The framework’s architecture rests on three interlocking computational pillars. At its foundation lies a Markov chain analysis that quantifies historical land-use transition probabilities from observed satellite-derived land-cover maps spanning 2018 to 2021, generating a mathematical matrix where each cell represents the likelihood of one land class converting to another over time. This Markov-derived demand projection establishes how much of each land type should exist by 2050 under different assumptions. The second pillar employs a Random Forest classifier, an ensemble machine learning algorithm consisting of 400 decision trees, each trained to recognize the biophysical, climatic, and socioeconomic conditions under which specific land transitions are likely to occur. Unlike conventional CA-Markov models that rely on static heuristic suitability rules, the Random Forest approach captures nonlinear relationships between driving factors and land-change outcomes, effectively learning from 14 distinct predictor variables including elevation, slope, aspect, temperature, precipitation, population density, and Euclidean distances to roads, railways, commercial zones, industrial areas, hotels, villages, and suburban settlements. The third pillar is a cellular automata allocation engine that spatially distributes the projected land-use changes across the landscape, constrained by neighborhood interactions, transition resistance factors, and scenario-specific policy rules. The composite transition potential for each pixel is calculated as the product of Random Forest probability, a transition resistance multiplier, and a neighborhood influence term weighted by a tunable coefficient, producing a spatially explicit probability surface that guides where each hectare of change materializes.

What distinguishes this study from prior land-change modeling efforts is its insistence on transparency through the integration of Shapley Additive Explanations, or SHAP, an explainable artificial intelligence technique rooted in cooperative game theory. SHAP quantifies the marginal contribution of each driving factor to every individual prediction, revealing not only which variables matter most but also the direction and nonlinear threshold effects of their influence on land-use transitions. For instance, the method can reveal whether the probability of cropland converting to built-up area increases sharply once distance to a major road falls below a certain threshold, or whether population density exerts an accelerating rather than linear effect on urbanization probability. This interpretability layer transforms the modeling framework from a black-box predictor into a diagnostic instrument capable of informing policy debates. The researchers argue that most existing studies either emphasize prediction accuracy without explaining the mechanistic drivers of land transitions, or assess carbon storage without explicitly linking those transitions to future carbon dynamics, a gap that becomes particularly consequential in heterogeneous metropolitan regions where urban growth, agricultural abandonment, and vegetation recovery occur simultaneously and create competing carbon outcomes across relatively small geographic areas.

The study area itself presents an unusually rich test bed for the methodology. The Prague Metropolitan Area encompasses approximately 190,000 hectares of exceptionally diverse landscape within a compact geographic extent, where the Vltava River carves through rolling hills and river valleys, creating a mosaic of urban fabric, cropland, mixed forest, grassland, and wetlands. Between 2001 and 2021, the metropolitan population grew by roughly 22 percent, accompanied by well-documented conversion of agricultural land to urban development in peri-urban zones. This combination of rapid suburbanization, persistent agricultural activity, and forest regeneration within a single bounded region creates precisely the kind of spatially complex carbon trade-offs that the researchers sought to capture. Land-cover data were derived from the Esri Land Cover product, generated from Sentinel-2 satellite imagery at 10-meter resolution using a deep learning classification framework, with temporal snapshots analyzed for 2018, 2021, and 2024. The original nine-class global product was reduced to seven dominant classes relevant to the study area, with all layers reprojected to WGS 84/UTM Zone 33N and resampled to a consistent 10-meter grid. Driving variables were assembled from the ASTER Global Digital Elevation Model Version 3, WorldClim Version 2.1 climate normals, OpenStreetMap infrastructure vectors, and population density surfaces derived from Esri demographic datasets and Charles University spatial databases. Multicollinearity among predictors was assessed using Pearson correlation analysis and Variance Inflation Factor calculations on a random sample of 120,000 valid pixels, with only the elevation-temperature pair exceeding the conventional correlation threshold at r equals negative 0.93, a relationship retained because both variables represent distinct environmental processes and because Random Forest’s random feature selection mechanism renders it inherently robust to collinearity.

