How AI Supports Global Biodiversity Efforts, IBM Insights

AI’s ability to process huge amounts of data and spot patterns can help make sense of the complex, interconnected cause-and-effect factors that influence local and global biodiversity.

IBM recently highlighted some of the ways AI can support biodiversity and the use cases where its technology has supported projects worldwide.

Processing Satellite Data

The European Space Agency’s Sentinel-2 satellites collect images of Earth's land surfaces, coastal areas and inland waters every five days, averaging 3.2 terabytes of data per day. Weather projections generated by the European Centre for Medium-Range Weather Forecasts could use as much as 250 terabytes per day.

According to Adam Thompson, global sustainable finance and ESG offering leader at IBM Consulting, AI can transform how countries handle, process and understand these otherwise impenetrable quantities of information.

“In the past, the problem statement was how to effectively work on arbitrary geospatial problems across heterogeneous datasets ranging from earth observation via weather model output to IoT sensors,’” he said.

“From a capacity point of view, it is clearly not feasible for a lot of organizations to manage such volumes of data for modeling purposes.”

While generative AI stands accused of creating sustainability problems of its own, it could hold the answer. According to Thompson, researchers can deploy smaller models, like IBM Granite foundation models, for specific sustainability-related purposes, such as Earth observation and energy consumption.

Related:IBM Unveils Granite 3.0 as 'Workhorse' AI Model

“The accuracy of modeling using foundational models helps users improve results,” Thompson says.

Tracking African Forest Elephants

The World Wide Fund for Nature (WWF) Germany last year used IBM’s Maximo Visual Inspection (MVI) tools to WWF -Germany to track the movements of African forest elephants in the Congo Basin, the second-largest rainforest in the world.

African forest elephants play a vital role as “ecosystem engineers,” clearing out less important vegetation so that more resilient varieties can thrive. However, the population has been in drastic decline for decades due to habitat loss, climate change and poaching.

The WWF team used IBM Maximo Visual Inspection (MVI) with its camera traps to help monitor and track individual elephants, which can be identified by their unique head and tusk shapes.

Monitoring Coral Reefs

Similar technology is helping monitor the health of coral reefs. Climate change causes sea temperatures to rise which in turn leads to coral bleaching, which is when corals expel the algae living in their tissues, turning them white. Scientists estimate 25% of all sea life depends on coral reefs at some point in their life cycles.

Related:AI-Enhanced App Helps Monitor, Protect the World's Coral Reefs

IBM worked with the Reef Company, which builds artificial reefs to restore reefs lost to climate change, to collect data on how the ocean is changing and where reefs are needed. They used IBM’s BluBoxx ocean data platform to collect sensor data that measures water’s salinity, temperature, pH, dissolved oxygen, pressure and carbon dioxide.

AI can help process that data to provide immediate insights into the condition of a reef and offer an understanding of how an ecosystem changes over time.

“Today, we have massive amounts of data, but it's not always accessible, relevant or consistently computed to scientific standards,” Thompson said.

“We need trustworthy and transparent data for risk and opportunity identification and corrective actions.”