An improved assessment of forest disturbance using a novel approach of combining a Gaussian mixture model with an EM algorithm
Bibliographic record
Abstract
• DGE method detects forest disturbances with GMM and EM. • DGE outperforms traditional methods like ANAC, PGC, BL, and AI. • Broad DGE applications in disturbances, growth-climate relationship and other ecology fields. Forests have experienced unprecedented decline and mortality beyond their historical range in past decades, which is attributed to disturbances like drought, fire, insects and disease. Traditional disturbance detection methods that typically employ a time series perspective to identify discrete disturbance events within continuous tree growth signals and were mainly designed for gap-scale often fail to identify disturbances across populations. To more accurately identify growth suppression and release clusters based on the perspective of forest population dynamics, here we applied a novel method of detecting forest disturbances using a Gaussian mixture model with an expectation maximisation algorithm (DGE), to fit annual distributions of growth indicators, i.e., tree-ring index. We further compared our novel approach of DGE with five traditional methods based on two sets of real tree-ring data and simulated tree-ring data. The results show an improvement of accuracy (35.5 %–48.1 %), sensitivity (36.6 %–58.1 %), precision (21.2 %–51.5 %) and specificity (11.1 %–20.6 %) for the average of two real radial growth datasets and an improvement of accuracy (7.6 %–13.9 %), sensitivity (70 %), precision (100 %) and specificity (9.1 %–9.7 %) for the simulation radial growth dataset, indicating that our DGE approach performs much better than the traditional methods. This study contributes to an improved strategy and understanding for sustainable forest management in the context of climate warming, demonstrating that our DGE approach can be better applied to global forest disturbance detection under global change.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".