171–180 of 237 posts
Earlier quoted context omitted.
I mean, what could possibly go wrong?
What are you worried about, zombies that want to eat your batteries?
Earlier quoted context omitted.
So it turns out that there's no theoretical reason that gradient boosting will always outperform RF (which would violate the "no free lunch" theorem). But it does usually seem to be the case in practice, even with small and noisy data. I would hazard a guess that with better tuning, XGBoost would still have won. (The paper notes that the authors chose a suboptimal set of hyperparameters out of fear of overfitting - m…
That's been my experience. RF tends to do quite well out of the box, and is very fast to fit. It's less of a pain to cross-validate too, with fewer tuning parameters. XGBoost has a huge number of knobs to tune, and its performance varies from god-awful with bad hyperparameters to somewhat better than RF with good ones. Giant PITA with nested cross-validation, etc. though. I haven't read in detail what their validatio…
They explain it for selecting the hyper parameters for ML models:
> In this article, we talk about Bayesian Optimization, a suite of techniques often used to tune hyperparameters. More generally, Bayesian Optimization can be used to optimize any black-box function.
But the example at the beginning of the article is mining gold:
> Let us start with the example of gold mining. Our goal is to mine for gold in an unknown land 1 . For now, we assume that the gold is distributed about a line. We want to find the location along this line with the maximum gold while only drilling a few times (as drilling is expensive).
Well I guess this is a good win for short term energy infrastructure, though I'm always pretty torn when its at the cost of ripping open huge swaths of earth to get at the raw material. It is interesting to see how much of this data could be modelled based on wastewater brines from other industries in the area, assuming we go on to mine the lithium it will say a lot if the ML predictions prove accurate. One thing I c…
> cost of ripping open huge swaths of earth to get at the raw material. This mining offsets mining for other things that is happening at several orders of magnitude larger scale. Oil, coal, gas, etc. mining is huge and lithium batteries plus renewables are already reducing the need for those. So, the transition to renewables and batteries might actually result in a net reduction of mining. Of course doing lithium min…
This point is overlooked so often in these discussions. Lithium is not a consumable in batteries, whereas oil / tar / coal etc. is. So, we do some ugly mining for a bit, and then basically stop once we have the lithium we need for use in batteries over and over again. It’s a completely different model than extract-and-burn.
From the paper's method section, a bit more about which type of ML algo was used: An RF machine-learning model was developed to predict lithium concentrations in Smackover Formation brines throughout southern Arkansas. The model was developed by (i) assigning explanatory variables to brine samples collected at wells, (ii) tuning the RF model to make predictions at wells and assess model performance, (iii) mapping spa…
for other folks wonder what the acronym means; RF in this context is Random Forest
Earlier quoted context omitted.
Not everyone agrees that this is a good place for a mine: https://www.protectthackerpass.org/ "to shut down the tar sands, we actually have to shut down the tar sands, not just blow up other mountains elsewhere and hope that leads to the end of the tar sands." https://maxwilbert.substack.com/p/the-long-shadow-of-the-tar...
[flagged]
Earlier quoted context omitted.
> It seems backwards, but pretty much the only fuel that protects ecosystems on a large scale are fossil fuels and nuclear. This is ludicrously off-base for fossil fuels, even if we're only talking about local pollutants from the plants themselves, nevermind things like Exxon Valdez or the pipelines or the act of mining. Nuclear seems likely, though as the other commenter noted it's not a magic bullet either. > Globa…
What do you think the people in cities burn for fuel to keep themselves warm?
From the paper's method section, a bit more about which type of ML algo was used: An RF machine-learning model was developed to predict lithium concentrations in Smackover Formation brines throughout southern Arkansas. The model was developed by (i) assigning explanatory variables to brine samples collected at wells, (ii) tuning the RF model to make predictions at wells and assess model performance, (iii) mapping spa…
So it turns out that there's no theoretical reason that gradient boosting will always outperform RF (which would violate the "no free lunch" theorem). But it does usually seem to be the case in practice, even with small and noisy data. I would hazard a guess that with better tuning, XGBoost would still have won. (The paper notes that the authors chose a suboptimal set of hyperparameters out of fear of overfitting - m…
Earlier quoted context omitted.
It's not even close to as large as the footprint of oil and gas. The Thacker Pass project, which is one of several that are all individually described as satisfying global demand, will ultimately disturb only 7000 acres. Fossil fuel wells usually disturb 5 net acres each, and there are five million such wells in America alone.
Additionally, that area in Nevada can be - at best - charitably described as moonscape. Which, for those of us that like moonscape, is a bit sad. But there is a lot of moonscape in that region, and there aren’t a huge number of moonscape fans. At least that are going to try to picket any projects. So overall, meh. That area of Nevada is also pretty economically ‘challenged’, so why not.
I'm half expecting the future more conservative SCOTUS to shoot down land use regulation as a taking, requiring such regulation to be combined with payment for the value lost instead.
Earlier quoted context omitted.
Not everyone agrees that this is a good place for a mine: https://www.protectthackerpass.org/ "to shut down the tar sands, we actually have to shut down the tar sands, not just blow up other mountains elsewhere and hope that leads to the end of the tar sands." https://maxwilbert.substack.com/p/the-long-shadow-of-the-tar...
[flagged]
ugh i really don't want people to mine in the mobile basin. that's one of the most diverse ecosystems in north america. https://www.youtube.com/watch?v=8j9coyJeB4Q
Extracting lithium from brine is cleaner than e.g. extraction from spodumene ore. Also direct lithium extraction from brine is faster, cleaner, smaller footprint, lower energy consumption.
Sulfur, currently extracted by desulfurization of oil and gas, gets more expensive in the post fossil fuel society, but there are other sources (like pyrite).