View the original opportunity posting here.

Overview

Goal of the competition

Mobile and habitat-diverse species serve as valuable indicators of biodiversity change, as shifts in their assemblages and population dynamics can signal the success or failure of ecological restoration efforts. However, conducting traditional observer-based biodiversity surveys across large areas is both costly and logistically demanding. In contrast, passive acoustic monitoring (PAM), combined with modern machine learning techniques, enables conservationists to sample across broader spatial scales with greater temporal resolution, providing deeper insights into the relationship between restoration interventions and biodiversity.

For this competition, you'll apply your machine-learning expertise to identify under-studied species based on their acoustic signatures. Specifically, you'll develop computational methods to process continuous audio data and recognize species from different taxonomic groups by their sounds. The most effective solutions will demonstrate the ability to train reliable classifiers with limited labeled data. If successful, your work will contribute to ongoing efforts to enhance biodiversity monitoring, including research initiatives in the lowlands of the Magdalena Valley of Colombia.

Context

Humid tropical rainforests, Earth's most biodiverse and ancient ecosystems, are vital for climate regulation and water resource protection. However, rainforests face severe threats. In Colombia, a megadiverse country, the lowlands of the Magdalena Valley are a biodiversity hotspot and home to many endangered species. Over 70% of the Magdalena Valley lowland rainforests are replaced by vast pastures for cattle ranching, and illegal logging is common in forest fragment remnants. The protection of the last forest remnants and wetlands is an urgent need.

Fundación Biodiversa Colombia (FBC) collaborates with local communities, landowners, and organizations to conserve, restore, and connect fragments of forests and wetlands. Established in 2012, El Silencio Natural Reserve protects 5,407 acres of tropical lowland forests and wetlands. Home to diverse wildlife, including 295 birds, 34 amphibians, 69 mammals, 50 reptiles, and nearly 500 plant species, El Silencio is a model for regional conservation and sustainability.

A significant part of the reserve, previously used for extensive livestock farming, is under an ecological restoration project. Through the Kaggle competition, we aim to automate detecting and classifying different taxonomic groups of soundscapes from El Silencio Natural Reserve, intending to provide a better understanding of the ecological process of the restoration projects.

The broader goals for this Kaggle competition include:

(1) Identify species of different taxonomic groups in the Middle Magdalena Valley of Colombia/El Silencio Natural Reserve in soundscape data.

(2) Train machine learning models with very limited amounts of training samples for rare and endangered species.

(3) Enhance machine learning models with unlabeled data for improving detection/classification.

Thanks to your innovations, it will be easier for researchers and conservation practitioners to understand restoration activities' effect trends accurately. As a result, they'll be able to evaluate threats and adjust their conservation actions regularly and more effectively.

This competition is collaboratively organized by (alphabetic order) the Chemnitz University of Technology, Fundación Biodiversa Colombia, Google Research, iNaturalist, Instituto Humboldt, K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology, LifeCLEF, Red Ecoacústica Colombiana, University College London, and Xeno-canto.

Timeline

• March 10, 2025 - Start Date.
• May 29, 2025 - Entry Deadline. You must accept the competition rules before this date to compete.
• May 29, 2025 - Team Merger Deadline. This is the last day participants may join or merge teams.
• June 5, 2025 - Final Submission Deadline.

All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.

Evaluation

The evaluation metric for this contest is a version of macro-averaged ROC-AUC that skips classes which have no true positive labels.

Submission Format

For each row_id, you should predict the probability that a given species was present. There is one column per species. Each row covers a five-second window of audio.

Working Note Award Criteria (optional)

Criteria for the BirdCLEF Best Working Note Award:

Originality. The value of a paper is a function of the degree to which it presents new or novel technical material. Does the paper present results previously unknown? Does it push forward the frontiers of knowledge? Does it present new methods for solving old problems or new viewpoints on old problems? Or, on the other hand, is it a rehash of information already known?

Quality. A paper's value is a function of the innate character or degree of excellence of the work described. Was the work performed or the study made with a high degree of thoroughness? Was high engineering skill demonstrated? Is an experiment described which has a high degree of elegance? Or, on the other hand, is the work described pretty much of a run-of-the-mill nature?

Contribution. The value of a paper is a function of the degree to which it represents an overall contribution to the advancement of the art. This is different from originality. A paper may be highly original but may be concerned with a very minor, or even insignificant, matter or problem. On the other hand, a paper may make a great contribution by collecting and analyzing known data and facts and pointing out their significance. Or, a fine exposition of a known but obscure or complex phenomenon or theory or system or operating technique may be a very real contribution to the art. Obviously, a paper may well score highly on both originality and contribution. Perhaps the important question is, will the engineer who reads the paper be able to practice his profession more effectively because of having read it?

Presentation. The value of the paper is a function of the ease with which the reader can determine what the author is trying to present. Regardless of the other criteria, a paper is not good unless the material is presented clearly and effectively. Is the paper well written? Is the meaning of the author clear? Are the tables, charts, and figures clear? Is their meaning readily apparent? Is the information presented in the paper complete? At the same time, is the paper concise?

Evaluation of the submitted BirdCLEF working notes:

Each working note will be reviewed by two reviewers and scores averaged. Maximum score: 15.

a) Evaluation of work and contribution

• 5 points: Excellent work and a major contribution
• 4 points: Good, solid work of some importance
• 3 points: Solid work but a marginal contribution
• 2 points: Marginal work and minor contribution
• 1 point: Work doesn't meet scientific standards

b) Originality and novelty

• 5 points Trailblazing
• 4 points: A pioneering piece of work
• 3 points: One step ahead of the pack
• 2 points: Yet another paper about…
• 1 point: It's been said many times before

c) Readability and organization

• 5 points: Excellent
• 4 points: Well written
• 3 points: Readable
• 2 points: Needs considerable work
• 1 point: Work doesn't meet scientific standards

Prizes

• 1st Place - $ 15,000
• 2nd Place - $ 10,000
• 3rd Place - $ 8,000
• 4th Place - $ 7,000
• 5th Place - $ 5,000

Best working note award (optional):

Participants of this competition are encouraged to submit working notes to the CLEF 2025 conference. A best BirdCLEF+ working note competition will be held as part of the conference. The top two best working note award winners will receive $2,500 each. See the Evaluation page for judging criteria.

Code Requirements

This is a Code Competition.

Submissions to this competition must be made through Notebooks. For the "Submit" button to be active after a commit, the following conditions must be met:

• CPU Notebook <= 90 minutes run-time
• GPU Notebook submissions are disabled. You can technically submit but will only have 1 minute of runtime.
• Internet access disabled
• Freely & publicly available external data is allowed, including pre-trained models
• Submission file must be named submission.csv

Please see the Code Competition FAQ for more information on how to submit. And review the code debugging doc if you encounter submission errors.