Computational intelligence for local decision support and explainability in climatic change

Motivation and Scope

In the current situation in which Climatic Change (CC) is a reality, governments have many challenges to address and must be able to act to mitigate the consequences derived from it. Although the global world must fight together against CC, in each country, region and city the CC will affect in a different way, and therefore will have to be prepared accordingly. While in some places there will be droughts, in others there will be floods and in all of them there will be changes in the productive structures and all this will be aggravated little by little and, what is worse, will happen simultaneously to all the planet. What management can or should politicians or decision makers do to prepare their regions or face the consequences of the CC? The resilience of the population and cities to climate events is a fundamental issue for governments. These need tools that help them answer questions such are, for example: – What actions must be carried out in our environment in order to obtain a certain level of desirable resilience? – How much time is needed to achieve this level of resilience taking into account the current economic situation together with the institutional willingness to apply the resources necessary for this purpose? Currently precise models to predict global climate change scenarios are available, but the local vision is rarely addressed. Local politicians need tools to work with the different scenarios and know what they are facing. These tools allow to provide reliable estimates at different scales, that is, at national, municipal or housing levels. CI can provide tools to help decision-making in this area and to offer explainable models. This special session aims to show the recent developments in the field of computational intelligence in the face of the challenge of climate change. Topics of interest include, but are not limited to:

• Computational intelligence techniques to study the impact of CC

• Multi-criteria approaches to model vulnerabilities in CC scenarios

• Computational intelligence approaches to measure CC vulnerabilities

• Explainable computational intelligence in the CC context

• Fuzzy control for CC scenarios

• Hybrid systems of computational intelligence techniques in climatic change challenges

• Increasing resilience to climate change using CI adaptive management approaches

• Fuzzy rule-based downscaling in the context of CC

• Neural networks for downscaling in the context of CC

• Interpretable machine learning models in the CC context

• Decision-support systems to achieve a resilience objective

• Fuzzy modeling of climate change impacts

• Models for explainable recommendations in the CC context

• Downscaled climate projections suitable for resource management