Search

The Gotthard Base Tunnel (GBT), constructed between 2000 and 2011, is a 57 km long and up to 2.5 km deep high-speed railway tunnel located in the Swiss Alps. Significant ground surface displacements reaching about 10 cm were observed during and after the tunnel construction. To gain a better understanding of the causal mechanism of such conspicuous ground deformations, we develop a three-dimensional (3D) fully-coupled hydro-mechanical model to simulate GBT-induced groundwater drainage, stress redistribution, rock mass consolidation, and fault zone deformation at the regional scale. First, we construct a geological model with topographical features, lithological units, and natural faults realistically represented. We constrain the material properties of fault zones and rock masses based on available extensive laboratory testing results and site characterisation datasets. We then simulate the tunnelling process over time, with the resulting coupled hydro-mechanical responses of faulted rock masses well captured and ground surface/subsurface displacements quantitatively analysed. The simulation results in general show a good agreement with the field monitoring data of ground surface displacement, subsurface tunnel settlement, and groundwater inflow into the tunnel. Our model indicates that ground surface displacements originate from GBT-induced water drainage and rock mass consolidation in the deep subsurface. Our results also show that the GBT construction could trigger faults to shear via drainage-induced pressure diffusion and poroelastic stressing. The research findings from our work have important implications for many groundwater drainage-related geoengineering activities such as underground excavation in alpine mountains and fluid withdrawal in subsurface reservoirs. ISSN:1365-1609 ISSN:0148-9062 ISSN:1873-4545

The construction/operation of ultrahigh arch dams may impose significant perturbations to surrounding mountains, resulting in landslide motions of rock slopes and endangering the safety of hydropower systems and human habitats. For example, the Laxiwa Hydropower Station in China witnessed its nearby Guobu slope displacing significantly after the reservoir impoundment and having so far displaced up to ~40 m. It is of great importance to understand the mechanisms driving this large deformation. Here, we present some preliminary results from a combined remote sensing and numerical modelling investigation of this slope before, during, and after the reservoir impoundment. Analysis based on the differential interferometric synthetic aperture radar (DInSAR) data indicates that the slope had already been actively creeping at a rate of ~10 cm/year (e.g. in years of 2003-2005). We develop a geological model including different rock mass compartments and various discontinuity structures as well as a realistic representation of the suspended ancient landslide. We model the coupled hydro-mechanical and creep behaviour of the slope in response to reservoir impoundment. A good agreement is reached between the simulation results and field measurements of slope displacement time series recorded at different elevations of the slope surface. Our results show that the reservoir impoundment causes notable pressure changes at the toe region of the slope, leading to strong deformations (under coupled poroelastic and primary creep effects) that propagate upslope with the ancient landslide partially reactivated. These deformations tend to decelerate significantly after the impoundment due to the transition to secondary creeps.

We study the physical mechanisms that drive alpine slope deformation during water infiltration and depletion into fractured bedrocks. We develop a fully coupled hydromechanical model at the valley scale with multiscale fracture systems ranging from meter to kilometer scales represented. The model parameterized with realistic rock mass properties captures the effects of fractures via an upscaling framework with equivalent hydraulic and mechanical properties assigned to local rock mass blocks. The important heterogeneous and anisotropic characteristics of bedrocks due to depth-dependent variations of fracture density and stress state are taken into account and found to play a critical role in groundwater recharge and valley-scale deformation. Our simulation results show that pore pressure actively diffuses downward from the groundwater table during a recharge event, rendering a critical hydraulic response zone controlling surface deformation patterns. During the recession, the hydraulic front migrates downwards and the deformation recorded at the surface (up to ~4 cm) rotates accordingly. The most essential parameters in our model are the fracture network geometry, initial fracture aperture (controlling the rock mass permeability), and regional stress conditions. The magnitude and orientation of our model’s transient annual slope surface deformation are consistent with field observations at our study site in the Aletsch valley. Our research findings have important implications for understanding groundwater flow and slope deformations in alpine mountain environments., ESS Open Archive

Solid earth : SE 13(2), 301-322 (2022). doi:10.5194/se-13-301-2022, Published by Copernicus Publ., Go��ttingen

In deglaciating environments, rock mass weakening and potential formation of rock slope instabilities is driven by long-term and seasonal changes in thermal- and hydraulic boundary conditions, combined with unloading due to ice melting. However, in-situ observations are rare. In this study, we present new monitoring data from three highly instrumented boreholes, and numerical simulations to investigate rock slope temperature evolution and micrometer-scale deformation during deglaciation. Our results show that the subsurface temperatures are adjusting to a new, warmer surface temperature following ice retreat. Heat conduction is identified as the dominant heat transfer process at sites with intact rock. Observed nonconductive processes are related to groundwater exchange with cold subglacial water, snowmelt infiltration, or creek water infiltration. Our strain data shows that annual surface temperature cycles cause thermoelastic deformation that dominate the strain signals in the shallow thermally active layer at our stable rock slope locations. At deeper sensors, reversible strain signals correlating with pore pressure fluctuations dominate. Irreversible deformation, which we relate with progressive rock mass damage, occurs as short-term (hours to weeks) strain events and as slower, continuous strain trends. The majority of the short-term irreversible strain events coincides with precipitation events or pore pressure changes. Longer-term trends in the strain time series and a minority of short-term strain events cannot directly be related to any of the investigated drivers, but changes of glacial loading and fatigue processes are considered as potential causes., Earth and Space Science Open Archive

