The research on active tectonics and geomorphology involves extensive sub-topics, including the kinematics of crustal movements, the processes underlying the evolution of landforms, and the associated dynamic mechanisms. These sub-topics are intricately connected with the interactions between the Earth’s endogenic and exogenic processes. In the contemporary realm of the Earth system science, research in active tectonics and geomorphology has become a hot topic for interdisciplinary study. The advancement in big data research coupled with the progressive developments in deep learning technologies has furnished this field of study with a voluminous array of data sources and the requisite analytical tools for technical analysis. In recent years, the application of big data and deep learning technologies in this research field has yielded a series of outstanding results, fostering new research directions, and ushering the discipline into a new phase. In this paper we synthesize existing research to outline the data sources pertinent to the study of active tectonics and geomorphology, including field geological survey, unmanned aerial vehicle (UAV)-based photography, aerial photography, and remote sensing observations. Then, we discuss in-depth examination of the recent innovations progresses in deep learning algorithms, including but not limited to convolutional neural networks(CNNs), deep Gaussian processes, and autoencoders. This article further elaborates on innovative applications of deep learning in the study of active tectonics and geomorphology. These include the identification of changes in glacier extent, monitoring volcanic activity and deformation, recognizing river systems, precise surveillance of landslide events, as well as observations of lithospheric deformation co-seismic surface ruptures.
Based on the summary of prior studies, this paper showcases a distinct application instance. By employing convolutional neural networks(CNNs)within the realm of deep learning image analysis and utilizing UAV-obtained high-resolution images, we undertake the automated detection of structural fractures in granite rocks in Meizhou island, in the southeast of Fujian province, China. In fault damage zones, structural rock fractures are widely developed, and the study of their orientation, system, and secondary characteristics is of great importance for determining their mechanisms of development and the multi-phase tectonic activity events in the region. Under conventional methodologies, the study of structural fractures in rocks is time-consuming and requires considerable manual effort in conducting exhaustive field surveys and detailed interpretation of cartographic representations. However, the application of deep learning can greatly enhance the efficiency of cartographic work. This application case has improved the classic deep learning framework by developing a CNN model specifically designed for the extraction of complex features and multi-scale rock fractures. This model achieved rapid identification of over 9 000 fractures with varied shapes and complex distributions within 55 minutes, attaining an accuracy of 85% and a recall rate of 89%. These findings demonstrate that deep learning significantly enhances operational efficiency in comparison to manual statistical methods for the automated identification of rock structural fractures, while also maintaining exceptional accuracy in fracture detection. Based on the results identified by deep learning, it can be clearly observed that two sets of fractures, oriented NE and NW, develop on the granite outcrops in the study area. According to previous research and the cross-cutting relationships of the fractures, it is known that NE-oriented fractures formed earlier than NW-oriented fractures, corresponding respectively to the Indosinian Movement and the expansion movement of the South China Sea in the tectonic history of South China. Through the automated extraction of deep learning models, the workload of manual mapping can be greatly reduced, yielding results consistent with actual geomorphological phenomena.
Scarps are typical geomorphic features of tectonics, climatic changes, and erosion processes. On one hand, interpreting geological information encoded in scarps allows for the quantitative constraint of the kinematic and dynamic mechanisms of the active structures. On the other hand, studying the evolution processes of scarps contribute to a better understanding of the couplings among tectonics, erosion, and climate during geomorphic evolution processes. In regions characterized by adverse geological conditions, limited accessibility, and logistical challenges hindering researchers from reaching certain areas, traditional dating methods such as radiocarbon dating, luminescence dating, and cosmogenic nuclide dating often face difficulties in determining the age of scarps. The geomorphic dating method of scarps, however, offers a promising avenue to address the scarcity of chronological samples in research areas where either sample availability is limited or conventional dating techniques are impractical. This paper provides a concise summary of the theoretical evolution of geomorphic dating of scarps. Emphasis is placed on elucidating the slope evolution processes, transport models, and associated computational methodologies integral to this approach. Additionally, the specific applications of these methods in active tectonics and geomorphology are highlighted, accompanied by a case study showcasing their practical implementation.
The theoretical foundation of geomorphic dating of scarps posits that the evolution of scarps during stable erosion stages can be simulated through models describing the evolution of slope surfaces over time. In practical dating applications, it is essential to determine the theoretical models and computational methods for the evolution of scarps. This necessitates the integration of measured profiles of the scarp to establish boundary and initial conditions, facilitating the determination of the geomorphic age of the studied scarps. On one hand, the related slope evolution model mainly involves processes such as bedrock weathering, sediment transport, and tectonic uplift. Previous studies have proposed dozens of quantitative slope evolution models and geomorphic transport functions(e.g., local linear, local nonlinear, non-local, etc.)based on various slope processes, theoretical assumptions, and numerical simulations. In various transport equations, compared to earlier local linear models, later local nonlinear transport models proposed based on experimental simulations and physical derivations exhibit higher fitting accuracy for real slope evolution. In the past decade, some scientists have proposed nonlocal transport models because of the limitations of traditional transport models, and have applied them in research. This nonlocal model assumes that the distance of sediment movement within a given area follows a probability distribution, thus allowing the simulation of long-distance slope processes over short periods. Additionally, many other transport models have been derived from specific slope processes, such as biotic disturbance and dry ravel. The solution methods for the aforementioned models vary as well. For instance, the analytical solution of a local linear diffusion transport model can be relatively easily obtained, while local nonlinear models and nonlocal models can only be numerically solved through specific approaches. On the other hand, the measured topographic profiles of the studied scarps can be used to determine the practical parameters of slope evolution models, including the present-day morphology of the scarps and their ages since their initial formation. In practical applications, various methods have emerged for the geomorphic dating of scarps, generally classified into two types based on the approach to fitting model calculations with actual topographic profiles: the mid-point slope method and the full slope method. The mid-point slope method uses the mid-point gradient value as the fitting morphological feature, representing an early method for dating scarps, mostly combined with linear diffusion transport functions and requiring numerous profiles for statistical analysis. Due to its low data utilization and limited spatiotemporal precision in statistical methods, the mid-point slope method has gradually been replaced by the full slope method. The full slope method involves fitting the overall shape of actual profile curves using model solutions. With the continuous improvement of observation techniques in the field of Earth sciences and the deepening research on related theories, the application scope of scarps geomorphic dating methods is no longer limited to the study of terraces and simple fault scarp evolution processes but has expanded to more complex geological environments, providing more precise constraints on their formation and evolution history.
For method application, we systematically present the progress in scarp geomorphic dating research across various geomorphic settings(such as river and coastal terraces, lake shorelines, alluvial fans, marine terraces, and extraterrestrial planets). It employs the geomorphic dating of the northeastern Pamir fault scarp as a case study to further explore and anticipate the developmental trajectory of geomorphic dating of scarps within the field of tectonic geomorphology.
