UAV-Based Air Pollutant Source Localization Using Combined Metaheuristic and Probabilistic Methods
Bibliographic record
Abstract
Air pollution is one of the greatest risks for the health of people. In recent years, platforms based on Unmanned Aerial Vehicles (UAVs) for the monitoring of pollution in the air have been studied to deal with this problem, due to several advantages, such as low-costs, security, multitask and ease of deployment. However, due to the limitations in the flying time of the UAVs, these platforms could perform monitoring tasks poorly if the mission is not executed with an adequate strategy and algorithm. Their application can be improved if the UAVs have the ability to perform autonomous monitoring of the areas with a high concentration of the pollutant, or even to locate the pollutant source. This work proposes an algorithm to locate an air pollutant’s source by using a UAV. The algorithm has two components: (i) a metaheuristic technique is used to trace the increasing gradient of the pollutant concentration, and (ii) a probabilistic component complements the method by concentrating the search in the most promising areas in the targeted environment. The metaheuristic technique has been selected from a simulation-based comparative analysis between some classical techniques. The probabilistic component uses the Bayesian methodology to build and update a probability map of the pollutant source location, with each new sensor information available, while the UAV navigates in the environment. The proposed solution was tested experimentally with a real quadrotor navigating in a virtual polluted environment. The results show the effectiveness and robustness of the algorithm.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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 | 0.000 |
| 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".