The broad suite of tools that are available signals an encouraging trend of demand among practitioners in both the public and private sector. It is imperative ,however, that these digital maps are underpinned by tested biodiversity models, with bounds of use that are understood and communicated clearly. Modelling biodiversity is a active and rapidly developing field of science, and will be elevated by including practitioners in the design process of these visualisation platforms to ensure model outputs meet the specific needs of practitioners and regulators.
Therefore, at the World Biodiversity Forum 2026, we are proposing a session called ‘Mapping Life’ with the explicit objective of convening both developers and users of biodiversity maps. The session will, by design, reach across disciplinary divides and offer an opportunity for practitioners and scientists to develop a shared understanding and vocabulary around the subject.
For examples of biodiversity mapping tools, see:
https://www.ibat-alliance.org
https://abc-map.fao.org
Fence is a globally ubiquitous form of linear infrastructure that interrupts animal movement, compromises population fitness, alters ecological processes, and diminishes landscape connectivity. However, fences are also widely used as conservation and land-management tools to mitigate human–wildlife conflict. Despite their significant relevance to biodiversity conservation, they remain largely absent from regional to global biodiversity assessments, in contrast to other linear infrastructures such as roads and railways. This omission stems primarily from the absence of large-scale spatial datasets and scalable, consistent mapping methods. Existing efforts rely heavily on field surveys or manual interpretation of remote sensing imagery, both of which are time-consuming, labor-intensive, and difficult to scale, thereby limiting their broader applicability and long-term utility.
Here, we introduce FenceMapper, an AI-driven framework for accurate and scalable fence detection using multi-scale segmentation of high-resolution remote sensing imagery. A local model extracts fine-scale fence features from small image patches, while a global refinement model improves structural continuity by incorporating broader contextual information and reducing fragmentation. Using 972 sampling sites containing 24,632 km of fences and more than 170,000 image patches across western U.S. rangelands, we trained and evaluated the framework and demonstrated robust performance: FenceMapper achieved 77% correctness, 75% completeness, and 76% quality under a 10 m tolerance, with highly consistent fence-length estimates (R² = 0.83). We then scaled the workflow to map 740,283 km of fences across the rangelands of the western United States, producing the most comprehensive sub-continental fence dataset to date.
FenceMapper and the resulting open-access dataset provide a critical missing layer for biodiversity monitoring. For example, ecologists can pair spatial fence location with animal tracking or occurrence data to assess how fences alter animal behavior and influence community dynamics. Large-scale spatial fence density complements current landscape connectivity assessment, hence provides critical information for landscape-level conservation prioritization across diverse ecological settings. This work demonstrates how remote sensing and AI can address key gaps in global biodiversity observation systems and strengthen the integration of structural landscape information into conservation planning and decision support.
How to cite: Li, W., Hu, Z., Liu, M., Lv, Z., Huo, X., Ye, J., He, C., Fu, H., Barker, K., Dodhia, R., Ferres, J. L., Merkle, J., Middleton, A., Mueller, T., Stabach, J., Miao, Z., and Xu, W.: AI-driven fence identification and mapping for large-landscape conservation, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-567, https://doi.org/10.5194/wbf2026-567, 2026.
Restoring degraded ecosystems is essential for recovering biodiversity as well as increasing the benefits nature provides to people. There is increasing evidence that investing in ecosystem restoration provides multiple net benefits. While restoration efforts have been traditionally funded by public institutions, the need for private sector’s investment and engagement in restoration is becoming increasingly important. There is also increasing interest from the private sector in investing in restoration efforts. However, it is challenging to know where restoration investments and efforts will make the biggest impact for both nature and people. This study aims to address this gap by identifying priority areas for ecosystem restoration by integrating biodiversity and socio-ecological criteria. It highlights where restoration investments can deliver the greatest ecological returns. We developed a global restoration opportunities layer intended to help screen locations where ecosystem restoration can deliver multiple benefits. Our analysis focused on global terrestrial and coastal areas that are not currently built up or under active cultivation. Spatial planning is a powerful tool that can help with decision making on where to restore by prioritizing the most efficient areas. We conducted spatial prioritization analyses to find areas that maximize the potential co-benefit of restoration for both nature and people. The analysis incorporated multiple datasets, including rarity-weighted species richness, useful plant species, key ecosystem types and globally recognized conservation sites. We also included areas that provide important Nature’s Contributions to People, such as carbon sequestration, water quality regulation, and coastal protection. Our resulting global map highlights locations with restoration opportunities ranging from highest to lowest priority. Based on these findings, we suggest how to evaluate where restoration investments and interventions can have the most impact. These findings can guide global investment in restoration initiatives and help contribute towards countries achieving their restoration targets such as Target 2 of the Kunming-Montreal Global Biodiversity Framework.
