Thesis

Big Data Processing and Machine Learning for CLOUD/PS215 at CERN

• Call:

  PT-CERN Call 2021/2

• Academic Year:

  2021

• Domain:

  Astrophysics

• Supervisor:

  Antonio Amorim

• Co-Supervisor:

  Jonathan Duplissy

• Institution:

  FCUL (Universidade de Lisboa)

• Host Institution:

  CENTRA - Center for astrophysics and gravitation

• Abstract:

  The main objectives of this proposal involve the application of AI/Machine learning methods to reprocess large amounts of existing and future CLOUD data to train three different AI systems to: • Replace the non-linear “control system” that presently is carried out by user informed trial and adjustment by a trained automatic AI agent. We propose evaluating, training, and deploying the deep neural networks to act as a CLOUD non-linear “control system”. • Create a tool for automatic identification of new particle formation events (NPF). We propose looking at “banana plots” where the aerosol concentrations for different diameters are plotted over time, applying Region-based Convolution Neural Network methods for image recognition, and identifying and possibly classifying the obtained nucleation events. • Train a deep neural network from the observed evolution of aerosol distribution data to provide the growth rates in several conditions. To apply this model to reference data and estimate its performance.