Ships and small boats produce underwater sound through their engines and propellers. This noise can affect marine animals that rely on hearing to navigate, feed and communicate. The challenge aims to help researchers monitor vessel-related noise along the South African coast and distinguish it from wind, waves and marine life.

The South African data come from hydrophones, or underwater microphones. You receive one-minute summaries of sound energy in different frequency bands, showing how energy varies from lower- to higher-pitched sounds; the original audio is not provided. AIS vessel-tracking data show the reported positions of nearby vessels, but do not confirm which vessel produced a sound. The South African measurements have no verified vessel-noise labels.

In this challenge, you will train on real data supplied by SAEON, SANBI, and the SA Underwater Radiated Noise Consortium (SA URN). Use these unlabelled South African measurements to develop and adapt models that recognise vessel-related acoustic patterns. Synthetic training data are not provided.

You may use public external acoustic datasets under their applicable licences. Share source links, versions and access instructions with the community through the challenge discussion board so other participants can obtain the same data. Redistribute files only where their licences permit it. You may adapt your methods using the South African data provided.

Since the real South African measurements do not have verified vessel-noise labels, the scored test uses controlled additions. Each test window combines real background measurements with an added vessel-sound component whose energy is known. This gives all models the same measurable target for comparison. Performance on this test must be supported by evidence on real data before claiming reliable vessel-noise monitoring.

For each test window, predict two values between 0 and 1: the fraction of total measured energy contributed by the added vessel component, and an evidence score indicating how strongly your model detects that component. For example, a predicted fraction of 0.20 means that the added component accounts for 20% of the window's measured energy. This target describes the controlled addition, not all vessel noise naturally present in the background.

Research write-ups should demonstrate how the model works on real South African measurements and produces a useful pressure map: a view of how vessel-related acoustic activity varies across monitoring sites and over time. Compare the map with observed acoustic patterns, explain uncertainty and show that the model responds to relevant signals rather than general noise. Without independent calibration, describe the map as relative acoustic activity. Supported interpretations of vessel number or size are an additional strength.

There are additional prizes for methodology or research write-ups.

SPONSORED BY:

French Embassy in South Africa, Lesotho and Malawi through Le Shift Lab:

The Embassy of France in South Africa, Lesotho and Malawi is the main sponsor of this challenge via its Le Shift Lab programme, a 2-year initiative to support green & digital transformation in Southern Africa and connect climate tech ecosystems with France. One of its components is specifically dedicated to cooperation on sustainable AI.

South African Environmental Observation Network (SAEON) The National Research Foundation’s South African Environmental Observation Network (NRF-SAEON) is a national research infrastructure dedicated to long-term environmental observation, research and data management. Through its network of observation sites, research platforms and data systems, SAEON collects, preserves and makes environmental data accessible to support scientific discovery, evidence-based decision-making and sustainable development.

SUPPORTED BY:

AI for Good - International Telecommunication Union (ITU)

AI for Good is organized by ITU in partnership with 40 UN Sister Agencies. The goal of AI for Good is to identify practical applications of AI to advance the United Nations Sustainable Development Goals and scale those solutions for global impact. It’s the leading action-oriented, global & inclusive United Nations platform on AI.

The South African National Biodiversity Institute (SANBI)

SANBI leads and coordinates research, and monitors and reports on the state of biodiversity in South Africa. The institute provides knowledge and information, gives planning and policy advice and pilots best-practice management models in partnership with stakeholders. SANBI engages in ecosystem restoration and rehabilitation, leads the human capital development strategy of the sector and manages the National Botanical and Zoological Gardens as ‘windows’ to South Africa’s biodiversity for enjoyment and education.

Coalition for Sustainable AI

The Coalition for Sustainable AI is an initiative coordinated by France, the UN Environment Programme and the International Telecommunication Union, with the support of several international organizations. Launched at the Paris AI Action Summit in 2025, it aims at building a global community of stakeholders willing to contribute to initiatives for aligning AI development with global sustainability goals and fostering responsible AI that supports the environmental policies.

This challenge will be integrated into the resources of the AI and Ocean vertical of the Coalition so as to further expand its potential for re-use and impact.

The leaderboard score is (1 − RMSE), where RMSE (Root Mean Squared Error) is calculated on share_added_vessel. Higher scores are better; a perfect prediction scores 1. Each test window contributes equally to RMSE.

share_added_vessel estimates the fraction of the window's total acoustic energy contributed by the controlled addition of a vessel-passage reference. The reference target is the sum of added passage-reference energy divided by the sum of total mixture energy. Both sums use the same observed minute-band cells across the 25 test bands, in linear energy units.

For example, 2 units of added passage-reference energy in a mixture containing 10 units gives a target of 0.20. This represents an energy fraction, not a probability. A target of zero means that no passage reference was added; the original background may still contain naturally occurring vessel sounds.

