Some of the potential topics of interest for the department are listed below.

• Classification Methods
• Multivariate Methods
• Deep Learning : Convolutional Neuronal Networks
• Causal Effect Networks for Time-series Analysis

Currently working on the application of classification methods for the effect evaluation of the variability of meteorological variables on the concentration of specific pollutants. Another topic of study is the improvement of the emission model outputs by combining classification/Analogues methods with existing Kalman Filters (KF) algorithms. For more details, look at AC Machine Learning

The use of Deep Learning methods, in particular convolutional neuronal networks, can be applied to Hurricanes and cyclones observational databases to predict the number of such extreme events for the subsequent years.

The use of the Analogues technique utilized to improve the CALIOPE forecast might also be implemented within the MEDSCOPE project to improve the Bias correction and forecast calibration. Mutivariate-Analysis will also play an important role in the development of multivariate scores using EOF approach.

• Improvement in the characterization of uncertainty in multi-ensembles models like EC-Earth by using an adaptive methodology. adaptive
• Extending and adapting existing Classification /Clustering algorithms to the department tools.
• Deep Learning and GPUs applications to Online Diagnostics and Hurricanes forecast.