Identification of water bodies using machine learning and satellite images in a region of the Peruvian Amazon
Bibliographic record
Abstract
The contamination of water bodies in the Peruvian Amazon, particularly in the Madre de Dios region, has increased significantly due to illegal mining activities that severely impact human health and ecosystems. This issue is exacerbated by the lack of effective tools for monitoring and managing water bodies, which could help mitigate negative effects and ensure their preservation. In this study, water bodies were identified using machine learning and satellite image analysis from the area known as 'La Pampa', a zone severely affected by illegal mining located between kilometers 98 and 115 of the Interoceanic Highway in the Madre de Dios region, Peru. Using Google Earth Engine, 600 satellite images were collected and classified into three categories: water bodies (200), soil (200), and vegetation (200). Models such as Random Forest, K-Nearest Neighbors, Support Vector Machines, and a Multilayer Perceptron were trained and validated. The results show that the K-Nearest Neighbors model achieved the best performance, with a precision of 92.58%, recall of 92.74%, F1-Score of 92.61%, and an accuracy of 92.49%, outperforming the other evaluated models. These findings highlight the feasibility of combining machine learning with satellite images for the management of water resources in affected areas, offering a valuable tool for environmental decision-making.
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 | 0.002 | 0.002 |
| 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".