Three contrasting scenarios were constructed to bracket the plausible range of future land-use trajectories through 2050. The Business-as-Usual scenario projects continuation of historical 2018-to-2021 transition dynamics without policy intervention, deriving land demand directly from the observed Markov transition matrix. The Urban Growth Scenario accelerates built-up expansion by promoting conversion of cropland, grassland, and bare land to urban fabric near existing settlements, road corridors, and suburban zones, while simultaneously reducing ecological protection coefficients. The Ecological Optimization Scenario inverts these assumptions, promoting transitions toward tree cover, grassland, water bodies, and flooded vegetation while strongly restricting conversion of ecologically valuable classes to built-up land through enhanced protection coefficients and greater resistance to urban expansion. Under the Business-as-Usual projection, tree-covered areas increase from 44,927 hectares in 2021 to approximately 55,647 hectares by 2050, while cropland declines from 78,483 hectares to 65,000 hectares, reflecting continued land conversion pressures. The model was calibrated against observed 2018-to-2021 transitions and validated by simulating the 2024 land-cover map and comparing predictions against the actual Sentinel-2-derived classification, providing an empirical check on spatial accuracy before scenario projections were generated for the 2024-to-2050 period.

Carbon consequences were quantified by coupling each simulated land-use map to the InVEST Carbon Storage and Sequestration model, which estimates ecosystem carbon stocks across four pools: aboveground biomass, belowground biomass, soil organic carbon, and dead organic matter. Carbon density coefficients were assigned to each land class following IPCC Tier 1 guidelines for temperate zones, with trees storing 120 megagrams of carbon per hectare aboveground, 30 belowground, 90 in soil, and 2 in dead organic matter, for a total of 242 megagrams per hectare. Cropland, by comparison, stores only 97 megagrams per hectare across all four pools combined, while grassland stores 102 and bare land stores just 4. The resulting carbon storage maps reveal the spatial distribution of carbon across the metropolitan landscape under each scenario, allowing researchers to calculate the net carbon change between the 2021 baseline and each 2050 projection. A first-order sensitivity analysis was conducted by simultaneously increasing and decreasing all carbon density coefficients by 10 percent to evaluate how uncertainty in these parameters propagates into scenario-level carbon estimates, confirming that the relative ordering of scenarios remained robust across the tested coefficient range.

The implications extend well beyond Prague’s administrative boundaries. Central European metropolitan regions remain significantly underrepresented in machine learning-based land-use and carbon modeling literature, which has concentrated heavily on rapidly urbanizing regions in Asia and Africa. The Prague application demonstrates that the framework can handle the particular complexity of European peri-urban landscapes, where historical land tenure patterns, EU agricultural subsidies, and post-socialist land restitution create transition dynamics that differ substantially from those in developing-world megacities. The Czech Republic’s legal commitment under the EU Climate Law to restore its land-sector carbon sink provides an immediate policy context for the scenario results, transforming abstract model outputs into concrete decision-support information for planners weighing ecological restoration against development pressure. The researchers emphasize that the scenarios represent exploratory planning pathways rather than deterministic forecasts, designed to illuminate the consequences of alternative policy choices rather than to predict a single inevitable future.

The broader significance of this work lies in its demonstration that explainable artificial intelligence can be operationalized within environmental modeling pipelines at metropolitan scale, producing results that are simultaneously spatially precise, mechanistically interpretable, and directly relevant to carbon accounting frameworks used in international climate policy. As cities worldwide grapple with the dual mandates of accommodating population growth and meeting net-zero emissions targets, tools that can quantify the carbon consequences of specific land-use decisions in advance become increasingly indispensable. The Prague framework, released as open-source Python code, offers a transferable template for other metropolitan regions seeking to understand how the landscapes they shape today will determine their climate resilience tomorrow.

The central theme underscoring the workshop was “Evidence-based decision-making in the public sector.” This focus directed a series of meticulously planned sessions designed to probe the intersection of ecological science and practical policymaking. Over four intensive days, participants engaged in dynamic exchanges, sharing substantive updates on SELINA’s progress within its public Demonstration Projects. These interactions were aimed at refining methodologies and outputs to ensure their maximum applicability and impact in policy contexts.

Opening the workshop, project leaders presented an overview encapsulating recent advancements and upcoming objectives within SELINA’s multifaceted workstreams. Special emphasis was placed on urban ecosystem management, where strategies to enhance green infrastructure were explored in depth. Discussions illuminated the nuanced needs of decision-makers operating at various governance scales, from municipal to national levels, underscoring the importance of tailored approaches in ecosystem service application.

