. Since SDO image data products are created every 10 seconds, there is a considerable gap between labeled observations and the continuous data stream. In order to address this shortcoming, we trained a deep regression network to track the movement of two solar phenomena: Active Region and Coronal Hole events. To the best of our knowledge, this is the first attempt of solar event tracking using a deep learning approach. Since it is impossible to fully evaluate the performance of the suggested event tracks with the original data (only partial ground truth is available), we demonstrate with several metrics the effectiveness of our approach. With the purpose of generating continuously labeled solar image data, we present this feasibility analysis showing the great promise of deep regression networks for this task.

show abstract

“…For training our model, a database for overexposure is established. e raw data is cropped from LSDO [36].…”

Section: Solar Oer Recovery Databasementioning

confidence: 99%

“…(3) Additionally, a new database of overexposure is established for training and testing the proposed mask-Pix2Pix network, where 13700 images are collected from the Largescale Solar Dynamics Observatory image database (LSDO) [36].…”

Section: Introductionmentioning

confidence: 99%

Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image

Dong

Chen

et al. 2019

Advances in Astronomy

View full text Add to dashboard Cite

Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.

show abstract

A large-scale solar dynamics observatory image dataset for computer vision applications

Cited by 25 publications

References 22 publications

A Machine-learning Data Set Prepared from the NASA Solar Dynamics Observatory Mission

A Machine-learning Data Set Prepared from the NASA Solar Dynamics Observatory Mission

Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation

Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image

Contact Info

Product

Resources

About