L’INTELLIGENZA ARTIFICIALE PER LA GESTIONE SOSTENIBILE DELLE RISORSE IDRICHE. CASO DI STUDIO: GORGOVIVO, ANCONA

SIMONA EPASTO, ALESSANDRO GALDELLI

Abstract


Artificial Intelligence for Sustainable Water Resources Management. Case Study: Gorgovivo, Ancona. – The urgent need to address challenges related to the sustainable management of water resources has prompted the scientific and technological community to explore innovative solutions that can make a significant contribution to achieving the goals and sustainability strategies of the UN’s 2030 Agenda. In this context, Artificial Intelligence (AI) emerges as a powerful ally, offering advanced tools for the collection, analysis, and management of water data efficiently and effectively. Using machine learning algorithms and neural networks, AI enables accurate prediction of water demand, facilitating optimal planning and allocation of resources. Moreover, the integration of smart sensors and monitoring systems allows real-time control of water resources, improving the response capacity to environmental variations and emergencies.
The purpose of the research is to examine how AI can optimize water treatment and distribution processes, reducing waste and enhancing the energy efficiency of water facilities; the use of predictive models based on historical data and environmental variables allows for proactive management of resources, thus contributing to their conservation and long-term sustainability. In this perspective, an AI-based system will be adopted to predict the groundwater levels of the Gorgovivo spring (AN), using historical data from the spring itself, the level of the Esino river, and rainfall stations. The proposed AI model is based on the Prophet predictive algorithm, specifically designed to manage time series forecasting applications; as adapted by us, the predictive model was evaluated using the mean absolute error (MAE), mean squared error (MSE), and correlation criteria.

Keyword


Sustainable water management; Artificial intelligence; Predictive modelling

Full Text

PDF


DOI: http://dx.doi.org/10.19246/DOCUGEO2281-7549/202401_14

Refback

  • Non ci sono refbacks, per ora.




ISSN: 2281-7549

Licenza Creative Commons
Quest'opera è distribuita con Licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 4.0 Internazionale.