Machine learning leads to a first in forestry management tools

By Jenifer Fouch
University of Arkansas System Division of Agriculture
Arkansas Agricultural Experiment Station

FAYETTEVILLE, Ark. — A new dataset is providing a bird’s-eye view of Arkansas’ forests 1 meter at a time.

An Arkansas researcher has developed the first high-resolution forest canopy cover dataset for an entire state, providing valuable insights for forest management and conservation to a major economic sector in Arkansas.

“I had this vision of creating something that we can rely on,” said Hamdi Zurqani, assistant professor for the College of Forestry, Agriculture and Natural Resources at the University of Arkansas at Monticello and researcher with the Arkansas Agricultural Experiment Station. “No data of this kind existed before for an entire state. Usually, people only create similar data for site-specific projects.”

FOREST CANOPY COVER — Hamdi Zurqani developed the first high-resolution forest canopy cover dataset for an entire state. (College of Forestry, Agriculture and Natural Resources at the University of Arkansas at Monticello photo by Lonnie Tegels.)

The 1-meter measurements are unique. Until now, the most common forest measurements and datasets have come from satellite imagery at 30-meter spatial resolution, said Zurqani, who conducts research as part of the Arkansas Forest Resources Center, a partnership between the University of Arkansas System Division of Agriculture and UAM. The experiment station is the research arm of the Division of Agriculture.

Forest canopy cover measures the coverage of tree crowns from an aerial view. It shows how much a forest’s uppermost layer of branches, leaves and vegetation forms a continuous cover over the ground. This detailed information is crucial for tracking forest health, as canopy cover is essential for carbon sequestration, wildlife habitat and water regulation.

Zurqani says accurate mapping of tree coverage helps scientists monitor and manage forest resources effectively, ensuring the sustainability of these ecosystems. This information can also assist with wildfire risk assessments, tracking forest health threats from pests and climate, and urban planning.

Zurqani’s research was published late last year in the academic journal Remote Sensing Applications: Society and Environment. The article was titled “High-resolution forest canopy cover estimation in eco-diverse landscape using machine learning and Google Earth Engine: Validity and reliability assessment.”

According to the latest Arkansas Agricultural Profile, forests cover 57 percent of the state, and timber was one of the state’s top commodities in 2021 with about $409 million in cash farm receipts.

Machine learning

To create the Arkansas forest canopy cover dataset, Zurqani used machine learning techniques and the Google Earth Engine.

Machine learning is a branch of artificial intelligence that allows computers to “learn” from data and improve their performance over time without being programmed. Machine learning algorithms identify patterns in data, make predictions and adapt to new information.

The Google Earth Engine is a cloud-based platform designed for processing and analyzing large-scale geospatial data. It provides access to a vast repository of satellite imagery and geospatial datasets.

Zurqani’s research utilized high-resolution National Agriculture Imagery Program aerial imagery to apply and test his methods.

The National Agriculture Imagery Program, administered by the United States Department of Agriculture, captures high-resolution aerial imagery of agricultural areas during the growing season. The imagery is used for monitoring crop conditions, assessing land use changes, and supporting various agricultural and environmental applications.

Room for growth

A finer spatial resolution of Arkansas forests provides a more accurate assessment of canopy structure and composition. Zurqani says this precision is essential for monitoring changes in forest dynamics, identifying vulnerable areas and implementing targeted conservation strategies. Zurqani hopes his 1-meter dataset could become the new standard for measuring forest canopy cover.

HEALTHY FORESTS — Aerial view of the Arkansas Agricultural Experiment Station's Livestock and Forestry Research Station in Batesville (U of A System Division of Ag photo by Ben Aaron).

“So, in the future, we can use this dataset to cover all forest areas and see which trees are healthy and which ones are diseased,” Zurqani said. “Because it's high-resolution imagery, we can detect the location of the trees within urban areas.”

There are 502 cities and 75 counties in Arkansas, according to the U.S. Census Bureau, and Zurqani said he evaluated forests and tree-covered areas within those cities and counties. While initially focused on the state of Arkansas, Zurqani envisions expanding this innovative approach to cover all 50 states.

“The studies demonstrate that machine learning and cloud computing technologies can produce reliable, high-resolution forest cover datasets,” Zurqani said. “These methods can be applied to other regions globally, enhancing forest management and conservation efforts worldwide.”

To learn more about Division of Agriculture research, visit the Arkansas Agricultural Experiment Station website. Follow us on X at @ArkAgResearch, subscribe to the Food, Farms and Forests podcast and sign up for our monthly newsletter, the Arkansas Agricultural Research Report. To learn more about the Division of Agriculture, visit uada.edu. Follow us on X at @AgInArk. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit uaex.uada.edu.

Geospatial AI provides new avenue for forest health research

By Nick Kordsmeier
U of A System Division of Agriculture 

MONTICELLO, Ark. — While an emerging fungal disease continues to chip away at the forestry industry in the southern United States, remote sensing researcher Hamdi Zurqani is developing artificial intelligence models to seek answers from the skies.

