Nowadays, Generative Large Language Models (GLLMs) have made a significant impact in the field of Artificial Intelligence (AI). One of the domains extensively explored for these models is their ability as generators of functional source code for software projects. Nevertheless, their potential as assistants to write the code needed to generate and model Machine Learning (ML) or Deep Learning (DL) architectures has not been fully explored to date. For this reason, this work focuses on evaluating the extent to which different tools based on GLLMs, such as ChatGPT or Copilot, are able to correctly define the source code necessary to generate viable predictive models. The use case defined is the forecasting of a time series that reports the indoor temperature of a greenhouse. The results indicate that, while it is possible to achieve good accuracy metrics with simple predictive models generated by GLLMs, the composition of predictive models with complex architectures using GLLMs is still far from improving the accuracy of predictive models generated by human data scientists.

Nowadays, air pollution is one of the most relevant environmental problems in most urban settings. Due to the utility in operational terms of anticipating certain pollution levels, several predictors based on Graph Neural Networks (GNN) have been proposed for the last years. Most of these solutions usually encode the relationships among stations in terms of their spatial distance, but they fail when it comes to capturing other spatial and feature-based contextual factors. Besides, they assume a homogeneous setting where all the stations are able to capture the same pollutants. However, large-scale settings frequently comprise different types of stations, each one with different measurement capabilities. For that reason, the present article introduces a novel GNN framework able to capture the similarities among stations related to the land use of their locations and their primary source of pollution. Furthermore, we define a methodology to deal with heterogeneous settings on the top of the GNN architecture. Finally, the proposal has been tested with a nation-wide Spanish air-pollution dataset with very promising results.

Nowadays, cities are the most relevant type of human settlement and their population has been endlessly growing for decades. At the same time, we are witnessing an explosion of digital data that capture many different aspects and details of city life. This allows detecting human mobility patterns in urban areas with more detail than ever before. In this context, based on the fusion of mobility data from different and heterogeneous sources, such as public transport, transport-network connectivity and Online Social Networks, this study puts forward a novel approach to uncover the actual land use of a city. Unlike previous solutions, our work avoids a time-invariant approach and it considers the temporal factor based on the assumption that urban areas are not used by citizens all the time in the same manner. We have tested our solution in two different cities showing high accuracy rates.

Energy efficiency is in the interest of everyone, from individuals to governments, since it yields economical savings, reduces greenhouse gas emissions and alleviates energy poverty. Buildings are one of the largest consumers of primary energy and attaining their efficiency is, therefore, an important goal. The Internet of Things currently provides vast amounts of data that can be used to extract knowledge of all kinds, including that regarding energy prediction. This has motivated us to test wether the prior information on the physics of building heat transfer, that is currently available is now redundant owing to the completeness of the data from the system. We propose a machine learning approach and a grey-box model approach with which to test this hypothesis. The former is blind to the physiscs of the problem, while the latter is greatly influenced by it. The energy consumption prediction models were created with both approaches and then used to estimate energy consumption in a normal operation state and compare it with energy consumption when an energy efficiency campaign is run. Our black-box method, which is based on a combination of statistical and machine learning models and on a time series structurization of the data, shows better prediction accuracy than the so-called grey-box methods that include basic physical equations. This shows that also a data driven approach outperforms more informed methods in this, like other fields.