Capturing expert uncertainty: ICC-informed soft labelling for volcano-seismicity
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces ICC-informed soft labels for volcano-seismic signals, improving machine learning accuracy by quantifying expert disagreement. This method enhances volcano monitoring and eruption forecasting by capturing classification uncertainty.
Area Of Science
- Geophysics
- Seismology
- Machine Learning
Background
- Volcano-seismic signal classification is crucial for monitoring and eruption forecasting.
- Traditional methods may not account for expert judgment variability and uncertainty.
- Inter-expert agreement is often overlooked in seismic data analysis.
Purpose Of The Study
- To develop a novel method for quantifying inter-expert agreement in volcano-seismic signal classification.
- To incorporate this agreement measure into probabilistic, ICC-informed soft labels for machine learning.
- To enhance the accuracy, robustness, and transferability of machine learning models in volcanology.
Main Methods
- A global survey of 89 experts classifying 80 volcano-seismic events from Ruapehu, New Zealand.
- Utilized the intraclass correlation coefficient (ICC) to quantify inter-expert agreement.
- Developed a soft labeling methodology weighting class probabilities by ICC scores.
Main Results
- Single-rater scores showed poor agreement, even for established volcano-tectonic (VT) and long-period (LP) classifications.
- Combining multiple expert ratings significantly improved reliability for VT and LP signals.
- Substantial expert disagreement persisted for hybrid (HYB) and other (OT) categories.
- ICC-informed soft labels effectively captured and reflected expert uncertainty.
Conclusions
- ICC-informed soft labels offer a robust alternative to hard labels by explicitly capturing classification uncertainty.
- This probabilistic approach can significantly enhance machine learning model performance in volcano monitoring.
- The methodology represents a fundamental shift in labeling and interpreting volcano-seismic data for automated frameworks.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
Suppose a quality...
All the digits in a measurement, including the uncertain last digit, are called significant figures or significant digits. Note that zero may be a measured value; for example, if a scale that shows weight to the nearest pound reads “140,” then the 1 (hundreds), 4 (tens), and 0 (ones) are all significant (measured) values.
A measurement result is properly reported when its significant digits accurately represent the certainty of the measurement process. Below are a set of rules to...
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...