Announcing the Pollen API

It's both funny and sad how "Google" has become synonymous with "time-limited". You start treating a new API like a pop-up store downtown — it's okay or even good to be interested, but relying on it would be folly.

Re: Announcing the Pollen API

#6

Post by criddell » Tue, Aug 29, 2023, 9:33 AM UTC

I initially thought Google partnered with Matthew Butterick on a publishing system? then clicked through and was a bit disappointed.

Re: Announcing the Pollen API

#7

Post by daedlanth » Tue, Aug 29, 2023, 9:37 AM UTC

[dead]

Re: Announcing the Pollen API

#8

Post by frou_dh » Tue, Aug 29, 2023, 9:38 AM UTC

themedes_ wrote: post #3

[flagged]

How bored are you to register an account just to post that formulaic comment?

Re: Announcing the Pollen API

#9

Post by VeejayRampay » Tue, Aug 29, 2023, 9:42 AM UTC

sgammon wrote: post #4

[flagged]

vitriolic comment voicing your own little issues that adds nothing to the conversation about the topic at hand

Re: Announcing the Pollen API

#10

Post by Waterluvian » Tue, Aug 29, 2023, 9:44 AM UTC

I’m a bit surprised to see a single geodata theme packaged as a whole “thing.” And goodness the marketing fluff is quite repetitive given they have so little to talk about.

Call me jaded but it feels like someone’s really announcing, “I shipped something! Give me my promotion!”

> Our Pollen API is based on a model that calculates the seasonality and daily amount of pollen grains on a 1x1 km2 grid in over 65 countries worldwide, supporting an up to 5-day forecast, 3 plant types, and 15 different plant species. The model uses various inputs like land cover, climatological data, annual pollen production per plant, and more to deliver reliable output predictions of the local pollen level and exposure risk.

The maps look like what you get when you throw Ordinary Kriging at a dataset of very limited coverage. I’d be skeptical of this model without thorough analysis.