Search across all content
projectThe Forest Pest Control Support System is a platform that provides functions ranging from data management for pine wilt disease control to detection and basic design support, as well as comparing and displaying control results.
Current detection of forest pests and diseases (Pine Wilt Disease) relies on expert visual interpretation, leading to time delays and reduced accuracy during hyper-scale regional diagnostics. This limits the timely establishment of efficient control plans for the right locations. Therefore, this project aimed to build a system that shortens forest pest identification time and improves accuracy by integrating and utilizing Pine Wilt Disease Forest image data accumulated by the Korea Forest Service with AI technology.
To develop an AI solution, the project obtained and refined approximately 274.7 hectares of drone imagery captured between 2019 and 2023 from the Korea Forest Service (collaborating agency) and the Korean Forestry Promotion Institute's Pine Wilt Disease Center (demand agency). This yielded 125,000 pieces of suspected dead tree training data. Based on this, the system was trained by an AI model for detecting suspected pine wilt disease-affected dead trees and developed and validated the solution.
The Forest Pest Control Support System is a platform that provides functions ranging from data management for pine wilt disease control to detection and basic design support, as well as comparing and displaying control results. Its primary function is forest pest detection management, using AI to detect suspected pine wilt disease-affected dead trees, manage their history, verify detection results, and provide result files (SHP).
Quantity of data provided by demand agency
| Category | Data Type | First Year | Second Year | Third Year | Total |
|---|---|---|---|---|---|
| Quantity Provided by Korea Forest Promotion Agency | Drone imagery (ha) | 1,385,000 | 636,000 | 726,000 | 2,747,000 |
| Quantity Provided by Korea Forest Promotion Agency | Dead tree location coordinates (units) | 146,938 | 171,593 | 223,899 | 542,430 |
Over the past three years, through ministry-collaborative AI diffusion projects, the performance of the AI-based forest pest control support system for detecting suspected pine wilt disease-affected dead trees was enhanced through verification by an accredited testing agency (TTA).
Furthermore, through on-site verification in the jurisdiction of the Southern Regional Forest Service, the project achieved a significant improvement in operational efficiency by reducing the design time from the previous 25 days to just 4 days, a reduction of approximately 80%.
It is anticipated that applying this AI solution in the future by regional forest offices or nationwide local governments will reduce the costs associated with the hundreds of billions of won budget and manpower allocated annually for forest pest control. Furthermore, it is expected to contribute to the protection of our beautiful forests and natural ecosystems.
Launch year: 2022
Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.1, https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=28997&parentSeq=29034
In partnership with
National Information Society Agency (NIA)
In partnership with
National Information Society Agency (NIA)
Connect with 500,000+ public servants solving your hardest challenges.
Connect with 500,000+ public servants solving your hardest challenges.
Help public servants worldwide learn from your work, what worked, what flopped and what you'd do differently
Share your project
Log in or sign up to continue the conversation