Accurately Map and Monitor Deforestation

Intro

Regular monitoring of deforestation activities

The economic, social, and environmental impacts of deforestation can be drastic. However, due to the vast areas and inaccessibility of rainforest, monitoring deforestation is a huge challenge. Satellite monitoring enables the true extent of deforestation to be understood through regular, automated, and accurate deforestation mapping.

Overview

High-resolution satellite imagery

Access a vast library of archive Pleiades imagery and task a satellite at regular intervals, guaranteeing high-quality capture at a low cloud coverage.

Deforestation mapping algorithms

Assess the area of deforestation from one satellite image to another to get ongoing insights into the level of deforestation in your area of interest.

Automate and integrate insights

Use our Python SDK to automate and scale analysis, parallelizing jobs for large AOIs and seamlessly integrating insights into your own tools via API.

Benefits

Benefits for you

Receive regular imagery as it becomes available through our vast archive of high-resolution satellite imagery.
Alongside satellite imagery, access even higher-resolution aerial imagery to zoom in on specific areas.
Access a range of out-of-the-box change detection, land use classification, and deforestation mapping algorithms.
Access future satellite imagery to track changes to forest coverage, utilizing our bespoke tasking service.

Benefits for your customers

Avoid costly, arduous in-person deforestation monitoring and tracking by taking a remote, automated approach.
Save time by using deforestation mapping algorithms, avoiding the requirement to interpret imagery manually.
Avoid adding another software platform to your stack. Receive insights directly in existing tools via API.

Build your solution with UP42

Deforestation monitoring for:

Environmental Protection

Protect the natural environment by identifying areas and quantifying the loss where excessive or illegal deforestation has occurred.

Land Use and Management

Understand and analyze land-use changes in vast areas, identifying where the forest has made way for farmland.

The technical details

How can you use UP42 to build deforestation monitoring solutions?

Data

High-quality satellite imagery

Stream high-resolution Pleiades imagery into your analytics workflow in UP42. For historical deforestation mapping, you can access UP42's vast library of archive imagery, paying only for your AOI and picking images with low cloud coverage. For guaranteed regular imagery for your AOI, you can task a satellite with UP42 to be used in your UP42 workflow.

Processing

Map deforestation over time

With an out-of-the-box deforestation mapping processing block from Vasundharaa, you can quickly and easily map the change in forest area between two Pleiades images using temporal analysis. This deforestation mapping block is also compatible with Sentinel-2, Landsat-8, and SPOT 6/7 imagery.

Insights

Download or integrate outputs

The deforestation mapping block generates a georeferenced binary image where white pixels represent deforested areas. In addition to the binary image, the block generates a deforestation heatmap. These inputs can be easily downloaded, fed directly into your Google Cloud or AWS storage, or integrated via API into your products or your customers' solutions.

API & Python SDK

Automate your analysis

Build and automate analytics workflows leveraging UP42's infrastructure but working in Jupyter Notebooks or other command-line tools. With our Python SDK, you can access all the functionality of the UP42 platform within the command line, enabling UP42 to work seamlessly within your existing processes, interacting with your regular analytics workflows, tools, and libraries.

Access our Python SDK

import up42
up42.authenticate(project_id="12345", project_api_key="12345")
project=up42.initialize_project()

workflow = project.create_workflow(name="Deforestation", use_existing=True)
input_tasks=['oneatlas-pleiades-aoiclipped','deforestation']
workflow.add_workflow_tasks(input_tasks=input_tasks)
parameter = workflow.construct_parameters(
    geometry=[13.41686, 52.51167, 13.422503, 52.514706],
    geometry_operation="intersects",
    start_date="2020-01-01",
    end_date="2020-10-14",
    limit=2)

job = workflow.run_job(input_parameters=parameter, track_status=True)
job.download_results()

Use case