A Dynamic Graph Neural Network Approach for Forest Cover Change Detection and Carbon Sink Assessment Using Remote Sensing Imagery
Bibliographic record
Abstract
Against the backdrop of accelerating global climate change, accurate assessment of forest cover dynamics and carbon sink capacity is critical to addressing the climate crisis and achieving the "dual carbon" goals.With the growing availability of high-resolution, multitemporal remote sensing data, efficiently processing complex spatial relationships and temporal dynamics has become a central challenge in forest change detection and carbon sink estimation.Traditional pixel-or object-based remote sensing classification methods often overlook spatial correlations and contextual information, leading to limited detection accuracy in regions with complex terrain.Similarly, carbon sink assessment methods based on statistical models or static data fail to capture the dynamic processes of forest change and their spatiotemporal coupling with carbon sequestration, resulting in insufficient accuracy and timeliness.Moreover, the low efficiency of large-scale data processing remains a pressing issue.To address these challenges, this study proposes a dynamic graph neural network-based approach for forest cover change detection and carbon sink assessment.On one hand, a dynamic graph model tailored for forest remote sensing imagery is constructed, leveraging the powerful spatiotemporal representation capabilities of graph neural networks to achieve precise detection of forest cover changes.On the other hand, based on the detection results, a carbon sink estimation model is developed that integrates forest type, growth stage, and climatic conditions to quantify carbon sink capacity and potential.The proposed method enhances both the accuracy and efficiency of forest change detection in complex environments and provides a theoretical and technical foundation for dynamically tracking forest carbon sink evolution, informing forest management policies, and guiding carbon trading strategies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".