Predicting Alder shrub expansion in Sub-Arctic Alaska using machine learning, satellite data, and environmental variables
Bibliographic record
Abstract
The wider Fairbanks area, a sub-Arctic region of Alaska, USA, is home to a variety of alpine, oroarctic tundra that is being impacted by climate warming. This has resulted in an infilling and expansion of shrubs across the tundra and an elevational increase in the range limits of tall shrubs. Expansion of Alder (a key pioneer tall shrub) is thought to result from Arctic warming and shifts in its spread are likely to be a result of such warming. \n \nAlder can fix atmospheric nitrogen by virtue of a mutualistic association with soil bacteria, which subsequently becomes available to other shrubs, potentially relieving local soil nitrogen limitations and promoting a positive growth response to climate warming. This potential landscape-scale change requires information of change at a suitable scale. However, Alder and other tall shrubs have been hard to measure using existing remote sensing approaches alone. This is mainly due to issues surrounding data availability and suitable spatial resolution of imagery. \n \nSatellite remote sensing and environmental data are combined to create a map of Alder expansion across the wider Fairbanks area. A methodology is presented where ecological variables are integrated into prediction maps using a combination of regression and machine learning to estimate spatial extents. A baseline for a minimum number of high resolution training polygons is found to understand minimum required inputs. Field-based validation data were collected using a random sampling design across four different locations within the Yukon-Koyukuk area, Alaska. The combination of satellite data and environmental variables yields the best results for predicting Alder locations across the study area with a model accuracy of 0.99 and User’s accuracy of 43.66%. Orthomosaics as validation data are found to be very useful, enabling better quantification of smaller plant functional types for more accurate error matrix class assignment increasing overall model accuracy. \n
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".