HOLISMOKES Cañameras, R.; Schuldt, S.; Suyu, S. H. ...
Astronomy and astrophysics (Berlin),
12/2020, Letnik:
644
Journal Article
Recenzirano
Odprti dostop
We present a systematic search for wide-separation (with Einstein radius
θ
E
≳ 1.5″), galaxy-scale strong lenses in the 30 000 deg
2
of the Pan-STARRS 3
π
survey on the Northern sky. With long time ...delays of a few days to weeks, these types of systems are particularly well-suited for catching strongly lensed supernovae with spatially-resolved multiple images and offer new insights on early-phase supernova spectroscopy and cosmography. We produced a set of realistic simulations by painting lensed COSMOS sources on Pan-STARRS image cutouts of lens luminous red galaxies (LRGs) with redshift and velocity dispersion known from the sloan digital sky survey (SDSS). First, we computed the photometry of mock lenses in
g
r
i
bands and applied a simple catalog-level neural network to identify a sample of 1 050 207 galaxies with similar colors and magnitudes as the mocks. Second, we trained a convolutional neural network (CNN) on Pan-STARRS
g
r
i
image cutouts to classify this sample and obtain sets of 105 760 and 12 382 lens candidates with scores of
p
CNN
> 0.5 and > 0.9, respectively. Extensive tests showed that CNN performances rely heavily on the design of lens simulations and the choice of negative examples for training, but little on the network architecture. The CNN correctly classified 14 out of 16 test lenses, which are previously confirmed lens systems above the detection limit of Pan-STARRS. Finally, we visually inspected all galaxies with
p
CNN
> 0.9 to assemble a final set of 330 high-quality newly-discovered lens candidates while recovering 23 published systems. For a subset, SDSS spectroscopy on the lens central regions proves that our method correctly identifies lens LRGs at
z
∼ 0.1–0.7. Five spectra also show robust signatures of high-redshift background sources, and Pan-STARRS imaging confirms one of them as a quadruply-imaged red source at
z
s
= 1.185, which is likely a recently quenched galaxy strongly lensed by a foreground LRG at
z
d
= 0.3155. In the future, high-resolution imaging and spectroscopic follow-up will be required to validate Pan-STARRS lens candidates and derive strong lensing models. We also expect that the efficient and automated two-step classification method presented in this paper will be applicable to the ∼4 mag deeper
g
r
i
stacks from the
Rubin
Observatory Legacy Survey of Space and Time (LSST) with minor adjustments.
One-Shot Video Object Segmentation Caelles, S.; Maninis, K.-K.; Pont-Tuset, J. ...
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
2017-July
Conference Proceeding
Odprti dostop
This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot ...Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).
Galaxy redshifts are a key characteristic for nearly all extragalactic studies. Since spectroscopic redshifts require additional telescope and human resources, millions of galaxies are known without ...spectroscopic redshifts. Therefore, it is crucial to have methods for estimating the redshift of a galaxy based on its photometric properties, the so-called photo-
z
. We have developed NetZ, a new method using a convolutional neural network (CNN) to predict the photo-
z
based on galaxy images, in contrast to previous methods that often used only the integrated photometry of galaxies without their images. We use data from the Hyper Suprime-Cam Subaru Strategic Program (HSC SSP) in five different filters as the training data. The network over the whole redshift range between 0 and 4 performs well overall and especially in the high-
z
range, where it fares better than other methods on the same data. We obtained a precision |
z
pred
−
z
ref
| of
σ
= 0.12 (68% confidence interval) with a CNN working for all galaxy types averaged over all galaxies in the redshift range of 0 to ∼4. We carried out a comparison with a network trained on point-like sources, highlighting the importance of morphological information for our redshift estimation. By limiting the scope to smaller redshift ranges or to luminous red galaxies, we find a further notable improvement. We have published more than 34 million new photo-
z
values predicted with NetZ. This shows that the new method is very simple and swift in application, and, importantly, it covers a wide redshift range that is limited only by the available training data. It is broadly applicable, particularly with regard to upcoming surveys such as the
Rubin
Observatory Legacy Survey of Space and Time, which will provide images of billions of galaxies with similar image quality as HSC. Our HSC photo-
z
estimates are also beneficial to the
Euclid
survey, given the overlap in the footprints of the HSC and
Euclid
.
HOLISMOKES Schuldt, S.; Suyu, S. H.; Meinhardt, T. ...
