Automating the Implementation of Unsupervised Machine Learning Processes in Smart Cities Scenarios.

Climate Change has become a problem for all the inhabitants of the planet and the solutions to curb it involve knowing all the data on its causes and effects. To this end, it is essential to have mechanisms capable of reading data from different media in real time. This will make it possible to solve many of the problems that arise in areas such as medicine, Smart Cities, industry, transport, etc. Analysing raw data to provide it with semantics is essential to exploit its full potential, making it possible to manage a large number of everyday tasks. All this raw data often comes from a large number of sensors and other sources, in very different types and formats. The analysis of this data read in real time and cross-referenced with information stored in heterogeneous databases, with data from simulations or with data from digital twins is a great opportunity to combat problems such as Climate Change. This work presents a successful use case by characterising the city of Salamanca in vegetation clusters, where a decarbonisation process of a communication artery that crosses the city from north to south is being carried out. The results of this study will serve to identify the most necessary areas for action in the fight against the polluting gases that cause Climate Change.