Are the communities most vulnerable to climate risk properly represented in open map data? Open map data underpins emergency dispatch, evacuation routing, and disaster relief. But coverage is often uneven.

Our hypothesis is that the communities most exposed to climate risk are also among the least well-mapped. Where those gaps overlap with wildfire corridors, extreme-heat cities, and drought-prone tribal lands, the consequences can be life-threatening.

Your task is to measure coverage gaps in Overture Maps across U.S. Census tracts by comparing it against Census TIGER/Line Roads, Microsoft US Building Footprints, USGS National Map critical facilities, and Census County Business Patterns establishment counts. Every submission is then automatically evaluated against the CDC Social Vulnerability Index (SVI), the U.S. Climate Vulnerability Index, tribal land boundaries, and hazard data for heat, wildfire, and drought. That evaluation is the bias scorecard described below and requires no work on your part.

The challenge covers four pre-packaged study regions, each provided as a ready-to-use data package requiring no geospatial preprocessing: Maricopa County AZ (heat and drought), the Northern California fire corridor (wildfire), Eastern Oklahoma tribal statistical areas (drought and heat), and South-Central Texas along I-35/I-37 (heat and drought). All scored tracts fall within these four regions.

Each region spans hundreds to thousands of Census tracts across the urban-rural spectrum and includes tribal lands. Scored tract counts are Eastern Oklahoma 1,192; Maricopa 1,593; Northern California 591; and South-Central Texas 6,003. One membership note: the Maricopa package is 1,592 Arizona tracts plus one New Mexico tract, 35023970000 (Hidalgo County, Tract 9700), which the region boundary meets at the state line.

This challenge also pilots a new Bias Score (built by Humane Intelligence and Zindi) that automatically evaluates every submission not just for accuracy, but for equity too. While traditional data science challenges evaluate submissions based on accuracy alone, this challenge also values the question: accurate for whom?

Every submission receives a full bias scorecard alongside your leaderboard score: how do coverage gaps fall across rural vs. urban tracts, tribal vs. non-tribal, high-SVI vs. low-SVI, and communities facing high heat, wildfire, or drought exposure? After this challenge, the API will be available for future Zindi challenges across domains.

Humane Intelligence is a 501(c)(3) nonprofit dedicated to breaking down barriers to AI deployment for social good. We collaboratively design and run rigorous evaluations that make AI systems more accountable, responsible, and fair. The Bias Score piloted in this challenge is Humane Intelligence infrastructure that makes disparity measurement a standard feature of data science challenges.

Radiant Earth is an open geospatial data commons that accelerates climate action by making Earth observation data and machine learning tools accessible to all. Radiant Earth provides the Overture Maps query infrastructure and geospatial support for this challenge.

This challenge is made possible with generous support from the Heising-Simons Foundation.

🥇 1st place: $4500 USD

🥈 2nd place: $2500 USD

🥉 3rd place: $1500 USD

Best Bias Discovery: $1000 USD. Most impactful coverage gap pattern not captured by the automated API, with a narrative contextualizing who is affected and what the real-world consequences are for disaster preparedness or climate resilience.

Best Documentation: $500 USD. Clearest, most reproducible methodology writeup. Document your data sources, how you computed each component, how you handled edge cases (zero-population tracts, water-dominated tracts, tracts with no Overture data), and any alternative weightings you applied and why.

There are 10 000 Zindi points available. You can read more about Zindi points here.

The error metric for this competition is Root Mean Squared Error. Submissions are scored by RMSE against organiser-computed reference coverage gap scores.

The coverage gap score is a composite between 0 and 1 per tract, where 0 means full coverage and 1 means no coverage. It combines three components:

• Road network gap: compare Overture road length per tract against Census TIGER/Line Roads, using named-highway classes only: TIGER MTFCC in (S1100, S1200) against Overture class in (motorway, trunk, primary, secondary). Note that transport gap values are not comparable across regions: Overture and TIGER draw the primary/secondary boundary differently in each region, and the ratio of the two ranges from 0.71 to 1.59 across the four study regions.
• Building footprint gap: compare Overture building counts per tract against Microsoft US Building Footprints. ACS housing unit counts are a sanity check only and are not part of the ratio: ACS counts housing units where Microsoft counts structures, so using ACS as a floor on the denominator manufactures an urban coverage gap out of dwelling density.
• POI gap: the mean of two halves. The facilities half is the mean of three per-type gaps (fire stations, EMS stations, and schools), each comparing Overture places in that category against USGS National Map facility counts. The establishments half compares all Overture places against Census County Business Patterns establishment counts. Hospitals are deliberately excluded: Overture’s hospital category runs about 12 times the reference count overall, so the term can never show a deficit.

