RESUMO
Quantifying and mapping cultural ecosystem services are complex because of their intangibility. Data from social media, such as geo-tagged photographs, has been proposed for mapping cultural use or appreciation of ecosystems. However, manual content analysis and classification of large numbers of photographs is time-consuming. The potential of deep learning for automating the analysis of crowdsourced social media content is still being explored in CES research. Here, we use a new deep learning model for automating the classification of natural and human elements relevant to CES from Flickr images. This approach applies a convolutional neural network architecture to analyze over 29,000 photographs from the Lithuanian coast and uses hierarchical clustering to group these photographs. The accuracy of the classification was assessed by comparison with manual classification. Over 37% of the photographs were taken for the landscape appreciation class, and 28% of the photographs were taken of nature, of animals or plants, which represent the nature appreciation class. The main clusters were identified in urban areas, more precisely in the main coastal cities of Lithuania. The distribution of the nature photographs was concentrated around particular natural attractions, and they were more likely to occur in parks and natural reserves with high levels of vegetation and animal cover. This approach that was developed for clustering the photographs was accurate and saved approximately 100 km of manual work. The method demonstrates how analyzing large numbers of digital photographs expands the analytical toolbox available to researchers and allows the quantification and mapping of CES at large geographical scales. Automated assessment and mapping of cultural ecosystem services could be used to inform urban planning and improve nature reserve management.
RESUMO
Farming of shellfish and seaweeds is a tested tool for mitigating eutrophication consequences in coastal environments, however as many other marine economic activities it should be a subject of marine spatial planning for designating suitable sites. The present study proposes site selection framework for provisional zebra mussel farming in a eutrophic lagoon ecosystem, aimed primarily at remediation purposes. GIS-based multi-criteria approach was applied, combining data from empirical maps, numerical models and remote sensing to estimate suitability parameters. Site selection and prioritisation of suitable areas considered 15 environmental and socio-economic criteria, which contributed to 4 optimisation models (settlement, growth and survival of mussels, environmental and socio-economic) and 3 predefined scenarios representing provisional goals of mussel cultivation: spat production, biomass production and bioremediation. The relative importance of each criterion was assessed utilizing the Analytical Hierarchy Process. Site suitability index was calculated and the final result of the site selection analysis was summarized for 3 scenarios and overall suitability map. Four suitability classes (unsuitable, least, moderately and most suitable) were applied, and 3 most suitable zones for provisional zebra mussel cultivation with 12 candidate sites were selected accordingly. The integrated approach presented in this study can be adjusted for designating zebra mussel farming sites in other estuarine lagoon ecosystems, or cultivation of other mussel species for bioremediation purposes. The analytical framework and the workflow designed in this study are also adoptable for addressing other aquaculture-related spatial planning issues.
