Search

This document provides DESIRA's third set of practice abstracts (PAs) which is a compilation of seven PAs. Those PAs are based on the experiences, lessons learned, project actions and reporting of the WP3 activities that aimed at the development of scenarios and showcasing of technologies building on the concept of digital game changers. Tasks 3.5 'Use Case development' and 3.6 'Showcase Technologies', are the main contributing project tasks that provided concrete results on which these seven PAs, cited in this report, are based. The first five PAs provide a concise description of five use cases that were developed during the second period of the DESIRA project. An array of conducted activities inside the boundaries of five preselected Living Labs, and with the participation of those LL's stakeholders, were planned so that WP3 could culminate in the development of five technology adoption use cases. The last two PAs of this report, supplement the five aforementioned use case PAs by showcasing two additional promising technology solutions that have the potential to contribute to sustainable digital transition pathways, as those are defined by the DESIRA's theoretical framework and as reflected by the examined agro-rural-forestry settings of this project. For a thorough and detailed analysis of the methodology, activities, and outcomes that contributed to the production of the use cases and showcase technology reports, it is recommended the reading of deliverables D3.3 'Use Cases Report' and D3.4 'Showcase Technology Report' which are the foundation documents on which this deliverable is based on.

Precise and reliable identification of riparian vegetation along rivers is of paramount importance for managing bodies, enabling them to accurately plan key duties, such as the design of river maintenance interventions. Nonetheless, manual mapping is significantly expensive in terms of time and human costs, especially when authorities have to manage extensive river networks. Accordingly, in the present paper, we propose a methodology for classifying and automatically mapping the riparian vegetation of urban rivers. Specifically, the calibration of an unsupervised (Isodata Clustering) and a supervised (Random Forest) machine learning algorithm (MLA) is carried out for the classification of the riparian vegetation detected in high-resolution (1m) aerial orthoimages. Riparian vegetation is classified using Normalized Difference Vegetation Index (NDVI) features. In the framework of this research, the Isodata Clustering slightly outperforms the Random Forest, achieving a higher level of predictive performance and reliability throughout all the computed performance metrics. Moreover, being unsupervised, it does not require ground truth information, which makes it particularly competitive in terms of annotation costs when compared with supervised algorithms, and definitely appropriate in case of limited resources. We encourage river authorities to use MLA-based tools, such as the ones we propose in this work, for mapping riparian vegetation, since they can bring relevant benefits, such as limited implementation costs, easy calibration, fast training, and adequate reliability.