Winners of the 2026 International Cherry Blossom Prediction Competition!

Winners of the 2026 International Cherry Blossom Prediction Competition

We challenged contestants to predict the day that the cherry trees will reach peak bloom.

We asked contestants to submit their best predictions for select trees in Washington, D.C. and New York City (USA), Kyoto (Japan), Liestal-Weideli (Switzerland), and Vancouver, B.C. (Canada), along with a compelling narrative and reproducible analysis containing any data and code used. The competition is challenging because while it is known that cherry trees tend to bloom earlier as climates warm, complex weather patterns make annual predictions extremely difficult.

For the fifth year in a row, students, researchers, and citizen scientists from around the world accepted our challenge. Each entry was evaluated by its predictive performance and interpretability—with the help of an independent panel of judges. We are now thrilled to announce the winners.

Award for Most Accurate Prediction goes to Wesley Demontigny

Wesley Demontigny submitted the most accurate forecast. Wesley combined a mixed-effects linear model with deep learning. The bloom dates were first detrended using the linear model. Local temperature idiosyncrasies were captured by pre-training a stacked LSTM on historical NASA POWER temperature data and NOAA ENSO anomalies from 1980 onward. A secondary neural network was then used to model the residuals of the linear model from the output of the temperature model. The final predictions were constructed by combining the linear model projections with the predicted residuals. Congratulations Wesley!

Award for Best Model goes to Bethany Gopinath

Bethany Gopinath used model averaging to combine traditional phenological forecasting models into a single prediction. The component models included the Utah Chill model and variants of linear regression. The weight of each component was determined using leave-one-out cross validation. The judges were impressed by the combination of biological theory, traditional statistics, and machine learning—as well as the clear and compelling motivation. Congratulations Bethany!

Honorable Mention goes to Cassandra Kujawa and Mitchell Nicolai

Cassandra Kujawa and Mitchell Nicolai independently noted that the bloom date was largely determined by temperature, but the exact relationship between temperature and the bloom date could be complicated. Both set up their analysis as a dimension reduction problem, with Cassandra relying primarily on random forest and Mitchell on LASSO. Congratulations Mitchell and Cassandra!

A big thanks to all competition participants

We know every contestant worked hard to produce their most accurate and interpretable predictions. All their work will help scientists better understand the impacts of climate change, and we hope their contribution does not end here. We encourage each contestant to continue to work on their models and narratives. We provide a summary of the 2026 entries for future reference.

Contestants vary widely in their predictions for 2026

The calendars below show the days the contestants predict the peak bloom date will occur. Some believe peak bloom will occur in early March, while others believe it will occur in early May. When the entries are combined, the consensus is that the cherry trees will reach peak bloom between late March and early April. The average predicted peak bloom dates are March 30^th for Vancouver, BC, April 1^st for Kyoto, April 2^nd for Washington D.C. and Liestal-Weideli, and April 6^th for New York City—denoted on the calendars by 🌸.

Overall, the contestants agree with the Japan Meteorological Corporation prediction

The contestants agree with the Japan Meteorological Corporation’s 6^th forecast on average, which predicts that the peak bloom of the Kyoto cherry trees will occur on March 31^st. (Note JMC provided predictions for Prunus × yedoensis while the contestants predicted Prunus jamasakura. These species have similar but not identical bloom dates.)

The National Park Service predicts the peak bloom of the Washington D.C. cherry trees will occur between March 29^th and April 1^st. The entries from the contestants suggest a similar range (March 31^st to April 4^th). This also overlaps with the predictions from Storm Team4 (March 30^th to April 5^th) and The Washington Post (April 3^rd to April 7^th).

For Vancouver, BC and New York City, where there is almost no historical data, contestants thought that full bloom would be March 30^th and April 6^th, respectively. The Vancouver Cherry Blossom Festival posts updates on the stage of their cherry trees on the UBC Botanical Garden Forums.

A big thanks to our sponsors, partners, and judges.

We thank Posit, American Statistical Association, Washington Statistical Society, Caucus for Women in Statistics, George Mason University’s Department of Statistics, Georgetown University’s Massive Data Institute, and Columbia University’s Department of Statistics and Real World Data Science for their support, and partnerships with the International Society of Biometeorology, MeteoSwiss, USA National Phenology Network, the Vancouver Cherry Blossom Festival, Local Nature Lab, and WSP Eco Projects—as well as Mason’s Institute for Digital InnovAtion, Institute for a Sustainable Earth, and the Department of Modern and Classical Languages. We also thank our observers who send in observations of flowering, and our judges Lelys Bravo de Guenni, Brittany Sutherland, Mason Heberling, Nathan Lenssen, Will Pearse, and Christine Rollinson. Thank you!

Organizers

Judges