Forecasting induced seismicity in Oklahoma using machine learning methods

Uncovering the factors that affect earthquake insurance uptake using supervised machine learning

The escalating threat of natural disasters to public safety worldwide underlines the crucial role of effective environmental risk management tools, such as insurance. This is particularly evident in the case of earthquakes that occurred in Oklahoma between 2011 and 2020, which were linked to wastewater injection, underscoring the need for earthquake insurance. In this regard, from a survey of 812 respondents in Oklahoma, USA, we used supervised machine learning techniques (i.e., logit, ridge, least absolute shrinkage and selection operator (LASSO), decision tree, and random forest classifiers) to identify the factors that influence earthquake insurance uptake and to predict individuals who would acquire earthquake insurance. Our findings reveal that influential factors that affect earthquake insurance uptake include demographic factors such as older age, male gender, race, and ethnicity. These were found to significantly influence the decision to purchase earthquake insurance. Additionally, individuals residing in rental properties were less likely to purchase earthquake insurance, while longer residency in Oklahoma had a positive influence. Past experience of earthquakes was also found to positively influence the decision to purchase earthquake insurance. Both decision trees and random forests demonstrated good predictive capabilities for identifying earthquake insurance uptake. Notably, random forests exhibited higher precision and robustness, emerging as an encouraging choice for earthquake insurance modeling and other classification problems. Empirically, we highlight the importance of insurance as an environmental risk management tool and emphasize the need for awareness and education on earthquake insurance as well as the use of supervised machine learning algorithms for classification problems.

Physics-informed deep learning to forecast [Formula: see text] during hydraulic fracturing

Short-term forecasting of estimated maximum magnitude ([Formula: see text]) is crucial to mitigate risks of induced seismicity during fluid stimulation. Most previous methods require real-time injection data, which are not always available. This study proposes two deep learning (DL) approaches, along with two data-partitioning methods, that rely solely on preceding patterns of seismicity. The first approach forecasts [Formula: see text] directly using DL; the second incorporates physical constraints by using DL to forecast seismicity rate, which is then used to estimate [Formula: see text]. These approaches are tested using a hydraulic-fracture monitoring dataset from western Canada. We find that direct DL learns from previous seismicity patterns to provide an accurate forecast, albeit with a time lag that limits its practical utility. The physics-informed approach accurately forecasts changes in seismicity rate, but sometimes under- (or over-) estimates [Formula: see text]. We propose that significant exceedance of [Formula: see text] may herald the onset of runaway fault rupture.

Major southern San Andreas earthquakes modulated by lake-filling events

Hydrologic loads can stimulate seismicity in the Earth's crust1. However, evidence for the triggering of large earthquakes remains elusive. The southern San Andreas Fault (SSAF) in Southern California lies next to the Salton Sea2, a remnant of ancient Lake Cahuilla that periodically filled and desiccated over the past millennium3-5. Here we use new geologic and palaeoseismic data to demonstrate that the past six major earthquakes on the SSAF probably occurred during highstands of Lake Cahuilla5,6. To investigate possible causal relationships, we computed time-dependent Coulomb stress changes7,8 due to variations in the lake level. Using a fully coupled model of a poroelastic crust9-11 overlying a viscoelastic mantle12,13, we find that hydrologic loads increased Coulomb stress on the SSAF by several hundred kilopascals and fault-stressing rates by more than a factor of 2, which is probably sufficient for earthquake triggering7,8. The destabilizing effects of lake inundation are enhanced by a nonvertical fault dip14-17, the presence of a fault damage zone18,19 and lateral pore-pressure diffusion20,21. Our model may be applicable to other regions in which hydrologic loading, either natural8,22 or anthropogenic1,23, was associated with substantial seismicity.