Peoples’ recreation and well-being are closely related to their aesthetic enjoyment of the landscape. Ecosystem service (ES) assessments record the aesthetic contributions of landscapes to peoples’ well-being in support of sustainable policy goals. However, the survey methods available to measure these contributions restrict modelling at large scales. As a result, most studies rely on environmental indicator models but these do not incorporate peoples’ actual use of the landscape. Now, social media has emerged as a rich new source of information to understand human-nature interactions while advances in deep learning have enabled large-scale analysis of the imagery uploaded to these platforms. In this study, we test the accuracy of Flickr and deep learning-based models of landscape quality using a crowdsourced survey in Great Britain. We find that this novel modelling approach generates a strong and comparable level of accuracy versus an indicator model and, in combination, captures additional aesthetic information. At the same time, social media provides a direct measure of individuals’ aesthetic enjoyment, a point of view inaccessible to indicator models, as well as a greater independence of the scale of measurement and insights into how peoples’ appreciation of the landscape changes over time. Our results show how social media and deep learning can support significant advances in modelling the aesthetic contributions of ecosystems for ES assessments.
Payments for ecosystem services (PES) have been developed as a policy instrument to help safeguard the contributions of ecosystems to human well-being. A critical measure of a programme's effectiveness is whether it is generating an additional supply of ecosystem services (ES). So far, there has been limited analysis of PES programmes based on the actual supply of ES. In line with ecosystem accounting principles, we spatially quantified three ES recognised by Costa Rica's Pago de Servicios Ambientales (PSA) programme: carbon storage, soil erosion control and habitat suitability for biodiversity as a cultural ES. We used the machine learning algorithm random forest to model carbon storage, the Revised Universal Soil Loss Equation (RUSLE) to model soil erosion control and Maxent to model habitat suitability. The additional effect of the PSA programme on carbon storage was examined using linear regression. Forested land was found to store 235.3 Mt of carbon, control for 148 Mt yr −1 of soil erosion and contain 762,891 ha of suitable habitat for three iconic but threatened species. PSA areas enrolled in the programme in both 2011 and 2013 were found to store an additional 9 tonC ha −1 on average. As well as enabling a direct quantification of additionality, spatial distribution analysis can help administrators target high-value areas, confirm the conditional supply of ES and support the monetary valuation of ES. Ultimately, this can help improve the social efficiency of payments by enabling a comparison of societal costs and benefits. In this context, the System of Environmental Economic Accounting -Ecosystem Accounting (SEEA-EA) provides a consistent system to analyse, store and provide easy access to information on ecosystem changes and human implications (
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.