Astronomy and astrophysics (Berlin),
02/2021, Letnik:
646
Journal Article
Recenzirano
Odprti dostop
Modeling the mass distributions of strong gravitational lenses is often necessary in order to use them as astrophysical and cosmological probes. With the large number of lens systems (≳10
5
) ...expected from upcoming surveys, it is timely to explore efficient modeling approaches beyond traditional Markov chain Monte Carlo techniques that are time consuming. We train a convolutional neural network (CNN) on images of galaxy-scale lens systems to predict the five parameters of the singular isothermal ellipsoid (SIE) mass model (lens center
x
and
y
, complex ellipticity
e
x
and
e
y
, and Einstein radius
θ
E
). To train the network we simulate images based on real observations from the Hyper Suprime-Cam Survey for the lens galaxies and from the
Hubble
Ultra Deep Field as lensed galaxies. We tested different network architectures and the effect of different data sets, such as using only double or quad systems defined based on the source center and using different input distributions of
θ
E
. We find that the CNN performs well, and with the network trained on both doubles and quads with a uniform distribution of
θ
E
> 0.5″ we obtain the following median values with 1
σ
scatter: Δ
x
= (0.00
−0.30
+0.30
)″, Δ
y
= (0.00
−0.29
+0.30
)″, Δ
θ
E
= (0.07
−0.12
+0.29
)″, Δ
e
x
= −0.01
−0.09
+0.08
, and Δ
e
y
= 0.00
−0.09
+0.08
. The bias in
θ
E
is driven by systems with small
θ
E
. Therefore, when we further predict the multiple lensed image positions and time-delays based on the network output, we apply the network to the sample limited to
θ
E
> 0.8″. In this case the offset between the predicted and input lensed image positions is (0.00
−0.29
+0.29
)″ and (0.00
−0.31
+0.32
)″ for the
x
and
y
coordinates, respectively. For the fractional difference between the predicted and true time-delay, we obtain 0.04
−0.05
+0.27
. Our CNN model is able to predict the SIE parameter values in fractions of a second on a single CPU, and with the output we can predict the image positions and time-delays in an automated way, such that we are able to process efficiently the huge amount of expected galaxy-scale lens detections in the near future.
HOLISMOKES Cañameras, R.; Schuldt, S.; Shu, Y. ...
Astronomy and astrophysics (Berlin),
09/2021, Letnik:
653
Journal Article
Recenzirano
Odprti dostop
We have carried out a systematic search for galaxy-scale strong lenses in multiband imaging from the Hyper Suprime-Cam (HSC) survey. Our automated pipeline, based on realistic strong-lens ...simulations, deep neural network classification, and visual inspection, is aimed at efficiently selecting systems with wide image separations (Einstein radii
θ
E
∼ 1.0–3.0″), intermediate redshift lenses (
z
∼ 0.4–0.7), and bright arcs for galaxy evolution and cosmology. We classified
gri
images of all 62.5 million galaxies in HSC Wide with
i
-band Kron radius ≥0.8″ to avoid strict preselections and to prepare for the upcoming era of deep, wide-scale imaging surveys with Euclid and Rubin Observatory. We obtained 206 newly-discovered candidates classified as definite or probable lenses with either spatially-resolved multiple images or extended, distorted arcs. In addition, we found 88 high-quality candidates that were assigned lower confidence in previous HSC searches, and we recovered 173 known systems in the literature. These results demonstrate that, aided by limited human input, deep learning pipelines with false positive rates as low as ≃0.01% can be very powerful tools for identifying the rare strong lenses from large catalogs, and can also largely extend the samples found by traditional algorithms. We provide a ranked list of candidates for future spectroscopic confirmation.
HOLISMOKES Schuldt, S.; Cañameras, R.; Shu, Y. ...
Astronomy and astrophysics (Berlin),
03/2023, Letnik:
671
Journal Article
Recenzirano
Odprti dostop
Modeling of strong gravitational lenses is a necessity for further applications in astrophysics and cosmology. With the large number of detections in current and upcoming surveys, such as the
Rubin
...Legacy Survey of Space and Time (LSST), it is pertinent to investigate automated and fast analysis techniques beyond the traditional and time-consuming Markov chain Monte Carlo sampling methods. Building upon our (simple) convolutional neural network (CNN), we present here another CNN, specifically a residual neural network (ResNet), that predicts the five mass parameters of a singular isothermal ellipsoid (SIE) profile (lens center
x
and
y
, ellipticity
e
x
and
e
y
, Einstein radius
θ
E
) and the external shear (
γ
ext, 1
,
γ
ext, 2
) from ground-based imaging data. In contrast to our previous CNN, this ResNet further predicts the 1
σ
uncertainty for each parameter. To train our network, we use our improved pipeline to simulate lens images using real images of galaxies from the Hyper Suprime-Cam Survey (HSC) and from the
Hubble
Ultra Deep Field as lens galaxies and background sources, respectively. We find very good recoveries overall for the SIE parameters, especially for the lens center in comparison to our previous CNN, while significant differences remain in predicting the external shear. From our multiple tests, it appears that most likely the low ground-based image resolution is the limiting factor in predicting the external shear. Given the run time of milli-seconds per system, our network is perfectly suited to quickly predict the next appearing image and time delays of lensed transients. Therefore, we use the network-predicted mass model to estimate these quantities and compare to those values obtained from our simulations. Unfortunately, the achieved precision allows only a first-order estimate of time delays on real lens systems and requires further refinement through follow-up modeling. Nonetheless, our ResNet is able to predict the SIE and shear parameter values in fractions of a second on a single CPU, meaning that we are able to efficiently process the huge amount of galaxy-scale lenses expected in the near future.
