Context Human driven land-use and land-cover change (LULC) is considered to be among the greatest ecological pressures in mountain regions. Over the past century, across the European Alps, extensive LULC changes have been observed, affecting ecosystem goods and services (ESs). Objectives For eight case study sites across the Alpine arc we aimed to provide a spatiotemporal explicit assessment of the impacts of LULC dynamics on ES provision and interactions, including cultivated crops, plant material, climate regulation, soil erosion control and aesthetics. Methods We quantified ES provision in biophysical terms at four time periods (1850, 1955, 1985, 2005) using spatially explicit LULC based assessment models. ES interactions were identified by statistically analyzing the spatiotemporal pattern among ES capacities. Results Over the past century forested areas have increased mainly at the cost of grasslands, while on easily accessible sites and fertile valley floors agricultural intensification occurred. ES provision shifted between 1850 and 2005, from a predominance of production ESs in 1850 to a landscape characterized by regulating ESs in 2005. Spatiotemporal analyses of ES interactions revealed trade-offs between regulating and cultural ESs and within the provisioning ES bundle and allowed to derive three different ES trajectories: regions developing from single to multifunctional sites in terms of service provision, sites reducing their service capacities and sites with rather stationary patterns over broad time periods. Conclusions We demonstrated that ES capacities in complex agro-ecological mountain regions are highly sensitive to long-term landscape dynamics. We conclude that assessing ES capacities and interactions in an explicitly spatiotemporal manner can help to guide evidence-based environmental measures.

Cultural Ecosystem Services (CESs), such as aesthetic and recreational enjoyment, as well as sense of place and cultural heritage, play an outstanding role in the contribution of landscapes to human well‐being. Scientists, however, still often struggle to understand how landscape characteristics contribute to deliver these intangible benefits, largely because it is hard to navigate how people value nature, and because there is a lack in methods that accommodate both comprehensive and time‐efficient evaluations. Recent advances in technology and the proliferation of new data sources, such as social media data, open promising alternatives to traditional, resource‐intensive methods, facilitating the understanding of the multiple relationships between people and nature. Here, we examine a user‐friendly artificial intelligence (AI)‐based approach for inferring visual‐sensory landscape values from Flickr data, combining computer vision with text mining. We show it is possible to automatically relate photographers' preferences in capturing landscape elements to a set of CESs (aesthetic value, outdoor recreation, cultural heritage, symbolic species) with reasonable accuracy, using the semantic content provided by approximately 640,000 artificially generated tags of photographs taken in the UNESCO world heritage site ‘The Dolomites’ (Italy). We used the geographic information in the data to demonstrate that these preferences can be further linked to different natural and human variables and be used to spatially predict CES patterns. Over 90% of photograph tags could be linked to four CES categories with reasonable confidence (accuracy ration ∼ 80%). The Dolomites are highly appreciated for its aesthetic value (66% of images classified to that category) and vast cultural heritage (13%), followed by its outdoor recreation opportunities (11%) and symbolic species (10%). CES benefiting hotspots were found in areas with high tourism development and close to residential areas, and could largely be explained by a combination of environmental (e.g. landscape composition) and infrastructural (e.g. accessibility) variables. We conclude that online available AI technology and social media data can effectively be used to support rapid, flexible and transferrable CES assessments. Our work can provide a reference for innovative adaptive management approaches that can harness emerging technologies to gain insights into human–nature relationships and to sustainably manage our environment. A free Plain Language Summary can be found within the Supporting Information of this article.

Managing multiple ecosystem services (ES) in agricultural landscapes is a challenging task, especially in regions with complex topographical and agro-ecological conditions. These challenges require ES assessment approaches that go beyond the case study level and provide multi-temporal information at a transnational level. We used a spatiotemporal approach to examine the impact of specific land use/land cover (LULC) trajectories on eight ES for the past 150 years. We show how a spatially explicit ES upscaling procedure, from case study to an Alpine-wide level, based on topographical, agro-ecological and socioeconomic parameters, can improve our understanding of ES dynamics and bundles. Our results indicated that the provision of multiple ES was not stable during the 150 years surveyed, mainly depending on the prevailing land management type and the biophysical conditions. ES bundle mapping enabled us to identify landscapes with consistent socioecological characteristics that are most likely to either enhance or diminish the provision of specific types of services. By introducing a spatiotemporal perspective into ES assessment, we provide clear evidence of the dynamic nature of ES provision and contribute to identifying processes and drivers behind these interactions. Our results emphasize that mountain ES supply is particularly sensitive to long-term LULC change, to biophysical characteristics and to regional socioeconomic conditions. They indicate the benefit of integrating of ES bundles into environmental policies at national and transnational level.