View profile

Planet:tech - Issue #3: AI as the future of disaster response



September 17 · Issue #3 · View online

Dedicated to curating tech products and startups solving the world's most pressing problems, including climate change, pollution, and sustainability.

Hi, it’s Andrea!
Whether or not you want to believe climate change is making weather more extreme, in light of Hurricane Florence and Typhoon Mangkhut there’s an undeniable truth that preparedness saves lives: how are we preparing ourselves, our cities, our resources to confront this new wave of disasters and how can tech aid?
What in the world is going on?
  • The number of major natural disasters on an annual basis has grown nearly four times since the 1970s.
  • An annual average of 21.5 million people have been forcibly displaced by weather-related sudden onset hazards – such as floods, storms, wildfires, extreme temperature – each year since 2008
There’s a reason disaster relief was named one of the hottest, fastest-growing segments for starting a business. For this issue we wanted highlight two companies that are hoping to save lives by predicting damage from hurricanes, wildfires and earthquakes.

One Concern is definitely one of the most interesting startups in this space. They aim to help complex ecosystems within communities, from health care, to power, to food and shelter, recover much faster after an event. 
One Concern analyzes the data on buildings, elevation, soil types, weather data, and other factors to predict earthquake damage, runs realistic training scenarios and builds collaborative plans to better prepare communities for emergencies.
You can save an order-of-magnitude more lives with good planning”, One Concern co-founder Nicole Hu
Their software is already being used in San Francisco to plan drills, as it can predict, for example, whether and where an earthquake is likely to cause fires, based on where that earthquake strikes and how strong it is. It also assesses various data to predict earthquake damage block by block and identify which buildings are most in need of reinforcement. After a quake, it can recommend the safest routes for bringing aid and other supplies into the city, send first responders, and set up shelters.
Watch the story of One Concern here
Geospiza co-founder Sarah Tuneberg is familiar with the devastation that disasters, both natural and man-made, can cause. Her company sells artificial intelligence software that scours data to help cities find and protect their most vulnerable residents during a disaster.
Geospiza is trying to harness AI to save lives by predicting damage from hurricanes, wildfires, and earthquakes better and faster than humans do. It filters, integrates, analyzes, and consolidates endless raw data into comprehensive consequence-projections and clear pathways to action. Geospiza has a contracts and pilot agreements with a few cities and counties around the US.
An open-source project to use AI and data from Twitter for a better disaster response
We at Planet:tech are big fans of twitter. We actually met on Twitter. 
Also, when Aleks experienced her first earthquake in San Francisco, it was Twitter that helped her find real-time information and safety tips:
“The quake was large enough to wake me up and really scared me. First minutes I could not really understand what was happening and jumped on Twitter to confirm that there was indeed an earthquake. It was comforting to find real-time information and safety tips, as well as see alike tweets from SF friends in the middle of the night.”
Ryan Hoover
Hello to everyone else checking Twitter after that earthquake 😮
The use of social media in emergency situations and crisis alerts is of a big interest for us.
Apart from mega-popular tweets from celebrities and Elon Musk, Twitter receives an overwhelming amount of situational awareness information and real-time disaster insights which are of a significant importance for emergency response. 
Fun Fact: Did you know that the #hashtag as we know it was created by Chris Messina in 2007, but initially Twitter was hesitant to adopt it. On October 23rd, 2007 a web developer Nate Ritter began rapidly posting information about road closures and neighborhood evacuations during the San Diego fires in what became as he saw it, “an exercise in citizen journalism.” Messina urged him to use #SanDiegoFire and quickly other Twitter users began copying the # into their own tweets, the hashtag gradually became used more frequently—the use of it during public safety events like these has allowed the media to turn citizens into news gatherers!
ɴᴀᴛᴇ ʀɪᴛᴛᴇʀ
#sandiegofire About 15 houses have burned on the Rincon res, and 25 at La Jolla res. That fire also burned houses on the Barona res
Though finding actionable and tactical information in real-time is still challenging, we were curious to find the projects that are using technology to make sense of ‘big data’ during a disaster.
One of the interesting projects in this space that we stumbled upon was developed by Qatar Computing Research Institute (QCRI). AIDR - Artificial Intelligence for Digital Response – is a free and open-source platform that combines human computing with artificial intelligence to automatically identify relevant information from a massive volume of tweets and text messages related to emergencies, disasters, and humanitarian crises.
The platform was already successfully used during the 7.8 magnitude earthquake in Nepal in 2015, the Hurricane Harvey in Texas in 2017, and Hurricane Maria, which devastated large parts of the Caribbean in September 2017. 
You can find and contribute to AIDR on Github and read more about it’s application on Medium
A TED Talk to watch
Back in 2011, Paul Conneally gave a TED Talk on digital humanitarianism and how social media and other technologies becoming central to humanitarian aid. 
Paul Conneally: How mobile phones power disaster relief | TED Talk
When disaster strikes, who’s first on the scene? More and more, it’s a robot. In her lab, Robin Murphy builds robots that fly, tunnel, swim and crawl through disaster scenes, helping firefighters and rescue workers save more lives safely – and help communities return to normal up to three years faster.
Robin Murphy: These robots come to the rescue after a disaster | TED Talk
More reads on the topic
An amazing coverage by Wired of how humanitarian disaster response has changed over a relatively short period of time. The the 2010 Haiti earthquake was a turning point when people’s social media and technology use had matured enough to bring masses of relevant, accessible user-generated data.
There is a lot of untapped potential in terms of AI usage in humanitarian areas, especially in developing countries, where resources are limited. Forbes highlighted some of the use cases where AI can have a huge impact in developing countries, including emergency response. 
The Wall Street Journal published an article highlighting the various ways cities across North America use artificial intelligence to predict and respond to natural disasters. According to WSJ, these systems make it easier for emergency response personnel to help the people most in need post-disaster.
The Canadian Geographic published a good overview of the researchers’ efforts to train a computational model to predict extreme “fire weather” — the combination of prolonged hot, dry and windy conditions that leads to the biggest and most destructive fires. The model, called a self-organizing map (SOM), could be used to make critical fire management decisions in realtime.
Tweet to retweet
LAUNCH ALERT! We’re about to send @NASA_ICE’s #ICESat2 to orbit, where it will measure the changing height of Earth's ice. Watch the 9:02am ET liftoff live:
Wrapping up... We are happy to have you here ✨
Your feedback means a lot to us. 💚
Let’s connect on twitter and let us know what you think or email us at: 🌎
Till next week,
Aleksandra, Andrea, and Jessica. 💚
Did you enjoy this issue?
In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue