Signal processing of ultra-fast gamma-ray detectors using Machine Learning
In the frame of the ANR project AAIMME dedicated to the Positron-Emission Tomography (PET), we propose a 24-month post-doctoral position that will focus on the development of signal processing methods for the detector ClearMind, designed at the CEA-IRFU. The detector is specifically developed to provide a precise interaction time in the sensitive volume. It consists of a scintillator PbWO4 detector, coupling with a Micro Channel Plate PhotoMultiplier Tube, whose signals are digitized using fast acquisition modules SAMPIC. The main advantage is to exploit both fast Tcherenkov and scintillation photons to reconstruct as accurately as possible the interactions inside the Crystal.
The analysis of the detector signal represents a major challenge: they are complex and intricated, thus, it necessitates a dedicated processing step.
The objective of this post-doc is to develop these trustworthy Machine Learning algorithms to reconstruct the properties of the gamma-ray interaction in the detector, with the highest achievable accuracy, using the detector signals.
Multi-objective topological optimization in nonlinear mechanics
The CEA-Cesta aims at developing topological optimization tools with performances that are not achievable by commercial software. As part of this post-doc, it will be a question of taking advantage of a collaboration initiated in the LRC Cosims (I2M-Arts et métiers Bordeaux) to progress on the subject, to develop innovative optimization methods in the field of non-linear mechanics. Two application test cases are envisaged:
- Topological optimization of two geometric structures of very different shapes;
- Optimization of a structuring spring.
Advanced reconstruction methods for cryo-electron tomography of biological samples
Cryo-electron tomography (CET) is a powerful technique for the 3D structural analysis of biological samples in their near-native state. CET has seen remarkable advances in instrumentation in the last decade but the classical weighted back-projection (WBP) remains by far the standard CET reconstruction method. Due to radiation damage and the limited tilt range within the microscope, WBP reconstructions suffer from low contrast and elongation artifacts, known as ‘missing wedge’ (MW) artifacts. Recently, there has been a revival of interest in iterative approaches to improve the quality and hence the interpretability of the CET data.
In this project, we propose to go beyond the state-of-the-art in CET by (1) applying curvelet- and shearlet-based compressed sensing (CS) algorithms, and (2) exploring deep learning (DL) strategies with the aim to denoise et correct for the MW artifacts. These approaches have the potential to improve the resolution of the CET reconstructions and facilitate the segmentation and sub-tomogram averaging tasks.
The candidate will conduct a comparative study of iterative algorithms used in life science, and CS and DL approaches optimized in this project for thin curved structures.
Modeling of charge noise in spin qubits
Thanks to strong partnerships between several research institutes, Grenoble is a pioneer in the development of future technologies based on spin qubits using manufacturing processes identical to those used in the silicon microelectronics industry. The spin of a qubit is often manipulated with alternating electrical (AC) signals through various spin-orbit coupling (SOC) mechanisms that couple it to electric fields. This also makes it sensitive to fluctuations in the qubit's electrical environment, which can lead to large qubit-to-qubit variability and charge noise. The charge noise in the spin qubit devices potentially comes from charging/discharging events within amorphous and defective materials (SiO2, Si3N4, etc.) and device interfaces. The objective of this postdoc is to improve the understanding of charge noise in spin qubit devices through simulations at different scales. This research work will be carried out using an ab initio type method and also through the use of the TB_Sim code, developed within the CEA-IRIG institute. This last one is able of describing very realistic qubit structures using strong atomic and multi-band k.p binding models.
detection of multiplets and application to turkey-Syria seismic crisis of february 2023
The correlation technique, or template matching, applied to the detection and analysis of seismic events has demonstrated its performance and usefulness in the processing chain of the CEA/DAM National Data Center. Unfortunately, this method suffers from limitations which limit its effectiveness and its use in the operational environment, linked on the one hand to the computational cost of massive data processing, and on the other hand to the rate of false detections that could generate low-level processing. The use of denoising methods upstream of processing (example: deepDenoiser, by Zhu et al., 2020), could also increase the number of erroneous detections. The first part of the research project consists of providing a methodology aimed at improving the processing time performance of the multiplets detector, in particular by using information indexing techniques developed in collaboration with LIPADE (L-MESSI method , Botao Peng, Panagiota Fatourou, Themis Palpanas. Fast Data Series Indexing for In-Memory Data. International Journal on Very Large Data Bases (VLDBJ) 2021). The second part of the project concerns the development of an auto-encoder type “filtering” tool for false detections built using machine learning. The Syria-Turkey seismic crisis of February 2023, dominated by two earthquakes of magnitude greater than 7.0, will serve as a learning database for this study.
