Development of the National Land Cover Monitoring System for Nepal

Date 22 Aug 2022 to 26 Aug 2022
Venue ICIMOD, Nepal
Contact Persons servirhkh@icimod.org
Type Production workshop
Programmes SERVIR-HKH

About the workshop

We are organising a production workshop focused on the technology transfer and capacity building of the Forest Research and Training Centre (FRTC) team on the National Land Cover Monitoring System (NLCMS) for Nepal. The production workshop will guide FRTC professionals on deriving land cover ‘primitive’ elements for 2020 and 2021, assembling the data primitives into target land cover classes, and setting explicit accuracy assessment procedures.

Being organised under our SERVIR-HKH Initiative, the five-day event will train FRTC professionals in implementing image processing, developing primitives, data assembly algorithms, accuracy assessment procedures and implications, and document how these procedures can be run at FRTC independently.

Objectives

  • Share procedures for creating image composite and land cover primitive classes
  • Use Collect Earth Online (CEO) to collect reference data for the development of land cover primitives
  • Design, test, and refine procedures for assembling land cover primitives and other information sources into explicit land cover classes
  • Specify appropriate accuracy assessment procedures and products that provide critical context to data users. Finalise validation protocols and finalise data collection in Collect Earth Online (CEO) for validation, and
  • Refine the NLCMS logic and workflow further to meet identified FRTC needs

Expected participants

Selected professionals (about eight participants) from FRTC, who will work as a core team to continue land cover mapping for Nepal using methods developed for the NLCMS, will attend the training.

Expected outcomes

Upon completion of the workshop, FRTC professionals can independently adopt the NLCMS methods to generate land cover primitives and develop the land cover maps for Nepal for 2020 and 2021, respectively.

Key resource persons

Kabir Uddin

Kabir Uddin

GIS and Remote Sensing Specialist, ICIMOD
Sajana Maharjan

Sajana Maharjan

Remote Sensing and Geoinformation Analyst – SERVIR, ICIMOD
Deepak Kumar Shah

Deepak Kumar Shah

Geospatial Programmer/Application Developer, ICIMOD

Background

Land cover mapping is the most common application of Earth observation (EO) science, which renders meaningful information about the Earth’s surface. Using land cover data can help policymakers and land managers understand vast landscapes better and observe historical changes over time. An archive of national land cover data is a critical asset, particularly for Nepal.

FRTC with technical support from SERVIR-HKH, a joint initiative of the United States Agency for International Development (USAID), the National Aeronautics and Space Administration (NASA) and the International Centre for Integrated Mountain Development (ICIMOD), developed Nepal’s National Land Cover Monitoring System (NLCMS). Collaborators include SERVIR–Mekong at the Asian Disaster Preparedness Center (ADPC), SilvaCarbon, Global Land Analysis, and Discovery (GLAD) group at the University of Maryland, and the US Forest Service.

The NLCMS uses freely available remote-sensing data (Landsat) and a cloud-based machine learning architecture in the Google Earth Engine (GEE) platform to generate land cover maps annually using a harmonised and consistent classification system. The system was further customised from ICIMOD’s Regional Land Cover Monitoring System (RLCMS) for Nepal. The NLCMS generates spatially seamless and temporally consistent annual land cover maps of the country. These maps and data will be useful for national and international reporting on forest cover change, preparing a long-term strategy for achieving Nepal’s Nationally Determined Contribution targets, and as a foundational dataset for evidence-based planning and policy development.

 

Tentative agenda

  • Day 1
    Time Topics/Tasks Remarks
    9:15–16:45 Registration

    Background of the workshop and opening of the workshop

    Demonstration activity: Generate Landsat image composite

    Selection of Landsat imagery, image correction, preparation of annual composites, and image indices and covariates creation.

    ­­­Demonstration and activity: Collection

    ·        Point sample distribution

    ·        Set up Collect Earth Online (CEO) project

    Demonstration and activity: Collection of training points using CEO

    Reflection and review of the day

  • Day 2
    Time Topics/Tasks Remarks
    9:15–16:45 Collection of training points using CEO
    Demonstration and activity: Generate built-up layers
    Reflection and review of the day
  • Day 3
    Time Topics/Tasks Remarks
    9:15–16:45 Collection of training points using CEO

    Demonstration and activity: Exporting training samples

    Compilation and uploading the training sample in GEE

    Reflection and review of the day

  • Day 4
    Time Topics/Tasks Remarks
    9:15–16:45 Demonstration and activity: Generate land cover primitives (tree, water, crop)

    Review of the land cover decision tree

    Assemblage of Land cover using the land cover primitive

    Reflection and review of the day

  • Day 5
    Time Topics/Tasks Remarks
    9:15–16:45 Review and validation of the exported land cover

    Discussion on developed land cover and way forward and joint work plan for NLCMS Nepal

    Closing session

    Reflection and review of the day