Integrating Remote Sensing and in-situ observations of Biodiversity, towards a fully interoperable observation and data framework

Expected Outcome: Project results are expected to contribute to all of the following expected outcomes: advancing robust, policy-relevant ecosystem assessment, nature protection and restoration planning activities, and biodiversity trend prediction based on fit for purpose data, thus supporting EU biodiversity and climate objectives; strengthened capacity of researchers, practitioners and decision-makers to improve biodiversity monitoring practices and address knowledge gaps via the integration of data and observations across sensors and platforms, ranging from omics-based data (genomic, transcriptomic, metabolomic), various in-situ to satellite-based Earth observation data; enhanced usability of in-situ datasets as training and validation resources for statistical, machine learning and advanced AI-based approaches, in support of applications such as habitat classification, ecosystem mapping and biodiversity trend prediction. Scope: Achieving the goals of the EU biodiversity strategy for 2030 , the Kunming-Montreal Global Biodiversity Framework, and assessing progress towards their defined targets, requires coherent, integrated and long-term monitoring approaches, underpinned by FAIR (Findable, Accessible, Interoperable and Re-usable) data systems. Many existing in-situ data collections (i.e. genomic assessments, ground sampling, drone and airborne observations) were not designed with Satellite Remote Sensing integration in mind (i.e. for validation and calibration, integrated data products, or statistical scaling of information) and lack the structure, interface and metadata required to support advanced analytics, including AI. FAIR data on species and ecosystems will also help to ensure that biodiversity preservation is a mainstream feature of other sectors, such as agriculture, transport, energy or the bioeconomy. There is a need for systemic, harmonised or standardised biodiversity data at Earth’s surface in order to support AI applications ranging from genome to space and to build up our knowledge on the status and trends of habitats, species, ecosystems, and on the drivers of decline. To address these challenges, proposals should: develop and validate fit-for-purpose multisensory biodiversity data integration systems, to enable omics-based and in-situ data harmonization and integration with remote sensing data from space or sub-orbital platforms, as well as socio-ecological and climatic data for enhancing assessment of ecosystem condition and degradation, and the predictive modelling of biodiversity trends at international, regional and European sc…