Optimization of a metrological approach to radionuclide identification based on spectral unmixing
The Laboratoire national Henri Becquerel (LNE-LNHB) at CEA/Saclay is the laboratory responsible for French references in the field of ionizing radiations. For several years now, it has been involved in the development of an automatic analysis tool for low-statistics gamma spectra, based on the spectral unmixing technique. This approach makes it possible to respond to metrological constraints such as robust decision-making and unbiased estimation of counts associated with identified radionuclides. To extend this technique to field measurements, and in particular to the deformation of spectra due to interactions in the environment of a radioactive source, a hybrid spectral unmixing model combining statistical and automatic learning methods is currently being developed. The aim of this mathematical solution is to implement a joint estimation of the spectra measured and the counts associated with the radionuclides identified. The next step will be to quantify the uncertainties of the quantities estimated from the hybrid model. The aim is also to investigate the technique of spectral unmixing in the case of neutron detection with a NaIL detector. The future candidate will contribute to these various studies in collaboration with the Laboratoire d'ingénierie logicielle pour les applications scientifiques (CEA/DRF).
Development of Algorithms for the Detection and Quantification of Biomarkers from Voltammograms
The objective of the post-doctoral research is to develop a high-performance algorithmic and software solution for the detection and quantification of biomarkers of interest from voltammograms. These voltammograms are one-dimensional signals obtained from innovative electrochemical sensors. The study will be carried out in close collaboration with another laboratory at CEA-LIST, the LIST/DIN/SIMRI/LCIM, which will provide dedicated and innovative electrochemical sensors, as well as with the start-up USENSE, which is developing a medical device for measuring multiple biomarkers in urine.
Earthquake effect on underground facilities
The Industrial Centre for Geological Disposal (Cigeo) is a project for a deep geological disposal facility for radioactive waste to be built in France. These wastes will be put in sealed packages in tunnels designed at 500 meters depth. The seals are made of a bentonite/sand mixture which has a high swelling capacity and a low water permeability. As a part of the long-term safety demonstration of the repository, it must be demonstrated that the sealing structures can fulfill their functions under seismic loads over their entire lifetime. In order to guarantee this future nuclear waste repository, CEA and Andra are collaborating to work on the potential scientific and engineering challenges involved.
The responses of underground repository to earthquake events are complex due to the spatially and temporally evolving hydro-mechanical properties of the surrounding media and the structure itself. Accurate modeling of the behavior, therefore, requires a coupled multiphysics numerical code to efficiently model the seismic responses for these underground repositories within their estimated lifespan of 100 thousand years.
The research will therefore, propose a performance assessment for sequential and parallel finite element numerical modeling for earthquake analysis of deep underground facilities. Then perform a synthetic data sampling to account for material uncertainties and based on the obtained results in the previous assessment, run a sensitivity analysis using a FEM or a metamodeling process. Finally, the results and knowledge gained within the span of this project will be processed and interpreted to provide responses for industrial needs.
Development of artificial intelligence algorithms for narrow-band localization
Narrowband (NB) radio signals are widely used in the context of low power, wide area (LPWA) networks, which are one of the key components of the Internet-of-Things (NB-IoT). However, because of their limited bandwidth, such signals are not well suited for accurate localization, especially when used in a complex environment like high buildings areas or urban canyons, which create signals reflections and obstructions. One approach to overcome these difficulties is to use a 3D model of the city and its buildings in order to better predict the signal propagation. Because this modelling is very complex, state-of-the art localization algorithms cannot handle it efficiently and new techniques based on machine learning and artificial intelligence should be considered to solve this very hard problem. The LCOI laboratory has deployed a NB-IoT network in the city of Grenoble and is currently building a very large database to support these studies.
Based on an analysis of the existing literature and using the knowledge acquired in the LCOI laboratory, the researcher will
- Contribute and supervise the current data collection.
- Exploit existing database to perform statistical analysis and modelling of NB-IoT signal propagation in various environments.
- Develop a toolchain to simulate signal propagation using 3D topology.
- Refine existing performance bounds through a more accurate signal modelling.
- Develop and implement real-time as well as off line AI-based localization algorithms using 3D topology.
- Evaluate and compare developed algorithms with respect to SoTA algorithms.
- Contribute to collaborative or industrial projects through this research work.
- Publish research papers in high quality journals and conference proceedings.