Optimizing surface water monitoring by fusion of UAV and ASV platforms
Bibliographic record
Abstract
Geological surveys often cover vast areas, traditionally requiring significant time and resources. Surveys of surface water are particularly challenging, as they typically rely on crewed vessels carrying specialized equipment, which is costly, potentially hazardous, and limited in both spatial and temporal resolution. With recent developments in drone technology, uncrewed platforms such as uncrewed aerial vehicles (UAVs) and autonomous surface vessels (ASVs) have increasingly been used in these applications, however, each has distinct limitations, and few attempts have been made to fuse both platforms for survey optimization. UAVs can rapidly cover large areas with high spatial resolution but provide low sensitivity as they are not in contact with the target, while ASVs deliver high sensitivity but are slow with limited coverage. This project proposes a multiplatform approach that combines UAVs, ASVs, and floating sensors to overcome these limitations with a focus on pinpointing specific targets, such as algal blooms. Algal bloom surveys can be conducted using a multistage approach where UAV-based hyperspectral scans identify regions of interest, which guide the targeted deployment of floating sensors via UAVs, whose data will inform where the ASVs should be deployed for high-sensitivity sampling. UAVs could also transport samples collected by ASVs to the shore or testing facilities, reducing transit times and increasing the number of samples taken. ASVs may additionally provide real-time validation of UAV surveys, offering a safer and more cost-effective alternative to traditional ground verification methods. In this project, we designed and 3D-printed a UAV deployable floating sensor frame, adopted a remote UAV drop-off and pick-up system, and updated a Seafloor Systems EchoBoat-160 ASV with improved internal hardware and software. This multiplatform strategy has the potential to transform water-based geological surveying by increasing efficiency, reducing operational costs, and enabling higher temporal and spatial resolution compared to both conventional and single-platform methods.
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 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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| 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 teacher head, 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".