SPADE (SPArse DEnse) is a family of advanced geospatial generative Machine Learning models by Mathclick, designed to enhance the quality and utility of sparse data streams, such as those coming from sensors on buoys or drones, or coming from periodic surveys. It operates similarly to a Generative Pretrained Transformer model, like GPT4 by OpenAI, using learned patterns to generate new content.

In practical applications, SPADE can be used in an industrial port setting or in a tourist Marina setting to nowcast (provide present and past values up to 3 years back) and forecast (up to 5 days into the future) the water depth in any area of the port that undergoes periodic water depth surveys. This predictive maintenance capability can improve operations, reduce costs, and decrease the carbon footprint of port operations. It can lead to more efficient use of surveys, improved and less expensive dredging, enhanced decision-making abilities, and the transformation of survey costs into strategic investments.

SPADE based “predictive maintenance” can provide value by improving operations, reducing costs and reducing the carbon footprint of Port operations:

1) Reduction and more efficient use of surveys

4) Turning survey costs into strategic investments

2) Improved and less expensive dredging

5) Enabling of “single point” surveys

3) Daily (virtual) surveys

Tests conducted with data from one of the major world ports shows that the "drift" of SPADE depth predictions/estimates can be below 9mm/day, providing an invaluable tool to operators.

Contact us (via the interaction link) fore more details and for a preliminary assessment of the potential application of SPADE to your Port or Marina!