# Forecasting time series data with neural ordinary differential equations in Julia

**URL:** <https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977>\
**Category:** General Usage\
**Tags:** ode, machine-learning, sciml, ml, neural-network\
**Created:** [January 15, 2023, 1:41am UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977 "2023-01-15T01:41:17Z")\
**Posts on this page:** 8\
**Page:** 2

<div class="post-metadata">

**Author:** ![dlakelan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dlakelan/32/8491_2.png) [@dlakelan](https://discourse.julialang.org/u/dlakelan)\
**Post date:** [January 29, 2023, 2:09pm UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/21 "2023-01-29T14:09:15Z")

</div>

[https://sco.library.emory.edu/research-data-management/publishing/copyright-data.html](https://sco.library.emory.edu/research-data-management/publishing/copyright-data.html)

Facts are not copyrightable. Kaggle can’t copyright a set of data. There is no legal basis on which they can prevent you from just including the ENSO dataset in your example.

The part about databases as a whole being copyrightable is mainly for something like an indexed book of facts where effort goes in to making it easily searchable and soforth. It doesn’t prevent someone from yoinking out one particular table and using it elsewhere.

---

<div class="post-metadata">

**Author:** ![baggepinnen](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/baggepinnen/32/693_2.png) [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)\
**Post date:** [January 30, 2023, 9:03am UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/22 "2023-01-30T09:03:33Z")

</div>

> [@dlakelan](#):
>
> Facts are not copyrightable. Kaggle can’t copyright a set of data.

Would you mind sharing some reference for this? What makes a dataset different from any other “work” such as a document, book, code or piece of art?

---

<div class="post-metadata">

**Author:** ![SebastianCallh](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/sebastiancallh/32/16102_2.png) [@SebastianCallh](https://discourse.julialang.org/u/SebastianCallh)\
**Post date:** [January 30, 2023, 11:39am UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/23 "2023-01-30T11:39:05Z")

</div>

The dataset [Daily Climate time series data | Kaggle](https://www.kaggle.com/datasets/sumanthvrao/daily-climate-time-series-data) claims [Creative Commons — CC0 1.0 Universal](https://creativecommons.org/publicdomain/zero/1.0/) so I guess we can pull it and put it somewhere else accessible to DataDeps.jl?

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [January 30, 2023, 11:52am UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/24 "2023-01-30T11:52:29Z")

</div>

CC0 would be fine.

---

<div class="post-metadata">

**Author:** ![SebastianCallh](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/sebastiancallh/32/16102_2.png) [@SebastianCallh](https://discourse.julialang.org/u/SebastianCallh)\
**Post date:** [January 30, 2023, 12:22pm UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/25 "2023-01-30T12:22:47Z")

</div>

Where should the data be hosted?

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [January 30, 2023, 1:34pm UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/26 "2023-01-30T13:34:39Z")

</div>

The github repo might be fine? How big is it?

---

<div class="post-metadata">

**Author:** ![dmjalal90](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dmjalal90/32/45867_2.png) [@dmjalal90](https://discourse.julialang.org/u/dmjalal90)\
**Post date:** [January 31, 2023, 2:56am UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/27 "2023-01-31T02:56:11Z")

</div>

I also tried with the code on Github but am getting the following error (please see the attached photo).

 ![error](https://global.discourse-cdn.com/julialang/original/3X/5/4/54debf0cbe8d7b2fdceaab9fcb0e982129197ef0.png)

---

<div class="post-metadata">

**Author:** ![dlakelan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dlakelan/32/8491_2.png) [@dlakelan](https://discourse.julialang.org/u/dlakelan)\
**Post date:** [January 31, 2023, 11:50pm UTC](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977/28 "2023-01-31T23:50:03Z")

</div>

> [@baggepinnen](#):
>
> Would you mind sharing some reference for this?

It was already there in the post, see the link repeated below. But yes, in order to make this explicit people should CC0 their datasets. Datasets are copyrightable in other countries.

> **[Copyright for Data](https://libraries.emory.edu/research/copyright/copyright-data)**
>
> In the United States, facts by themselves are not protected by copyright.

[Previous page](https://discourse.julialang.org/t/forecasting-time-series-data-with-neural-ordinary-differential-equations-in-julia/92977.md?page=1)