Automatic machine learning identification of nanoscale features in transmission electron microscopy images
Imaging nanoscale features using transmission electron microscopy (TEM) is key to predicting and assessing the mechanical behaviour of structural materials in nuclear reactors or in the fields of nanotechnology. These features, visible by phase contrast (nanobubbles) or diffraction contrast (dislocation loops or coherent precipitates), are prime candidates for automation. Analysing these micrographs manually is often tedious, time-consuming, non-universal and somehow subjective.
In this project, the objective is to develop a Python-based framework for data treatment of transmission electron microscopy (TEM) images.
Machine Learning approaches will be implemented in order to tackle the following tasks:
- Data collection: The success of any machine learning approach is linked to the database quality. In this project, a huge database is available. Four microscopists are involved in the project and will continuously enrich the database with images containing easily recognizable features.
- Denoising and finding the defect contour both through existing open-access software and in-house developed descriptors. Representative ROI (region-of-Interest) will be generated on images.
- Design of the Convolutional Neural Network (CNN) Architecture and model training: A collective feature map will be generated for the entire images in order to identify some representatives ROI. Each ROI is then overlaid to the original feature map and is passed to the CNN for individual region classifications. Secondly, recent advances in image segmentation will be placed in the core engine of the workflow.
- Model performance metrics: The aim is to reach a compromise between the training time and the detector performance.
The process will be applied to nanometer-sized features formed under irradiation in nuclear oriented materials (Co-free high entropy alloys (HEA), UO2) and precipitates in materials with a technological interest (coherent Cr precipitates in Cu).
Cascade of circulicity in compressible turbulence
In this post-doctorate, we propose to study the properties of the small scales of forced compressible homogeneous turbulence. More precisely, exact statistical relations similar to the Monin-Yaglom relation will be investigated. The idea, detailed in reference [1], is to understand how the transfer of circulicity is organized in the inertial range. Circulicity is a quantity associated with angular momentum and, by extension, with vortex motions. The analysis of its inertial properties allows to complete the description of the energy cascade already highlighted in previous works [2,3].
The objective of the post-doctorate is to carry out and exploit direct simulations of compressible homogeneous turbulence with forcing, in order to highlight the inertial properties of circulicity .
To this end, the post-doctoral student will be given access to the very large computing center (TGCC) as well as a code, Triclade, solving the compressible Navier-Stokes equations [4]. This code does not have a forcing mechanism and the first task will therefore be to add this functionality. Once this task has been accomplished, simulations will be carried out by varying the nature of the forcing and in particular the ratio between its solenoidal and dilatational components. These simulations will then be exploited by analyzing the transfer terms of circulicity.
[1] Soulard and Briard. Submitted to Phys. Rev. Fluids. Preprint at arXviv:2207.03761v1
[2] Aluie. Phys. Rev. Lett. 106(17):174502, 2011.
[3] Eyink and Drivas.Phys. Rev. X 8(1):011022, 2018.
[4] Thornber et al. Phys. Fluids 29:105107, 2017.
Study and modeling of fiber Bragg grating acoustic receivers
CEA List has been working for several years on the development of advanced monitoring solutions using fibre optic acoustic receivers called Fiber Bragg Gratings. These optical sensors have a great potential for structural health monitoring, both because of their ability to be integrated into materials (concrete, organic composites, metal) and because of their ability to be deployed in severe environments (embedded, radiative, high temperature).
A post-doctoral work is proposed to carry out modelling of these Fiber Bragg Grating transducers in order to refine the understanding of their sensitivity to ultrasonic guided elastic waves and to help in the design of an associated control system thanks to an intelligent placement of the sensors. Ultimately, the aim is to be able to simulate their response within the Civa non-destructive testing software developed by CEA List, and more particularly via its module dedicated to Structural Health Monitoring (SHM). Such work would strongly contribute to the adoption and exploitation of this technology for Structural Health Monitoring applications.
Modeling of faults on low voltage DC networks in buildings, towards fault detection algorithms
The development of the use of renewable energies and energy storage as well as the progress made by power electronic components are gradually leading to a rethinking of the architectures of low voltage electrical distribution networks in buildings. These developments will allow the development of direct current or mixed alternating-direct current networks supplied by static converters. On this type of network, faults become more difficult to manage due to the power sources used. Indeed, the usual signatures of the short-circuit or the overload are no longer the same and will vary according to the converters used and the architecture of the network. For this, it is necessary to identify, by simulation, the most suitable protection topologies (by neutral systems for example) and to identify the typical fault signatures. Ultimately, these signatures will provide optimum detection devices.
Lean-Rare Earth Magnetic materials
The energy transition will lead to a very strong growth in the demand for rare earths (RE) over the next decade, especially for the elements (Nd, Pr) and (Dy, Tb). These RE, classified as critical materials, are used almost exclusively to produce NdFeB permanent magnets, and constitute 30% of their mass.
Several recent international studies, aiming to identify new alloys with low RE content and comparable performances to the dense magnetic phase Nd2Fe14B, put hard magnetic compounds of RE-Fe12 type as advantageous substitution solutions, allowing to reduce more that 35% of the amount of RE, while keeping the intrinsic magnetic properties close to those of the Nd2Fe14B composition.
