Tommaso Galeazzo

Tommaso Galeazzo

Postdoctoral Research Scholar

Department of Chemistry, UC Irvine

About

I am a third year Postdoctoral Scholar in Physical chemistry and cheminformatics at AirUCI at the University of California - Irvine (UCI). My primary research interests are algorithms, artificial intelligence, data modelling, and their applications to real world problems. I work with Prof. Manabu Shiraiwa at the intersection of atmospheric chemistry, artificial intelligence and Natural Language Processing (NLP). Currently I am developing APIs that predict physicochemical properties of atmospheric chemical species. I also work as a data scientist, developing predictive models for the private sector and startups.

Before joining UCI, I obtained a Ph.D. in Applied physical chemistry from Sorbonne University in Paris while on residence at the Institut Pierre-Simon Laplace (IPSL). During my Ph.D. I have developed a subpackage of a community software that simulates physicochemical reactions in the gas phase. Prior to my Ph.D., I pursued a MSc. degree in Physical Chemistry from the University of Copenhagen, where I worked on computational chemistry and statistical thermodynamics applied to atmospheric chemistry under the supervision of Prof. Matthew S. Johnson.

Interests

  • Atmospheric Chemistry
  • Chemical Kinetics
  • Artificial Intelligence

Education

  • PhD. in Atmospheric Sciences, 2018

    Sorbonne University

  • MSc. in Physical Chemistry, 2014

    University of Copenhagen

  • BSc. in Chemistry, 2011

    University of Padua

Experience

 
 
 
 
 

Data Scientist (consultant project)

Pageant Media

Aug 2020 – Sep 2020 New York City, NY, US

Developed an AI driven software for text analysis and classification increasing information extraction and productivity by 30%

Responsibilities include:

  • Writing pipelines for text extraction and processing
  • Development of advanced NLP text classification algorithms
  • Training and deployment of state-of-the-art neural network models (RNNs, LSTM, CNNs)
  • Named-entity recognition models (NER)
 
 
 
 
 

Postdoctoral Research Scholar

University of California - Irvine

Sep 2019 – Present Irvine, CA, US

Application of machine learning algorithms to atmospheric chemical modelling

Responsibilities include:

  • Applying NLP techniques (word2vec, embeddings, t-SNE, text classification) to molecular modelling for classification of atmospheric chemical reactions

  • Predicting molecular physical properties using supervised and unsupervised machine learning algorithms

  • Developing a community software simulating air pollutants generation and evolution (chemical kinetics)

 
 
 
 
 

Data Scientist

Datasoil s.r.l.

Jun 2019 – Sep 2019 Padua, Italy

Collaboration

Responsibilities include:

  • Identified and developed machine learning algorithms for anomaly detection on streamed data fluxes (t-digest, Random Forest, DBSCAN)
  • Implemented algorithms in SYN, Datasoil’s platform for assets management

Skills

Chemistry

Machine learning

Analytics

Python

Software Development

Problem solving

Projects

Gecko2vec

Gecko2vec is an embedding software based on mol2vec. It is an application of word2vec algorithm to atmospheric molecules representation. It builds a large and unique database of atmospheric molecules, where embedding representations retain information on molecular structures (i.e. functional groups distribution) and chemical compositions. It allows further investigation of molecular properties via machine learning algorithms.

Mechanism Synthesizer

The mechanism synthesizer is an autoencoder that unfolds and reduces automatically generated chemical mechanisms of atmospheric chemistry. The synthesizer encodes chemical reactions in a multidimensional chemical space and identifies the most representative reactions via unsupervised learning algorithms. It relies on multidimendsional representations of atmospheric molecules via word2vec implementation (i.e. gecko2vec) and on Natural Language Processing algorithms for text and reactions classification.

Publications

Quickly discover relevant content by filtering publications.

Predicting glass transition temperature and melting point of organic compounds via machine learning and molecular embeddings

Gas-particle partitioning of secondary organic aerosols is impacted by particle phase state and viscosity, which can be inferred from …
Predicting glass transition temperature and melting point of organic compounds via machine learning and molecular embeddings

Environmentally Persistent Free Radicals, Reactive Oxygen Species Generation, and Oxidative Potential of Highway PM2.5

In urban environments, vehicle exhaust and nonexhaust emissions represent important sources of fine particulate matter with an …
Environmentally Persistent Free Radicals, Reactive Oxygen Species Generation, and Oxidative Potential of Highway PM2.5

Estimation of Secondary Organic Aerosol Viscosity from Explicit Modeling of Gas-Phase Oxidation of Isoprene and α-pinene

Secondary organic aerosols (SOA) are major components of atmospheric fine particulate matter, affecting climate and air quality. …
Estimation of Secondary Organic Aerosol Viscosity from Explicit Modeling of Gas-Phase Oxidation of Isoprene and α-pinene

Halogens role in volcanic sulphur oxidation: photochemical modelling and isotopic constraints (In preparation)

The photochemical box-model CiTTyCAT is used to simulate volcanic sulphur oxidation and the resulting volcanic sulphate oxygen isotopic …
Halogens role in volcanic sulphur oxidation: photochemical modelling and isotopic constraints (In preparation)

Photochemical box modelling of volcanic SO$_2$ oxidation: isotopic constraints

The photochemical box-model CiTTyCAT is used to analyse the absence of oxygen mass-independent anomalies (O-MIF) in volcanic sulphates …
Photochemical box modelling of volcanic SO$_2$ oxidation: isotopic constraints

Accomplish­ments

Deep Learning

See certificate

Sequence Models

See certificate

Convolutional Neural Networks

See certificate

Structuring Machine Learning Projects

See certificate

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

See certificate

Neural Networks and Deep Learning

See certificate

Machine Learning

See certificate

Recent Posts

Contact

  • 395 Rowland Hall, Irvine, CA 92697
  • Twitter