The reference score is the mean of the components that are defined for that tract. A component is undefined when there is no reference to compare against (no named-highway road in the tract, no building footprint, no facility or establishment), in which case it is excluded from the mean, so the divisor varies by tract rather than always being three. This is not a rare case: at least one component is undefined in 21% of Eastern Oklahoma tracts, 37% of Northern California, 28% of South-Central Texas, and 55% of Maricopa, where over half the region has no named-highway road to score against.

The scored coverage gap computation must use only the datasets provided for this challenge; additional data sources are permitted only for the Best Bias Discovery prize.

To make a submission:

1. Compute a coverage gap score for every tract ID in the sample submission file, reference/<region>/<region>-sample-submission.csv. That file is the authoritative scored tract list for its region. Read GEOID as text, not as a number: Maricopa is FIPS 04, and reading the column as an integer drops the leading zero and breaks every join.
2. Format your submission as a CSV with the tract GEOID and your coverage gap score, following the sample submission on the Data page. Component scores may be included as optional columns. Fill every row of every column you include; a blank cell in an included column will cause the submission to be rejected, with the column named in the error.
3. Upload on the Zindi challenge page. You may submit up to 10 times per day, 300 total.

Every submission also automatically receives a Bias Score. Alongside your RMSE, your bias scorecard shows five equity metrics (Coverage Disparity Ratio, POI Desert Index, Emergency Access Gap, Road Network Equity Ratio, and Climate-Justice Composite) broken down across strata: urban/rural, social vulnerability (SVI), climate vulnerability (CVI), tribal vs. non-tribal, and hazard exposure (heat, wildfire, drought). The bias scorecard does not affect challenge leaderboard ranking, but participants are encouraged to reflect on it in their methodology writeups.

Read more about the Bias Score here

How to Compete for Best Bias Discovery

Both special prizes are judged from the methodology writeup submitted with your entry; no separate submission is required. For Best Bias Discovery, include a clearly labeled section in your writeup that does three things:

Identify a disparity pattern the automated scorecard does not surface. The API evaluates five fixed metrics across predefined strata; a discovery lives outside that grid. Examples: an intersection the strata miss (colonias within otherwise low-gap counties), a pattern within a stratum (gaps concentrated in post-disaster rebuilt areas rather than rural areas generally), a data source behavior (coverage varying by which upstream dataset feeds Overture), or a stratum you construct yourself from the provided tables or from additional public data.

Show the evidence. Name the tracts or areas involved, the data and comparisons behind the finding, and enough detail that judges can reproduce it from the challenge data.

Explain who is affected and why it matters. Connect the pattern to concrete consequences for emergency dispatch, evacuation routing, or disaster relief in the affected communities.

For this prize only, discoveries may draw on additional public datasets beyond those provided (for example, broadband access, language isolation, flood exposure, or colonias registries). Any additional source must be publicly accessible, openly licensed, documented in your writeup with URLs and retrieval dates, and reproducible by the judges. The scored coverage gap submission itself must still use only the provided datasets.

The strata tables in the data package carry far more detail than the API uses (232 columns), so there is plenty of room to find patterns the scorecard cannot see. A submission does not need a top leaderboard score to win this prize.

Entries for Best Bias Discovery are judged from the writeup by the organizing team against four criteria:

• Impact (30%): the pattern connects to concrete consequences for emergency dispatch, evacuation routing, or disaster relief in the affected communities, specific to the places and people involved rather than generic;
• Novelty (25%): the pattern lives outside the automated scorecard, not a restatement of one of the five metrics across the predefined strata;
• Evidence (25%): the tracts or areas are named, the comparisons are sound, and the size of the disparity is quantified;
• Reproducibility (20%): judges can reproduce the finding from the challenge data and any documented additional sources.

