The International Centre for Integrated Mountain Development (ICIMOD); the Asian Disaster Preparedness Center (ADPC); the Geospatial Service and Technology Center (GTAC), United States Forest Services (USFS); and SilvaCarbon are co- developing a flexible regional land cover monitoring system (RLCMS). The system will generate high-quality land cover/land use data to monitor land cover/land use and will conduct change analysis using a consistent regional classification scheme compatible with different national requirements. The system is being developed under SERVIR – a joint initiative of the United States Agency for International Development (USAID) and the National Aeronautics and Space Administration (NASA). The need for such a system was identified during multiple stakeholder consultations conducted at national and regional levels under the SERVIR Hindu Kush Himalaya (SERVIR-HKH) initiative at ICIMOD and the SERVIR-Mekong initiative at the ADPC. An RLCMS uses the architecture of cloud-based remote- sensing technology, such as Google Earth Engine (GEE), and a common set of data sources to generate high-quality land cover maps on a regular basis. ICIMOD and its partners are now convening a production workshop focused on building the capacity of partners and refining algorithms to derive key land cover “primitive” elements, determine methods for assembling the data primitives into target land cover classes, and decide explicit accuracy assessment procedures. The five-day event will train partners in the implementation of the primitives, data assembly algorithms, accuracy assessment procedures and implications, and documentation of how these elements of the system fit within the overall system. Objectives Besides developing a mechanism for the production of key RLCMS elements, this event will serve as a forum for discussion, consultation, and capacity building. The specific objectives of the workshop are as follows: Introduce and refine procedures for creating primitive classes Use Collect Earth Online to target the concentration of additional reference data to be used to improve the performance of the primitive classifier Design, test, and refine procedures for assembling data primitives and other information sources into explicit land cover classes Specify appropriate accuracy assessment procedures and products that will provide crucial context to data users Finalize validation protocols and develop a project plan for validating collected data in Collect Earth Online Further refine the RLCMS logic and work plan for meeting identified end-user needs Expected Outcomes The principal workshop outputs will be as follows: A set of explicit procedures and tools for combining data primitives and other information into final land cover classes as set out in the agreed regional typology Specification of reference data needs and procedures to support the (potentially iterative) accuracy assessment of land cover products produced by the RLCMS Refinement and endorsement of the roadmap for completing the remaining elements of the RLCMS