Past exploration missions have revealed that the lunar topography is eroded through mass wasting processes such as rockfalls and other types of landslides, similar to Earth. We have analyzed an archive of more than 2 million high-resolution images using an AI and big data-driven approach and created the first global map of 136.610 lunar rockfall events. Using this map, we show that mass wasting is primarily driven by impacts and impact-induced fracture networks. We further identify a large number of currently unknown rockfall clusters, potentially revealing regions of recent seismic activity. Our observations show that the oldest, pre-Nectarian topography still hosts rockfalls, indicating that its erosion has been active throughout the late Copernican age and likely continues today. Our findings have important implications for the estimation of the Moon’s erosional state and other airless bodies as well as for the understanding of the topographic evolution of planetary surfaces in general., Nature Communications, 11 (1), ISSN:2041-1723

The Flims rockslide/rock avalanche (FRRA) is the largest long runout landslide in Europe. This event provides a unique opportunity to study the pre-failure and failure behavior of a large rock slope, as both the source zone and deposit of this event are accessible. In this study, we perform engineering geological and geomorphic field mapping as well as stability and runout modeling in order to explore the preconditioning and triggering factors that resulted in failure of this event, and to infer the mechanisms that governed its runout. By combining these analyses, we qualitatively comment on the mechanisms that lead to the transition from a rockslide to a long runout, catastrophic rock avalanche. Our engineering geological and geomorphic field mapping has revealed that the FRRA failed along a sliding zone that features numerous, large scale steps. Previous work at the site, as well as new analysis of thin sections, has revealed the presence of marl-like layers within the failed stratigraphic unit. Our stability analysis shows that the presence of low strength layers at the depth of the rupture surface is required for failure to initiate, and that failure could be triggered either by strong seismic shaking, elevated pore-water pressures, or a combination of both. The results of the runout analysis show that this event likely remained coherent for a large portion of its motion, and that liquefaction of alluvial sediments at the toe of the slope may have enhanced the runout distance of this rock avalanche. Combining the mapping, stability and runout modeling has shown that the basal shear strength required for the runout analysis is ∼6°–10° lower than that back-analyzed for the stability of this event. Thus, a mechanism to reduce strength along the rupture surface immediately following the initial instability was required for catastrophic failure of this event. This mechanism is poorly understood at present, but is likely crucial for understanding the transition from an initially stable slope to a catastrophic, long runout rock avalanche., Frontiers in Earth Science, 8, ISSN:2296-6463

Mapping landslides using automated methods is a challenging task, which is still largely done using human efforts. Today, the availability of high-resolution EO data products is increasing exponentially, and one of the targets is to exploit this data source for the rapid generation of landslide inventory. Conventional methods like pixel-based and object-based machine learning strategies have been studied extensively in the last decade. In addition, recent advances in CNN (convolutional neural network), a type of deep-learning method, has been widely successful in extracting information from images and have outperformed other conventional learning methods. In the last few years, there have been only a few attempts to adapt CNN for landslide mapping. In this study, we introduce a modified U-Net model for semantic segmentation of landslides at a regional scale from EO data using ResNet34 blocks for feature extraction. We also compare this with conventional pixel-based and object-based methods. The experiment was done in Douglas County, a study area selected in the south of Portland in Oregon, USA, and landslide inventory extracted from SLIDO (Statewide Landslide Information Database of Oregon) was considered as the ground truth. Landslide mapping is an imbalanced learning problem with very limited availability of training data. Our network was trained on a combination of focal Tversky loss and cross-entropy loss functions using augmented image tiles sampled from a selected training area. The deep-learning method was observed to have a better performance than the conventional methods with an MCC (Matthews correlation coefficient) score of 0.495 and a POD (probability of detection) rate of 0.72 ., Remote Sensing, 12 (3), ISSN:2072-4292

