Avatar

Thomas Di Martino

PhD Student in AI & Remote Sensing

SONDRA @ CentraleSupélec/ONERA

About

As a French Ph.D. student, I am passionate to whatever comes close to Artificial Intelligence & Earth Observation. Whether it is theoretical content with exploring state-of-the-art models or more concrete applicative programming with Jupyter Notebooks, I always find myself curious about what the world is up to !

Additionally, I am currently exploring the depth of SAR imagery seeing how it can help to better monitor forests.

SAR-iously studying is my motto. 😉

🛰️ 🛰️ 🛰️

Interests

  • Artificial Intelligence
  • Remote Sensing
  • Computer Vision
  • Earth Observation

Education

  • PhD in Remote Sensing, 2020-2023

    SONDRA Laboratory, CentraleSupélec, Gif-sur-Yvette, France; ONERA DTIS, Palaiseau, France

  • MSc in Artificial Intelligence & Multimodal Interaction, with Distinction, 2019-2020

    Heriot-Watt University, Edinburgh, Scotland

  • Engineering degree in Computer Science, 2017-2020

    EISTI, Cergy, France

  • BSc degree in Computer Science, 2015-2018

    Cergy-Pontoise University, Cergy, France

Experience

 
 
 
 
 

Visiting Researcher

Φ-lab, ESA-ESRIN

Oct 2022 – Dec 2022 Frascati, Italy
As a visiting researcher at Φ-lab, ESA-ESRIN, I pursue my Ph.D. research in change detection and unsupervised learning of SAR time series of forests. In particular, I aim at generalizing the algorithms developed for agricultural use cases to forest use cases, even more so for anomaly detection.
 
 
 
 
 

PhD Student in Remote Sensing (application of Deep Learning to SAR Time Series)

SONDRA Laboratory | CentraleSupélec/ONERA

Sep 2020 – Present Paris, France

Working on problematics of target detection in SAR Time Series of forests with the help of Deep Learning methods.

SONDRA Laboratory is a laboratory mixing 4 entities: Supélec (known today as CentraleSupélec), ONERA, the National University of Singapore and the DSO of Singapore.

 
 
 
 
 

Machine Learning and Computer Vision Intern

E.Fundamentals

Apr 2020 – Aug 2020 Edinburgh, Scotland
Industrial Placement as part of the DataLab MSc program that led to the redaction of my Master Thesis.

  • Use of multimodal deep learning networks for duplicate product identification in a multi-retailer database.
  • Development of multimodal siamese networks with different losses evaluated and benchmarked (contrastive loss, triplet loss).
  • Analysis of sampling strategy: mini-batch hard sampling, semi-hard sampling, uniform-random sampling, mini-batch distance weighted negative sampling
  • Comparison with more traditional ML approaches (PCA + Decision Tree + Handcoded textual features)
 
 
 
 
 

Deep Learning Intern

Thales

Apr 2019 – Sep 2019 Osny, France

As a deep learning Intern, I have trained, tuned and tested a model capable of doing building segmentation using satellite imagery. In this internship, I have tried multiple models (Mask RCNN, UNet, Deep UNet) and tried to take the best out of them all. The code was written using Keras with Tensorflow Back-End and was manipulated using a web-based RESTFul GUI with Flask and HTML5 technologies.

Also, multiple postprocessing technologies were considered and tried such as Logistic Regression (using scikit-learn) or Conditional Random Field (using pycrf).

 
 
 
 
 

Software Engineering Intern

Worldline ATOS

Jun 2018 – Sep 2018 Bezons, France
I have actively participated in the elaboration of a four tiers architecture implementing an Angular 6 Front-End, a Spring Boot middleware and J2EE back-office connected to COBOL programs using IBM JZOS technology.

