AI Helping to Predict Flooding
Carla Archibald, The University of Queensland and Nathalie Butt, The University of Queensland
What do you do if you have a question? You probably Google it.
According to Google Trends, in 2017 Australians were keen to know about tennis, Sophie Monk, fidget spinners and Bitcoin. But besides these arguably trivial queries, our Google searches also revealed our concerns about extreme weather events such as Cyclone Debbie, Hurricane Irma, and the Bali volcano.
Our research, published in the journal Climatic Change, suggests that Google search histories can be used as a “barometer of social awareness” to measure communities’ awareness of climate change, and their ability to adapt to it.
We found that Fiji, the Solomon Islands and Vanuatu share the highest levels of climate change awareness, according to their Google searches – as might be expected of island nations where climate change is a pressing reality. Australia is close behind, with a high level of public knowledge about climate change, despite the current lack of political action.
Pacific islands are not passive victims of climate change, but will need help
Google searches are like a window into the questions and concerns that are playing on society’s collective mind. Search histories have been used to alert epidemiologists to ‘flu outbreaks (albeit with varying success) and to gauge how communities may respond to extreme weather events like hurricanes.
Talk of climate change action like “adaptation” often centres on well-known and at-risk places such as the Pacific Islands. As sea level rises, communities are forced to adapt by building sea walls or, in extreme cases, relocate.
Understanding how conscious communities are of the impacts of climate change is crucial to determining how willing they may be to adapt. So finding a way to rapidly gauge public awareness of climate change could help deliver funding and resources to areas that not only need it the most, but are also willing to take the action required.
In our research, we used Google search histories to measure the climate change awareness in different communities, and to show how awareness maps (like the one below) can help better target funding and resources.
Google’s vast library reveals the rising tide of climate-related words in literature
Google is asked more than 3.6 billion questions every day, some of which are about climate change. We looked at how many climate-related Google searches were made in 150 different countries, and ranked these countries from most to least aware of climate change.
Countries such as Fiji and Canada, which reported high rates of climate change Googling, were considered as having a high awareness of climate change.
We then divided countries into categories based on their climate awareness, their wealth, and their risk of climate change impacts (based on factors such as temperature, rainfall, and population density). All of these variables can influence communities’ ability to adapt to climate change.
This is a quick way to gauge how ready communities are to adapt to climate change, especially at a large global scale. For example, two countries in the “high awareness, high risk” category are Australia and the Solomon Islands, yet these two nations differ greatly in their financial resources. Australia has a large economy and should therefore be financing its own climate adaptation, whereas the Solomon Islands would be a candidate for international climate aid funding.
By looking at countries’ specific situations – not only in terms of their relative wealth but also their degree of public engagement with climate issues – we can not only improve the strategic delivery of climate change adaptation funding, but can also help to determine what type of approach may be best.
Of course, there are plenty of other ways to assess climate preparedness besides Google searches. What’s more, internet access is limited in many countries, which means Google search histories may be skewed towards the concerns of that country’s more affluent or urbanised citizens.
Climate change awareness has previously been measured using surveys and interviews. This approach provides plenty of detail, but is also painstaking and resource-intensive. Our big-data method may therefore be more helpful in making rapid, large-scale decisions about where and when to deliver climate adaptation funding.
Google search histories also don’t tell us about governments’ policy positions on climate issues. This is a notable concern in Australia, which has a high degree of public climate awareness, at least judging by Google searches, but also a history of political decisions that fail to deliver climate action.
Lack of climate policy threatens to trip up Australian diplomacy this summit season
Amid the political impasse in much of the world, big data can help reveal how society feels about environmental issues at a grassroots level. This approach also provides an opportunity to link with other big data projects, such as Google’s new Environmental Insights Explorer and Data Set Search.
The untapped potential of big data to help shape policy in the future could provide hope for communities that are threatened by climate change.
Carla Archibald, PhD Candidate, Conservation Science, The University of Queensland and Nathalie Butt, Postdoctoral Fellow, The University of Queensland
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Jake Clark, University of Southern Queensland
Two new exoplanets have been discovered thanks to NASA’s collaboration with Google’s artificial intelligence (AI). One of those in today’s announcement is an eighth planet – Kepler-90i – found orbiting the Sun-like star Kepler-90. This makes it the first system discovered with an equal number of planets to our own Solar system.
