Increasingly variable hydrologic regimes combined with more frequent and intense extreme events are challenging water systems management worldwide. These trends emphasize the need of accurate medium- to long-term predictions to timely prompt anticipatory operations. In this work, we introduce the Climate State Intelligence framework that relies in Artificial Intelligence tools to capture the concurrent state of multiple global climate signals, such as El Nino Southern Oscillation (ENSO) and the North Atlantic Oscillation (NAO), and improve seasonal forecasts. The use of multiple climate signals ensures the portability of this framework to different geographic locations, including regions where traditional teleconnections are weak. Adopting a data-driven modeling approach, we use these teleconnections and other observed preseason sea surface temperature anomalies to forecast local meteorological variables on a seasonal time scale. The resulting forecasts are subsequently transformed using a dynamic hydrologic model into streamflow predictions, which are used as additional inputs for informing water systems operations. Finally, we quantify the operational value of the hydrologic forecasts as the corresponding gain in system performance with respect to a baseline solution that does not use any forecast information. We apply the framework to the Lake Como basin, a regulated lake in northern Italy which is mainly operated for flood control and irrigation supply. Numerical results show the existence of notable teleconnection patterns dependent on both ENSO and NAO over the Alpine region, which contribute in generating skillful seasonal precipitation and hydrologic forecasts. The use of this information for conditioning the lake operations produces an average 44% improvement in system performance with respect to a baseline solution not informed by any forecast, with this gain that further increases during extreme drought episodes.

Can artificial intelligence improve seasonal forecasts and inform reservoir operations?

M. Giuliani;M. Zaniolo;A. Castelletti
2020

Abstract

Increasingly variable hydrologic regimes combined with more frequent and intense extreme events are challenging water systems management worldwide. These trends emphasize the need of accurate medium- to long-term predictions to timely prompt anticipatory operations. In this work, we introduce the Climate State Intelligence framework that relies in Artificial Intelligence tools to capture the concurrent state of multiple global climate signals, such as El Nino Southern Oscillation (ENSO) and the North Atlantic Oscillation (NAO), and improve seasonal forecasts. The use of multiple climate signals ensures the portability of this framework to different geographic locations, including regions where traditional teleconnections are weak. Adopting a data-driven modeling approach, we use these teleconnections and other observed preseason sea surface temperature anomalies to forecast local meteorological variables on a seasonal time scale. The resulting forecasts are subsequently transformed using a dynamic hydrologic model into streamflow predictions, which are used as additional inputs for informing water systems operations. Finally, we quantify the operational value of the hydrologic forecasts as the corresponding gain in system performance with respect to a baseline solution that does not use any forecast information. We apply the framework to the Lake Como basin, a regulated lake in northern Italy which is mainly operated for flood control and irrigation supply. Numerical results show the existence of notable teleconnection patterns dependent on both ENSO and NAO over the Alpine region, which contribute in generating skillful seasonal precipitation and hydrologic forecasts. The use of this information for conditioning the lake operations produces an average 44% improvement in system performance with respect to a baseline solution not informed by any forecast, with this gain that further increases during extreme drought episodes.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1209034
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact