How Data Governance Can Help Create a Digital Twin of the World’s Oceans

On May 21, 2021, the G7 Ministers responsible for Climate and Environment communicated an urgent and concrete action to move towards global sustainability.

In response to the growing pandemic, the G7 recognized that the key drivers of global biodiversity loss and climate change are the same as those that increase the risk of zoonoses — or diseases that animals can transmit to humans. As the past year has demonstrated, these diseases can lead to pandemics.

Creating a digital twin of the world’s oceans would help enhance scientific discoveries and provide key tools for policy in climate change and the global natural environment.

What Is A Digital Twin?

A digital twin is a three-dimensional digital replica of an object in the physical world. It could be a jet engine, a wind farm — or a larger object like a building or even a city. This article explores the twinning of the entire world’s oceans.

Twinning technology not only creates digital representations of these physical objects but can collect data that simulates processes in order to predict future behavior.

The result is an ecosystem model filled with real-time data capable of making forecasts and predictions.

The Real-World Case for Twinning of the World’s Oceans

So, a digital twin ocean would contain real-world data to create simulations that can predict how oceans will behave in the future. Examples of this data include the topology of the ocean, ocean currents, the biology of the animals living in the ocean, and most importantly, the effects of human interaction on the ocean.

Programs can integrate the Internet of Things, (Industry 4.0), artificial intelligence (AI), and software analytics to enhance the output of the digital twin model.

What ML Has Taught Us

With the advancement of machine learning and factors such as big data, virtual models have become a staple in driving innovation and improving performance in modern engineering.

Creating a digital twin of the ocean could:

• enhance strategic technology trends
• prevent costly failures in physical objects
• test processes and services by using advanced analytical, monitoring, and predictive capabilities.

Data, captured with analog and digital sensors — combined with geospatial information, video, audio, and reports — is the currency of a digital twin ocean.

How that data is collected, aggregated, communicated, and shared across entities, nations, and organizations to be included and standardized in a simulation model is a massive data governance challenge that has not been solved.

How Data Governance Can Help

According to an Official UN World Oceans Day event with Steven Adler, CEO of Oceans Data Alliance, and Peter El Hajj, Head of National Digital Twin Programme Delivery at Centre for Digital Built Britain, the value of ocean twin data is only realized if it is open and available to all users. At the event, the purpose of which was to ultimately define a global architecture for Ocean Digital Twin programs — including ontologies and a data governance framework for natural world entities — these experts broke down the data governance challenge into three parts:

1. The lack of cataloging for all the available data collected by separate and distinct scientists
2. The lack of understanding the data in the proper context and the manual need to link similar data sets together
3. Similar to the current challenges faced by many financial services, retail, and healthcare companies today, there is a lack of resources (e.g., data stewards) to curate and maintain the quality of the data.

How BigID Can Help

BigID offers a modern, innovative AI/ML technology that discovers and connects data from varied data sources — and provides data insights to today’s leading organizations.

According to Peggy Tsai, BigID VP of Data Solutions, by eliminating the need to copy and move original data, BigID’s discovery-in-depth platform allows organizations to virtually connect to their entire data landscape to create:

1. an automated data catalog that inventories all their data assets for easier searching and more consistent understanding of the data
2. automatic labeling or classification of the data for consumption by downstream users such as scientists from other research labs
3. a correlation between all the available data attributes to identify relationships between data sets; these relationships can include similarities in the data or reveal similar data attributes that are adjacent to its definition and usage.

With BigID’s data catalog, data can be identified to build complex digital twins. To avoid creating dummy data to fill in the gaps of digital twins, environmentalists can improve the accuracy of the model predictions with accurate data. Comprehensive ontologies and semantics can be built out, addressing the data architect’s need to curate and link data assets to the concepts.

So what’s next for the Ocean Data Alliance to promote the development of an ocean digital twin? This is only the start of many global conversations and efforts to hopefully bring us closer to our goal. The G7 will collaborate and advance our collective work on ocean science, ocean observing, and ocean action throughout the UN Decade of Ocean Science for Sustainable Development.

Stay tuned for additional workshops to dive deeper into data and technology needed to create an ocean digital twin — and find out more about BigID’s data intelligence platform for discovery and data governance.