A mere road trip away, at 2,545 light-years from Earth, Kepler-90i orbits its host star every 14.4 Earth days, with a sizzling surface temperature similar to Venus of 426°C.
The new exoplanets are added to the growing list of known worlds found orbiting other stars.
This new Solar system rival provides evidence that a similar process occurred within Kepler-90 that formed our very own planetary neighbourhood: small terrestrial worlds close to the host star, and larger gassy planets further away. But to say the system is a twin of our own Solar system is a stretch.
Read more: Exoplanet discovery by an amateur astronomer shows the power of citizen science
The entire Kepler-90 system of eight planets would easily fit within Earth’s orbit of the Sun. All eight planets, bar Kepler-90h, would be too hostile for life, lying outside the so-called habitable zone.
Evidence also suggests that planets within the Kepler-90 system started out farther apart, much like our own Solar system. Some form of migration occurred, dragging this system inwards, producing the orbits we see in Kepler-90 today.
Google’s collaboration with NASA’s space telescope Kepler mission has now opened up new and exciting opportunities into AI helping with scientific discoveries.
So how exactly did Google’s AI discover these planets? And what sort of future discoveries can this technology provide?
Traditionally, software developers program computers to perform a particular task, from playing your favourite cat video, to determining exoplanetary signals from space based telescopes such as NASA’s Kepler Mission.
These programs are executed to serve a single purpose. Using code intended for cat videos to hunt exoplanets in light curves would lead to some very interesting, yet false, results.
Googles’s AI is programmed rather differently, using machine learning. In machine learning, AI is trained through artificial neural networks – somewhat replicating our brain’s biological neural networks – to perform tasks like reading this article. It then learns from its mistakes, becoming more efficient at its particular task.
Google’s DeepMind AI, AlphaGo, was trained previously to play Go, an extremely complex yet elegant Chinese board game. Last year, AlphaGo defeated Lee Sedol, the world’s best Go player, by four games to one. It simply trained itself by watching thousands of previously played games, then competing against itself.
In our exoplantary case, AI was trained to identify transiting exoplanets, sifting through 15,000 signals from the Kepler exoplanet catalogue. It learned what was and wasn’t a signal caused by an exoplanet eclipsing its host star. These 15,000 signals were previously vetted by NASA scientists prior to the AI’s training, guiding it to a 96% efficiency of detecting known exoplanets.
Researchers then directed their AI network to search in multiplanetary systems for weaker signals. This research culminated in today’s announcement of both Kepler-90i and another Earth-sized exoplanet, Kepler-80g, in a separate planetary system.
Google’s AI has analysed only 10% of the 150,000 stars NASA’s Kepler Mission has been eyeing off across the Milky Way galaxy.
There’s potential then for sifting through Kepler’s entire catalogue and finding other exoplanetary worlds that have either been skimmed by scientist or haven’t been checked yet, due to Kepler’s rich data set. And that’s exactly what Google’s researchers are planning to do.
Machine learning neural networks have been assisting astronomers for a few years now. But the potential for AI to assist in exoplanetary discoveries will only increase within the next decade.
The Kepler mission has been running since 2009, with observations slowly coming to an end. Within the next 12 months, all of its on-board fuel will be fully depleted, ending what has been, one of the greatest scientific endeavours in modern times.
Kepler’s successor, the Transiting Exoplanet Survey Satellite (TESS) will be launching this coming March.
Read more: A machine astronomer could help us find the unknowns in the universe
TESS is predicted to find 20,000 exoplanet candidates during its two-year mission. To put that into perspective, in the past 25 years, we’ve managed to discover just over 3,500.
This unprecedented inundation of exoplanetary data needs to either be confirmed by other transiting observations or other methods such as ground-based radial velocity measurements.
There just isn’t enough people-power to sift through all of this data. That’s why these machine learning networks are needed, so they can aid astronomers in sifting through big data sets, ultimately assisting in more exoplanetary discoveries. Which begs the question, who exactly gets credit for such a discovery?
Jake Clark, PhD Student, University of Southern Queensland
This article was originally published on The Conversation. Read the original article.
The link below is to an article that takes a look at how to use Google Keep for organizing travel.
For more visit:
The link below is to an article that takes a look at using Google Trips when planning your next adventure.
For more visit:
You must be logged in to post a comment.