HOLISMOKES Huber, S.; Suyu, S. H.; Ghoshdastidar, D. ...
Astronomy and astrophysics (Berlin),
02/2022, Letnik:
658
Journal Article
Recenzirano
Odprti dostop
The Hubble constant (
H
0
) is one of the fundamental parameters in cosmology, but there is a heated debate around the > 4
σ
tension between the local Cepheid distance ladder and the early Universe ...measurements. Strongly lensed Type Ia supernovae (LSNe Ia) are an independent and direct way to measure
H
0
, where a time-delay measurement between the multiple supernova (SN) images is required. In this work, we present two machine learning approaches for measuring time delays in LSNe Ia, namely, a fully connected neural network (FCNN) and a random forest (RF). For the training of the FCNN and the RF, we simulate mock LSNe Ia from theoretical SN Ia models that include observational noise and microlensing. We test the generalizability of the machine learning models by using a final test set based on empirical LSN Ia light curves not used in the training process, and we find that only the RF provides a low enough bias to achieve precision cosmology; as such, RF is therefore preferred over our FCNN approach for applications to real systems. For the RF with single-band photometry in the
i
band, we obtain an accuracy better than 1% in all investigated cases for time delays longer than 15 days, assuming follow-up observations with a 5
σ
point-source depth of 24.7, a two day cadence with a few random gaps, and a detection of the LSNe Ia 8 to 10 days before peak in the observer frame. In terms of precision, we can achieve an approximately 1.5-day uncertainty for a typical source redshift of ∼0.8 on the
i
band under the same assumptions. To improve the measurement, we find that using three bands, where we train a RF for each band separately and combine them afterward, helps to reduce the uncertainty to ∼1.0 day. The dominant source of uncertainty is the observational noise, and therefore the depth is an especially important factor when follow-up observations are triggered. We have publicly released the microlensed spectra and light curves used in this work.
HOLISMOKES Schuldt, S; Suyu, S H; Meinhardt, T ...
Astronomy and astrophysics (Berlin),
02/2021, Letnik:
646
Journal Article
Recenzirano
Odprti dostop
Modeling the mass distributions of strong gravitational lenses is often necessary in order to use them as astrophysical and cosmological probes. With the large number of lens systems (≳105) expected ...from upcoming surveys, it is timely to explore efficient modeling approaches beyond traditional Markov chain Monte Carlo techniques that are time consuming. We train a convolutional neural network (CNN) on images of galaxy-scale lens systems to predict the five parameters of the singular isothermal ellipsoid (SIE) mass model (lens center x and y, complex ellipticity ex and ey, and Einstein radius θE). To train the network we simulate images based on real observations from the Hyper Suprime-Cam Survey for the lens galaxies and from the Hubble Ultra Deep Field as lensed galaxies. We tested different network architectures and the effect of different data sets, such as using only double or quad systems defined based on the source center and using different input distributions of θE. We find that the CNN performs well, and with the network trained on both doubles and quads with a uniform distribution of θE > 0.5″ we obtain the following median values with 1σ scatter: Δx = (0.00−0.30+0.30)″, Δy = (0.00−0.29+0.30)″, ΔθE = (0.07−0.12+0.29)″, Δex = −0.01−0.09+0.08, and Δey = 0.00−0.09+0.08. The bias in θE is driven by systems with small θE. Therefore, when we further predict the multiple lensed image positions and time-delays based on the network output, we apply the network to the sample limited to θE > 0.8″. In this case the offset between the predicted and input lensed image positions is (0.00−0.29+0.29)″ and (0.00−0.31+0.32)″ for the x and y coordinates, respectively. For the fractional difference between the predicted and true time-delay, we obtain 0.04−0.05+0.27. Our CNN model is able to predict the SIE parameter values in fractions of a second on a single CPU, and with the output we can predict the image positions and time-delays in an automated way, such that we are able to process efficiently the huge amount of expected galaxy-scale lens detections in the near future.
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the ...temporal smoothness is suddenly broken, such as when an object is occluded, or some frames are missing in a sequence, the result of these methods can deteriorate significantly. This paper explores the orthogonal approach of processing each frame independently, i.e., disregarding the temporal information. In particular, it tackles the task of semi-supervised video object segmentation: the separation of an object from the background in a video, given its mask in the first frame. We present Semantic One-Shot Video Object Segmentation (OSVOS^\mathrm {S}S), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one shot). We show that instance-level semantic information, when combined effectively, can dramatically improve the results of our previous method, OSVOS. We perform experiments on two recent single-object video segmentation databases, which show that OSVOS^\mathrm {S}S is both the fastest and most accurate method in the state of the art. Experiments on multi-object video segmentation show that OSVOS^\mathrm {S}S obtains competitive results.
PDF
