Machine-learning characterization of tectonic, hydrological and anthropogenic sources of active ground deformation in California

Tectonic, hydrological and industrial processes coexist in the dynamic natural environments. However, our knowledge of ground deformation associated with tectonic, hydrological and anthropogenic processes and their interactions has not been systematically linked, although scientific advances have been achieved in every individual geoscience discipline with more extensive and accurate observations and more robust models, which are remarkably complete in California. California represents a natural laboratory that hosts the San Andreas Fault (SAF) System, the Central Valley and other aquifer systems, and areas with extensive human extraction of natural resources. All these processes contribute to multi-scale ground deformation that has been mapped using Copernicus Sentinel-1 twin-Synthetic Aperture Radar (SAR)-satellite constellation from four ascending tracks and five descending tracks during 2014-2018. We consider the secular horizontal surface velocities and strain rates, constrained from GNSS measurements and tectonic models, as proxies for tectonic processes, and seasonal displacement amplitudes from interferometric SAR (InSAR) time series as proxies for hydrological processes. We synergize 23 types of multidisciplinary spatial data sets, including ground deformation, sedimentary basins, precipitation, soil moisture, topography, and hydrocarbon production fields, using a fundamental machine learning algorithm – random forest, and we succeed in predicting 86%-95% of the representative data sets. High-strain rates along the SAF system mainly occur in areas with a low-to-moderate summer vegetation fraction (~0.3), suggesting the correlation of rough/high-relief coastal range morphology and topography with the active faulting, seasonal and orographic rainfall, and vegetation growth, and likely also a disturbing environment in the shallow shear zone may jointly obstruct the vegetation growth. Linear discontinuities in the long-term, seasonal amplitude and phase of surface displacement fields coincide with some fault strands, the boundary zone between the sediment-fill Central Valley and bedrock-dominated Sierra Nevada, and the margins of the inelastically deforming aquifer in the San Joaquin Valley, suggesting the inference of seismogenic structures influencing groundwater flow, contrasting elastic properties, and heterogeneous hydrological units. On the other hand, the role of fluid extraction and injection in influencing tectonic and hydrological processes is not evident in this analysis, given the insufficient spatial resolution of the available remote sensing data and incomplete knowledge of the distribution of energy fields.