Identification of Forest Road Construction Year from Historical Remotely Sensed Data by Integrating Change Detection and Geometric Connectivity
Bibliographic record
Abstract
Current and highly accurate forest disturbance information is critical for monitoring and managing forested ecosystems. The types, rates, and responses to past disturbances allow for improved predictions for how forests will respond to current and future disturbances. Forest roads, a short-term forest stand replacing disturbance, are associated with ecosystem degradation. Determining the age of different elements of forest road networks can enable long term monitoring and assist with sustainable forestry management. To determine the age of construction of forest roads within Ontario’s managed forests, a semi-automatic road extraction and Post-Classification Change Detection (PCCD) approach was developed with Best Available Pixel (BAP) composites of Landsat imagery. A study site was selected near Savant Lake, Ontario for the years between 1974 and 2019. The BAP composite approach uses sensor, day of year (DOY), distance to cloud or cloud shadow, opacity, and pixel brightness scores to create yearly composites which are free of clouds or anomalies and optimized for the intended analysis. An unsupervised classifier, Jenks Optimization, was used to differentiate road and non-road pixels from an image masked with current known road areas. This method aims to reduce the average deviation of each value from the mean of the class and increase the deviation of each class from the mean of other classes. PCCD was completed with the pre- and post-1984 periods resulting in overall accuracies of 80% and 68%, respectively. Four logic rules, which leverage the topological relations between road segments and address road gaps due to occlusions or sensor anomalies, were applied twice throughout the process. The logic rules increased the overall accuracy up to 3% for each annual binary road network and up to 3% for the final year of construction road network. Understanding historic types, rates, trends, and patterns of ecosystem change across large areas with high spatial detail is essential for effective forest monitoring and sustainable management. Time series analyses based on optimized annual BAP composites and post-processing logic rules can provide information to support these endeavors.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".