TITAN 2 Postdoc positions (Heraklion, Greece) : Cosmology and/or Machine learning

TITAN AstroStatistics Postdoc position (Heraklion, Greece)

Position: Two Postdoc positions, 2 years with possible extension, Heraklion Crete
Deadline:  15/12/2023 Contact: Jean-Luc Starck.  Details about this position are provided in the following PDF.
Contacts: See attached pdf

Details about this position are provided in the following PDF.

TITAN AstroStatistics PhD position (Heraklion, Greece) : Morphology and Spatial Distribution of the Dust Emission using Deep Learning Methods

TITAN AstroStatistics PhD position (Heraklion, Greece) : Morphology and Spatial Distribution of the Dust Emission using Deep Learning Methods

Position: PhD 3 years, Heraklion Crete
Deadline:  28/02/2023 starting before December 2023 
Contacts: See attached pdf

Details about this position are provided in the following PDF.

NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction

Deep Learning has become a very promising avenue for magnetic resonance image (MRI) reconstruction. In this work, we explore the potential of unrolled networks for the non-Cartesian acquisition setting. We design the NC-PDNet, the first density-compensated unrolled network and validate the need for its key components via an ablation study. Moreover, we conduct some generalizability experiments to test our network in out-of-distribution settings, for example training on knee data and validating on brain data. The results show that the NC-PDNet outperforms the baseline models visually and quantitatively in the 2D settings. Additionally, in the 3D settings, it outperforms them visually. In particular, in the 2D multi-coil acquisition scenario, the NC-PDNet provides up to a 1.2 dB improvement in peak signal-to-noise ratio (PSNR) over baseline networks, while also allowing a gain of at least 1 dB in PSNR in generalization settings. We provide the opensource implementation of our network, and in particular the Non-uniform Fourier Transform in TensorFlow, tested on 2D multi-coil and 3D data.

Reference: Z. Ramzi,  Chaithya G.R.,  J.-L. Starck and P. Ciuciu “NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction.

This conference paper presents an adaptation of unrolled networks to the challenging setup of Non-Cartesian MRI Reconstruction. It also introduces the implementation of the Non-Uniform Fast Fourier Transform in TensorFlow: tfkbnufft.
It has been accepted at ISBI 2021.

Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction

Deep neural networks have recently been thoroughly investigated as a powerful tool for MRI reconstruction. There is a lack of research, however, regarding their use for a specific setting of MRI, namely non-Cartesian acquisitions. In this work, we introduce a novel kind of deep neural networks to tackle this problem, namely density compensated unrolled neural networks, which rely on Density Compensation to correct the uneven weighting of the k-space. We assess their efficiency on the publicly available fastMRI dataset, and perform a small ablation study. Our results show that the density-compensated unrolled neural networks outperform the different baselines, and that all parts of the design are needed. We also open source our code, in particular a Non-Uniform Fast Fourier transform for TensorFlow.

Reference: Z. Ramzi,  J.-L. Starck and P. Ciuciu “Density Compensated Unrolled Networks for Non-Cartesian MRI Reconstruction.

This conference paper presents an adaptation of unrolled networks to the challenging setup of Non-Cartesian MRI Reconstruction. It also introduces the implementation of the Non-Uniform Fast Fourier Transform in TensorFlow: tfkbnufft.
It has been accepted at ISBI 2021.

Cosmostat Day on Machine Learning in Astrophysics

Date: March the 5th, 2021

Organizer:  Joana Frontera-Pons  <joana.frontera-pons@cea.fr>

Venue: Remote conference. Zoom link:https://esade.zoom.us/j/88535176160?pwd=RzU1cHA5Z0xrWXkyN0x1a2tJSHZ1Zz09


On March the 5th, 2021, we organize the 6th day on machine learning in astrophysics at DAp, CEA Saclay. 

Program:

All talks are taking place remotely

13:30 - 13:40h. Welcome message                                                   
13:40 - 14:20h. Data-driven detection of multi-messenger transientsIftach Sadeh (Deutsches Elektronen-Synchrotron)
14:20 - 15:00h. Deep Learning in Radio AstronomyVesna Lukic (Vrije Universiteit Brussel)   
15:00 - 15:40h. Machine Learning for Galaxy Image Reconstruction with Problem Specific Loss - Fadi Nammour (CosmoStat - CEA Saclay)   

15:40 - 16:00h. Coffee break with virtual croissants

16:00 - 16:40h. Anomaly detection with generative methodsColoma Ballester (Universitat Pompeu Fabra)
16:40 - 17:20h. Deep learning for environmental sciencesJan Dirk Wegner (ETH Zurich)
17:20 - 18:00h. Graph Neural NetworksFernando Gama ( University of California, Berkeley)

18:00 - 18:05h. End of the day


Data-driven detection of multi-messenger transients

Iftach Sadeh (Deutsches Elektronen-Synchrotron)

