Climate change and water abstraction impacts on the long-term variability of water levels in Lake Bracciano (Central Italy): A Random Forest approach

Study Region: Lake Bracciano has been historically used as a strategic water reservoir for the city of Rome (Italy) since ancient times. However, following the severe water crisis of 2017, water abstraction has been completely stopped. Study Focus: The relative impact of the various drivers of change (climatological and management) on fluctuations in lake water level is not yet clear. To quantify this impact, we applied the Random Forest (RF) machine learning approach, taking advantage of a century of observations. New Hydrological Insights for the Region: Since the late 1990s the monthly variation in lake water levels has doubled, as has variation in monthly abstraction. Increased variation in annual cumulated precipitation and a rise in mean air temperature have also been observed. The RF machine learning approach made it possible to confirm the marginal role of temperature, the increasing role of abstraction during the last two decades (from 24 % to 39 %), and the key role played by the increased precipitation variability. These results highlight the notable prediction and inference capabilities of RF in a complex and partially unknown hydrological context. We conclude by discussing the limits of this approach, which are mainly associated with its capacity to generates scenarios compared to physical based models.