Spectral-analysis-based extraction of land disturbances arising from oil and gas development in diverse landscapes
Bibliographic record
Abstract
Accurate and frequent monitoring of land surface changes arising from oil and gas exploration and extraction is a key requirement for the responsible and sustainable development of these resources. Petroleum deposits typically extend over large geographic regions but much of the infrastructure required for oil and gas recovery takes the form of numerous small-scale features (e.g., well sites, access roads, etc.) scattered over the landscape. Increasing exploitation of oil and gas deposits will increase the presence of these disturbances in heavily populated regions. An object-based approach is proposed to utilize RapidEye satellite imagery to delineate well sites and related access roads in diverse complex landscapes, where land surface changes also arise from other human activities, such as forest logging and agriculture. A simplified object-based change vector approach, adaptable to operational use, is introduced to identify the disturbances on land based on red–green spectral response and spatial attributes of candidate object size and proximity to roads. Testing of the techniques has been undertaken with RapidEye multitemporal imagery in two test sites located at Alberta, Canada: one was a predominant natural forest landscape and the other landscape dominated by intensive agricultural activities. Accuracies of 84% and 73%, respectively, have been achieved for the identification of well site and access road infrastructure of the two sites based on fully automated processing. Limited manual relabeling of selected image segments can improve these accuracies to 95%.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| 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 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".