Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan
Japan’s forest sector faces persistent challenges due to fragmented land ownership and an increasingly skewed age-class structure, undermining not only management efficiency but also economic viability and long-term sustainability. This study proposes a novel approach to forest stand aggregation by...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525001923 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850279293170483200 |
|---|---|
| author | YangYu You Hyun Bae Kim Takuyuki Yoshioka |
| author_facet | YangYu You Hyun Bae Kim Takuyuki Yoshioka |
| author_sort | YangYu You |
| collection | DOAJ |
| description | Japan’s forest sector faces persistent challenges due to fragmented land ownership and an increasingly skewed age-class structure, undermining not only management efficiency but also economic viability and long-term sustainability. This study proposes a novel approach to forest stand aggregation by integrating Geographic Information Systems (GIS) with Graph Convolutional Networks (GCNs), enabling a data-driven modeling of spatial interactions among forest stands. Unlike traditional rule-based methods that rely on fixed thresholds and static adjacency rules, the GCN framework allows stand-level attributes—such as slope, road proximity, and spatial adjacency—to influence each other through a graph structure. This interaction generates new aggregated feature values that reflect underlying spatial dependencies. Using forestry data from the Nishikawa area, two types of stand connectivity models—selective and full connection—were constructed to represent different spatial contexts. Results show that the selective model emphasizes road accessibility, while the full model better maintains age-class continuity and internal cohesion. This GCN-based aggregation method offers a flexible and scalable solution to stand consolidation, forming a foundation for more precise and terrain-aware harvesting plans in future forest management strategies. |
| format | Article |
| id | doaj-art-538604d8ac68411bbf9a7a1db51a240f |
| institution | OA Journals |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-538604d8ac68411bbf9a7a1db51a240f2025-08-20T01:49:08ZengElsevierSmart Agricultural Technology2772-37552025-08-011110095910.1016/j.atech.2025.100959Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in JapanYangYu You0Hyun Bae Kim1Takuyuki Yoshioka2Graduate School of Agricultural and Life Sciences, The University of TokyoDepartment of Biobased Materials, Chungnam National UniversityGraduate School of Agricultural and Life Sciences, The University of TokyoJapan’s forest sector faces persistent challenges due to fragmented land ownership and an increasingly skewed age-class structure, undermining not only management efficiency but also economic viability and long-term sustainability. This study proposes a novel approach to forest stand aggregation by integrating Geographic Information Systems (GIS) with Graph Convolutional Networks (GCNs), enabling a data-driven modeling of spatial interactions among forest stands. Unlike traditional rule-based methods that rely on fixed thresholds and static adjacency rules, the GCN framework allows stand-level attributes—such as slope, road proximity, and spatial adjacency—to influence each other through a graph structure. This interaction generates new aggregated feature values that reflect underlying spatial dependencies. Using forestry data from the Nishikawa area, two types of stand connectivity models—selective and full connection—were constructed to represent different spatial contexts. Results show that the selective model emphasizes road accessibility, while the full model better maintains age-class continuity and internal cohesion. This GCN-based aggregation method offers a flexible and scalable solution to stand consolidation, forming a foundation for more precise and terrain-aware harvesting plans in future forest management strategies.http://www.sciencedirect.com/science/article/pii/S2772375525001923Stand aggregationGraph neural networkForest managementHarvesting planSustainability |
| spellingShingle | YangYu You Hyun Bae Kim Takuyuki Yoshioka Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan Smart Agricultural Technology Stand aggregation Graph neural network Forest management Harvesting plan Sustainability |
| title | Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan |
| title_full | Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan |
| title_fullStr | Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan |
| title_full_unstemmed | Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan |
| title_short | Optimizing forest stand aggregation in fragmented stands using graph convolutional networks: A case study in Japan |
| title_sort | optimizing forest stand aggregation in fragmented stands using graph convolutional networks a case study in japan |
| topic | Stand aggregation Graph neural network Forest management Harvesting plan Sustainability |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525001923 |
| work_keys_str_mv | AT yangyuyou optimizingforeststandaggregationinfragmentedstandsusinggraphconvolutionalnetworksacasestudyinjapan AT hyunbaekim optimizingforeststandaggregationinfragmentedstandsusinggraphconvolutionalnetworksacasestudyinjapan AT takuyukiyoshioka optimizingforeststandaggregationinfragmentedstandsusinggraphconvolutionalnetworksacasestudyinjapan |