Complete the following questionnaire for - **Postdoctoral Fellowship in Simulation of Wave Propagation**
(254 KB)

Topic: Deep Learning Based Inversion with Energy Applications

Applications are invited for a postdoctoral position within the Simulation of Wave Propagation group at BCAM. The project, entitled “Deep Learning Based Inversion with Energy Applications”, deals with Solving inverse problems in computational mechanics using deep learning algorithms with applications to geophysics.

The preferred candidate will work in one of the following research areas (depending upon the candidate’s scientific profile):

**Research Area 1 (RA1): Development of Deep Learning Algorithms for Real-Time Inversion. **The postdoctoral fellow working on RA1 will be trained on solving inverse problems using Deep Neural Networks (DNNs). Specifically, he/she will improve an existing encoder-decoder Deep Convolutional Neural Network (DCNN) by adding residual blocks with a boosting strategy. The implementation will be based on TensorFlow 2.0. The results will be applied geophysical problems.

**Research Area 2 (RA2): Development of Finite Element Methods for generating a training database for Deep Learning algorithms. **The postdoctoral fellow working on RA2 will explore various numerical methods such as Proper Generalized Decomposition (PGD), Fourier based strategies, multiscale methods, and Finite Element Methods. Then, starting from our existing in-house finite element simulators, the objective is to develop a numerical method that solves one million two-dimensional (2D) forward problems in eight hours on a computer equipped with four quad-core CPUs.

The postdoctoral candidate will work under the supervision of Ikerbasque Research Professor David Pardo. (SIWP group, BCAM)

** Deadline: September 13th 2019, 14:00 CET. (UTC+1) **.

Applications will be evaluated in a continuous manner, with a response period no longer than 4 weeks after the call deadline .
() Compulsory field.