Data vs. Disaster: 5 Ways Analytics Is Helping Tackle Climate Change - DATAVERSITY

• Read original article here

With the recent Intergovernmental Panel on Climate Change (IPPC) report painting a worrying picture of our battle against climate change, we will explore five ways analytics can help turn the tide.

The UN Secretary-General, Antonio Guterres, called the report “a code red for humanity,” adding that “the alarm bells are deafening and evidence irrefutable.” U.S. President Joe Biden said about it, “The cost of inaction is mounting.” 

In summary, without immediate action, the damage we’ve done may be irreversible. 

For this to change, we’re going to have to rely on the latest tools and technologies, including big data, advanced analytics, modeling, and simulation techniques. Here’s how Data Science can help find a solution to this rapidly growing crisis. 

Climate change is a global concern, but evidence shows that just 90 companies are responsible for as much as two-thirds of all historical greenhouse gas emissions.

As much as it is everyone’s responsibility to tackle this issue, individual businesses have the opportunity to make the biggest impact on our society. The first step in doing this is being able to accurately calculate their carbon footprints. 

This is an extremely challenging and data-intensive process, with emissions spread over three different categories: direct emissions (Scope 1), emissions required to generate electricity (Scope 2), and emissions that contribute to the production and consumption of products across the value chain (Scope 3). 

In large companies, with sprawling international supply chains, the last of these three categories can be incredibly hard to calculate. 

However, start-ups like Watershed are currently using analytics to help companies track their emissions across these three bands in a matter of days, and build a carbon reduction plan based on that data.  

Operational emissions from buildings account for around 30% of the world’s carbon emissions, which makes them an ample target for reducing our impact on the planet. 

Traditional methods for heating and cooling buildings are incredibly inefficient. But as a positive, this means there’s lots of room for improvement. As far back as 2017, DeepMind artificial intelligence proved that it could reduce the energy consumption of Google data centers by as much as 40% using deep learning. 

This is a great example of how analytics and AI can see things human operators can’t, maximizing efficiency with lots of small improvements the naked eye might miss. Today, similar technologies are increasingly becoming available to help building owners reduce emissions and costs.

One example is 75F, a company backed by Bill Gates with a goal of providing the most energy-efficient, affordable commercial building controls in the world.  

When faced with any complex issue, analytics can be a great tool for helping us see the forest from the trees and gaining a clearer picture of reality.  

One great example of this is Climate Central’s Surging Seas project – an interactive map that shows real-time information about rising sea levels in the United States. 

The map provides accurate insights into current sea levels along with historical data and action plans for mitigation.  

The project also uses analytics to share the impacts of rising sea levels on the population, recently discovering that hundreds of millions more people than previously estimated are at risk of coastal flooding.

These insights can help people make safer and more informed decisions about how to stem these impacts going forward – and, vitally, show where is and where isn’t safe to grow crops, build infrastructures, and house our citizens.

The Surging Seas project isn’t the only one using analytics to help us predict risk. 

Athenium Analytics (previously Weather Analytics) estimates that 33% of the world’s current GDP is directly impacted by weather events. As extreme events grow in both frequency and ferocity, businesses and governments alike have to find ways to minimize their impacts on activities, assets, and people – and big data, simulation, and modeling techniques have a huge role to play in this process. 

New research from Arizona State and Stanford Universities is currently augmenting meteorological studies with a host of human-originated factors to better predict global warming events and paint a clearer picture of risk. Deep learning is also being explored for its ability to predict events like tornadoes before they strike. And further research at the University of Alberta is using statistical analysis and modeling to gain new insight into wildfires. 

Elsewhere, a growing number of companies have developed their own climate risk simulation models, designed to help governments and organizations visualize risk, identify hazards as they develop, and understand, predict, and mitigate their impacts.

Going forward, this view of risk may be essential to maintaining business-as-usual operations.  

From wind turbines to solar panels and smart grids, clean energy solutions play a vital part in our battle against climate change, and analytics is becoming increasingly integral to optimizing their performance. 

Big data gathered from hundreds of thousands of IoT sensors, as well as historic data sources, is currently being used to improve efficiency, provide vital maintenance insights, and cut down on the costs associated with renewable technologies. All of this combines to make clean energy initiatives more impactful, more affordable, and, ultimately, more appealing to potential investors. 

At a government level, analytics is also being used to assess which areas of the grid should be prioritized for improvement, leading to better budget allocation. By applying these techniques, the United States is currently on track to use renewables for 30% of its energy generation by 2030. Similarly, the U.K. government recently announced its plans to work towards net zero emissions by 2050.

The above are just some examples of how analytics is helping to fight climate change. There are many more, and going forward we should both expect and hope to see further developments in this field. As with most things in life, data holds the answer to the problem – it all comes down to how we use it.