A pivotal segment of the workshop involved detailed presentations on the Compendium of Guidance (CoG), a cornerstone decision-support tool developed by SELINA. The CoG serves as an integrative framework facilitating the assimilation of complex ecological data into accessible formats for policymakers. Latest iterations of the CoG were showcased, highlighting enhancements aimed at broadening its utility within diverse public sector environments. This tool exemplifies how sophisticated scientific outputs can be rendered actionable for real-world decisions.

The workshop’s second day offered a compelling blend of field excursions and targeted working sessions. Participants immersed themselves in the Trento region’s rich biodiversity, with visits to Mount Bondone and the Viote Botanical Garden providing tangible experiences of nature-based solutions in action. These excursions underscored the importance of place-based knowledge and ecological context in shaping effective biodiversity strategies, reinforcing the principle that policy frameworks must be grounded in local realities.

Afternoon sessions on the second day revisited the strategies for communication, dissemination, and stakeholder engagement. Recognizing that scientific findings alone are insufficient to drive change, participants delved into methods of amplifying impact through effective engagement across public and private sectors. The dialogue emphasized bridging gaps between diverse stakeholders, fostering collaborative networks essential for cohesive and sustained ecosystem stewardship.

On the third day, the focus shifted towards the technical integration of ecosystem condition assessments, services valuation, and natural capital accounting within SELINA’s demonstration projects and test sites. Participants collaboratively refined datasets and aligned analytical outputs, laying the groundwork for forthcoming joint publications. A critical part of these discussions centered on ethical considerations and justice implications inherent in ecosystem assessments, highlighting how inclusivity and equity must permeate environmental governance.

Throughout the workshop, the ethical and justice dimensions of ecosystem service assessments were given particular attention. Discussions probed how procedural fairness and distributional equity influence both the legitimacy and effectiveness of ecological policymaking. These reflections signal a progressive shift toward embedding social sciences into environmental assessments, an approach vital for addressing complex societal-environmental challenges innovatively and responsibly.

The culmination of the workshop was marked by a ceremony that celebrated the collective achievements of the participants over the four days. Symbolically, stewardship of the SELINA initiative was handed over from the University of Trento to the Cohab Initiative and the Capitals Coalition. This transition signals a strategic pivot towards enhancing private sector involvement, recognizing the indispensable role businesses play in ecosystem management and biodiversity conservation.

Looking ahead, SELINA’s 7th workshop is slated to occur in Galway, Ireland, during the summer of 2026. This upcoming event is anticipated to foreground private sector engagement, advancing SELINA’s agenda of reinforcing the interface between science, policy, and business sectors across Europe. The evolution of this multidisciplinary dialogue underscores the project’s adaptability and its pivotal role in shaping holistic environmental governance paradigms.

The workshop’s format reinforced SELINA’s wider mission to provide actionable frameworks and tools that can be adapted and scaled within different governance contexts. By prioritizing both scientific rigor and practical usability, SELINA supports decision-makers in navigating the inherent complexities of biodiversity and ecosystem services within an increasingly anthropogenically altered landscape.

In sum, the 6th SELINA thematic workshop in Trento not only showcased interdisciplinary scientific collaboration but also emphasized the critical need for integrated analytical tools and stakeholder partnerships. The convergence of field experience, policy discourse, and ethical considerations provided a comprehensive platform to propel ecosystem service assessments from theoretical constructs to influential policy instruments.

For continuous updates and further insights, interested professionals and stakeholders are encouraged to explore the SELINA website and follow the project’s active social media channels on LinkedIn, Bluesky, and YouTube. These platforms ensure sustained engagement and dissemination, promoting transparency and inclusivity in the ongoing journey toward ecosystem-informed public sector decision-making.

Subject of Research: Evidence-based decision-making in biodiversity and ecosystem service assessments in the public sector.

Article Title: SELINA Project’s 6th Thematic Workshop Advances Science-Policy Integration for Ecosystem Governance

News Publication Date: October 2025

Web References:

• SELINA LinkedIn
• SELINA Bluesky
• SELINA YouTube

Image Credits: Pensoft Publishers

Keywords: Science communication, biodiversity, ecosystem services, evidence-based decision making, public sector, natural capital accounting, urban greening, ethical governance, stakeholder engagement

Significantly, the study delves into ecosystem service values, which encompass all the benefits that humans derive from the natural environment. Reforestation, soil conservation, and sustainable agricultural practices are just some of the watershed management interventions analyzed in the research. Each of these actions carries a unique set of consequences for the ecosystem, underlining the complexity of human-nature interactions in the model of sustainable development.

