This study examined the evaluation of cultural ecosystem services (CESs) and their impact on well-being in peri-urban areas, using a case study in Harku municipality, Estonia. CESs, encompassing intangible factors such as emotions and values, are crucial for well-being but challenging to assess. To address this, a pilot method was developed, involving a typology of natural environment types (NETs) and contact types (CTs), assessed by a panel of local experts. The results revealed that “spiritual, historic, and symbolic” gardens exhibited a strong positive connection to well-being. Blue and green spaces offering physical activities and aesthetics were also highly rated. Surprisingly, cemeteries scored higher than expected. Agreement among experts varied, with “parks + sporting” showing near-perfect consensus and weaker agreement found in “parks + food production”, “blue spaces + providing gathering places”, and “green landscape elements + education”, highlighting diverse expert perspectives in identifying suitable combinations of NETs and CTs. This study addresses research-to-practice gaps and methodological challenges in applying CESs within planning frameworks, providing valuable insights for managing and conserving services in peri-urban areas. By testing the proposed method, this research contributes to a better understanding of how CESs can be effectively integrated into planning processes, fostering sustainable well-being in peri-urbanised regions.

This paper uses the tripartite place attachment framework to examine six rural parishes across Estonia and Latvia. Existing analyses/frameworks on participatory processes often neglect the complexity of relationships that rural residents have to their local environments. From a qualitative analysis of face-to-face, semi-structured interviews with case study area inhabitants (23 interviews in Estonia and 27 in Latvia), we depict varying degrees of attachment of individuals to each other and to the place in which they live and their readiness to participate in terms of willingness and ability to participate in a landscape-scale management process. Attachment to the local area was strongest where the social ties were strongest, independent of their sociogeographical features. Social ties were strong where there were good family connections or strong religious or cultural institutions. Taking individual parishes and engaging inhabitants through in-depth interviews using place attachment analysis gives an overall perspective of life in that rural location. These findings reveal important connections within the communities with the potential for planners to engage with local inhabitants and possible barriers to participation.

Generative AI (GenAI), particularly text-to-image (TTI) models, is reshaping landscape representation by transforming textual descriptions into visual outputs. However, these models often reinforce biases embedded in their training datasets, shaping how landscapes are perceived and represented. This research examines the biases in GenAI-generated landscape imagery through the lens of Edward Said’s “imaginative geographies”, focusing on how geographic references, cultural archetypes, and methodological factors influence AI outputs. We employed a structured approach to create prompts based on the Global Ecosystem Typology (GET), using Midjourney V6.1 as the primary tool for image generation. We extracted landscape descriptors from GET classifications and structured them into both simple and detailed prompts. The analysis involved comparing AI-generated images to ecological classifications and reference images to assess biases. The findings reveal the following three key types of biases: (1) geographic biases, where certain locations act as semantic triggers, leading to culturally stereotypical portrayals; (2) representation biases, where landscapes frequently depicted in AI training datasets appear with greater accuracy, while underrepresented landscapes are simplified into essentialized visual tropes; and (3) methodological biases, where prompt complexity influences representational accuracy but does not eliminate pre-existing cultural hierarchies. To address the bias challenges, the research presents the following four key recommendations for future research and practice: (1) incorporating finer-scale ecosystem classifications; (2) diversifying training datasets; (3) engaging local communities in participatory data collection; and (4) refining prompt-writing methodologies. These insights contribute to broader discussions on AI bias, emphasizing the necessity of critically evaluating the role of generative models in shaping landscape imaginaries.

Background: While the unique marine and coastal environment of the Baltic Sea provides numerous ecosystem services, its ecosystems are under pressure due to the intensification and diversification of anthropogenic uses. This present work constitutes a systematic map of the evidence of the impacts of ecosystem services and disservices on human health and well-being. The aim is to create a better understanding of the threats of unsustainable management or the benefits of sustainable management of the Baltic Sea and the impacts these may have on the health and well-being of human populations and present these findings to policy advisors. The mapping process is described, and the characteristics of the evidence base are presented. Methods: The applied method has been previously published in a systematic map protocol. Literature searches were carried out in English considering published peer-reviewed literature from traditional scientific journals and scientific reports from the grey literature, using synthesis software. A total of 17 databases were searched. Articles were screened in stages at title and abstract stage, then full-text stage. Geographic limitations were placed on the searches in accordance with research funders call, however, watersheds that had an impact on the Baltic Sea marine and coastal regions were considered. We used the more open PEO format, where population (P) included the human populations within the marine and coastal environment of the Baltic Sea region, exposure (E) related to the Baltic Sea ecosystems services and disservices, and the outcome (O) included all aspects of human health and well-being. After full-text screening articles selected for inclusion were searched for metadata connected to bibliographic information, ecosystem services, health and well-being outcomes and policy relevance. Review findings: Out of 6456 hits only 460 studies discussed either health or well-being indicators to some extent. Of these, only 67 explicitly mentioned ecosystem services and health and well-being indicators. However, few in this subset engaged with the topic of ecosystem services or disservices and health and well-being in depth. Studies are increasingly relating the two concepts but currently it is mainly studies focussed on cultural ecosystem services that deal with the concept of health and well-being to a greater degree. Studies in the medical literature relating to impacts on health from exposure to the Baltic Sea did not relate their findings to ecosystem services. The database of 67 studies is attached as Additional file 5. Conclusions: Ecosystem services play an important role in human health and well-being; however, we found few studies that explicitly examine these impacts in detail. Further research is needed to link the health and well-being outcomes from the Baltic Sea to the ecosystem services supplied and therefore to demonstrate the benefits and disservices provided by the Baltic Sea ecosystems to human populations.