Log In Sign Up

Monitoring through many eyes: Integrating scientific and crowd-sourced datasets to improve monitoring of the Great Barrier Reef

by   Erin E Peterson, et al.

Data in the Great Barrier Reef (GBR) are collected by numerous organisations and rarely analysed together. We developed a weighted spatiotemporal Bayesian model that integrate datasets, while accounting for differences in method and quality, which we fit to image based, hard coral data collected by professional and citizen scientists. Citizens provided underwater images and classified those images. We used the model to make coral-cover predictions across the GBR with estimates of uncertainty. A simulation study was undertaken to investigate how citizen-science data affects model outputs as participation increases. The citizens average classification accuracy (79 percent) was relatively high compared to marine scientists (assumed 100 percent), but variability in most participants accuracy was also high. Though, a large number of citizens (greater than 1000) must classify images before their data affects model outputs. Including additional data increased the models predictive ability by 43 percent, suggesting that a loss of much-needed management information occurs when data are not integrated.


page 11

page 23

page 24


Correcting misclassification errors in crowdsourced ecological data: A Bayesian perspective

Many research domains use data elicited from "citizen scientists" when a...

The CSIRO Crown-of-Thorn Starfish Detection Dataset

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss...

Predicting Sediment and Nutrient Concentrations in Rivers Using High Frequency Water Quality Surrogates

A particular focus of water-quality monitoring is the concentrations of ...

Design Strategies and Approximation Methods for High-Performance Computing Variability Management

Performance variability management is an active research area in high-pe...

Classification of Motorcycles using Extracted Images of Traffic Monitoring Videos

Due to the great growth of motorcycles in the urban fleet and the growth...

BayesNetCNN: incorporating uncertainty in neural networks for image-based classification tasks

The willingness to trust predictions formulated by automatic algorithms ...