I am a P.h.D student at the Earthquake Engineering and Structural Dynamics (EESD) group, EPFL.
I have had the chance to explore different domains in my P.h.D. from experimental tests on stone masonry walls to crack detection by deep learning. On the right, you can see an image of a cracked wall that Dr. Michele Godio and I tested at EPFL.
2017 - Present
P.H.D IN STRUCTURAL ENGINEERING, EPFL
I started my P.h.D at EPFL in 2017 under the supervision of Prof. Katrin Beyer. I have been working on the Image-based damage assessment of stone masonry walls. I have conducted an experimental campaign including testing of 12 stone masonry walls. Using the data of the experiments, I used a convolutional neural network to detect cracks and built machine learning models to predict the level of damage based on crack features.
2020 - 2021
MICRO MASTER IN DATA SCIENCE,
UNIVERSITY OF CALIFORNIA SAN DIEGO
To enhance and consolidate my knowledge in the data science field, I have followed a micro master's degree at the University of California San Diego. This program contained four courses, including
Big Data Analytics Using Spark
2015 - 2017
MS IN STRUCTURAL ENGINEERING,
UNIVERSITY OF TEHRAN
I took my master's degree in Structural Engineering from the University of Tehran.
During my master's, I was working on the "Seismic vibration Reduction in Structures Using Wave Barriers in the Ground, Considering Soil-structure Interaction Effects" as the subject of my thesis, which was supervised by Dr. Reza Rafiee and Dr. Kiarash Dolatshahi.
I graduated in 2017 with an overall GPA of 18.86/20 while I was ranked 1st among more than 90 fellow civil engineering students.
If you would like to learn more about my work at master, you may have a look at my publications about the mitigation of the vertical component of seismic ground motions and shear waves by wave barriers.
2011 - 2015
BS IN CIVIL ENGINEERING,
UNIVERSITY OF TEHRAN
I finished my Bachelor's degree in Civil Engineering from the University of Tehran in 2015.
I was ranked 1st among more than 90 fellow civil engineering students of the 2011 intake with a GPA of 18.86/20.
MY P.H.D ROAD MAP
 EXPERIMENTAL TESTS
We designed and tested 6 large scale stone masonry walls under shear-compression loading. Click on the button below to see some images from the construction of the walls and test setup.
 DEEP LEARNING
After testing my walls, I needed to build a predictive model between surface cracks, i.e., cracks that develop on the walls surfaces, and the level of damage to the walls. So the first step was to detect (segment) crack pixels on the images we took from the walls. To do so, I implemented a deep model to segment crack pixels from the background. Click on the button below to see our publication about the crack detection on laboratory images.
 MACHINE LEARNING
The next step in my road map was to build machine learning models to predict the level of damage, represented as the residual force/displacement capacity and stiffness loss. To do so, crack features were first extracted from images then, several machine learning models were implemented to map extracted features to the level of damage.
EPFL ENAC IIC EESD
GC B2 494 (Bâtiment GC)
+41 21 693 93 74