For every example_id in sample_submission.csv, submit one row containing:

• share_added_vessel: your estimated added energy fraction.
• score_added_vessel: a continuous evidence score indicating whether a controlled vessel-passage addition is present.

Both predictions must be finite numbers between 0 and 1. Submit one value per output for the entire window, rather than separate predictions for individual minutes or frequency bands.

Only share_added_vessel determines the leaderboard score. score_added_vessel is collected for diagnostic analysis using ROC AUC and does not affect ranking. It should not be interpreted as a calibrated probability of natural vessel presence.

Your submission file should follow this format. The IDs and values below are illustrative only; use the actual IDs and column order from sample_submission.csv.

ID,share_added_vessel,score_added_vessel

EXAMPLE_A,0.20,0.50

EXAMPLE_B,0.00,0.30

The public leaderboard uses approximately 30% of the test examples. Final rankings are determined by RMSE on the remaining 70%, used for private evaluation. Individual examples' public/private membership is not disclosed during the competition.

Pressure maps and evidence of performance on real South African data belong in the research write-up and do not contribute to the automated leaderboard score. Synthetic test performance alone does not establish accuracy on natural vessel activity.

Research write-ups

Research write-ups are expected to demonstrate high-quality model performance on real South African acoustic data and construct well-supported pressure maps. Claims must be backed by reproducible acoustic evidence, controls and uncertainty; synthetic rank or AIS proximity alone is insufficient.

• Evaluation: hold out released South African stations or periods from training and adaptation. Declare window identifiers, sample sizes and tuning.
• Acoustic evidence: align observed frequency-band signals and predictions. Include weak activity, interference, missing data and failures, with a summary of the full evaluated sample alongside selected examples.
• Controls: compare with received energy or another simple acoustic baseline. Use relevant spectral/time controls or ablations; if AIS informs the model, also show results without AIS.
• Pressure maps: provide maps of acoustic pressure or a clearly defined relative proxy, with coverage, time alignment, units, uncertainty and correspondence with observed signals. Validate any spatial interpolation. Distinguish total sound from inferred vessel contributions; physical-pressure or probability claims require calibration.
• Interpretability is a major plus: explain which acoustic features drive predictions. Independently validated estimates of simultaneous vessel number and size or size class add value. Report errors, uncertainty and AIS coverage limits. These are not scored synthetic targets.
• Accompanying code: each research write-up must include runnable code or notebooks that reproduce its analysis, figures and pressure maps. Provide dependency versions and clear execution instructions.
• Reproducibility: supply runnable analysis and outputs; uncertainty should account for repeated observations. Explain failures and what additional evidence would establish vessel identity or ship-only energy.

Review considers evidence quality, usefulness, uncertainty, reproducibility and efficiency. Unlabelled observations are not confirmed negatives. Demonstrated limitations are valuable; unsupported transfer or vessel-count/size claims do not qualify. Research write-ups will be submitted at the end of the challenge.

🥇1st place: $1,500 USD + invitation to ChangeNOW Summit 2027 for one person to present your winning solution, worth $2,500 USD

🥈 2nd place: $1,000 USD

🥉 3rd place: $500 USD

📝 Best writeup: 2x $1,000

There are 5 000 Zindi points available. You can read more about Zindi points here.

• 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, 200 submissions overall.
• Team size: Max 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: The data shared in this challenge is intended solely for use in this challenge.
• 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.

Training may use released South African data and declared public corpora, including ONC and HearMyShip, under provider licences and equal access. Declare source URLs, versions, preprocessing and access requirements. Participants may create augmentations from permitted data; organisers supply no synthetic training set.

Test inputs are for inference only: do not fit, fine-tune, calibrate, pseudo-label or build training examples from them. Fixed per-window transformations are allowed. Do not use hidden answers, source identities or unreleased backgrounds, or reconstruct per-example labels through leaderboard probes.

Provide runnable inference code, trained weights and dependency versions reproducing submitted predictions. Declare training splits, preprocessing, seeds and nondeterminism. Report training hardware/time, inference runtime, peak memory and model size. Submit one finite [0,1] value per output and test ID.

You may use pretrained 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 exclusively for the purposes of participating in this challenge. Any unauthorised usage constitutes a breach of Zindi terms of use.

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 public and private leaderboards. Approximately 30% of test examples determine the public leaderboard score during the challenge; the remaining 70% determine the private leaderboard score and final ranking at close. Both scores are calculated as 1 − RMSE on share_added_vessel, with higher scores being better. Per-example leaderboard membership and private scores remain hidden until close.

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.

🚀 What to know to get started with Zindi Challenges

How to get started on Zindi

How to create a team on Zindi

How to run notebooks in Colab

How to update your profile