BMO, TELUS, and partners use Vector AI toolkit to apply computer vision techniques in the fight against climate change
June 20, 2024
June 20, 2024
By Ian Gormely
A new open-source AI toolkit called SegMate, developed by the Vector Institute, can help organizations and researchers apply cutting-edge computer vision techniques in the fight against climate change. The toolkit includes an intuitive interface to apply Meta’s Segment Anything Model (SAM), allowing users to precisely isolate individual objects in an image – an important step in recognizing, classifying, and segmenting objects in machine learning applications.
The model, created in collaboration with Vector Platinum sponsor BMO and Vector Gold sponsor TELUS, who helped drive the project forward, as well as other partners, can be applied to satellite images to track changes in deforestation, agricultural land use, ocean and inshore water bodies, and natural disaster responses. It replaces current methods, which rely on hand annotation and analysis, and can help companies better understand potential environmental risks to their investments.
“If we are to meet the urgent timelines in addressing climate change, machine learning and AI will be among the sharpest tools in our arsenal,” says Deval Pandya, Vector’s Vice President AI Engineering. “At Vector, our partnerships with invested industry leaders like BMO and TELUS are key to translating cutting-edge AI research into real-world solutions. Our collaborative open-source toolkit demonstrates the power of applied AI in understanding and addressing climate change.”
If we are to meet the urgent timelines in addressing climate change, machine learning and AI will be among the sharpest tools in our arsenal.
Deval Pandya
Vice President AI Engineering, Vector Institute
SegMate provides more accurate and detailed information more quickly than previous methods. It extends SAM’s field of view from strictly natural objects to accommodate satellite imagery and allows researchers to infer high-resolution regions from the satellite imagery inputs, like forest cover across large areas, a key factor in understanding the human impact on forests. It also automates region of interest generation at the scales demanded by remote sensing applications and provides a prompt-based method for defining the desired masking using natural language.
The toolkit has been open-sourced, giving academics and industry professionals access to tools that can help analyze satellite images for climate change monitoring and environmental hazard identification.
“BMO’s Climate Ambition is to be our clients’ lead partner in the transition to a net-zero world. This includes developing analytical capabilities and insights to enable a better understanding of the effects of climate change,” says Eric Morrow, Managing Director, Enterprise Data Science & AI, BMO. “Partnering with the Vector Institute to develop techniques that unlock the power of AI to address pressing, real-world climate challenges is a demonstrable way that BMO is living its Purpose, to Boldly Grow the Good in business and life.”
“At TELUS, we are committed to using our world-leading technology to address some of society’s most pressing challenges, including sustainability,” says Ivey Chiu, Senior Strategy Manager of Special Projects and Innovation at TELUS. “Through this collaboration between TELUS’ AI Accelerator team, TELUS Environmental Solutions, and the Vector Institute, we are leveraging the power of AI to better understand how climate change impacts vegetation so that we can make smarter decisions and develop effective strategies to improve our planet’s health.”
The initiative underscores the value of co-development practices when bridging the gap between state-of-the-art research and real-world application. By emphasizing open-source solutions, the partners hope to increase the potential for widespread application, offering promising pathways for future advancements in the field.
View the toolkit now: GitHub – VectorInstitute/SegMate: SegMate: A Segmentation Toolkit