Academic Publications

Detection of Forest Fires through Deep Unsupervised Learning Modeling of Sentinel-1 Time Series

With an increase in the amount of natural disasters, the combined use of cloud-penetrating Synthetic Aperture Radar and deep learning …

Grad-SLAM: Explaining Convolutional Autoencoders’ Latent Space of Satellite Image Time Series

This paper introduces a tool for explaining the latent space generated by applying convolutional autoencoders to satellite image time …

FARMSAR: Fixing AgRicultural Mislabels Using Sentinel-1 Time Series and AutoencodeRs

This paper aims to quantify the errors in the provided agricultural crop types, estimate the possible error rate in the available …

Extracting relevance from SAR temporal profiles on a glacier and an alpine watershed by a deep autoencoder

This paper proposes to use methods for compressing the temporal profiles of Sentinel-1 images, in order to be able to evaluate and …

Accomplishments

3rd place Winner of the Data Fusion Contest 2021 - Detection of Settlements without Electricity

My team (Maxime Lenormand, Elise COLIN KOENIGUER) tied for 3rd place at the Data Fusion Contest 2021.
The challenge in question, involving the detection of settlements without electricity, aims to leverage multimodal and multitemporal remote sensing data, combining SAR & Optical data, for the greater good.
For that task, we developed a custom Multi-Channel Deep Learning architecture that we will present during an invited session at IGARSS 2021, in Belgium.

Winner of 2 categories of the Sentinel Hub custom script competition 2020

Collaborative work realized by me, Elise COLIN KOENIGUER, Regis Guinvarc’h, and Laetitia Thirion-Lefevre with the implementation of REACTIV, a multi-temporal method for change visualization in SAR Time Series, has been announced as the winning submission of the Early Bird section of the Sentinel Hub custom scripts competition as well as the winning submission of the main contest track.

The Data Lab MSc Scholarship

I was offered a scholarship to pay for my tuition fees, as well as invitations to all DataLab events for my 2019-2020 year of study at Heriot-Watt University. Award winning candidates were chosen based on their resume as well as a statement of purpose.
The Data Lab organisation puts emphasis on making connections between Scotland’s finnest Data Scientist and data students. These events are opportunities to chat with professionals and exchange knowledge with other students.

Side Projects

*

GEE SAR Fetcher

Python library to download temporal stacks of Sentinel 1 GRD images straight from Google Earth Engine

Deep Similarity Learning & Siamese Networks

In this project, I explored deep similarity learning algorithms and their behaviour with different type of data (sequential data, spatial data, multimodal data). For each of these different modalities, I wrote 2 Medium articles detailing the retained method and providing my implementation.

Deep Reinforcement Learning projects

These 3 projects are implementations made for the udacity’s nanodegree program, all passed through a reviewer. They contain a small report, gathering my comprehension fo the algorithm as well as details on my implementation and my parameters.

Time Series Land Cover Challenge: a Deep Learning Perspective

In this project, I explored a Time Series of satellite images dataset by building different deep learning classifiers, finding inspiration in paper research in the field of Time Series classification.

Segmentation Models on artificial moon imagery

In this project, I trained 4 DL segmentation models on an artificial Lunar Dataset to see how they will perform on real moon images from Nasa.

Blog Posts

The Artificial Intelligence Act, the new GDPR ?

This article will detail the european Artificial Intelligence Act (AIA), while making a parallel with the impact of the GDPR on AI …

Copernicus 2: The future of the Copernicus programme

The iconic European Programme that provided scientists with the Sentinel missions has something else up its sleeve and this for the …

REACTIV — Implementation for Sentinel Hub Custom Scripts Platform

REACTIV — Implementation for Sentinel Hub Custom Scripts Platform: Rapid and EAsy Change detection in radar TIme-series by Variation …

How to choose your loss when designing a Siamese Neural Network ? Contrastive, Triplet or Quadruplet ?

Deep Similarity Learning is the training of a deep learning architecture to learn to detect similarity and disimilarity between two …

Introduction to Deep Similarity Learning for sequences

Deep Similarity Learning is the training of a deep learning architecture to learn to detect similarity and disimilarity between two …

CV

Alternative text - include a link to the PDF!