Field experiments have demonstrated that atmospheric ozone can damage crops, leading to yield reduction and a deteriorating crop quality . The availability of regional scale air pollution models allows one to combine modeled ozone fields, exposure-response functions, crop location and growing season, to obtain regional estimates of crop losses. Since 2008 the Air Quality Model Evaluation International Initiative (AQMEII) coordinated by the EC/Joint Research Center and the US EPA has worked toward knowledge and experience sharing on air quality modeling in Europe and North America . Within this context multi-model ensemble has been exercised proving to be very instrumental for a number of applications (e.g. ). In this work we explore the capabilities of neural networks to combine model results and improve ozone predictions, under current and future scenarios, over the European region. The ability of neural networks to account for both nonlinear input-output relationships and interactions between inputs has made them popular in areas where model interpretation is of secondary importance to predictive skill. The possibility to improve the predictive capabilities of the existing models has fundamental implications both on the model forecasting ability necessary to sketch future scenarios and on legislation to regulate the impact of air quality.
|Titolo:||The impact of ozone on crop yields by combining multi-model results through a neural network approach|
RICCIO, Angelo (Corresponding)
|Data di pubblicazione:||2017|
|Appare nelle tipologie:||4.1 Contributo in Atti di convegno|