Data has evolved to be present in every part of our lives. When buying a product, we search for a consumer rating or an expert giving us a statistic on how effective the product is. We collect data from our experiences and use it to guide future actions. A similar method can be used to understand and make decisions about the environment through sustainability data.

There is a wealth of information about the environment that is available, even if some sustainability data is still hard to gather. Yet, we do not often use data-based insights when we make decisions about the environment.

For example, the onus is put on consumers to make lifestyle changes to save the planet. We are frequently told to avoid plastic straws, carry cloth bags instead of using single-use plastic bags at the supermarket or sort our waste and recycle.

However, when we look at the problem using data, we see that in many cases, the majority of our global environmental issues are being caused by major corporations, not individuals. Even if every human on the planet lived as sustainably as possible, the numbers show that we would only solve a small percentage of the problem.

Surprising statistics about the environment

• Aluminum is a material that may be recycled multiple times. Recycling one 300ml aluminum saves enough energy to power a TV for over 3 hours. Scale this up a bit, and imagine how much energy you can save by recycling all the cans you buy.

• 91% of the world’s plastic waste is not recycled, and 10% of this goes into our oceans. There are 5.25 trillion pieces of plastic debris in the sea. That number is nearly beyond comprehension. What makes it easier to understand – but perhaps harder to accept – is that plastic waste thrown into the ocean kills as many as 1,000,000 sea creatures every year. 

• Electric vehicles are commonly seen as the answer to a greener future, helping to reduce the polluting emissions released by fuel-powered vehicles. This is not yet a reality, as we only produce just over a quarter of our electricity sustainably. We make most of our electricity from the combustion of fossil fuels. In other words, it could be said that Tesla manufactures mostly coal-powered vehicles, not electric ones.

The insights found in sustainability data can be used to paint a bigger picture. Globally 28% of electricity comes from renewable sources. We are still reliant on fossil fuels for most of our electricity and energy needs. In a world where we are trying to be more sustainable and environmentally friendly, energy is increasingly expensive. Recycling materials we use and plastics we create is the need of the hour. This would save energy, save animals and help our environment.

Climate change awareness is the next step

Awareness is the first step in a long list of things that need to happen to slow and someday reverse climate change. There is so much to learn about our environment and what is happening. We have caused the planet to heat up faster than it should; we are the reason the sea levels are rising. To fix the problems we face, we need to be aware. Some organizations and websites devote their resources to giving people the information they need to know about the world that they live in and the problems that we face. “The World Counts” is one such website. 

Focussing on global challenges, consumer economy, and world population, the World Counts collects data from several reliable sources and presents the information in an easy-to-understand and impactful format. Using point estimates and projections gives us a “real-time” counter of the data. 

The World Counts tries to balance the negative and positive information on its site. It does this to ensure that sustainability data leaves a significant impression in the viewers’ minds and hopefully motivates a change in their consumer behavior. This organization understands that the first step is awareness and that it is not always easy to find what you want to know. It hopes to be the site that collects, organizes and presents the information we need to know about the environment and the global population.

Sustainability data can hold policymakers accountable 

In the global economy that we live in, the consumers are the first part of a much larger chain. Consumer behavior needs to shift away from use and throw consumption, and we need to practice sustainable living. These efforts are necessary for producers to shift to sustainable production, as public demand will influence what is created and how.

But this will not be enough to stop climate change or effectively make global changes. Developed countries contribute more emissions and do more damage to the environment than developing countries. Sustainability data tells us that around 100 companies alone are responsible for 70% of historical greenhouse gas emissions. To make large-scale, long-term, and effective programs to address climate change, the government needs to step in. Innovative government policy is the key to effective solutions for the global challenges that we face. 

The UK government has been working on its plastic recycling policy and implementation. Standardizing the production of plastic in the country, improving the labeling of plastic products, so consumers know how to dispose of their waste, and reducing the usage of single-use plastics are some of the steps that the policy encouraged. However, recent news describes how the UK cannot recycle all the plastic waste that it collects, and most of that is exported to Turkey. 

