←back to thread

USGS uses machine learning to show large lithium potential in Arkansas

(www.usgs.gov)
282 points antidnan | 4 comments | 22 Oct 24 17:05 UTC | HN request time: 0.001s | source
Show context
hiddencost ◴[22 Oct 24 17:36 UTC] No.41916647[source]▶
Love to see a project that uses bog standard ML techniques and doesn't call them AI. Respect.
replies(7): >>41916805 #>>41916961 #>>41916963 #>>41917059 #>>41917432 #>>41917794 #>>41918105 #
1. driggs ◴[22 Oct 24 18:06 UTC] No.41916961[source]▶
Quoth the article:

  The USGS predictive model provides the first estimate of total lithium present in Smackover Formation brines in southern Arkansas, using machine learning, which is a type of artificial intelligence.
replies(1): >>41917075 #
2. janalsncm ◴[22 Oct 24 18:16 UTC] No.41917075[source]▶
I was disappointed in that line. They could’ve mentioned it used a random forest, which is much more informative. “ML is a type of AI” isn’t even a cocktail party understanding of the topic.
replies(1): >>41917183 #
3. textlapse ◴[22 Oct 24 18:26 UTC] No.41917183[source]▶
For a layperson, this is an accessible and directionally correct definition.

For the HN audience, of course this is 'technically incorrect'.

The article was written for the (larger) general public.

I am also glad they didn't squeeze in a word salad of LLMs and quantum technology and instead stuck to 'it's just standard ML'.

replies(1): >>41917417 #
4. gowld ◴[22 Oct 24 18:51 UTC] No.41917417{3}[source]▶
The only informational dividable from the statement is "we used a computer to analyze data".