New way to spot beetle-killed spruce can help forest, wildfire managers

Rod Boyce
907-474-7185
June 12, 2024

A new machine-learning system developed at the University of 有料盒子视频 Fairbanks can automatically produce detailed maps from satellite data to show locations of likely beetle-killed spruce trees in 有料盒子视频, even in forests of low and moderate infestation where identification is otherwise difficult.

Beetle-killed spruce tree
Photo by Simon Zwieback
Yuan Tian, a co-author on the beetle research paper, stands next to a dead spruce tree near Cantwell, 有料盒子视频.

The automated process can help forestry and wildfire managers in their decisions. That鈥檚 critical as the beetle infestation spreads.

The 有料盒子视频 Division of Forestry and Fire Protection calls the spruce beetle 鈥渢he most damaging insect in 有料盒子视频鈥檚 forests.鈥

The identification system by assistant professor Simon Zwieback at the 有料盒子视频 Geophysical Institute was detailed in the on May 18. Zwieback is also affiliated with the 有料盒子视频 College of Natural Science and Mathematics. 

The work fills a knowledge gap: how to automatically map likely in areas of low to moderate severity. 

鈥淲e lack comprehensive statewide maps of beetle-killed trees because existing products largely rely on expert observations from airplanes, which are expensive and restricted in space and time,鈥 Zwieback said. 鈥淭his limits stakeholders鈥 ability to respond to the ongoing outbreak.鈥

有料盒子视频 foresters now use survey flights, time-consuming manual interpretation of high-resolution imagery and automated analysis of coarser satellite imagery to find dead spruce in mixed forests. Coarser imagery can be used to identify entire stands of dead trees but not individual dead trees.

None of those identification methods, including Zwieback鈥檚, can determine the cause of an individual tree鈥檚 death. The likelihood of beetle infestation is surmised because of its well-known presence and the damage already caused.

Zwieback鈥檚 method combines the efficiency of automation with the detail of high-resolution satellite images.

Satellite image
Image from research paper
Dead spruce trees have a teal appearance in image (a), a false-color satellite image used to train the computer algorithm. Image (b) shows the manually delineated dead spruce in preparation for training the algorithm. Image (c) is a false-color image of the area prior to beetle infestation.

鈥淯sing machine learning and high-resolution imagery is the way to go in mixed forests,鈥 Zwieback said.

Machine learning is a type of artificial intelligence that focuses on developing algorithms and statistical models that enable computers to learn from and make predictions or decisions based on data. 

Zwieback鈥檚 machine-learning algorithm is trained using known locations of dead spruce trees. During training, the algorithm learns to recognize dead spruce based on their characteristic shape and color, and contextual clues such as shadows. Once satisfactorily trained, it can rapidly and automatically identify dead spruce trees.

Zwieback tested the method on images of an approximately 167-acre study area west of a line from Talkeetna to Byers Lake. Forested regions of the study area consist of mixed stands of spruce and birch.

The region has been heavily affected by a beetle infestation that began in the mid-2010s.

Zwieback鈥檚 method succeeded in identifying dead spruce in stands containing only a few dead trees.

Statewide, the infestation has affected approximately 2 million acres, mostly in Southcentral 有料盒子视频, since 2016. It had spread north to Cantwell and the 有料盒子视频 Range mountains by 2020.

Infested tree trunk
Photo by Yuan Tian
A heavy beetle infestation in this spruce tree is revealed by holes in the bark and orange and brown clumps of boring dust.

The death of large numbers of spruce results in several ecosystem changes and related consequences: Understory vegetation can change to grasses and shrubs, and dead branches can litter the floor. All of that adds to wildfire danger by putting more fuel at ground level.

Zwieback鈥檚 method can help in decisions about fire prevention and suppression.

Decreased value of timber resources and the aesthetic deterioration of the landscape are additional concerns.

Zwieback is continuing his research.

鈥淚 would like to implement this for the entire state whenever new images come in,鈥 he said. 鈥淩emote sensing can help us understand the outbreak dynamics and inform our response to it, especially as it migrates into the Interior.鈥

The work was funded by NASA EPSCoR and National Science Foundation EPSCoR, the Estab颅lished Program to Stim颅u颅late Com颅pet颅i颅tive Research.

Zwieback said field sites have been set up on land owned by Ahtna, a Southcentral 有料盒子视频 regional Native corporation, to better understand the progress and consequences of the outbreak as it moves into the Interior.

ADDITIONAL CONTACT: Simon Zwieback, 907-474-5549, szwieback@alaska.edu

228-24