The Science Behind Sofar Ocean Marine Weather Forecasts

We deployed an array of 200 weather sensors in the Pacific and assimilate the data in our global models. We have reduced forecast rms errors by over 20%, providing the highest fidelity wave forecasts in the world.

Tim Janssen

Feb 26, 2020

To improve ocean insights and forecasts, Sofar operates the largest privately owned ocean weather sensor network in the world, currently consisting of nearly 200 real-time weather sensors in the Pacific. Each sensor measures wave conditions, surface winds, and drift currents, and transmits the data to the Sofar cloud in real-time. We assimilate the data in our wave forecast models to create the highest fidelity wave forecasts in the world. Compared to NOAA models, the Sofar data network reduces model rms errors by more than 20% and more than 50% in high-energy swell forecasts.

On December 27th 2019, an energetic storm system developed in the western Pacific about 1000km east of the Japanese coast. The extreme surface winds generated 30m waves, taller than a 7-story building. These energetic waves radiate across the northern Pacific basin, first approaching Hawaii and then making their way to the west coast of the United States.

Figure 1: The map shows part of the Sofar sensor network with a wave height overlay for December 27th (Sofar model)...

Predicting the size and arrival times of these waves at sites around the Pacific is important for coastal protection, safety at sea, and offshore operations. The forecast centers of the National Oceanographic and Atmospheric Administration (NOAA) use statistical wave models (WaveWatchIII) to do this. For these types of energetic events, predictions are often inaccurate, predicting arrival times that are many hours too early (or late) and wave heights that can be off by 100% or more. To improve this, Sofar ingests all available data from its network in its own version of a global wave forecast model. This data-driven model generally performs much better than NOAA, achieving rms error reductions of more than 50%.

With over 70% of our planet covered in water, the surface of the ocean is critical in prediction of global weather and climate. Yet we know almost nothing about it. Most buoy networks provide accurate data near the coast, leaving deep waters unmonitored. This lack of information affects safety at sea and limits our ability to predict weather events.

The ocean is a harsh environment. Most of it is too remote for wide-band communications, and it is unsuitable for traditional devices. Instead, we focus on developing distributed networks with low-cost nodes to provide unprecedented sensor density. We have deployed 200 Spotter sensors that collect real-time data on waves, wind, surface drift, and water temperature (SST).

To improve weather forecasts, the Sofar team runs its own global numerical weather models. We start with ocean waves and feed our real-time sensor data to improve model accuracy. Through this data assimilation, our model achieves impressive results, including a 25% reduction in RMS errors compared to NOAA.