Development of Advanced Remote Sensing Methods in Quantifying Wildlife Habitat Management
Bibliographic record
Abstract
Wildlife habitats have been affected by human activities and climate change. Animal diversity is declining at an unprecedented rate. Tools used to obtain a rapid assessment of wildlife habitats at different scales are urgently needed. The habitat management tools that are currently used for conservation and monitoring wildlife are often limited by the availability of mapped habitat information that is tailored to the wildlife of interest and that covers appropriate geographic and temporal extents of interest. Failure to adequately map specific habitat features can limit effective management. Advancements in remote sensing and related technologies have increased the resolution and quantity of landscape data, providing an excellent opportunity to extract various environmental features for examining habitat selection and mapping wildlife habitats to a broad extent. \nTo exploit the potential of the emergent remote sensing data sets, the focus of this study was to develop advanced methodologies to derive information related to the properties of environmental features at different scales and to generate tools to improve the understanding of a wildlife habitat landscape that can benefit from habitat management. Specifically, an advanced algorithm was developed that utilized spatial pattern analysis to classify the forest succession stages from optical imagery and had a classification accuracy of 89%. In addition, a novel method was proposed to extract road features from the road structure knowledge followed by a deep learning VGG 16 classification for a refined output. An overall accuracy of 74% was achieved for the forest road extraction. A robust and operational stepwise automatic thresholding method was developed to accurately map the dynamics of surface water bodies from SAR data, with an overall accuracy of 95%. In addition, an advanced fuzzy AHP model was utilized to accurately map beaver-altered wetlands in the landscape using remote sensing products derived based on the knowledge of beaver activities, where an average of 83.0% of the known beaver dams and 72.5% of the known beaver ponds were correctly identified. In conclusion, this research demonstrated that the advanced methods utilizing multi-source and multi-temporal remote sensing data could effectively characterize and extract environmental features that benefit wildlife habitat management.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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".