The industrial developments of the RE-Fe12 alloys cannot yet be considered due to the important technological and scientific challenge that remain to be lifted in order to be able to produce dense magnets with resistance to demagnetization sufficient for current applications (coercivity Hc > 800 kA/m).
The aim of the post-doctoral work is to develop Nd-Fe12 based alloys with optimized intrinsic magnetic properties and to master the sintering of the powders in order to obtain dense magnets with coercivity beyond 800 kA/m, to fulfil the requirements of the applications in electric mobility. Two technological and scientific challenges are identified:
- understanding of the role of secondary phases on the coercivity. This will open the way to the implementation of techniques called "grain boundary engineering", well known for the NdFeB magnets to have remarkably improved the resistance to demagnetization.
- mastering the sintering step of these powders at low temperature (< 600°C) in order to avoid the decomposotion of the magnetic phase by grain boundary engineering
Highgly reflective materials laser microwelding
In the frame of the Simulation Program, CEA/DAM conducts experiments on high powerful lasers involving complex targets. Intensive research is therefore conducted to study and manufacture a large panel of targets - with ambitious scientific and technological challenges ahead. In particular, CEA wants to extend its laser microwelding capabilities–at a sub-mm scale. The challenge is to weld both high-reflective and thin materials (aluminum, copper, gold …) with an accurate mastering of heat deposition and penetration depth. The goal is to implement, optimize and qualify a process based on the latest source generation (UV or green laser source), and to get an innovative set of experimental data. A phenomenological model might also be proposed.
The latest generation of laser source emitting in visible wavelengths (green, blue) will be exploited. He/she will participate in the design and qualification testing of the laser station associated with this new source. Once validated, he/she will carry out the study of the operational and metallurgical weldability of the sub-elements. He/she will compare his/her results with the use of a pulse infrared laser. He/she will appraise the joints obtained using different approaches and optimize the design of the welded joints. Its experimental study will go as far as carrying out functional tests on prototypes. External collaborations will be set up to compare the results obtained with simulations in order to deduce a phenomenological model.
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.
Design and fabrication of the magnetic control of 1.000 qubits arrays
Quantum computing is nowadays a strong field of research at CEA-LETI and in numerous institutes and companies around the world. In particular, RF magnetic fields allow to control the spin of silicon qubits, and pathway for large scale control is a real technological challenge.
The bibliographic analysis and the studies already carried out will able to draw out the pros and cons of the various existing solutions. In collaboration with integration, simulation and design staff, a proof of concept will be develloped and fabricated.
Synthesis by 3D printing of functionnalized geopolymer membrane for the treatment of complex radioactive effluents.
In the field of the treatment of liquid radioactive wastes on solid supports, the development of new composite materials synthetized by 3D printing under filtre shape is of primary of importance to decontaminate some radioactive effluents.
In this phD proposal, we propose to develop a membrane allowing to produce, from effluent containing somes traces of micronic solids in suspension and ionic species, a clarified effluent compatible with a nuclear outlet pipe. The challenge is to study the shaping of a material in a form of a filtration membrane allowing to trap in a single step an effluent containing some solids in suspension and some ionic species. In order to develop both functionnalities, 3D printing will be used to synthetise multiscale porous ceramic composites such as some geopolymers functionnalized by a selective adsorbants. The candidate, mainly based at CEA/ISEC Marcoule, could first formulate a functionnalized geopolymer paste with suitable rheological properties compatible with the constraints of the 3D printing process. A cross-flow filtration membrane with a controled macroporous network will be then printed by optimizing the geometry of the mesh. Finally, some sorption and cross-flow filtration tests will be performed on some model effluents containing calibrated solid in suspension and ions of interest such as Cs and Sr. The relevance of the printed membrane architecture will be assessed in relation to the capture of the solids and radioelements.
The candidate must have skills in the field of rheology, process and modeling. From this research work, job opportunities either in the field og 3D printing of materials or in the field of liquid waste treatment and depolution are potential options.
Auto-adaptive neural decoder for clinical brain-spine interfacing
CEA/LETI/CLINATEC invite applications for postdoctoral position to work on the HORIZON-EIC project. The project goal is to explore novel solutions for functional rehabilitation and/or compensation for people with sever motor disabilities using auto-adaptive Brain-Machine Interface (BMI) / neuroprosthetics. Neuroprosthetics record, and decode brain neuronal signal for activating effectors (exoskeleton, implantable spinal cord stimulator etc.) directly without physiological neural control command pass way interrupted by spinal cord injury. A set of algorithms to decode neuronal activity recorded at the level of the cerebral cortex (Electrocorticogram) using chronic WIMAGINE implants were developed at CLINATEC and tested in the frame of 2 clinical research protocols in tetraplegics in Grenoble and in paraplegics in Lausanne. The postdoctoral fellow will contribute to the next highly ambitious scientific breakthroughs addressing the medical needs of patients. The crucial improvement of usability may be achieved by alleviating the need of constant BMI decoder recalibration introducing an auto-adaptive framework to train the decoder in an adaptive manner during the neuroprosthetics self-directed use. Auto-adaptive BMI (A-BMI) adds a supplementary loop evaluating from neuronal data the level of coherence between user’s intended motions and effector actions. It may provide BMI task information (labels) to the data registered during the neuroprosthetics self-directed use to be employed for BMI decoder real-time update. Innovative A-BMI neural decoder will be explored and tested offline and in real-time in ongoing clinical trials.