The Center for Data Innovation recently spoke with Julie Stanford, CEO of eDNA Explorer, a California-based company developing an AI-powered platform that uses environmental DNA and mapping data to monitor biodiversity and ecosystem health. Stanford explained how the platform analyzes genetic traces from soil and water samples, combines them with geospatial data, and uses AI tools to identify species, track environmental change, and generate ecological insights.
David Kertai: What does eDNA Explorer offer?
Julie Stanford: Many organizations today struggle to understand ecosystem health because traditional biodiversity monitoring is slow, expensive, and often incomplete. Field surveys can miss rare or difficult-to-detect species, lab workflows can take months, and fragmented data makes it hard to track how environmental conditions change over time. As a result, conservation groups, land managers, governments, and sustainability teams often lack the timely information they need to guide restoration projects, verify environmental claims, or meet emerging reporting requirements.
eDNA Explorer addresses these challenges with an AI-powered platform that analyzes environmental DNA, or eDNA, alongside mapping and environmental data to generate biodiversity insights. Environmental DNA refers to tiny traces of genetic material that organisms leave behind in soil or water through skin cells, waste, hair, or other biological material. Instead of sending teams into the field to visually search for species one by one, a single soil or water sample can reveal hundreds of organisms at once.
Our platform streamlines planning, sampling, lab coordination, and data processing, then uses AI tools to interpret results and highlight meaningful ecological patterns. In turn, we give organizations a fast, clear view of species presence, ecosystem trends, and management priorities in a format that supports confident, data-driven decisions.
Kertai: How does eDNA identify what species are present in an ecosystem?
Stanford: Environmental DNA acts like a genetic fingerprint that organisms leave behind through shed skin and other biological traces. When we collect a soil or water sample, we capture those fragments from the surrounding environment. Lab tools then read the genetic code in the sample, revealing which organisms recently interacted with that ecosystem, from animals like salamanders to tiny fungi that traditional surveys often overlook.
Our AI-powered platform processes these DNA sequences and compares them against large genetic databases containing known species information. By automating this comparison, we quickly generate a comprehensive list of organisms present in the area. This provides a fast, non-invasive way to survey entire biological communities using only a small amount of soil or water.
Kertai: How does your platform combine DNA data with mapping tools to monitor ecosystems?
Stanford: We combine eDNA results with geospatial, or location-based, data to show where and when species appear across a landscape. By integrating our findings with Google Earth Engine and project-specific environmental information, we place each species detection in context. This helps land managers see biodiversity patterns, understand how environmental conditions or human activity influence species communities, and track ecosystem changes. The result is a clear, map-based view of ecosystem health that supports restoration planning, conservation efforts, and long-term environmental management.
Kertai: How does your AI platform enhance or improve the accuracy of biodiversity monitoring?
Stanford: Our AI tools analyze large, complex datasets to uncover ecological patterns that are difficult to detect manually. We use these models to identify the most important environmental variables, estimate which species are likely present in areas with limited sampling data, reveal relationships among organisms, and automatically generate ecosystem health indicators. These capabilities turn species lists into more meaningful measures of ecosystem stability and change.
As our dataset grows, our predictive models will help forecast biodiversity trends and identify the drivers behind species decline in specific areas. This shifts biodiversity monitoring from a reactive process to a more proactive one, helping organizations anticipate changes, allocate resources more effectively, and choose conservation strategies with a higher likelihood of success.
Kertai: What’s your vision for the future of eDNA Explorer?
Stanford: We want biodiversity insight to become as accessible and routine as checking the weather. Our long-term vision is a platform that delivers fast, accurate ecological intelligence to anyone managing land or environmental risk. We are already expanding the system with AI-powered tools that help users answer questions related to restoration, wildfire resilience, and forest productivity. Ultimately, we want to provide organizations with the information they need to slow species loss, strengthen ecosystem management, and make better environmental decisions at scale.