In Turkey, the waste is either dumped or incinerated. Essentially, Turkey bears the burden of air pollution and diseases resulting from plastic incineration and waste dumping. At the beginning of July, Turkey banned nearly all imports of plastic. The UK now needs to figure out how to handle its plastic waste domestically. While efforts are being made to improve recycling capacity in the UK, the country will struggle to take all the plastic waste collected in the short term.

Data is proving to be our most valuable tool for recognizing, addressing, and solving climate change. Scientists use data to keep track of global temperatures and emissions. The same information is then repackaged and presented in a digestible format for the global population. The very same data will then be used to formulate government policy. As consumers, readers, and humans on this planet, we need data to stay informed and be conscious of our actions.

Artificial Intelligence (AI) is shaping an increasing number of sectors globally. Degradation of the natural environment and the climate crisis are complex issues requiring the most advanced and innovative solutions. AI is expected to impact environmental, financial, and job stability, amongst other areas in the future. 

 But, how much can AI really help contribute to the climate crisis?

Environmental sustainability

Environmentally, Artificial Intelligence can aid management across agriculture, water, energy, and transport. 

In agriculture, AI can better monitor environmental conditions and crop yields. For water resource management, AI can help to reduce or eliminate waste while lowering costs and lessening environmental impact, such as AI-driven localized weather forecasting to help restrict water usage. AI can also manage the supply and demand of renewable energy using deep learning, predictive capabilities, and intelligent grid systems. Finally, AI can help reduce traffic congestion, improve cargo transport, and enable autonomous (or self-driving) cars. 

According to Microsoft and PwC UK, using AI for these environmental applications could contribute $5.2 trillion to the global economy in 2030. Also, AI application could reduce worldwide greenhouse gas (GHG) emissions by 4% in 2030, equivalent to the 2030 annual emissions of Australia, Canada, and Japan combined. 

This positive impact on the environment somewhat explains the broad harnessing of AI to contribute to managing environmental and climate change. 

Financial sustainability 

As a result of the environmental applications, AI could boost global GDP by 3.1 – 4.4% (Microsoft) and can generate a global economic uplift, yielding approximately US$3.6 – 5.2 trillion driven by optimized inputs, higher output productivity, and automation of manual tasks. 

More generally, AI technology can help companies encourage fast consumer decision-making and detect fraud and financial crime through machine learning. For example, automated wealth management services (robot advising) and algorithmic trading are helping financial institutions to optimize financial decisions; and ‘smart ledger’ technology could support the take-up of collective defined contribution (CDC) schemes. 

However, while AI promises to increase financial stability through minimized error margins, it brings new risks such as interconnectedness between financial markets and confusion regarding machine learning decision-making processes when working with AI. Therefore, macro-level standards need to be implemented, and regulators need to tighten governance on the use of AI by companies (Parker Fitzgerald) to mitigate these risks. 

Job sustainability 

There is no denying that smart machines will make today’s jobs more efficient. However, humans are more likely to work with smart machines in the digital enterprises of the future than being replaced by them.

The AI applications to agriculture, water, energy, and transport will also create 18.4 – 38.2 million net jobs globally (broadly equivalent to the number of people currently employed in the whole of the UK), offering many skilled jobs. And this is just the beginning. If these many jobs are being created in these sectors alone, the possibilities are substantial across industries globally. 

Therefore, companies need to train employees to work alongside machines rather than creating a fear culture that jobs will become irrelevant.

Conclusion

In addition to those highlighted in this article, there are so many ways that AI will enable a sustainable future. Companies will be looking to transition into more sustainable and efficient working practices, requiring workforces with the skills to support these changes. Therefore, as a society, we must accept and tackle the future of AI to reap the financial, job, and environmental sustainability and the personal advantages to a more sustainable future on our health, well-being, and lifestyle.

Lead the shift towards artificial intelligence in your organization, explore the latest technologies, such as machine learning and deep learning, with the online Artificial Intelligence MSc at the University of Leeds. 

With the help of a use case, Dr Patrick Vetter, Head of Competence Center Data Science at Supper and Supper GMBH explains how a deep learning methodology can locate and segment wind turbines on satellite imagery.

