# Outlier Detection Using DBSCAN - GBIF Data Blog

**URL:** <https://discourse.gbif.org/t/outlier-detection-using-dbscan-gbif-data-blog/2251>\
**Category:** Data blog\
**Created:** [August 21, 2020, 8:49am UTC](https://discourse.gbif.org/t/outlier-detection-using-dbscan-gbif-data-blog/2251 "2020-08-21T08:49:53Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![dodobot](https://sea1.discourse-cdn.com/gbif1/user_avatar/discourse.gbif.org/dodobot/32/12_2.png) [@dodobot](https://discourse.gbif.org/u/dodobot)\
**Post date:** [August 21, 2020, 8:49am UTC](https://discourse.gbif.org/t/outlier-detection-using-dbscan-gbif-data-blog/2251/1 "2020-08-21T08:49:53Z")

</div>

Geographic outliers at **GBIF** are a known problem.

**Outliers** can be errors, coordinates with high uncertainty, or simply occurrences from an undersampled region.

* * *
This is a companion discussion topic for the original entry at [https://data-blog.gbif.org/post/outlier-detection-using-dbscan/](https://data-blog.gbif.org/post/outlier-detection-using-dbscan/)

---

<div class="post-metadata">

**Author:** ![aleruete](https://sea1.discourse-cdn.com/gbif1/user_avatar/discourse.gbif.org/aleruete/32/190_2.png) [@aleruete](https://discourse.gbif.org/u/aleruete)\
**Post date:** [September 1, 2020, 1:03pm UTC](https://discourse.gbif.org/t/outlier-detection-using-dbscan-gbif-data-blog/2251/2 "2020-09-01T13:03:45Z")

</div>

It is difficult to know it GBIF “should” do it. But certainly a good tool to offer if available.

---

<div class="post-metadata">

**Author:** ![PaulGeerders](https://sea1.discourse-cdn.com/gbif1/user_avatar/discourse.gbif.org/paulgeerders/32/60_2.png) [@PaulGeerders](https://discourse.gbif.org/u/PaulGeerders)\
**Post date:** [September 1, 2020, 6:48pm UTC](https://discourse.gbif.org/t/outlier-detection-using-dbscan-gbif-data-blog/2251/3 "2020-09-01T18:48:51Z")

</div>

Careful here ! An outlier can also be a signal of something we did not know until now, remember that we only know half of the truth, i.e. what is behind us - Nature still has many surprises for us in store - the hole in the ozone layer was initially treated as an outlier, luckily they did not delete the data !! - of course that is what is real science about: discover something new and challenging through outliers … 😉