UNMANNED AIRCRAFT — Hamdi Zurqani, remote sensing researcher and assistant professor for the College of Forestry, Agriculture and Natural Resources at University of Arkansas at Monticello, inspects a drone outfitted with a LiDAR, or light detection and ranging, system. (U of A System photo courtesy of Zurqani.)

“My job is to identify different stages of mortality,” said Zurqani, assistant professor for the College of Forestry, Agriculture and Natural Resources at the University of Arkansas at Monticello. Using aerial imagery obtained from drones, Zurqani said he is developing tools that give landowners and other stakeholders the information they need to manage this growing threat to the forestry industry.

By applying geospatial artificial intelligence techniques, Zurqani said he can assess how many trees have been affected by the disease. “How many trees have already died? How many trees may be in the early stage that are going to get worse? How many trees are still green?” he said.

Since summer 2022, foresters and researchers have been fielding calls about pine decline in Arkansas. Pine decline is a convergence of environmental and genetic issues that cause tree health problems in pine forests. Results from diagnostic tests in July 2023 confirmed that a fungal disease called brown spot needle blight is at least partially to blame.

“It's kind of nipping away at pine forests,” said Michael Blazier, director of the Arkansas Forest Resources Center and dean of the College of Forestry, Agriculture and Natural Resources. “Although there are pockets of dying trees within affected forests, a bigger issue could be slower growth of infected forests.”

Blazier said that when trees lose their foliage, as often happens with the needle blight disease, they have less energy to invest in growing their trunk diameter. Less trunk growth means less wood production and delayed harvest.

DETECTED — Aerial imagery of pine forests from remote sensing researcher Hamdi Zurqani are used in an AI model under development. The top photo shows a section of pine trees in southeast Arkansas impacted by disease. The bottom graphic shows part of the output from the AI detection approach, which shows living trees in green and dead trees in brown. Red boxes have been added to show corresponding dead spots. (U of A System photo courtesy of Zurqani.)

Understanding the how and why of brown spot needle blight remains the primary focus for researchers in Arkansas and the wider region, Blazier said. That’s where Zurqani’s work comes in.

“If we were able to identify the early stages of the disease, we can somehow get a clue about what’s going to happen in the future,” Zurqani said.

In Arkansas, Blazier said the fight against pine decline has been highly collaborative. The Forestry Division of the Arkansas Department of Agriculture and the Arkansas Forestry Association have been working closely with the Arkansas Forest Resources Center, which conducts research and extension activities through the Arkansas Agricultural Experiment Station and the Cooperative Extension Service, the University of Arkansas System Division of Agriculture’s research and outreach arms.

“We have a tight working relationship between all of those agencies,” Blazier said. “There’s been excellent communication between the university, extension service, forestry association and the state’s forestry division.”

Regional challenge

In August 2023, Blazier attended a meeting at Auburn University to discuss the needle blight phenomenon with researchers and industry stakeholders from across the southern U.S.

According to information from the U.S. Department of Agriculture’s Forest Service, brown spot needle blight has been confirmed in nine states, including Alabama, Arkansas, Florida, Georgia, Louisiana, Mississippi, South Carolina, Tennessee and Texas. Severe damage, however, has so far been limited to Alabama, Arkansas, Louisiana and Mississippi.

The meeting was organized by Lori Eckhardt, professor and director of Auburn University’s Forest Health Cooperative.

“I organized this meeting to bring together industry, government, academia and private landowners to create a space in which attendees can discuss questions, brainstorm ideas, identify problems and make decisions and develop solutions pertaining to brown spot needle blight,” Eckhardt said.

“Collaboration is important between the researchers and the landowners,” she said. “The day-to-day managers in the field can share knowledge that assists us as researchers in asking good questions to design studies that better help us understand and manage the disease. Working together will help us find answers sooner.”

Collaboration leads to clues

Blazier said the Auburn meeting provided an opportunity for participants to share what actions each affected state is taking on the research side to understand what’s causing the problem.

“One of the things that was shared at the Auburn meeting was some anecdotal evidence from the forest industry showing that there may be a soil nutrient facet to this,” Blazier said. “And that's actually something that we are looking into further within the Arkansas Forest Resources Center.”

Researchers have been collecting samples this winter from stands of trees affected by pine decline and analyzing nutrient levels. If a nutrient deficiency is found to contribute to pine decline, Blazier said that targeted soil fertilization might be a way to fight the disease.

“And that would actually give us another tool,” he said.

Looking to the future

As the winter dormant season ends and the life cycles of fungal diseases pick up again, Blazier said that testing for pine decline will continue next month.

“We’re going to resume testing on a monthly basis as a group in February, and we’ll continue that all the way through the growing season,” he said. That information will continue to feed into Zurqani’s research efforts using geospatial AI.

Blazier sees hope for spatial analysis and machine learning tools to help researchers identify patterns in the data and get to the bottom of pine decline.

“We're really optimistic,” he said.

To learn more about Division of Agriculture research, visit the Arkansas Agricultural Experiment Station website: https://aaes.uada.edu/. Follow us on Twitter at @ArkAgResearch. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit www.uaex.uada.edu. Follow us on Twitter and Instagram at @AR_Extension. To learn more about the Division of Agriculture, visit https://uada.edu/. Follow us on Twitter at @AgInArk.