Suchergebnisse

Abstract. Assessing or forecasting seismic damage to buildings is an essential issue
for earthquake disaster management. In this study, we explore the efficacy
of several machine learning models for damage characterization, trained and
tested on the database of damage observed after Italian earthquakes (the Database of Observed Damage – DaDO).
Six models were considered: regression- and classification-based machine
learning models, each using random forest, gradient boosting, and extreme
gradient boosting. The structural features considered were divided into two
groups: all structural features provided by DaDO or only those considered to
be the most reliable and easiest to collect (age, number of storeys, floor
area, building height). Macroseismic intensity was also included as an input
feature. The seismic damage per building was determined according to the
EMS-98 scale observed after seven significant earthquakes occurring in
several Italian regions. The results showed that extreme gradient boosting
classification is statistically the most efficient method, particularly when
considering the basic structural features and grouping the damage according
to the traffic-light-based system used; for example, during the
post-disaster period (green, yellow, and red), 68 % of buildings were
correctly classified. The results obtained by the machine-learning-based
heuristic model for damage assessment are of the same order of accuracy
(error values were less than 17 %) as those obtained by the traditional
RISK-UE method. Finally, the machine learning analysis found that the
importance of structural features with respect to damage was conditioned by
the level of damage considered.

For government officials and the public to act on real-time forecasts of earthquakes, the seismological community needs to develop confidence in the underlying scientific hypotheses of the forecast generating models by assessing their predictive skill. For this purpose, the Collaboratory for the Study of Earthquake Predictability (CSEP) provides cyberinfrastructure and computational tools to evaluate earthquake forecasts. Here, we introduce pyCSEP, a Python package to help earthquake forecast developers embed model evaluation into the model development process. The package contains the following modules: (1) earthquake catalog access and processing, (2) data models for earthquake forecasts, (3) statistical tests for evaluating earthquake forecasts, and (4) visualization routines. pyCSEP can evaluate earthquake forecasts expressed as expected rates in space-magnitude bins, and simulation-based forecasts that produce thousands of synthetic seismicity catalogs. Most importantly, pyCSEP contains community-endorsed implementations of statistical tests to evaluate earthquake forecasts, and provides well defined file formats and standards to facilitate model comparisons. The toolkit will facilitate integrating new forecasting models into testing centers, which evaluate forecast models and prediction algorithms in an automated, prospective and independent manner, forming a critical step towards reliable operational earthquake forecasting. ; This research was supported by the Southern California Earthquake Center (Contribution No. 11030). SCEC is funded by NSF Cooperative Agreement EAR-1600087 & USGS Cooperative Agreement G17AC00047. Maximilian J. Werner and Danijel Schorlemmer received funding from the European Union's Horizon 2020 research and innovation program (Number 821115, RISE: Real-Time Earthquake Risk Reduction for a Resilient Europe).

For government officials and the public to act on real-time forecasts of earthquakes, the seismological community needs to develop confidence in the underlying scientific hypotheses of the forecast generating models by assessing their predictive skill. For this purpose, the Collaboratory for the Study of Earthquake Predictability (CSEP) provides cyberinfrastructure and computational tools to evaluate earthquake forecasts. Here, we introduce pyCSEP, a Python package to help earthquake forecast developers embed model evaluation into the model development process. The package contains the following modules: (1) earthquake catalog access and processing, (2) data models for earthquake forecasts, (3) statistical tests for evaluating earthquake forecasts, and (4) visualization routines. pyCSEP can evaluate earthquake forecasts expressed as expected rates in space-magnitude bins, and simulation-based forecasts that produce thousands of synthetic seismicity catalogs. Most importantly, pyCSEP contains community-endorsed implementations of statistical tests to evaluate earthquake forecasts, and provides well defined file formats and standards to facilitate model comparisons. The toolkit will facilitate integrating new forecasting models into testing centers, which evaluate forecast models and prediction algorithms in an automated, prospective and independent manner, forming a critical step towards reliable operational earthquake forecasting.

Abstract. Aftershock forecast models are usually provided on a uniform spatial grid, and the receiver operating characteristic (ROC) curve is often employed for evaluation, drawing a binary comparison of earthquake occurrences or non-occurrence for each grid cell. However, synthetic tests show flaws in using the ROC for aftershock forecast ranking. We suggest a twofold improvement in the testing strategy. First, we propose to replace ROC with the Matthews correlation coefficient (MCC) and the F1 curve. We also suggest using a multi-resolution test grid adapted to the earthquake density. We conduct a synthetic experiment where we analyse aftershock distributions stemming from a Coulomb failure (ΔCFS) model, including stress activation and shadow regions. Using these aftershock distributions, we test the true ΔCFS model as well as a simple distance-based forecast (R), only predicting activation. The standard test cannot clearly distinguish between both forecasts, particularly in the case of some outliers. However, using both MCC-F1 instead of ROC curves and a simple radial multi-resolution grid improves the test capabilities significantly. The novel findings of this study suggest that we should have at least 8 % and 5 % cells with observed earthquakes to differentiate between a near-perfect forecast model and an informationless forecast using ROC and MCC-F1, respectively. While we cannot change the observed data, we can adjust the spatial grid using a data-driven approach to reduce the disparity between the number of earthquakes and the total number of cells. Using the recently introduced Quadtree approach to generate multi-resolution grids, we test real aftershock forecast models for Chi-Chi and Landers aftershocks following the suggested guideline. Despite the improved tests, we find that the simple R model still outperforms the ΔCFS model in both cases, indicating that the latter should not be applied without further model adjustments.