Early Identification of Deforestation using Anomaly Detection
Bibliographic record
Abstract
Research involving anomaly detection in image streams has seen growth through the years, given the proliferation of high-quality image data in various applications. One such application that is in urgent need of attention is deforestation. Detecting anomalies in this context, however, remains challenging due to the irregular and low-probability nature of deforestation events. This study introduces two anomaly detection frameworks utilizing machine learning and deep learning for the early detection of deforestation activities in image streams. Furthermore, Explainable AI was used to explain the black box models of the deep learning-based anomaly detection framework. The class imbalance problem, the inter-dependency between the images with time, the lack of available labelled images, a data-driven anomalous threshold, and the trade-off of accuracy while increasing interpretability in the black box optimization methods are some key aspects considered in the model-building process. Our novel framework for anomaly detection in image streams underwent rigorous evaluation using a range of datasets that included synthetic and real-world data, notably datasets related to Amazon’s forest coverage. The objective of this evaluation was to detect occurrences of deforestation in the Amazon. Several metrics were used to evaluate the performance of the proposed framework.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".