SWIO 30*30: A social-ecological approach to identify marine priority areas for conservation under the Kunming-Montreal Global Biodiversity Framework in the South West Indian Ocean region.
Bibliographic record
Abstract
The SWIO 30*30 project is a social-ecological initiative focused on identifying priority marine conservation areas across the South West Indian Ocean (SWIO) region to meet the Kunming-Montreal Global Biodiversity Framework goal of protecting 30% of terrestrial and marine areas by 2030. SWIO marine ecosystems, while hosting exceptional biodiversity, face high ecological pressure from overfishing, pollution, and habitat loss. Despite these challenges, the coverage of Marine Protected Areas (MPAs) across this region remains low, with most countries far from the 30% protection target. This situation highlights the urgent need for strategic conservation planning that is tailored to SWIO’s unique ecological and socio-economic contexts. This project is built on our previous successful Peru 30*30 project, which provided promising results for expanding Peruvian protected areas through a combination of scientific methods and local stakeholder engagement. The current objective is to provide a framework for conservation planning in SWIO marine areas (for Madagascar, Mozambique, Mayotte, Reunion, Comoros) that not only promotes biodiversity but also enhances ecosystem services essential for local communities, such as carbon storage, food provision, and cultural values. To answer the project’s core research questions—namely, identifying priority areas for marine conservation and understanding how to balance various conservation factors—the SWIO 30*30 project adopts a transdisciplinary approach that involves three main methodological components. First, it integrates diverse data, combining information on biodiversity, ecosystem services, and socio-economic factors. These data can be sourced from both space/in situ earth observation agencies (e.g. ESA, CNES) and environmental marine monitoring programs (e.g. CMEMS Copernicus), ensuring that the conservation planning process is informed by high-quality, contextually relevant data. Second, it applies advanced artificial intelligence techniques, including mathematical optimization methods, to address the multi-objective complexity of marine conservation planning. These AI tools allow for more sophisticated prioritization of conservation areas by handling the high combinatorial demands of multi-factor decisions. Third, the project follows a stakeholder co-production model, involving local communities and decision-makers throughout the process. This collaboration increases the transparency, acceptance, and practical utility of conservation recommendations, improving the chances that the proposed MPAs will be adopted and managed effectively at the national level. To adapt conservation strategies to the specific regional needs, the project evaluates four different scenarios: (1) a Biodiversity scenario, focused solely on preserving biodiversity; (2) a Socio-ecological scenario that adds ecosystem services such as carbon storage, food provision, and cultural values; (3) a Pragmatic scenario that incorporates human impacts (e.g., fishing, sea transport) alongside ecological considerations; and (4) an Integrated scenario that combines all previous factors with an emphasis on ecological connectivity. These scenarios will allow decision-makers to weigh conservation trade-offs and synergies and identify the best path forward for MPAs. By offering a context-sensitive and data-driven framework, SWIO 30*30 aims to contribute not only to SWIO biodiversity and ecosystem services conservation but also pave the way to broader global efforts, potentially serving as a model for other biodiverse yet under-protected marine regions worldwide.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".