How to cite: Kamath, V., Harris, M., Fajardo, J., Arnell, A., van Soesbergen, A., Telhado, C., Miles, L., Worthington, T., and Bhattacharjee, A.: Mapping global opportunities for ecosystem restoration, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-774, https://doi.org/10.5194/wbf2026-774, 2026.
First proposed in 2005, the Biodiversity Intactness Index (BII) is a measure of ecological integrity. BII estimates the overlap between sites’ present-day ecological assemblages and their condition prior to marked anthropogenic change. It ranges from 100% (the assemblage is essentially intact) down to 0% (any species present are not native) and can be averaged across any region of interest. The PREDICTS project estimates BII from statistical models that relate biodiversity to land-use and related pressures, using our compilation of biodiversity survey data from over 50,000 sites worldwide that includes a taxonomically representative set of 75,000 plant, invertebrate and vertebrate species. As a model-based indicator, BII can be projected at high spatial and temporal resolution, so has a wide range of scientific, policy and commercial uses. Our first global estimate (in 2016) showed that BII had already fallen below the proposed planetary boundary of 90%, even though several limitations meant it underestimated losses at that time. We have been improving our input data, analytical methods and software engineering throughout the ten years since then. In this talk, I show these have overcome many of the problems with our early estimates of BII, and allowed us to now estimate both it and PDF (the potentially disappeared fraction of species) at kilometre resolution for each year since 2000.
Since 2023, our work has received support from Bloomberg via a data licence with the Natural History Museum. I will describe how Bloomberg combine their database of physical assets with global BII data produced by the Natural History Museum to provide summaries of biodiversity-related risks for nearly 50,000 companies. These insights form part of the sustainability data available to over 350,000 Bloomberg Terminal subscribers, helping investment professionals to make more nature-positive investment. Lastly, I will outline ongoing and planned developments, such as incorporating a broader range of drivers – including climate change – into our projections.
How to cite: Purvis, A., De Palma, A., Contu, S., Duffin, C., McGinty, C., and Walkden, P.: The Biodiversity Intactness Index: a model-based indicator of ecological integrity, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-177, https://doi.org/10.5194/wbf2026-177, 2026.
Amidst the ongoing biodiversity crisis, there is high demand for spatially explicit biodiversity indicators that can support conservation planning and national reporting. Global models that estimate the impacts of human pressures on biodiversity provide crucial insights, but their use in spatial projections calls for more systematic evaluation of how accurately they can predict biodiversity patterns at fine spatial scales. This is especially important because spatial projections require models to make predictions under a wide range of environmental and geographic contexts. Here we evaluate the generality of two different pressure-response models for estimating alpha and beta diversity, relative to ecologically intact reference sites, using a global dataset of 25,987 sites from 681 biodiversity studies. Generality is operationalized as the model accuracy when making out-of-sample predictions in sampled populations (generalizability) as well as in other contexts (transferability).
We find that mixed models with study-level random effects – commonly used in meta-analyses and forming the basis of several biodiversity indicators – exhibit generally low site-level accuracies. This reflects dependence on a limited set of averaged fixed effects and strong attribution of variation to the random effects, which cannot be used out-of-sample. In comparison, a model structure that incorporates biogeographic–taxonomic attributes together with environmental covariates achieves higher accuracy within contexts represented in training data. However, accuracy is low when predicting into new contexts, due to distribution shifts between training and test data. These patterns hold for both site-level diversity measures and for differences between paired sites.
Although both models estimate consistent and reasonable responses to land use, the results illustrate a large gap between effect-size inference and spatially explicit prediction. Models are essential for informed conservation efforts, but their applicability is fundamentally constrained by the availability and distribution of underlying data. Whereas countries with extensive data can build high-fidelity national indicators, accelerated data collection and macroecological model development are needed to better support data-poor regions with actionable biodiversity insights.