Entries whose findings cannot be reproduced, or that rely on undocumented or non-public sources, are not scored. Ties are broken by earlier submission.

• Languages and tools: You may only use open-source languages and tools in building models for this challenge.
• Who can compete: Open to all
• Submission Limits: 10 submissions per day, 300 submissions overall.
• Team size: Maximum team size of 4
• Public-Private Split: Zindi maintains a public leaderboard and a private leaderboard for each challenge. The public leaderboard includes approximately 30% of the test dataset. The private leaderboard will be revealed at the close of the challenge and contains the remaining 70% of the test set.
• Data Sharing: CC-BY SA 4.0 license
• Code Review: Top 10 on the private leaderboard will receive an email requesting their code at the close of the challenge. You will have 48 hours to submit your code.
• Code sharing: Multiple accounts, or sharing of code and information across accounts not in teams, is not allowed and will lead to disqualification.

ENTRY INTO THIS CHALLENGE CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL CHALLENGE RULES.

Full Challenge Rules

This challenge is open to all.

Teams and collaboration

You may participate in challenges as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the challenge, minus the total number of submissions among team members at team formation. Prizes are transferred only to the individual players or to the team leader.

Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be immediately disqualified from the platform.

Code must not be shared privately outside of a team. Any code that is shared, must be made available to all challenge participants through the platform. (i.e. on the discussion boards).

The Zindi data scientist who sets up a team is the default Team Leader but they can transfer leadership to another data scientist on the team. The Team Leader can invite other data scientists to their team. Invited data scientists can accept or reject invitations. Until a second data scientist accepts an invitation to join a team, the data scientist who initiated a team remains an individual on the leaderboard. No additional members may be added to teams within the final 5 days of the challenge or last hour of a hackathon.

The team leader can initiate a merge with another team. Only the team leader of the second team can accept the invite. The default team leader is the leader from the team who initiated the invite. Teams can only merge if the total number of members is less than or equal to the maximum team size of the challenge.

A team can be disbanded if it has not yet made a submission. Once a submission is made individual members cannot leave the team.

All members in the team receive points associated with their ranking in the challenge and there is no split or division of the points between team members.

Datasets, packages and general principles

The solution must use publicly-available, open-source packages only.

You may use only the datasets provided for this challenge, however you may use additional public datasets for the Best Bias Discovery prize only (documented and reproducible).

You may use pre-trained models as long as they are openly available to everyone.

Automated machine learning tools such as automl are not permitted.

If the error metric requires probabilities to be submitted, do not set thresholds (or round your probabilities) to improve your place on the leaderboard. In order to ensure that the client receives the best solution Zindi will need the raw probabilities. This will allow the clients to set thresholds to their own needs.

You are allowed to access, use and share challenge data for any commercial, non-commercial, research or education purposes, under a CC-BY SA 4.0 license.

You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the challenge data, and work with Zindi to rectify any unauthorised transmission or access.

Your solution must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.

Submissions and winning

You may make a maximum of 10 submissions per day.

You may make a maximum of 300 submissions for this challenge.

Before the end of the challenge you need to choose 2 submissions to be judged on for the private leaderboard. If you do not make a selection your 2 best public leaderboard submissions will be used to score on the private leaderboard.

During the challenge, your best public score will be displayed regardless of the submissions you have selected. When the challenge closes your best private score out of the 2 selected submissions will be displayed.

Zindi maintains a public leaderboard and a private leaderboard for each challenge. The Public Leaderboard includes approximately 30% of the test dataset. While the challenge is open, the Public Leaderboard will rank the submitted solutions by the accuracy score they achieve. Upon close of the challenge, the Private Leaderboard, which covers the other 70% of the test dataset, will be made public and will constitute the final ranking for the challenge.

Note that to count, your submission must first pass processing. If your submission fails during the processing step, it will not be counted and not receive a score; nor will it count against your daily submission limit. If you encounter problems with your submission file, your best course of action is to ask for advice on the challenge page.

