[Ráfaga] #1899: soil, pedestrians, ml

[Jorge Sanz]

#1899: soil, pedestrians, ml

Wed, 14 Sep 2022 by Raf

* The LUCAS 2018 dataset, the largest soil dataset in Europe, contains
19,000 samples analyzed for OC, pH, NPK, EC, Fe, Al, texture and other
physical properties, in both CSV and SHP

https://esdac.jrc.ec.europa.eu/content/lucas-2018-topsoil-data

* US-19, with eight lanes for cars, is the road with the most
pedestrians hit in the USA due to both the design of the roads and the
increase in traffic and the lack of empathy of vehicle drivers

https://www.vox.com/23178764/florida-us19-deadliest-pedestrian-fatality-crisis

* Apple machine learning researchers propose a self-supervised method
for learning geographic location representations from unlabeled GPS
trajectories

https://www.marktechpost.com/2022/08/09/apple-ml-researchers-propose-a-self-supervised-method-for-learning-representations-of-geographic-locations-from-unlabeled-gps-trajectories-to-solve-downstream-geospatial-computer-vision-tasks/

**********

web: https://geoinquiets.github.io/rafagas/
twitter: https://twitter.com/rafagaslinks