Accuracy and Precision of Low-Cost Echosounder and Automated Data Processing Software for Habitat Mapping in a Large River
Bibliographic record
Abstract
The development of consumer hydroacoustic systems continues to advance, enabling the use of low-cost methods for professional mapping purposes. Information describing habitat characteristics produced with a combination of low-cost commercial echosounder (Lowrance HDS) and a cloud-based automated data processing tool (BioBase EcoSound) was tested. The combination frequently underestimated water depth, with a mean absolute error of 0.17 ± 0.13 m (avg ± 1SD). The average EcoSound bottom hardness value was high (0.37–0.5) for all the substrate types found in the study area and could not be used to differentiate between the substrate size classes that varied from silt to bedrock. Overall, the bottom hardness value is not informative in an alluvial river bed setting where the majority of the substrate is composed of hard sands, gravels, and stones. EcoSound separated vegetation presence/absence with 85–100% accuracy and assigned vegetation height (EcoSound biovolume) correctly in 55% of instances but often overestimated it in other instances. It was most accurate when the vegetation canopy was ≤25% or >75% of the water column. Overall, as a low-cost, easy-to-use application EcoSound offers rapid data collection and allows users with no specialized skill requirements to make more detailed bathymetry and vegetation maps than those typically available for many rivers, lakes, and estuaries.
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 | 0.007 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".