The primary challenge in the study of explosive astrophysical transients is their detection and characterisation using multiple messengers. For this purpose, we have developed a new data-driven discovery framework, based on deep learning. We demonstrate its use for searches involving neutrinos, optical supernovae, and gamma rays. We show that we can match or substantially improve upon the performance of state-of-the-art techniques, while significantly minimising the dependence on modelling and on instrument characterisation. Particularly, our approach is intended for near- and real-time analyses, which are essential for effective follow-up of detections. Our algorithm is designed to combine a range of instruments and types of input data, representing different messengers, physical regimes, and temporal scales. The methodology is optimised for agnostic searches of unexpected phenomena, and has the potential to substantially enhance their discovery prospects.


Deep Learning in Radio Astronomy

Vesna Lukic (Vrije Universiteit Brussel)

Machine learning techniques have proven to be increasingly useful in astronomical applications over the last few years, for example in image classification and time series analysis. A topic of current interest is the classification of radio galaxy morphologies, as it gives us insight into the nature of the Active Galactic Nuclei and structure formation. Future surveys such as the Square Kilometre Array (SKA), will detect many million sources and will require the use of automated techniques. Convolutional neural networks are a machine learning technique that have been very successful in image classification, due to their ability to capture high-dimensional features in the data. We show the performance of simple convolutional network architectures in classifying radio sources from the Radio Galaxy Zoo. The use of pooling in such networks results in information losses which adversely affect the classification performance, however Capsule networks preserve this information with the use of dynamic routing. We explore a couple of convolutional neural network architectures against variations of Capsule network setups and evaluate their performance in replicating the classifications of radio galaxies detected by the Low Frequency Array (LOFAR). Finally, we also show how it is possible to use convolutional neural networks to find sources in radio surveys.


Machine Learning for Galaxy Image Reconstruction with Problem Specific Loss

Fadi Nammour (CosmoStat - CEA Saclay)

Telescope images are corrupted with blur and noise. Generally, blur is represented by a convolution with a Point Spread Function and noise is modelled as Additive Gaussian Noise. Restoring galaxy images from the observations is an inverse problem that is ill-posed and specifically ill-conditioned. The majority of the standard reconstruction methods minimise the Mean Square Error to reconstruct images, without any guarantee that the shape objects contained in the data (e.g. galaxies) is preserved. Here we introduce a shape constraint, exhibit its properties and show how it preserves galaxy shapes when combined to Machine Learning reconstruction algorithms.


Anomaly detection with generative methods

Coloma Ballester (Universitat Pompeu Fabra)

Anomaly detection is frequently approached as out-of-distribution or outlier detection. In this talk, a method for out-of-distribution will be discussed. It leverages the learning of the probability distribution of normal data through generative adversarial networks while simultaneously keeping track of the states of the learning to finally estimate an efficient anomaly detector.


Deep learning for environmental sciences

 Jan Dirk Wegner (ETH Zurich) 

A multitude of different sensors is capturing massive amounts of geo-coded data with different spatial resolution, temporal frequency, viewpoint, and quality every day. Modelling functional relationships for applications is often hard and loses predictive power due to the high variance in sensor modality. Data-driven approaches, especially modern deep learning, come to the rescue and learn expressive models directly from (labeled) input data. In this talk, I will present deep learning methods to analyze geospatial data at large scale for two specific applications in the environmental sciences: biodiversity estimation and global vegetation height mapping.


Graph Neural Networks

Fernando Gama ( University of California, Berkeley)

Graphs are generic models of signal structure that can help to learn in several practical problems. To learn from graph data, we need scalable architectures that can be trained on moderate dataset sizes and that can be implemented distributedly. In this talk, I will draw from graph signal processing to define graph convolutions, and use them to introduce graph neural networks (GNNs). I will prove that GNNs are permutation equivariant and stable to perturbations of the graph, properties that explain their scalability and transferability. I will also use these results to explain the advantages of GNNs over linear graph filters. I will then discuss the problem of learning decentralized controllers, and how GNNs naturally leverage the partial information structure inherent to distributed systems. Using flocking as an illustrative example, I will show that GNNs, not only successfully learn distributed actions that coordinate the team but also transfer and scale to larger teams.


 Previous Cosmostat Days on Machine Learning in Astrophysics :

State-of-the-art Machine Learning MRI Reconstruction in 2020: Results of the Second fastMRI Challenge

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

Reference: Mathew J. Muckley, ...,   Z. Ramzi,  P. Ciuciu and J.-L. Starck et al . “State-of-the-art Machine Learning MRI Reconstruction in 2020: Results of the Second fastMRI Challenge.

This paper presents the results of the fastMRI 2020 challenge, where our team finished 2nd in the 4x and 8x supervised tracks.
It is currently being submitted to IEEE TMI.