As a pioneer in fighting global climate change, Germany is increasingly investing in renewable energies, especially wind energy. With around 300 new turbines from 2016 to 2017, North Rhine Westphalia is one of the leading federal states in building new wind turbines. For assessing the wind energy potential and planning of new turbines, it is essential to track the spatial location of wind turbines together with their type and to combine this with information on average wind speed characteristics.

In the present use case, a methodology is described, that can locate and segment wind turbines on satellite imagery. The implemented neural network architecture is called U-Net and constitutes the state-of-the-art standard for image segmentation. The output is a pixel-wise prediction of the probability of a pixel to belong to a wind turbine. The deep learning framework was trained to predict wind turbine polygons on 280,000 satellite images covering the entire area of North Rhine Westphalia. The output was transferred to the geoinformation system ArcGIS and can be accessed online through various devices. The layer of wind turbines can be used for a thorough analysis with regard to wind energy potentials and for the spatial planning of turbines.

In consideration of the growing scarcity of fossil fuels, renewable energy sources are becoming increasingly important economically, socially and politically as an environment-friendly and efficient way of generating electricity.

The aim of the project was to support the federal ministry in North Rhine-Westphalia in generating regional registers of the locations and types of wind turbines to guide national energy producers in the spatial planning process of new plants.

A Convolutional Neural Network (CNN) was trained to identify and segment wind turbines and on-shore wind parks based on satellite imagery. The output wind turbine polygons can then be fed into Geographic Information Systems (GIS) and enriched with current wind data to efficiently monitor the current wind power.

Provided Data

The satellite imagery used in this project contained 280,000 image tiles provided by Esri’s (the market leader in geoinformation systems) World Imagery. The images cover the bounding-box area of the federal state North Rhine Westphalia and have an area of 1 km2 each. For each image tile, the corresponding geographic metadata was tracked. For the training data set 500 images and 200 for the validation dataset were selected, including 200 wind turbines of different types and in different landcover situations. For both sets, wind turbine polygons have been created.

Applied Methods

First an image pre-processing was performed to normalize satellite images for differing brightness, saturation and contrast levels. Then the training and validation data had to be generated by visually locating wind parks and turbines in ArcGIS Pro (Esri’s Professional GIS-Tool). The located turbines were then marked and converted into georeferenced polygons. After matching the resulting polygons with the corresponding image tile, they were converted into image masks. The mask classifies if an image pixel belongs to a wind turbine or not. This serves as the desired classification scheme for the developed artificial neural network. The deep learning framework used, is based on a U-Net architecture, which has been proven to perform very well for segmentation tasks with a low amount of training data. The segmentation performance was tracked using the Jaccard-Index, which is an intersection over union measure. The training was calibrated to achieve the maximum accuracy in the validation set in order to prevent model overfitting. The final layer of the neural net outputs an image mask with a pixelwise prediction of the likelihood of a pixel to belong to a wind turbine.

Challenges

The first challenge was to create the training features and to generate polygons of the wind turbines within the 700 satellite images. The application of unsupervised clustering, namely a K-Means colour clustering, helped with pattern recognition and extracting the polygon shape. Another time-consuming challenge was to detect the false positives of the network, i.e. recognized image segments that were falsely identified as wind turbines, like branching roads or aircraft. Further training epochs were needed to train the neural net to differentiate between those similar looking objects.

Project Outcome

Using the developed deep learning model, a regional register of wind turbines for the state of North Rhine-Westphalia was successfully created. In total, about 3,300 wind turbines have been identified in the satellite images.

This register was also captured as a layer in ArcGIS Pro and is now available as map material within the software, displaying the location of all identified wind turbines as polygons of their shapes. As a next step, the model can also be applied to other German states or even to create a worldwide wind turbine register. The wind turbine layer can be merged with current wind speed data to monitor the wind power generation and with average wind speed layers to support the spatial planning of new wind turbine sites.

