heading 1

heading 2

heading 3

heading 4

heading 5
heading 6


(Improved Data Extraction and Screening)
Microlab Leader: Yifei Liu ☉
Lisa Gaudette ❍ Vladislav Gerasimov ❍ Sherin Thomas ❍ Leland Werden ❍

Vision: The Assisted Forest Regeneration (AFR) Lab is working to build the most comprehensive understanding of assisted restoration outcomes to date. To make this happen, we are integrating an incredible wealth of information on restoration outcomes, both from the traditional academic literature as well as “gray literature” (sources that are not published in the academic literature). This is akin to drinking from a knowledge firehose—so we need your help to refine an existing tool that helps distill this information into easily digestible ecosystem recovery nuggets. Our ultimate goal is to produce the first global model of assisted forest restoration carbon accumulation potential, which restoration practitioners around the world can use to refine how they implement their interventions. This will be a dynamic model that continually improves as we are able to gather more data on assisted restoration outcomes from around the world.

Problem Statement: To rapidly screen abstracts and titles of potential data sources to determine their relevance, the research team carrying out the literature review has been using ASReview, an open-source machine learning tool that helps to determine and tag the relevance of text-based data sources. ASReview helps tremendously to speed the review process, but currently only has functionality to label each data source as relevant or not-relevant. This means that after articles are marked as relevant, they must be screened a second time in a separate workflow to determine what kinds of information they contain. Adding the ability to add tags to data sources in ASReview would speed up this second screening round as key pieces of metadata would already be associated with data sources.

Proposed Solution: Our MicroLab will have two goals:

Part 1: Add frontend functionality to ASReview to allow the user to add tags to an article from a list of user-specified keywords (see mockup below)

Part 2: Add backend functionality to ASReview that suggests tags for each article reviewed based on keyword matching, which a user can then update.

Skills needed: We are looking to assemble a team to work on adding frontend and backend functionality to ASReview. Work will include assessing the ASReview tech stack, estimating the extent of work needed, and doing the frontend and backend web development to add a tagging feature to ASReview. ASReview is written in Python and JavaScript, so experience with those languages as well as with React is preferred.

Total number of hours per week needed: A team of 2-3 frontend and backend developers working about 4 hours/week​​ 1-2 months (estimate subject to evaluation of the tech team). The team will meet remotely on a weekly basis.

To participate in this MicroLab, please email us by July 23 at team@collaborative.earth.

Relevant Links:
AFR Lab description
Github repository
ASReview website
Documentation for ASReview

What it currently looks like:

Possible solution:

Coastal Wetland Forests
Elliott White Jr

The goal of our lab is to create a high-spatial resolution map of coastal forested wetlands at global scale. If we know precisely where these ecologically critical but fragile forests are located, we can manage freshwater flows to counteract saltwater introgression due to rising sea levels, and we can assist in their migration inland, preserving their critical function in protecting coastlines and sequestering carbon.

Jason Baldes
Gisel Booman

Across the continent, a number of first nations are in the process of reintroducing bison to the grasslands in which they were once the primary grazer and an ecologically vital species. Initial experiences and evolutionary considerations suggest that this may be ecologically beneficial in terms of grassland biodiversity, carbon cycle, and resilience to climate change. However, these questions have not yet been studied at scale. In this lab, we will leverage remote sensing to scale up from ground measurements, establishing the large-scale patterns of bison impact.

Riparian Ecosystems
Forrest Pound

Beaver dams are known to result in greener, more drought-resilient waterways in semi-arid environments. We are using computer vision to spot dams in satellite imagery, generating a large dataset that we can use to train models that will tell us what the ecological effects of a dam will be at any point on a waterway. The goal is to create a tool to guide efficient restoration through the introduction of small dams.

Bundled Ecological NFT
Philip Taylor

Markets in voluntary carbon credits are increasingly providing a flow of capital for regenerating ecosystems. The problem is, thriving and resilient ecosystems are not just carbon. We need to find ways to structure credits to incentivize the diverse and functional ecosystems we want, not merely high-concentrations of carbon. We will design the technological tools to support a market in bundled ecological credits.

Global Forests
Aron Boettcher

We are building an accurate and global model for predicting potential rates of reforestation and resulting carbon sequestration. Such a model could have a transformational impact on global reforestation efforts by opening new streams of financing in the form of carbon credit futures.

Impact & Risk
Aaron Hirsh
Valérie Lechêne

Leveraging The Earthshot Institute’s broad scientific and technical expertise, the Impact and Risk Lab helps investors and governments who earnestly want to forecast, measure, and address the socio-ecological risks to and/or impacts from their work. For a given system, we build simple process-based models to identify key socio-ecological risks and outcomes. We then draw on big data to improve and train our models, generating quantitative predictions and developing measurement systems for verification.

No items found.
Register for the

Earthshot Institute Launch Event
Fri April 22