The researchers utilized an array of quantitative methods to estimate the impacts of these interventions. By employing scenario modeling, they were able to contrast baseline conditions against various management strategies. This rigorous analysis allows for a holistic view of potential outcomes, highlighting both short-term gains and long-term sustainability. This approach is particularly crucial for policy-makers, as it provides a scientific basis for decision-making in watershed management.

One particularly striking finding from the study is the role of watershed management in enhancing water quality. The researchers observed that practices aimed at reducing surface runoff contributed to significant improvements in water resources. By implementing vegetative buffers and contour farming, the region has not only witnessed improved infiltration rates but has also experienced a notable reduction in sedimentation in downstream water bodies. Such improvements are vital for local agriculture, fisheries, and drinking water supplies, reinforcing the need for sustainable practices that go beyond mere cultivation.

Further analyzing social dimensions, the study underscores how watershed management impacts local livelihoods. Households engaged in sustainable practices reported higher levels of food security and increased resilience against climate fluctuations. This facet of the research underscores the interconnectedness of ecological health and economic stability, providing a compelling argument for integrating environmental concerns into developmental agendas.

Climate change poses an increasing threat to watershed stability. The researchers incorporated climate scenarios to assess the robustness of their management interventions. Remarkably, the analysis indicated that proactive watershed management could mitigate some negative effects of climate variability, particularly in terms of rainfall distribution and soil moisture retention. Thus, the study offers hope that investing in ecological sustainability can serve as a buffer against climate uncertainties.

From a broader perspective, the implications of this research extend beyond local boundaries. As global interest in sustainable development heightens, the findings from the Yezat Watershed provide a microcosm for understanding the benefits of watershed management on a global scale. Effective models of sustainable practices can inspire similar initiatives worldwide, especially in regions facing similar environmental challenges.

While the research illuminates significant positive outcomes associated with watershed management, it also addresses the challenges inherent in implementing these strategies. Engaging local communities in the planning and execution of interventions is crucial for ensuring the success of these initiatives. The study advocates for participatory approaches, emphasizing that local knowledge is invaluable in crafting effective and culturally appropriate management solutions.

Investments in education and awareness-raising campaigns are also highlighted as essential components of successful watershed management. As communities become more informed about the benefits of sustainable practices, their willingness to adopt these methods increases. Empowering local populations through knowledge can create a sense of ownership over natural resources, fostering a commitment to maintaining eco-friendly practices.

Looking to the future, the researchers propose a series of recommendations based on their findings. Policymakers are encouraged to adopt integrative frameworks that consider ecological, social, and economic dimensions in watershed management. By prioritizing collaboration among various stakeholders, including government entities, NGOs, and local communities, a more comprehensive approach to ecosystem management can be attained.

In conclusion, the study by Andualem, Meshesha, and Hassen offers a breadcrumb trail towards a more sustainable future for the Yezat Watershed and similar ecological landscapes. Through rigorous analysis and a commitment to holistic management approaches, the researchers advocate for the profound impact that well-planned watershed interventions can have on both ecosystem services and human well-being. As the world grapples with the intricacies of climate change and environmental degradation, the lessons from Yezat stand as a testament to the power of adaptive management strategies in fostering resilience and sustainability.

In this age of ecological uncertainty, such insights are invaluable. Not only do they provide a foundation for future research, but they also encourage proactive policies that can combat environmental decline. By recognizing the essential value of ecosystem services and implementing sound management strategies, we can ensure a healthier planet for generations to come, thus fulfilling our responsibility to the Earth and its myriad inhabitants.

Subject of Research:

Article Title: Estimating the impacts of watershed management interventions and scenarios on ecosystem service values and functions in Yezat Watershed, North West Ethiopia.

Article References:

Andualem, Z.A., Meshesha, D.T. & Hassen, E.E. Estimating the impacts of watershed management interventions and scenarios on ecosystem service values and functions in Yezat Watershed, North West Ethiopia.
Environ Sci Pollut Res (2025). https://doi.org/10.1007/s11356-025-36933-z

Image Credits: AI Generated

DOI:

Keywords: Ecosystem services, watershed management, sustainability, climate resilience, social impacts, Ethiopia.