Further applications

The developed deep learning model has already been utilized in other projects within the field of satellite image segmentation. Based on provided satellite imagery, stylized map material has been created. The neural net has been trained to detect different objects and land cover types on satellite imagery, such as roads, trees, forests, vehicles, buildings, rivers and agricultural fields.

Outlook

Satellite imagery has multiplicative application fields and can be used to gain a better understanding of other domains, e.g. to help identify natural resources more easily, to visualize and monitor climate or vegetative changes or to depict impacts of natural disasters more accurately. However, these things have mainly been achieved so far through manual or semi-automated methods. Artificial Intelligence and Satellite Imagery Feature Detection can contribute significantly to these geographical applications.

Dr Patrick Vetter will be speaking at Data Natives 2018– the data-driven conference of the future, hosted in Dataconomy’s hometown of Berlin. On the 22nd & 23rd November, 110 speakers and 1,600 attendees will come together to explore the tech of tomorrow. As well as two days of inspiring talks, Data Natives will also bring informative workshops, satellite events, art installations and food to our data-driven community, promising an immersive experience in the tech of tomorrow.

Global warming. For a topic as massive, important, and (somehow) controversial, big data is a clear option for sorting through the muck. What information is reliable? What solutions are realistic? When a global issue pits the future of humanity against, well, everything humanity is accustomed to, facts are vital. Big data doesn’t just give the public pretty visualizations, it reveals facts about climate change that make a difference. Instead of knowing only that the climate is changing, data studies are showing how fast, where, and which industries are making it worse. How is data being used in the fight against climate change, and will it work?

Mapping the Past to See the Future

The first step for data is to do what it does best: offer a thorough, easy-to-grasp glimpse into the realities of climate change. If GoogleMaps looks massively detailed, check out Landsat, NASA’s records of the state of the global land surface. It’s the longest and most complete record of its kind in existence, and it’s proved indispensable for studying the impacts of climate change. Even NASA has said such data is essential for monitoring how humans are specifically changing the planet and affecting climate change. The US’s Environmental Protection Agency has also used data to show where change is happening. Now, it’s clear the largest source of greenhouse emissions is electricity and heat production—though agriculture, forestry and land use is only one percent behind.

EPA Data makes it clear that China represents the world’s single largest source of CO2 emissions, with the US in second. The next question is, how can we use that information to make a difference? One great strength of data science is predictive modeling, and that will prove vital in upcoming initiatives. NASA uses data to answer questions about the future of the planet. For example, what will the Earth look like in 2100? By integrating actual measurements with climate simulation data, they created realistic expectations for the years to come, as well as a variety of possibilities dependent on a given greenhouse gas scenario.

Ellen Stofan, NASA chief scientist, notes that, “with this new global dataset, people around the world have a valuable new tool to use in planning how to cope with a warming planet.” While NASA won’t necessarily be offering consumer products or passing bills to regulate businesses, their data gives those in power everything they need to make better decisions—and even spend less money.

Creating Smarter, Less Costly Solutions

For cultures and governments that want to stop climate change, but also spend the least amount of money, and give up the least amount of comfort, accurate predictions remove a lot of pressure. Data means that solutions can be carefully evaluated, simulated and implemented. And that may make governments more open to giving them a try. One of the most popular examples is the Ronald Reagan Building in Washington, D.C., where solutions saved both energy and $800,000. And that is only one of several examples. Consumers, on the other hand, are less than excited about giving their daily comforts. But big data solutions are offering consumers the chance to save money by wasting less energy. Fortunately, it doesn’t matter whether people are using less energy for the environment or for themselves.

Of course, solutions aren’t always fun consumer products—sometimes they have much more sinister implication. The effects of climate change are already being felt. Predictive data is also being used to combat the rise in weather disasters. For example, by showing where flooding is most likely to happen, or where sea walls would be the most effective. One study by Data-Pop Alliance shows that data’s role in the climate change discussion go hand-in-hand with disaster relief usages. As climate change continues to increase the frequency and scale of weather related hazards, like cyclones, floods and tsunamis, that data will prove invaluable on a regular basis.

