|
|
Roser, J., Muñoz, E., Barrientos, L., Barrio, J., Bernabeu, J., Borja-Lloret, M., et al. (2020). Image reconstruction for a multi-layer Compton telescope: an analytical model for three interaction events. Phys. Med. Biol., 65(14), 145005–17pp.
Abstract: Compton Cameras are electronically collimated photon imagers suitable for sub-MeV to few MeV gamma-ray detection. Such features are desirable to enablein vivorange verification in hadron therapy, through the detection of secondary Prompt Gammas. A major concern with this technique is the poor image quality obtained when the incoming gamma-ray energy is unknown. Compton Cameras with more than two detector planes (multi-layer Compton Cameras) have been proposed as a solution, given that these devices incorporate more signal sequences of interactions to the conventional two interaction events. In particular, three interaction events convey more spectral information as they allow inferring directly the incident gamma-ray energy. A three-layer Compton Telescope based on continuous Lanthanum (III) Bromide crystals coupled to Silicon Photomultipliers is being developed at the IRIS group of IFIC-Valencia. In a previous work we proposed a spectral reconstruction algorithm for two interaction events based on an analytical model for the formation of the signal. To fully exploit the capabilities of our prototype, we present here an extension of the model for three interaction events. Analytical expressions of the sensitivity and the System Matrix are derived and validated against Monte Carlo simulations. Implemented in a List Mode Maximum Likelihood Expectation Maximization algorithm, the proposed model allows us to obtain four-dimensional (energy and position) images by using exclusively three interaction events. We are able to recover the correct spectrum and spatial distribution of gamma-ray sources when ideal data are employed. However, the uncertainties associated to experimental measurements result in a degradation when real data from complex structures are employed. Incorrect estimation of the incident gamma-ray interaction positions, and missing deposited energy associated with escaping secondaries, have been identified as the causes of such degradation by means of a detailed Monte Carlo study. As expected, our current experimental resolution and efficiency to three interaction events prevents us from correctly recovering complex structures of radioactive sources. However, given the better spectral information conveyed by three interaction events, we expect an improvement of the image quality of conventional Compton imaging when including such events. In this regard, future development includes the incorporation of the model assessed in this work to the two interaction events model in order to allow using simultaneously two and three interaction events in the image reconstruction.
|
|
|
|
Stoppa, F., Bhattacharyya, S., Ruiz de Austri, R., Vreeswijk, P., Caron, S., Zaharijas, G., et al. (2023). AutoSourceID-Classifier Star-galaxy classification using a convolutional neural network with spatial information. Astron. Astrophys., 680, A109–16pp.
Abstract: Aims. Traditional star-galaxy classification techniques often rely on feature estimation from catalogs, a process susceptible to introducing inaccuracies, thereby potentially jeopardizing the classification's reliability. Certain galaxies, especially those not manifesting as extended sources, can be misclassified when their shape parameters and flux solely drive the inference. We aim to create a robust and accurate classification network for identifying stars and galaxies directly from astronomical images.Methods. The AutoSourceID-Classifier (ASID-C) algorithm developed for this work uses 32x32 pixel single filter band source cutouts generated by the previously developed AutoSourceID-Light (ASID-L) code. By leveraging convolutional neural networks (CNN) and additional information about the source position within the full-field image, ASID-C aims to accurately classify all stars and galaxies within a survey. Subsequently, we employed a modified Platt scaling calibration for the output of the CNN, ensuring that the derived probabilities were effectively calibrated, delivering precise and reliable results.Results. We show that ASID-C, trained on MeerLICHT telescope images and using the Dark Energy Camera Legacy Survey (DECaLS) morphological classification, is a robust classifier and outperforms similar codes such as SourceExtractor. To facilitate a rigorous comparison, we also trained an eXtreme Gradient Boosting (XGBoost) model on tabular features extracted by SourceExtractor. While this XGBoost model approaches ASID-C in performance metrics, it does not offer the computational efficiency and reduced error propagation inherent in ASID-C's direct image-based classification approach. ASID-C excels in low signal-to-noise ratio and crowded scenarios, potentially aiding in transient host identification and advancing deep-sky astronomy.
|
|
|
|
Stoppa, F., Ruiz de Austri, R., Vreeswijk, P., Bhattacharyya, S., Caron, S., Bloemen, S., et al. (2023). AutoSourceID-FeatureExtractor Optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation. Astron. Astrophys., 680, A108–14pp.
Abstract: Aims. In astronomy, machine learning has been successful in various tasks such as source localisation, classification, anomaly detection, and segmentation. However, feature regression remains an area with room for improvement. We aim to design a network that can accurately estimate sources' features and their uncertainties from single-band image cutouts, given the approximated locations of the sources provided by the previously developed code AutoSourceID-Light (ASID-L) or other external catalogues. This work serves as a proof of concept, showing the potential of machine learning in estimating astronomical features when trained on meticulously crafted synthetic images and subsequently applied to real astronomical data.Methods. The algorithm presented here, AutoSourceID-FeatureExtractor (ASID-FE), uses single-band cutouts of 32x32 pixels around the localised sources to estimate flux, sub-pixel centre coordinates, and their uncertainties. ASID-FE employs a two-step mean variance estimation (TS-MVE) approach to first estimate the features and then their uncertainties without the need for additional information, for example the point spread function (PSF). For this proof of concept, we generated a synthetic dataset comprising only point sources directly derived from real images, ensuring a controlled yet authentic testing environment.Results. We show that ASID-FE, trained on synthetic images derived from the MeerLICHT telescope, can predict more accurate features with respect to similar codes such as SourceExtractor and that the two-step method can estimate well-calibrated uncertainties that are better behaved compared to similar methods that use deep ensembles of simple MVE networks. Finally, we evaluate the model on real images from the MeerLICHT telescope and the Zwicky Transient Facility (ZTF) to test its transfer learning abilities.
|
|
|
|
Stoppa, F., Vreeswijk, P., Bloemen, S., Bhattacharyya, S., Caron, S., Johannesson, G., et al. (2022). AutoSourceID-Light Fast optical source localization via U-Net and Laplacian of Gaussian. Astron. Astrophys., 662, A109–8pp.
Abstract: Aims. With the ever-increasing survey speed of optical wide-field telescopes and the importance of discovering transients when they are still young, rapid and reliable source localization is paramount. We present AutoSourceID-Light (ASID-L), an innovative framework that uses computer vision techniques that can naturally deal with large amounts of data and rapidly localize sources in optical images. Methods. We show that the ASID-L algorithm based on U-shaped networks and enhanced with a Laplacian of Gaussian filter provides outstanding performance in the localization of sources. A U-Net network discerns the sources in the images from many different artifacts and passes the result to a Laplacian of Gaussian filter that then estimates the exact location. Results. Using ASID-L on the optical images of the MeerLICHT telescope demonstrates the great speed and localization power of the method. We compare the results with SExtractor and show that our method outperforms this more widely used method. ASID-L rapidly detects more sources not only in low- and mid-density fields, but particularly in areas with more than 150 sources per square arcminute. The training set and code used in this paper are publicly available.
|
|
