
Privacy & Cookies: This site uses cookies. By continuing to use this website, you agree to their use.
To find out more, including how to control cookies, see here: Privacy Policy
To find out more, including how to control cookies, see here: Privacy Policy
Jona Raphael: Small town, big perspective
/in Bilge Dumping, Biodiversity, Climate, Oceans, Oil & Gas, Oil Spill, Team /by Amy MathewsSkyTruth’s machine learning engineer, Jona Raphael, grew up in Shepherdstown, West Virginia; SkyTruth’s home base. But it was his travels around the world that convinced him to knock on our door.
“I’ve always had an interest in sustainability,” Jona says. At SkyTruth, that interest translates into developing Cerulean, a machine learning model that automatically processes thousands of satellite images a day to detect oil pollution in the ocean,
Tracking vegetation trends along the Colorado River: Part 2
/in Biodiversity, Climate, Freshwater, Public Lands, Wildlife Conservation /by Ry CovingtonAn easy-to-use method helps watershed managers see hotspots of vegetation loss and recovery.
In Ry Covington’s first post on SkyTruth’s Colorado River watershed work, he shared a quick look at our 35-year dataset of spectral indices for the Colorado River. This time, he shares SkyTruth’s methods and shows how watershed managers can detect hotspots of vegetation loss and regrowth.
Systematic data analysis reveals false vessel tracks
/in False vessel tracking, Oceans /by Bjorn BergmanAnalysis of tracking data from Automatic Identification System broadcasts reveals vessel locations have been simulated for a number of ships, including military vessels. This false information could compromise vessel safety, decrease confidence in a crucial collision avoidance system and potentially spark international conflict.
Recently, analyst Bjorn Bergman came across a new category of false AIS ship positions: positions for vessels that were not present on the water anywhere. Yet these tracks appear extremely plausible. This new type of simulated AIS tracks represents a significant threat to data integrity and highlights the need for vigilance when interpreting AIS data.
Remote sensing for road detection Part 2: Improving the model and detecting changes
/in Climate, Hydraulic Fracturing, Oil & Gas /by Sasha BylsmaNear Infrared and Normalized Differential Vegetation Index bands improve predictions of SkyTruth’s automated road detection model.
In Part 2 of a two-part blog series, intern Sasha Bylsma explores whether adding spectral bands to SkyTruth’s road detection model improves the model’s predictions, and demonstrates the model’s ability to detect newly constructed roads in the Neuquen Basin of Argentina.
Remote sensing for road detection Part 1: First steps
/in Biodiversity, Conservation Vision, Protected Area Monitoring, Public Lands, Wildlife Conservation /by Sasha BylsmaSkyTruth’s team of interns built a machine learning model to detect one of the holy grails of conservation: roads
Road construction often precedes harmful activities like mining, drilling, logging, and poaching. And so detecting new road construction is one of the holy grails of conservation. This blog post describes how SkyTruth interns adapted previous SkyTruth work on oil and gas drilling sites to detecting roads.
Environmental justice victory: Indonesian seaweed farmers win, 12 years after Montara oil spill
/in Biodiversity, BP, Montara, Oceans, Offshore Drilling, Oil & Gas /by Amy MathewsWWF-Australia relied on SkyTruth’s monitoring of a disastrous oil spill to see the damage firsthand.Their testimony helped small-scale farmers recover damages from big oil.
A court in Australia finally ordered the company responsible for one of Australia’s worst oil spills to compensate Indonesian seaweed farmers harmed by that disaster, thanks in part to WWF-Australia using guidance from SkyTruth.