Skip site navigation
Maryland Today
Athletics Arts & Culture Campus & Community People Research
Athletics Arts & Culture Campus & Community People Research
Research

UMD-Led Team Awarded $3.6M NSF Grant to Advance Pollinator Conservation

AI and economics will help analyze the value of ecosystems.

21 0145 elinor lichtenberg0516 1920x10801

University of North Texas researcher Elinor Lichtenberg (right), part of a UMD-led research team, conducts a field survey of pollinators to verify satellite data and AI prediction models. (Photo by Ahna Hubnik / University of North Texas)

A University of Maryland-led research team has been awarded a $3.6 million grant from the National Science Foundation (NSF) to develop a new scientific framework for understanding and putting a value on the benefits that nature provides, with an initial focus on the conservation of pollinating insects required for many crops and other plants to grow.

Putting a value on these “ecosystem services” can be helpful for policymakers and conservationists trying to understand where conservation dollars would do the most good. The multi-institutional team is led by Professor Eric Lichtenberg of the Department of Agricultural and Resource Economics. 

“We know that wild bees and other insects are really important for pollinating so many of the fruits and vegetables we eat, but it’s been really hard to document just how valuable they are,” Lichtenberg said. “Pollination ecology studies provide great evidence, but they take so much time and labor that the evidence they give us is at scales that are too small and geographically limited to generalize from. Larger-scale studies use generalizations that don’t give us accurate estimates.”

The team’s new study combines artificial intelligence, theory and methods from ecology, and cutting-edge methods in economics to bridge the gap between the two, he said. The methods the project will create have great potential for documenting the value of other ecosystem services.

The first step is to develop AI and remote-sensing tools capable of detecting small objects such as individual bee boxes and flower density across large landscapes. The tools will generate datasets far more extensive than traditional surveys allow.

Next, the researchers will validate these AI-derived observations with on-the-ground ecological fieldwork, verifying that what the models detect from satellites or drones matches what is happening in the landscape and revising their algorithms as needed. Then they will combine data from remote sensing, surveys and government data for analysis using modern econometric methods, grounded in ecological and economic theory, to statistically link habitat conditions, managed pollinator populations (like commercial honeybee stocking), land use decisions and crop yields.

The end results will be fed into economic models that can assign a monetary value to a “nonmarket” good like pollination, which benefits farmers and society but doesn't have a direct price tag. The team expects to identify specific land-use practices that most benefit pollinators, and to quantify the economic value those practices generate.

While centered on pollinators, the resulting framework will offer a new transdisciplinary methodology for guiding conservation and land management decisions more broadly.

The five-year project supported by NSF’s Growing Convergence Research program begins Tuesday, bringing together expertise from five different disciplines and institutions. The team includes collaborators Kathy Baylis from the University of California, Santa Barbara’s geography department, Rufus Isaacs from Michigan State’s entomology department, and Elinor Lichtenberg and Xiaohui Yuan from the University of North Texas’s biology and computer science and engineering departments.

Related Articles

Research

July 16, 2026
Sylvain Veilleux and his collaborators will equip a ground-based telescope with the observing power of space telescopes for the first time.

Research

August 03, 2026
UMD researcher is developing a tool to optimize calculations to make decisions.