How to cite: Nyström, J., Smith, J. R., Mandle, L., Gonzalez, A., Schön, T. B., and Andermann, T.: Global data gaps contribute to low predictive accuracy in human pressure-based biodiversity models, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-904, https://doi.org/10.5194/wbf2026-904, 2026.
This abstract’s objective is to showcase how the MapBiomas initiative serves as a model of disruptive innovation for Land Use and Land Cover (LULC) mapping, achieved through a decentralized, network-based, and bottom-up approach. By providing a 40-year time series of LULC data—delivered entirely free and open-access and at unprecedented scale across Brazil and 14 other tropical countries—MapBiomas is fundamentally changing how conservation efforts are planned and executed. MapBiomas is a global, multi-institutional network formed by universities, NGOs, and technology companies that monitors changes in land cover and land use in different territories and their impacts. It provides the most up-to-date and detailed spatial database on land use in a country available in the world. All data, maps, methods, and codes are available to the public free of charge.
MapBiomas products not only allow users to tell the story of each little pixel of their countries’ territories, but also provide the tools and data for conducting complex analysis on ecosystems’ distribution and dynamics, and biodiversity threats like deforestation, mining, agriculture, fire, etc. This level of detail and temporal coverage is made possible by MapBiomas' pioneering network approach and use of satellite imagery, machine learning, and cloud computing. This fully automated, high-throughput methodology ensures transparency, scalability, and the timely production of data essential for effective spatial prioritization under post-2020 CBD targets.
The data's practical relevance will be highlighted through real-world applications, demonstrating its use in critical areas like the assessment of threatened species vulnerability and the monitoring of protected areas effectiveness—directly meeting the demand among practitioners and regulators for robust, actionable information.
Ultimately, the event aims to illustrate how collaborative, open-access platforms, underpinned by tested, scalable biodiversity models, are key to achieving resilient conservation action. By equipping a wider range of stakeholders with the information needed to make informed, spatially explicit decisions and respond effectively to environmental threats, MapBiomas exemplifies the essential role of convening developers and users to advance the science and practice of 'Mapping Life'.
How to cite: Del Lama Marques, C., Azevedo, T., Shimbo, J., and Rosa, M.: Mapping LULC for action planning, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-831, https://doi.org/10.5194/wbf2026-831, 2026.
As we approach the short- to medium-term implementation deadlines of major international biodiversity agreements, such as the United Nation's Kunming-Montreal Global Biodiversity Framework and the European biodiversity strategy, there is a pressing need for high-quality data products to guide large-scale conservation prioritization decisions. In this study, we implement a deep learning segmentation approach for detecting high-conservation-value forests using a nationwide inventory dataset and a set of remote sensing data products. Using this model we produce a national data product showing remaining high-conservation value forests in Sweden, with a predictive accuracy of 91% and a high-detail spatial resolution of 10-meter pixel size. Sweden serves as a good test case for the developed approach, as it is home to a large portion of Europe's remaining old-growth forests and is also characterized by robust biodiversity and environmental data availability. Our approach allowed us to identify over 50,000 km² of potential high conservation value forest (HCVF) at high confidence, which has the potential to considerably improve efficiency in manual inventory efforts. With its high accuracy and spatial resolution, our data product offers substantial utility for decision-makers at different administrative scales, and directly addresses the goals set by large international biodiversity conservation plans. The implemented approach demonstrates the utility of mapping structural ecosystem metrics to identify sites of particular conservation interest. This is partly enabled through the availability of high-resolution airborne LIDAR data, which are available as national data products in several countries. With improving availability of new global remote sensing data products, the prospect of mapping ecosystem structural intactness becomes increasingly feasible on a global scale. While this project focuses on detecting high conservation value forests in Sweden, the presented model serves as a proof-of-concept implementation that can be adapted and applied for modeling other regions and habitat types.
An interactive version of the data product can be found here: https://gee-hcvf-andermann.projects.earthengine.app/view/hcvf-viewer.
How to cite: Andermann, T., Häggmark, J., Olsson, P., and Högström, A.: BIOSCANN - A national scale predictive model for the detection of high-conservation value sites from remote sensing data, World Biodiversity Forum 2026, Davos, Switzerland, 14–19 Jun 2026, WBF2026-514, https://doi.org/10.5194/wbf2026-514, 2026.
