> For the complete documentation index, see [llms.txt](https://lus-organization.gitbook.io/lu_paper_reading/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lus-organization.gitbook.io/lu_paper_reading/smart-aquaculture/sensor-data/real-time-in-situ-prediction-of-ocean-currents.md).

# Real-time in situ prediction of ocean currents

Journal: Ocean Engineering (Q1)

## Abstract

Deep autoregressive networks (LSTM and Transformer) can predict ocean currents in real-time at any location in the world.

## Data

Ocean current data at 831 sites (222 stations have data length greater than 2 months) from [NOAA](https://tidesandcurrents.noaa.gov/cdata/StationList?type=Current+Data\&filter=historic). Sampling interval: 6 or 10 min

## Conclusion

LSTM and Transformer can predict ocean currents in real-time at any location in the world and even better than traditional Harmonic Method.

e.g., Comparison of speed Normalized Root Mean Squared Error (NRMSE) (lower is better)

| Station ID | Depth (ft) | LSTM | TF   | HM   |
| ---------- | ---------- | ---- | ---- | ---- |
| hb0401     | 15.7       | 0.14 | 0.12 | 0.12 |
| jx0302     | 29.5       | 0.1  | 0.09 | 0.33 |
| jx0701     | 15         | 0.09 | 0.10 | 0.12 |
| cb0701     | 13.9       | 0.18 | 0.19 | 0.2  |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://lus-organization.gitbook.io/lu_paper_reading/smart-aquaculture/sensor-data/real-time-in-situ-prediction-of-ocean-currents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.