The Lambro-Seveso-Olona (L-S-O) system derives from the human regulation of the natural hydrology of the territory around Milan city area. The average population density in the L-S-O area is among the highest in Italy and Europe. Industry is also highly developed in this basin: chemical, textile, paper, pulp and food industries being the most important ones. Although, at present, the L-S-O system no longer receives the untreated wastewaters of the Milan urban area, treated wastewaters constitute about half of the streamflow. Biotic communities in this river have a long history of poor quality status, having suffered great damage due to domestic and industrial discharges. Recently, new chemical quality standards for macropollutants have been set by the Italian legislation as support for the good ecological status according to the Water Framework Directive (WFD). This new index is very restrictive, and it makes it extremely challenging to achieve the water quality objectives for the L-S-O system. The aim of this study is to analyse through a modelling exercise the restoration possibilities of the L-S-O system, investigating both the source apportionment of the macropollutants, the discharge limits that should be set to achieve the good quality status and their corresponding cost.

No abstract

No abstract

In the last two decades, numerous models and modeling techniques have been developed to simulate nonpoint source pollution effects. Most models simulate the hydrological, chemical, and physical processes involved in the entrainment and transport of sediment, nutrients, and pesticides. Very often these models require a distributed modeling approach and are limited in scope by the requirement of homogeneity and by the need to manipulate extensive data sets. Physically based models are extensively used in this field as a decision support for managing the nonpoint source emissions. A common characteristic of this type of model is a demanding input of several state variables that makes the calibration and effort-costing in implementing any simulation scenario more difficult. In this study the USDA Soil and Water Assessment Tool (SWAT) was used to model the Venice Lagoon Watershed (VLW), Northern Italy. A Multi-Layer Perceptron (MLP) network was trained on SWAT simulations and used as a meta-model for scenario analysis. The MLP meta-model was successfully trained and showed an overall accuracy higher than 70% both on the training and on the evaluation set, allowing a significant simplification in conducting scenario analysis.