Deep fluid pathways beneath Mammoth Mountain, California, illuminated by migrating earthquake swarms

Abstract

Although most volcanic seismicity is shallow (within several kilometers of the surface), some volcanoes exhibit deeper seismicity (10 to 30+ km) that may reflect active processes such as magma resupply and volatile transfer. One such volcano is Mammoth Mountain, California, which has also recently exhibited high rates of CO₂ discharge at the surface. We perform high-resolution earthquake detection and relocation to reveal punctuated episodes of rapidly propagating seismicity at mid-crustal depths along a narrow fracture zone surrounding a body of partial melt. We infer that these earthquakes track dike intrusions or fluid pressure pulses associated with CO₂ exsolution, suggesting that the deep plumbing system of Mammoth Mountain is an active conduit for fluid transport from the base of the crust to the surface.

Fig. 1. Map and cross-sectional views of relocated seismicity.

(Top) Map view of deep (8 km+) relocated seismicity. Epicenters fall along a NE striking zone. The outline of dome complex is shaded, and the black dashed line corresponds to the topographic outline of Long Valley Caldera (10). The blue dashed line corresponds to local least compressive stress (T axis) from shallow focal mechanisms (11). (Bottom) Depth cross sections parallel (A-A′) and perpendicular (B-B′) to the NE trend in seismicity. The structure is vertical, with two arms surrounding a nearly aseismic core that hosts most of LP earthquakes. Horizontal features are denoted with arrows. Below 8 km, symbol size scales with magnitude.

Fig. 2. Spatiotemporal history of deep seismicity.

(A) Earthquake occurrence in the past 30 years by depth. Cataloged but not relocated seismicity is plotted at lower opacity. Shallow earthquakes are limited to >M1. Histogram at right bins M1+ earthquakes by depth, colored by type. (B) Expanded view of swarms with 20+ events illustrating migration in depth with time. Successive swarms are concatenated, with time between swarms removed; swarms are separated by vertical bars of thickness that scale to the amount of time removed, and start dates are listed along the top. Color is by location along A-A′ to highlight activity between branches; the color bar is copied below for reference to location within the cross section. (C to F) Views along A-A′ for four large swarms [arrows connecting from (B)] with color denoting time since date in the lower corner corresponding to the end of each swarm; arrows guide direction of migration over time.

Fig. 3. Annotated conceptual model overlaid on cross section A-A′.

Solid blue arrows note the direction of earthquake migration, which corresponds to the direction of inferred fluid motion. Dashed blue lines indicate gaps between swarms where flow may be aseismic, and horizontal barriers (depicted here as sills) inhibit flow. Fluids are presumably sourced from near-Moho depths and propagate along a preexisting fracture zone. Insets denote two possible views along B-B′ for a dike tip model (top) and a fracture mesh model (bottom) to explain the reversed focal mechanisms. The zone between the arms hosts LP earthquakes, likely of a more plastic rheology than the surrounding rock (for example, partial melt and higher temperatures). Volatiles eventually work toward the shallow subsurface where they may be stored (13, 14) before finally escaping to the surface.

Fig. 4. Map of local permanent seismic network of Mammoth Mountain and nearby Long Valley Caldera.

Temporary stations are not shown. The dotted blue box shows the extent of the original NCEDC earthquake catalog search, and the red box corresponds to the map view shown in Fig. 1. The inset map also shows two distant stations used in focal mechanism determination.

Fig. 5. Example waveforms and histogram of earthquake frequency content.

Waveforms from LP and brittle-failure earthquakes are located 241 m apart and recorded at the same broadband station (OMMB). Bins by FI [that is, ratio of high-frequency to low-frequency energy (31)] show a bimodal distribution separating LP seismicity (as labeled by an analyst) from brittle-failure seismicity. The dashed line indicates separation in symbology used in figures. Arrows denote the bins to which the earthquakes belong.

Fig. 6. Representative first-motion double-couple focal mechanisms for brittle-failure earthquakes.

Below each mechanism is a subset of associated waveforms. Most solutions have a steeply dipping nodal plane close to the strike of the trend of seismicity but a wide variety in slip vectors. The bottom right mechanism is an example that does not follow this pattern.