Search

Olive crops have become a strategic sector in Andalusia, Spain, providing an element of social cohesion and territorial management, but identified as vulnerable under climate change. Their great socioeconomic importance makes the mitigation of climate change effects an important strategy. The main contribution of this paper is to show the application of Bayesian networks into climate change assessment using the evaluation of its impact over olive system in Andalusia. Both classification and regression models were learnt and validated to predict the potential olive grove distribution under an Intergovernmental Panel on Climate Change scenario. A lower error rate was obtained for the regression problem compared to classification. Results predict that climate change will lead to changes into the territorial distribution of olive crops, with a movement from the river valley to the uplands due to the impact of the predicted increase in temperatures. Recommendations for Resource Managers: Bayesian networks are a powerful tool that allows dealing with both discrete and continuous data. However, if continuous data are available in order to retrieve all statistical information from them, discretization process should be avoided and original continuous data used for modeling purpose.Olive cropping area follows an altitudinal gradient from the river bed to the mountainous ranges. The minimum temperature limits the establishment of this crop over certain altitude.Under the scenario of climate change, the altitudinal gradient is lost and the main expanse of olive groves becomes fragmented into smaller patches. Besides, mountainous areas would reach optimal conditions for olive growth due to the increase in temperatures. [ABSTRACT FROM AUTHOR]

Bayesian networks (BNs) have been widely applied in environmental modelling to predict the behavior of an ecosystem under conditions of change. However, this approximation doesn't take time into consideration. To solve this issue, an extension of BNs, the dynamic Bayesian networks (DBNs), has been developed in mathematics and computer science areas but has scarcely been applied in environmental modelling. This paper presents the application of DBN to water reservoir systems in Andalusia, Spain. The aim is to predict changes in the percent fullness of the reservoirs under the irregular rainfall patterns of Mediterranean watersheds. In comparison to static BNs, DBNs provide results that can be extrapolated to a particular time so that a climate change scenario can be studied in detail over time. Because results are expressed by density functions rather than unique values, several metrics are obtained from the results, including the probability of certain values. This allows the probability that water level in a reservoir reaches a certain level to be directly computed. [ABSTRACT FROM AUTHOR]