Don’t worry—there are also more optimistic possibilities. The U.N.’s Global Pulse initiative started the Big Data Climate Change Challenge in 2014 due to a powerful need to strengthen “the economic case for action on climate change to show where such action is feasible, affordable and effective.” Again, one of data’s big roles is visually showing that change is both possible and economically plausible. The results of the challenge included a forest monitoring system, data and computational tools for building low-carbon and sustainable systems.

Spreading and Studying Awareness

Big data is doing plenty of work in the field of climate change, though the ordinary person may never see it. That may be simply because it’s a complicated and, oftentimes, entirely overwhelming subject. That’s why data is, once again, also being leveraged as a tool to get the public involved. NASA, the EPA, and Global Pulse don’t just gather and analyze data, they share it. Data solutions can also be used to analyze what the public knows and cares about: namely, social media analysis. To this end, Global Pulse assembled an incredible map of how the world tweets about climate change.

They show not only the when and where of tweets, but the topic. Is the public more interested in energy, climate change politics, or the state of the oceans? Analyzing public opinion and understanding is often associated with marketing campaigns. When a company wants to sell something, they analyze their audience. On the other hand, when a major discussion like that of climate change wants to better inform and engage with the populace, they simply must know what people are thinking. It is important both to create informative, shareable data visualizations, and to register the public response.

There are plenty of shortcomings when it comes to using data to combat climate change. Given the amount of energy information technology uses, it seems a particularly bizarre place to start. A study from IBM even pinpoints several problem areas, including the use of historically shallow data and trying to map complex, nonlinear dynamics. Of course, despite all of these drawbacks, virtually no one in the discussion considers big data anything less than a godsend.

Like this article? Subscribe to our weekly newsletter to never miss out!

Follow @DataconomyMedia

On June 6th, 2015 Big Data Utah and the Boulder/Denver Big Data Users Group (BDBDUG) kicked off the Global Data Competition, an inaugural event focused on climate change and split into 22 regions around the world.

The competition has two phases, each with a scoring system that allows solutions to be compared within the region it is submitted. Competitors can compete on an individual, group (2-10 people), or organization (10+) level.

Phase 1, centered on Learning Image Classification, is now underway. Participants are tasked with taking a set of 4,766 images of Mars and predicting whether or not a volcano is depicted in each image. All the data and tips necessary to get started can be found at http://www.global-data-competition.com/code-and-submissions/.

Beginning in late August, Phase 2 will include sessions, videos and tutorials on getting started with data science, reviewing exploratory data analysis techniques, data visualization and web scraping. The competition during this phase will tie the training into acquiring data from a variety of sources, including NASA’s newly released 11 Terabytes of data.

Visit www.global-data-competition.com for more information including registration, code and data.

When both NASA and the Pope are speaking out about climate change, you know something is up. Yesterday the NASA Earth Exchange (NEX) unveiled a public data set showing how rainfall, temperature and CO2 levels will change over the next 85 years.

The high-resolution data, which is as granular as looking at individual towns changing on a daily basis, will help scientists predict catastrophic environmental events such as floods and draughts. These insights will be particularly valuable to the agricultural industry, where it will help to optimize crop yield and prevent losses.

“NASA is in the business of taking what we’ve learned about our planet from space and creating new products that help us all safeguard our future,” said Ellen Stofan, NASA chief scientist. “With this new global dataset, people around the world have a valuable new tool to use in planning how to cope with a warming planet.”

This NASA dataset integrates actual measurements from around the world with data from climate simulations created by the international Fifth Coupled Model Intercomparison Project. These climate simulations used the best physical models of the climate system available to provide forecasts of what the global climate might look like under two different greenhouse gas emissions scenarios: a “business as usual” scenario based on current trends and an “extreme case” with a significant increase in emissions.

Additional information about the new NASA climate projection dataset is available at:

https://nex.nasa.gov/nex/projects/1356/

The dataset is available for download at:

https://cds.nccs.nasa.gov/nex-gddp/

OpenNEX information and training materials are available at:

http://nex.nasa.gov/opennex

For more information about NASA’s Earth science activities, visit:

http://www.nasa.gov/earth

[NASA]