Google Research Introduces SensorFM: A Wearable Health Foundation Model Pretrained on One Trillion Minutes of Sensor Data

Foundation Model Pretrained on One Trillion Minutes of Sensor Data">

Most wearable health models are built one outcome at a time. That approach breaks down at thirty-five endpoints. Labels are expensive and retrospective annotation is infeasible.

Google Research introduced SensorFM, a foundation model for wearable health pre-trained on more than 1 trillion minutes of sensor data from 5 million people.

SensorFM is a Large Sensor foundation Model for wearable time-series representation learning. It ingests 34 one-minute aggregate features drawn from five sensors: PPG, accelerometer, EDA, skin temperature, and altimeter. Those features are organized into seven categories, over a 24-hour context window.

The backbone is a ViT-1D encoder trained with a masked-autoencoder objective and a patch size of [20, 1]. Pretraining used 5,000,000 consented participants, sampled between September 2024 and September 2025. That corpus spans 100+ countries, all 50 U.S. states, and 20+ Fitbit and Pixel Watch models. It totals over two billion hours, or more than one trillion minutes.

Four variants exist, each paired with a proportional data volume.

Evaluation uses separate data. It covers 13,985 subjects across three prospective IRB-approved studies. Those are metabolic, cardiac and respiratory health (N = 1,655), sleep (N = 6,377), and mental health (N = 5,953). The 35 tasks cover cardiovascular (6), metabolic (8), mental health (8), sleep (3), demographics (4), and lifestyle (6).

With that setup, the first question is whether scale buys anything measurable. The research team swept four model sizes against four data volumes.

SensorFM-B on the 5M corpus cuts reconstruction validation loss by 31% versus SensorFM-XXS. Generative loss drops 28% on average. Downstream, it gains ΔAUC = 0.09 on classification and Δr = 0.21 on regression. Across variants, B wins 33 of 35 tasks, and XXS ranks last on 33 of 35.

The failure case is equally informative. SensorFM-B trained on only 5K subjects posts a 1.082 validation loss. That is worse than every smaller variant at the same volume. Pretraining was stopped early because the model overfit.

Consequently, all headline results assume data volumes scaled proportionally to capacity. Along that co-scaled diagonal, mean ROC AUC moves .664, .681, .710, .752. Mean Pearson r moves .386, .435, .536, .612. The above figure shows the trend has not saturated.

Scaling alone does not explain those numbers. Real streams fragment during charging, off-wrist periods, and power-saving modes. Conventional methods either impute the gaps, injecting bias, or drop the windows, discarding data.