+ special shout-out to @alexbchen.bsky.social who recorded the activity dataset!

Fantastic collaboration between Google Research, HHMI Janelia, and Harvard -- including @michalwj.bsky.social @stardazed0.bsky.social @aleximmer.bsky.social @mishaahrens.bsky.social and many more!

Paper: openreview.net/pdf?id=oCHsD...
Website: google-research.github.io/zapbench

🕸️ Last but not least -- the connectome for this specific 🐟 specimen is currently being reconstructed and will be available at a later date!

🧪 We test a number of SOTA time-series forecasting models to provide baselines. We also explore forecasting activity directly in voxel space in a companion paper (www.arxiv.org/abs/2503.00073).

📈 This dataset forms the core of the Zebrafish Activity Prediction Benchmark (ZAPBench), which uniquely measures progress on forecasting neural activity at full brain scale and single cell resolution in a vertebrate.

🔬 We collected and extensively processed a 4d dataset imaged with a lightsheet microscope. The resulting 3d movie covers over 70,000 neurons of a fish exposed to various visual stimuli.

🧠 How accurately can future neural activity be predicted from past activity at the scale of the whole brain? Larval zebrafish offer a unique opportunity to address this question, as they are currently the only vertebrate species in which whole-brain activity can be recorded at cellular resolution.