Ars Technica: How Google researchers used neural networks to make weather forecasts

Ars Technica: How Google researchers used neural networks to make weather forecasts. “The researchers say their results are a dramatic improvement over previous techniques in two key ways. One is speed. Google says that leading weather forecasting models today take one to three hours to run, making them useless if you want a weather forecast an hour in the future. By contrast, Google says its system can produce results in less than 10 minutes—including the time to collect data from sensors around the United States.”

Phys .org: Model shows Welsh language in no danger of extinction but te reo Māori is on its way out

Phys .org: Model shows Welsh language in no danger of extinction but te reo Māori is on its way out. “A team of researchers affiliated with multiple institutions in New Zealand has developed a mathematical model that can be used to predict whether a language is at risk of disappearing. In their paper published in Journal of the Royal Society Interface, the group describes their model and how it can be used.”

Towards Data Science: Using Google Trends data to leverage your predictive model

Towards Data Science: Using Google Trends data to leverage your predictive model. “Using Google Trends data in predictive models has some pitfalls. This article describes a way of making Google Trends data usable for a model to deliver breakthrough results by the hands-on example of predicting the success of movies by using Google Search volume.”

TechCrunch: Scientists turn undersea fiber optic cables into seismographs

TechCrunch: Scientists turn undersea fiber optic cables into seismographs. “Monitoring seismic activity all over the world is an important task, but one that requires equipment to be at the site it’s measuring — difficult in the middle of the ocean. But new research from Berkeley could turn existing undersea fiber optic cables into a network of seismographs, creating an unprecedented global view of the Earth’s tectonic movements.”

Towards Data Science: Reconstruct Google Trends Daily Data for Extended Period

Towards Data Science: Reconstruct Google Trends Daily Data for Extended Period. “My motivation into this subject was first inspired by the Rossmann competition in Kaggle where google search trends were used to predict sales number. I found it not so obvious to obtain the daily search trends and people used the weekly trends as surrogate. However, it is not ideal for any predictive model which necessitate precision at daily scale and real-time applications (as weekly data will only be available until the current week ends).”

Phys .org: Data science could help Californians battle future wildfires

Phys .org: Data science could help Californians battle future wildfires. “This year, I helped found the Crisis Technologies Innovation Lab at Indiana University, specifically to harness the power of data, technology and artificial intelligence to respond to and prepare for the impacts of climate change. Through a grant from the federal Economic Development Administration, we are building tools to help federal agencies like FEMA as well as local planners learn how to rebuild communities devastated by wildfires or hurricanes.”

EurekAlert: Using AI to predict where and when lightning will strike

EurekAlert: Using AI to predict where and when lightning will strike. “At EPFL’s School of Engineering, researchers in the Electromagnetic Compatibility Laboratory, led by Farhad Rachidi, have developed a simple and inexpensive system that can predict when lightning will strike to the nearest 10 to 30 minutes, within a 30-kilometer radius. The system uses a combination of standard meteorological data and artificial intelligence.”