Search

Abstract In consideration of ongoing climate changes, it has been necessary to provide new tools capable of mitigating hydrogeological risks. These effects will be more marked in small catchments, where the geological and environmental contexts do not require long warning times to implement risk mitigation measures. In this context, deep learning models can be an effective tool for local authorities to have solid forecasts of outflows and to make correct choices during the alarm phase. In this study, we investigate the use of deep learning models able to forecast hydrometric height in very fast hydrographic basins. The errors of the models are very small and about a few centimetres, with several forecasting hours. The models allow a prediction of extreme events with also 4–6 h (RMSE of about 10–30 cm, with a forecasting time of 6 h) in hydrographic basins characterized by rapid changes in the river flow rates. However, to reduce the uncertainties of the predictions with the increase in forecasting time, the system performs better when using a machine learning model able to provide a confidence interval of the prediction based on the last observed river flow rate. By testing models based on different input datasets, the results indicate that a combination of models can provide a set of predictions allowing for a more comprehensive description of the possible future evolutions of river flows. Once the deep learning models have been trained, their application is purely objective and very rapid, permitting the development of simple software that can be used even by lower skilled individuals.

In Italy, watermelon cultivation spans 9510 hectares, with production levels largely influenced by seasonal market demand. As a result, surplus watermelon left unsold by September often remain in the fields, where they decompose naturally and go to waste. A chemical analysis of the watermelon liquid fraction waste (WW) indicates a high carbohydrate concentration, highlighting the potential for biotechnological valorization of this waste stream, converting it into lipids or exopolysaccharides (EPSs). This study investigates the feasibility of utilizing WW as an alternative growth substrate for microalgae, aligning with circular economy principles and advancing sustainable agricultural practices. By repurposing agricultural byproducts, this research supports biorefinery objectives, aiming to convert biomass into high-value secondary products, including biofuels, pigments, and nutraceuticals. Scenedesmus and Chlorella strains demonstrated promising growth and adaptability in WW, achieving biomass yields of 0.95 ± 0.07 g L−1 and 0.37 ± 0.02 g L−1, respectively, with a significant EPS production observed as medium gelation. Although lipid accumulation was limited in this case by the WW substrate, the lipid profiles of both strains were distinctively altered, notably lacking linolenic acid.