MENU
data_weather

Big Data Takes On Big Weather

March 2, 2014 • Big Data & Analytics, Climate Change, SUSTAINABILITY & ETHICS, TECHNOLOGY

By Djeevan Schiferli, IBM

Some European cities are turning to Big Data to not only predict the weather and its potential impact, but also to address public safety and business concerns that accompany adverse conditions. Below, Djeevan Schiferli argues that the ability to make better use of all this data can dramatically improve the way cities, businesses and citizens plan for and manage the harsh conditions that extreme weather throws at our urban centres.

In recent months, many parts of Europe have been exposed to extreme weather episodes that have significantly disrupted day-to-day life, stretched emergency response services and most sadly, resulted in tragic loss of human life.

The statistics are intimidating. The European Environment Agency lists more than 175 major floods over the last 10 years, and predicts that flooding and other severe weather conditions will only continue to increase due to climate change.

In the UK, the River Thames reached record high levels in February 2014. Further downstream, the Thames Flood Barrier has closed a record 28 times since December 2013, representing one-fifth of all closures since it was inaugurated in the 1980s.

In the German city of Magdeburg, 23,000 people were forced to leave their homes last year after a dam burst on the flood-swollen River Elbe.

In my own native Netherlands, the recent combination of spring tide and northwesterly storm raised water in coastal province, Zeeland, to the highest levels since the devastating 1953 North Sea flood, when water levels rose to 4.55 meters above sea level. The impact of this adverse weather and tide combination were felt right along the European North Sea coastline.

Coastal flood threat is also proving to be a global phenomenon with extreme events such as Hurricane Sandy and Typhoon Haiyan bringing with them major humanitarian catastrophes.

Clearly, with approximately 3.4 billion people – more than half the world’s population – currently living in coastal areas, flood prediction and preparation is high on national and city leaders’ agendas.

 

 

From Physical to Digital

Today, the way many city and coastal authorities respond to severe weather conditions relies on a very ‘physical’ response, such as dredging, ever more robust sea walls and flood barriers. But relying solely on centuries-old engineering solutions is proving less viable for an increasingly complex 21st century problem.

In the U.S., IBM has created a Big Data system that enables highly targeted and locale-specific weather forecasting. This enables planning to predict and plan for operational problems that adverse weather can present to businesses.

Instead, city leaders are beginning to look at the difficulties of the situation more holistically, to better prepare and manage response to the impact of these increasingly frequent severe weather episodes. That means looking at Big Data.

Already, some European cities are turning to Big Data to not only predict the weather and its potential impact, but also to address public safety and business concerns that accompany adverse conditions.

According to Bryson Koehler, executive vice president and chief information officer (CIO) of The Weather Company, each day, more than 20 terabytes of data spanning temperature readings, wind speeds, barometric pressures, satellite images and more, from thousands of locations, is generated.

The ability to make better use of all this data – to build more precise, accurate weather forecasts – can dramatically improve the way cities, businesses and citizens plan for and manage through extreme weather episodes.

 

Digital Delta

In the Netherlands, which has a great heritage and urgency about coastal flood protection, IBM is working with the Dutch government to build an understanding of how Big Data can be used to better prepare for extreme weather episodes.

With 55 per cent of the Dutch population located in areas prone to large-scale flooding, the Netherlands has immense experience in managing water. So, by developing the concept of the Digital Delta, the Dutch government is harnessing insights from Big Data to transform flood control and the management of the entire Dutch water system.

The project investigates how to integrate and analyse water data from a wide range of existing data sources, such as precipitation measurements, water level and water quality monitors, radar data, model predictions as well as current and historic maintenance data from sluices, pumping stations, locks and dams.

By modeling weather events, the Netherlands can determine the best course of action including storing water, diverting from low-lying areas, avoiding saltwater intrusion, sewage overflow and contamination. With better integrated information, water authorities can prevent disasters and environmental degradation, while reducing the cost of managing water by up to 15 per cent.


Deep Thunder

In the U.S., IBM has created a Big Data system that enables highly targeted and locale-specific weather forecasting. This enables planning to predict and plan for operational problems that adverse weather can present to businesses — a challenge that traditional meteorology does not address.

The system, dubbed ‘Deep Thunder’, provides high–resolution forecasts for a region using a diversity of public data from the National Oceanic and Atmospheric Administration, the National Aeronautics and Space Administration and the U.S. Geological Survey as well as private data from companies like Earth Networks. With accuracy and precision, Deep Thunder can deliver hyper-localized weather predictions up to three days in advance, with calculations as fine as one kilometer and as granular as every 10 minutes. These reports can be customized to visualize specific weather elements that a business may be especially concerned about, such as wind speed and direction.

Not only this, but Deep Thunder can also help cities create forecasts of weather conditions and customize them to the needs of different industries. For example, trucking companies can use the Deep Thunder data analysis to divert their trucks from stormy routes with high-wind conditions, while utility companies can use it to estimate how much extra power might be needed on a hot afternoon. In addition, highway departments can use the system to deploy extra snowploughs to clear streets in specific sections of the city where heavier accumulations are expected, making cities safer and reducing disruption.


Weathering the Storm

As meteorologists increasingly become Big Data scientists, they need to be able to provide forecasts for a wide range of geographic and time scales, such as a flood tracking across Europe over the course of a week.

This can help put in place measures to not only prevent damage but also help them understand and respond instantly to events to minimize business and humanitarian impact.

As we continue to face extreme weather conditions for years to come, governments and authorities need to ensure they have the technology in place to better predict and prepare for these events to enable cities to become smarter, safer and sustainable.

About the Author

Djeevan Schiferli is a Business Development Executive, Climate Change and Water Management, IBM. He advises client executives on new business, societal and technology developments, and the potential impact on their business. In his role of Innovation Officer for IBM Global Services in Europe he has led the way in opening up IBM innovation programs like the Centers for Advanced Studies. Since 2007 he has been responsible as Business Development Executive for Climate Change and Water Management, which is part of IBM’s Smarter Planet Leadership Agenda. He was responsible for running IBM’s Global Center of Excellence for Water Management in 2008, which has since then extended with expertise hubs in the Netherlands, Ireland, France, Israel, China and the USA.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

« »