In this work, a data-driven forecasting system based on Convolutional Neural Network is formalized and applied. Convolutional Neural Networks allow the extraction of features from an image or a series of images. In this context, these models are applied to reproduce the concentration level of nitrogen dioxide in advance, starting from the emission maps of nitrogen oxides in the atmosphere. The system is applied to the Milan municipality (Italy), an area often affected by high levels of pollution, with very good performances in terms of both statistical analysis (errors and correlation) and threshold indexes (hit ratio and false alarm ratio). In the near future, the model will be included into a model predictive control system to manage air quality in the area.

In this work, a model predictive approach for climate change is presented. In particular, the problem ob-jective is to maintain temperature anomaly in the years 202S-2100 below a selected threshold, acting on the emissions of carbon dioxide (C02), methane (CH4) and greenhouse gases (GHG). The problem implements the constraints specified by to the last report of the IPCC (Intergovernmental Panel on Climate Change). Accordingly to these reports, three different thresholds have been tested, ranging from I.5oC to 2°C. An evaluation is performed to assess the impact of the different uncertainty sources on the problem results. The application of the methodology on the case study shows the capability of the control to find the solution of the problem only for threshold above I.5oC, as long as the control action will start very early in the next few years.

In this work, an optimization problem to control world temperature anomaly is presented. In particular, the problem is related to the computation of carbon dioxide (CO2), methane (CH4) and greenhouse gases (GHG) emission reduction for the period 2025–2100 in order to maintain temperature anomaly below a selected threshold. In accordance to the last IPCC (Intergovernmental Panel on Climate Change) reports and to the discussion of COP26 meeting (XXVIth COnference of the Parties, UNFCCC - United Nations Framework Convention on Climate Change), two different threshold have been tested, with value 2° and 1.5° respectively. The application of the methodology on the case study shows its capability for the solution of the problem. Nevertheless, while with a threshold of 2° the problem has a solution that respect all the constraints imposed by COP26 discussions, a lightening of the constraints is needed to ensure a temperature anomaly below 1.5° up to 2100.