DEEP LEARNING APLICADO NA DETECÇÃO DE CORPOS D’ÁGUA EM IMAGENS DE VANT DO PANTANAL BRASILEIRO
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The Pantanal, the largest continuous flooded plain in the world, faces preservation challenges due to the seasonal flooding cycle and human interventions. To better understand and preserve this biome, monitoring systems are essential, and the use of remote sensing techniques combined with advanced machine learning emerges as a promising strategy. This study investigated deep learning models for water body segmentation in UAV (unmanned aerial vehicle) images of the Pantanal. The images were captured using the MAVIC 2 Air camera, with a spatial resolution of 3 cm. Deep learning models such as InterImage, DeepLabv3+, and SegFormer were compared to evaluate their segmentation capabilities. A protocol was established for evaluation, considering metrics such as Intersection over Union (IoU) and Dice. SegFormer showed the best results, with an IoU of 96.16%, Recall of 97.85%, Precision of 99.46%, and an F1 Score of 98.04%. Although DeepLabv3+ and InterImage presented lower metrics, they also demonstrated robust performance. All models produced satisfactory results, but some difficulties were observed in accurately identifying water bodies.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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 it