About the challenge
Hurricanes, mass coral bleaching, disruption of sea mammal migration patterns, and extremely hot summers or cold winters all have one thing in common - they are driven by temperature changes in our seas and oceans. In this challenge, the aim for participants will be to investigate the predictability of global SSTs and SSTAs. Variability in sea surface temperatures (SSTs), also known as SST anomalies (SSTAs), is linked to climate oscillations and occurrences of extreme events, including the El Niño‐Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD) oscillation, and marine heatwaves. The participants will specifically focus on forecasting SSTs and SSTAs with a time horizon with a one-month and six-month lead time.
Predicting SST is crucial for several reasons:
- Climate Forecasting: SST is a key indicator of climate patterns and can help predict weather phenomena such as hurricanes, droughts, and floods. By understanding SST variations, meteorologists can better anticipate and prepare for extreme weather events.
- Ecosystem Management: SST influences marine ecosystems, including the distribution and abundance of species, migration patterns, and reproductive cycles. Predicting SST helps marine biologists and conservationists manage and protect marine biodiversity more effectively.
- Fisheries Management: Many fish species rely on specific temperature ranges for breeding, feeding, and migration. Predicting SST helps fisheries managers make informed decisions about quotas, fishing seasons, and habitat conservation to ensure sustainable fish populations.
- Human Activities: SST affects various human activities, such as shipping, tourism, and coastal development. Predicting SST enables stakeholders to plan and adapt infrastructure, coastal defenses, and tourism activities in response to changing ocean temperatures.
- Climate Change Monitoring: SST is a critical indicator of climate change, with rising temperatures affecting ocean circulation, sea levels, and weather patterns. Accurate predictions of SST trends help scientists monitor and assess the impacts of climate change on the oceans and the broader environment.

Challenge
Dataset
The SSTA data and additional features (sea surface pressure, air temperature 2 metres above the surface) were sourced from ERA5, the fifth-generation reanalysis conducted by the European Centre for Medium‐Range Weather Forecasts (ECMWF), covering the past nine decades globally. ERA5 offers monthly estimates of various atmospheric, land, and oceanic variables on a global scale, with a spatial resolution of 0.25°, spanning from January 1940 to the present. We prepared the SSTA training set by subtracting a climatology value for each month from the corresponding SST values. We define climatology here as the average value of SST over a certain time period. Each column of “.csv” file contains a time series of SSTA for a specific location, the coordinates for each location are contained in the “.csv”. The “...output.csv” contains SSTA values shifted 3 months in advance for the same location.Task: The task is to predict SSTA 3 months in advance based on the previous SSTA values and additional features - mean sea surface pressure and air temperature 2 metres above the surface.
Evaluation: We provide SSTA data for the evaluation structured in the following way. Each column in the “.csv” contains blocks of 12 time series of SSTA. The goal is to issue a 3 months ahead SSTA forecast for each block. For example, assume that the first block had time series with time stamps [Jan 2011 … Dec 2011] then the forecast would be for April 2012. In the dataset the time stamps are omitted. The evaluation metric is the difference between the RMSE of the simple baseline and RMSE of your forecast averaged across all locations. The simple baseline is the persistent model - the current SSTA value is used as a 3-month ahead forecast.
Additional support materials can be found at: Ding Ning, Varvara Vetrova, Karin R. Bryan, Yun Sing Koh (2023) Harnessing the Power of Graph Representation in Climate Forecasting: Predicting Global Monthly Mean Sea Surface Temperatures and Anomalies. In Earth and Space Science. Volume11, Issue3. https://doi.org/10.1029/2023EA003455
Technical Details
All the code for the competition and information about the dataset will be released here: [ZIP] You will find the sample submission and related information on the same website. Please submit a zip file containing a single csv named submission.csv, and it should be a single column with the 71 predicted SSTA.How to participate
Participants will be asked to complete a Google form [https://forms.gle/8Tcgpd6Y3ahnv4pF8] to enroll in the challenge. Participants is reminded that registering multiple times to gain an unfair advantage is strictly prohibited.Prizes
Issues and Question
Please use the Forum provided by CodaBench to ask questions and report issues.Use the contact email with [DIVING DEEP] in the subject for other necessities.
Terms and Conditions
1. Eligibility2. Competition Period
3. Intellectual Property
4. Code of Conduct
5. Disputes and Appeals
6. Changes to Terms & Conditions
Submission
Submission
Code submission portal: CodaBench
Report: Please also include a report/ The report must adhere to the outlined guidelines, including referencing the published source codes (e.g., GitHub repository). In your report please include the SSTA value for September 2024 for the Baltic Sea. They should be submitted by 31st July 2024, through our conference submission system, CMT
Timeline for the challenge
We anticipate that the challenge will follow the timeline below:Winners
Challenge Winners
Organizers
Organizing Committee

Dr Varvara Vetrova
University of Canterbury, New Zealand
Dr Phil Mourot
Waikato Regional Council, New Zealand
Ding Ning
University of Canterbury, New Zealand
Prof Karin Byran
University of Auckland, New Zealand