Construction and social implementation of an adaptive optimization system for pest spread prediction and control
| Project/Area Number |
18K14493
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 40010:Forest science-related
|
|---|
| Research Institution | Tokyo University of Science (2020-2022)
National Agriculture and Food Research Organization (2018-2019) |
|---|
Principal Investigator |
Itaka Shizu 東京理科大学, 創域理工学部経営システム工学科, 助教 (80776336)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2019: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
|
|---|
| Keywords | 被害木抽出 / 被害予測 / 拡散モデル / 拡散制御 / ナラ枯れ / 森林病害虫 / 防除 / おとり丸太 / 施設配置問題 / 森林管理 / 病害虫拡散モデル |
|---|
| Outline of Final Research Achievements |
What is needed in forest resource management is a versatile resource management system that not only predicts damage but also proposes a plan to control the spread of damage. The objective of this study was to construct an adaptive and versatile optimization system for pest spread forecasting and spread control and to propose a control plan for the field. This study focused on oak wilt disease. First, a method for classifying dead trees using a deep learning image classification technique based on aerial images obtained from unmanned aerial vehicle (drone) was proposed. Then, to construct a spread model, a machine learning technique was used to identify the factors that cause the spread, using meteorology and topography as explanatory variables, and conducted simulations. Furthermore, the optimal placement of log pile traps was analyzed, which is one of the methods to control oak wilt disease.
|
| Academic Significance and Societal Importance of the Research Achievements |
森林現場では、林業従事者の減少や高齢化により、経験に基づく現場感覚の継承は難しくなっている。現場感覚を科学的方法論に落とし込み、現場で使えるシステムを構築することは、意思決定の支援になると同時に知識の継承にもなる。本研究では、拡散モデルを構築するのみならず、意思決定者にその制御プランを提示できるようなシステムを構築することを目指した。森林現場におけるドローンの導入は進んでいるものの、得られた空撮画像の利用は限定的であるため、シンプルな手法による被害樹木を抽出する手法の提案は現場に寄与できる。ナラ枯れ防除手法の一つであるおとり丸太の最適配置を求めるモデルの提案に関して、このような研究は他に無い。
|
Report
(6 results)
Research Products
(7 results)