If you are in the top 10 at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 48 hours to respond and submit your code following the Reproducibility of submitted code guidelines detailed below. Failure to respond will result in disqualification.

If your solution places 1st, 2nd, or 3rd on the final leaderboard, you will be required to submit your winning solution code to us for verification, and you thereby agree to assign all worldwide rights of copyright in and to such winning solution to Zindi.

If two solutions earn identical scores on the leaderboard, the tiebreaker will be the date and time in which the submission was made (the earlier solution will win).

The winners will be paid via bank transfer, PayPal if payment is less than or equivalent to $100, or other international money transfer platform. International transfer fees will be deducted from the total prize amount, unless the prize money is under $500, in which case the international transfer fees will be covered by Zindi. In all cases, the winners are responsible for any other fees applied by their own bank or other institution for receiving the prize money. All taxes imposed on prizes are the sole responsibility of the winners. The top winners or team leaders will be required to present Zindi with proof of identification, proof of residence and a letter from your bank confirming your banking details. Winners will be paid in USD or the currency of the challenge. If your account cannot receive US Dollars or the currency of the challenge then your bank will need to provide proof of this and Zindi will try to accommodate this.

Please note that due to the ongoing Russia-Ukraine conflict, we are not currently able to make prize payments to winners located in Russia. We apologise for any inconvenience that may cause, and will handle any issues that arise on a case-by-case basis.

Payment will be made after code review and sealing the leaderboard.

You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this challenge constitutes your acceptance of these official challenge rules.

Zindi is committed to providing solutions of value to our clients and partners. To this end, we reserve the right to disqualify your submission on the grounds of usability or value. This includes but is not limited to the use of data leaks or any other practices that we deem to compromise the inherent value of your solution.

Zindi also reserves the right to disqualify you and/or your submissions from any challenge if we believe that you violated the rules or violated the spirit of the challenge or the platform in any other way. The disqualifications are irrespective of your position on the leaderboard and completely at the discretion of Zindi.

Please refer to the FAQs and Terms of Use for additional rules that may apply to this challenge. We reserve the right to update these rules at any time.

Reproducibility of submitted code

If your submitted code does not reproduce your score on the leaderboard, we reserve the right to adjust your rank to the score generated by the code you submitted.

If your code does not run you will be dropped from the top 10. Please make sure your code runs before submitting your solution.

Always set the seed. Rerunning your model should always place you at the same position on the leaderboard. When running your solution, if randomness shifts you down the leaderboard we reserve the right to adjust your rank to the closest score that your submission reproduces.

Custom packages in your submission notebook will not be accepted.

You may only use tools available to everyone i.e. no paid services or free trials that require a credit card.

Read this article on how to prepare your documentation and this article on how to ensure a successful code review.

Consequences of breaking any rules of the challenge or submission guidelines:

• First offence: No prizes for 6 months and 2000 points will be removed from your profile (probation period). If you are caught cheating, all individuals involved in cheating will be disqualified from the challenge(s) you were caught in and you will be disqualified from winning any challenges for the next six months and 2000 points will be removed from your profile. If you have less than 2000 points to your profile your points will be set to 0.
• Second offence: Banned from the platform. If you are caught for a second time your Zindi account will be disabled and you will be disqualified from winning any challenges or Zindi points using any other account.

Teams with individuals who are caught cheating will not be eligible to win prizes or points in the challenge in which the cheating occurred, regardless of the individuals’ knowledge of or participation in the offence.

Teams with individuals who have previously committed an offence will not be eligible for any prizes for any challenges during the 6-month probation period.

Monitoring of submissions

We will review the top 10 solutions of every challenge when the challenge ends.

We reserve the right to request code from any user at any time during a challenge. You will have 24 hours to submit your code following the rules for code review (see above). Zindi reserves the right not to explain our reasons for requesting code. If you do not submit your code within 24 hours you will be disqualified from winning any challenges or Zindi points for the next six months. If you fall under suspicion again and your code is requested and you fail to submit your code within 24 hours, your Zindi account will be disabled and you will be disqualified from winning any challenges or Zindi points with any other account.