Methodology for development of an expert system to derive knowledge from existing nature-based solutions experiences

Abstract

Learning from past experiences is essential for the adoption of Nature-Based Solutions (NBS). There is a growing number of knowledge repositories sharing the experience of NBS projects implemented worldwide. These repositories provide access to a large amount of information, however, acquiring knowledge from them remains a challenge. This paper outlines the technical details of the NBS Case-Based System (NBS-CBS), an expert system that facilitates knowledge acquisition from an NBS case repository. The NBS-CBS is a hybrid system integrating a black-box Artificial Neural Network (ANN) with a white-box Case-Based Reasoning model. The system involves: • a repository that stores the information of past NBS projects, and an input collection component, guiding the collection and encoding of the user's inputs; • a classifier that predicts solutions (i.e., generates a hypothesis), based on user input (target case), drawing on a pre-trained ANN model to guide the case retrieval, and a case retrieval engine that identifies cases similar to the target case; • a case adaption and retainment process in which the user assesses the provided recommendations and retains the solved problem as a new case in the repository.