Researchers Study AI Data Quality Improvements


A recent report from advanced robotics and enterprise software company Gecko Robotics and climate technology company Rho Impact has detailed how robots and artificial intelligence can improve their data collection to help maintain crumbling infrastructure and bring about a zero-carbon economy.

The report was published in the World Economic Forum and details how despite AI’s potential to stop the negative effects of climate change, the issue of data collection has often been overlooked.

According to the report, about 90% of private and public sector CEOs have stated that AI could be an essential tool to fight against climate change; however, 75% have stated that they don’t have much trust in the data that is collected.

Gecko explains that AI models are only as good as the data they have trained with, relying on “robust and granular data sets” to find patterns and trends to allow the models to learn and develop predictive capability.

If applied to flawed data, the analytical abilities of AI could lead to bad decisions and create risks when addressing complex issues like climate change. Additionally, if the data that is given to AI lacks accuracy, completeness, reliability, precision and timeliness, the system could become susceptible to improper outcomes.

The study says that the energy sector, which accounts for 80% of emissions in the United States and Europe, is an example of how data quality can affect climate goals. Achieving a timely and just transition to net zero reportedly requires strict data clarity, specifically related to power generation infrastructure and emissions.

Data Collection Approach

The report states that AI's impact on people’s daily lives has shown the potential to aid in emissions reduction in critical infrastructure.

Data-driven insights for decision-making are reportedly often relied on in daily life. As an example, a November 2023 Boston Consulting Group report detailed how AI-optimized transportation has aided drivers in finding more efficient routes, subsequently cutting emissions.

Additionally, the success of AI-driven thermostat adjustments has reportedly helped save a total of 113 billion kilowatts of energy, about double Portugal's annual electricity use between 2011 and 2022.

Gecko says that the shift towards data-informed decision-making can produce a strong base for the broader application of AI, with an emphasis on the role of accurate data in achieving net-zero emissions in important infrastructure across sectors.

According to the report, advances in robotics, sensors, drones and other data-collection technologies have allowed for the collection and analysis of data on the built world in ways that just five years ago were not attainable.

These innovations, the report adds, can offer new access to ground truth data gathered from the physical world.

Technologies such as robots armed with sensors like ultrasonics that crawl the surface of infrastructure, producing digital twins with high-fidelity data layers about asset health, have aided in addressing challenges that had previously been overlooked.

This new shift could reportedly be the difference between seamless operations and catastrophic failures at places like oil and gas refineries, power plants and manufacturing facilities.

Additionally, the report adds that this means people can feed and train AI to make accurate predictions, helping to optimize operations and improve sustainability metrics.

According to the United Nations, predictive maintenance with AI can reduce downtime in energy production, also reducing the planet’s carbon footprint.

Report Findings

The recent report by Rho Impact reportedly showed the environmental impact potential of using robotics and AI at scale against a single problem in the power generation industry: boiler tube failures.

The report adds that eliminating boiler tube failures inside power plants by pairing robotic inspections with AI-powered software could decrease carbon dioxide emissions across the globe by as much as 230 million metric tons, the same as 4.8% of U.S. emissions.

According to Rho Impact, when boiler tubes fail, power plants shut down and backup power generation is usually turned on to meet energy demands.

Backup power generation is reportedly less efficient and can lead to higher carbon dioxide emissions per unit of energy generated. Power generated on baseload can reportedly be up to 32% more efficient than the same amount of power generated by backup power plants.

The report states that adopting technology in responsible ways can help lead to larger sustainability gains.

The study found that even the most sophisticated AI systems reportedly cannot expect to perform their best without good data, which is now the problem to solve.

Over the next decade, the companies say that every industry will be affected by AI. However, there is still reportedly a large risk of these decisions being made with the assistance of algorithms trained on incomplete or unrepresentative data.

Because of this, the report adds that operators must begin giving these technologies first-order data sets.

More from Gecko

In April 2023, Gecko Robotics announced that it had expanded its work with the United States Navy to include robotic assessments of two vessels.

For the work, Gecko would reportedly utilize its wall-climbing robots and AI-powered software platform to build digital models of the vessels to increase the speed of maintenance cycles and reduce the time Navy vessels spend in dry dock. Specifically, the robots would assess the first amphibious assault ship and an additional Arleigh Burke Class destroyer.

The company reported that the expansion of work followed the approval of Gecko’s Rapid Ultrasonic Gridding (RUG) process by the U.S. Navy.

Previously, the wall-climbing robots and software platform have shown “impressive results” with the Navy in partnership with the Office of the Secretary of Defense (OSD), National Center for Manufacturing Sciences (NCMS) and the U.S. Naval Ship Repair Facility and Japan Regional Maintenance Center (SRF-JRMC).

According to the Navy data, Gecko was “significantly” reducing the lead time and work hours associated with maintenance cycles while increasing the availability of data and finding defects missing through traditional methods.

Prior to that, in October 2022, Gecko entered a collaboration with an energy provider to provide ultrasonic robotic inspection services across Europe.

According to the company's release, these advanced robotic inspections were anticipated to strengthen critical infrastructure and transform how installed equipment is inspected and maintained.

The wall-climbing robots were remote controlled and equipped with ultrasonic transducers, localization sensors, lasers and HD cameras. They could reportedly climb vertically and horizontally, adhering magnetically to an extensive range of equipment types.

These robots could then scan for changes in thickness, cracks, corrosion, blistering, and other forms of degradation. The company reported that the robots included localization technology to pinpoint exact locations on an asset for accurate inspections.

According to the release, data captured by the technology produced a validated report within 24 hours. Then, inspectors could examine corrosion trends over time, predict when failures would occur and estimate when repairs would be necessary.

Due to this process and quick turnaround, Gecko Robotics stated that inspectors were able to “reduce asset downtime and lost production while ensuring critical repairs were conducted with high confidence.”

The latest three-year agreement with Siemens Energy’s European Field Service organization would reportedly develop new technologies and services to better serve customers across several industries, including pulp and paper, power generation (conventional and renewable), and oil and gas.

Previously, Gecko Robotics and Siemens Energy completed in sections in Europe, including Poland (pulp/paper), Belgium (waste to energy), the Netherlands (food processing), and the United Kingdom (power generation). Siemens Energy also established a new Product Competence Center in the Netherlands, with expansion plans.


Tagged categories: Asia Pacific; Construction; EMEA (Europe, Middle East and Africa); Emissions; Environmental Control; Environmental Controls; Environmental Protection; Gecko Robotics; Green Infrastructure; Health & Safety; Health and safety; Infrastructure; Infrastructure; Inspection; Latin America; Net Zero Energy ; North America; Program/Project Management; Research; Research and development; Robotics; Safety; Technology; Z-Continents

Join the Conversation:

Sign in to our community to add your comments.