An official website of the United States government
Detecting and classifying solar filaments is critical in forecasting Earth-affecting transient solar events, including large solar flares and coronal mass ejections. Undetected, these space weather events can cause catastrophic geomagnetic storms resulting in substantial economic damage and death. A network of ground-based observatories, named the Global Oscillation Network Group, was created to provide continuous observation of solar activity. However, parsing the large volume of image data continuously streaming in from GONG tests the limitations of human analysis and presents challenges for space weather research. To address this, we proposed the Machine Learning Ecosystem for Filament Detection (MLEcoFi), an NSF-funded, multiyear project that will produce an open-source collection of filament data and computer vision software for space weather research. In cooperation with NSO, MLEcoFi will assist in automatically detecting, classifying, localizing, and segmenting solar filaments in full-disk H-alpha images. The present phase of research aims to produce a dataset of thousands of GONG H-alpha images, with all filaments’ chirality, bounding box, and segmentation mask manually annotated following strong quality assurance standards, advancing research of filaments and filament-related topics. This dataset, as the first MLEcoFi product, will aid in ongoing and future development of products, including a chirality-aware filament data augmentation engine, high-precision image segmentation loss function, deep neural network segmentation and classification model, and filament detection module that is planned for deployment into NSO’s live infrastructure for the research community. The MLEcoFi team is eager to present its progress and future milestones to obtain valuable feedback from the future users of this ecosystem.
more »
« less
MAGFILO: Manually Annotated GONG Filaments in H-Alpha Observations
MAGFiLO is a dataset of manually annotated solar filaments from H-Alpha observations captured by the Global Oscillation Network Group (GONG). This dataset includes over ten thousand annotated filaments, spanning the years 2011 through 2022. Each annotation details one filament's segmentation, minimum bounding box, spine, and magnetic field chirality. MAGFiLO is the first dataset of its size, enabling advanced deep learning models to identify filaments and their features with unprecedented precision. It also provides a testbed for solar physicists interested in large-scale analysis of filaments.
more »
« less
- Award ID(s):
- 2433781
- PAR ID:
- 10538884
- Publisher / Repository:
- Harvard Dataverse
- Date Published:
- Format(s):
- Medium: X
- Institution:
- University of Missouri - St. Louis
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Rooftop solar deployments are an excellent source for generating clean energy. As a result, their popularity among homeowners has grown significantly over the years. Unfortunately, estimating the solar potential of a roof requires homeowners to consult solar consultants, who manually evaluate the site. Recently there have been efforts to automatically estimate the solar potential for any roof within a city. However, current methods work only for places where LIDAR data is available, thereby limiting their reach to just a few places in the world. In this paper, we propose DeepRoof, a data-driven approach that uses widely available satellite images to assess the solar potential of a roof. Using satellite images, DeepRoof determines the roof's geometry and leverages publicly available real-estate and solar irradiance data to provide a pixel-level estimate of the solar potential for each planar roof segment. Such estimates can be used to identify ideal locations on the roof for installing solar panels. Further, we evaluate our approach on an annotated roof dataset, validate the results with solar experts and compare it to a LIDAR-based approach. Our results show that DeepRoof can accurately extract the roof geometry such as the planar roof segments and their orientation, achieving a true positive rate of 91.1% in identifying roofs and a low mean orientation error of 9.3 degree. We also show that DeepRoof's median estimate of the available solar installation area is within 11% of a LIDAR-based approach.more » « less
-
Solar Flares Triggered by a Filament Peeling Process Revealed by High-resolution GST Hα ObservationsAbstract The dynamic structures of solar filaments prior to solar flares provide important physical clues about the onset of solar eruptions. Observations of those structures under subarcsecond resolution with high cadence are rare. We present high-resolution observations covering preeruptive and eruptive phases of two C-class solar flares, C5.1 (SOL2022-11-14T17:29) and C5.1 (SOL2022-11-14T19:29), obtained by the Goode Solar Telescope at Big Bear Solar Observatory. Both flares are ejective, i.e., accompanied by coronal mass ejections (CMEs). High-resolution Hαobservations reveal details of the flares and some striking features, such as a filament peeling process: individual strands of thin flux tubes are separated from the main filament, followed shortly thereafter by a flare. The estimated flux of rising strands is in the order of 1017Mx, versus the 1019Mx of the entire filament. Our new finding may explain why photospheric magnetic fields and overall active region and filament structures as a whole do not have obvious changes after a flare, and why some CMEs have been traced back to the solar active regions with only nonerupting filaments, as the magnetic reconnection may only involve a very small amount of flux in the active region, requiring no significant filament eruptions. We suggest internal reconnection between filament threads, instead of reconnection to external loops, as the process responsible for triggering this peeling of threads that results in the two flares and their subsequent CMEs.more » « less
-
Gaze-annotated facial data is crucial for training deep neural networks (DNNs) for gaze estimation. However, obtaining these data is labor-intensive and requires specialized equipment due to the challenge of accurately annotating the gaze direction of a subject. In this work, we present a generative framework to create annotated gaze data by leveraging the benefits of labeled and unlabeled data sources. We propose a Gaze-aware Compositional GAN that learns to generate annotated facial images from a limited labeled dataset. Then we transfer this model to an unlabeled data domain to take advantage of the diversity it provides. Experiments demonstrate our approach's effectiveness in generating within-domain image augmentations in the ETH-XGaze dataset and cross-domain augmentations in the CelebAMask-HQ dataset domain for gaze estimation DNN training. We also show additional applications of our work, which include facial image editing and gaze redirection.more » « less
-
Grilli, Jacopo (Ed.)Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is to associate sensor data into individual crowns. While dozens of crown detection algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics. There is a need for a benchmark dataset to minimize differences in reported results as well as support evaluation of algorithms across a broad range of forest types. Combining RGB, LiDAR and hyperspectral sensor data from the USA National Ecological Observatory Network’s Airborne Observation Platform with multiple types of evaluation data, we created a benchmark dataset to assess crown detection and delineation methods for canopy trees covering dominant forest types in the United States. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. The benchmark dataset contains over 6,000 image-annotated crowns, 400 field-annotated crowns, and 3,000 canopy stem points from a wide range of forest types. In addition, we include over 10,000 training crowns for optional use. We discuss the different evaluation data sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as overlapping field-annotated crowns. We provide an example submission and score for an open-source algorithm that can serve as a baseline for future methods.more » « less