DECOVALEX 2019 Symposium Abstracts

Geophysical Research Abstracts, 21, ISSN:1029-7006, ISSN:1607-7962

Geophysical Research Abstracts, 21, ISSN:1029-7006, ISSN:1607-7962

Geophysical Research Abstracts, 21, ISSN:1029-7006, ISSN:1607-7962

Geophysical Research Abstracts, 21, ISSN:1029-7006, ISSN:1607-7962

DECOVALEX 2019 Symposium Abstracts

Geophysical Research Abstracts, 21, ISSN:1029-7006, ISSN:1607-7962

Zusammenfassung: Talklüfte können im Zusammenhang mit Strasseneinschnitten, Wasserkraftanlagen und geologischen Massenbewegungen in steilen Talflanken eine wichtige Rolle spielen. Die Schöllenenschlucht im Reusstal (zentrale Schweizer Alpen) bildet ein ideales Untersuchungsgebiet für das Studium der Eigenschaften und Entstehungsmechanismen solcher Talklüfte. Die Schöllenen- Schlucht liegt am Südrand des Zentralen Aaregranits, welcher vor rund 300Mio. Jahren intrudierte, während der Alpenbildung nur lokal duktil deformiert und anschliessend an die Oberfläche gehoben wurde. Die bis zu 600 m tiefe Schlucht bietet einen idealen Einblick in das komplexe Trennflächengefüge des Plutons. Einen Einblick in das Berginnere erlauben zudem die Stollen des Kraftwerks Göschenen. Die Kartierungsarbeit führte zur Unterscheidung von zwei vermutlich alpin-syntektonischen Kluftfamilien (S- und Q-Klüfte) sowie drei Generationen von Entlastungsklüften (subhorizontale Dehnungsklüfte (L-Klüfte) und zwei Generationen von mittelsteilen bis steilen Talklüften (T1- und T2- Klüfte)). Die zahlreichen S-Klüfte verlaufen meistens parallel zur alpinen Schieferung, d. h. ungefähr E-W streichend und steil gegen Süden einfallend. Die weniger häufigen Q-Klüfte fallen steil gegen SW ein, der Winkel zwischen den beiden Kluftfamilien beträgt 60 bis 80 Grad. Die räumliche Lage der verschiedenen Entlastungsklüfte wurde primär in Querprofilen durch die Schöllenen erfasst. Die ersten Entlastungsklüfte verlaufen horizontal, sie bildeten sich unabhängig von der Topographie möglicherweise während einer spätalpinen miocänen Hebung des Aarmassivs. Eine erste Generation von Talklüften (T1) fällt mit 30-45 Grad beidseitig talwärts ein und wurde vermutlich während einer frühen pleistozänen Eintalung gebildet. Die jüngsten Talklüfte (T2) sind parallel zur heutigen Taloberfläche der Schöllenenschlucht orientiert, d. h. sie liegen parallel zu den mit spätpleistozänen Gletscherschliffen markierten Felsoberflächen. Die Frequenz sowie die Grösse dieser Klüfte nehmen zumindest in einem Stollen gegen das Berginnere ab und konnten bis rund 150 Meter ins Berginnere nachgewiesen werden. Fraktographische Untersuchungen, d. h. die Untersuchung von Bruchstrukturen auf Kluftoberflächen (hauptsächlich Federmarken mit einer Grösse von 5 bis 10 m) bestätigten diese relative Alterabfolge. Ebenso konnten dadurch jeweils der Ursprungspunkt einer Kluft und die Bruchfortpflanzungsrichtung bestimmt werden. Es zeigte sich dabei stets, dass grosse Talklüfte (bis über hundert Meter Länge) aus mehreren 5-10 Meter grossen Extensionsklüften bestehen, welche durch primär subhorizontale stabile Rissausbreitung entstanden sind. Grosse Talklüfte bilden sich bevorzugt in Graniten mit nur geringer alpin-tektonischer überprägung. Die Talklüfte der Schöllenen bilden sich nicht als Scherbrüche, wie dies von früheren Autoren angenommen wurde, sondern als Extensionsrisse in einem kompressiven Spannungsfeld. Das räumliche Auftreten und die beobachteten Grössen der Talklüfte können teilweise mit quantitativen Bruchkriterien, wie sie für hohlraumnahe Extensionsrisse in Tunnelwerken entwickelt wurden, erklärt werden. Wesentlich für den Ort und die Grösse der Talklüfte sind neben den Deviatorspannungen und Zugspannungen auch die σ3/σ1 Hauptspannungsverhältnisse. Erste numerische Modellrechnungen zu einer mehrphasigen glazialen Eintalung vermögen die beobachteten Bildungsbereiche und Eigenschaften der Talklüfte grob abzubilden

Geophysical Research Abstracts, 20, ISSN:1029-7006, ISSN:1607-7962

Solid Earth, 9 (1), ISSN:1869-9510, ISSN:1869-9529

Geophysical Research Abstracts, 20, ISSN:1029-7006, ISSN:1607-7962

Scientific Data, 5, ISSN:2052-4463

Geophysical Research Abstracts, 20, ISSN:1029-7006, ISSN:1607-7962

Geophysical Research Abstracts, 20, ISSN:1029-7006, ISSN:1607-7962

We leverage on optical and radar remote sensing data acquired from the European Space Agency (ESA) Sentinels to monitor the surface deformation evolution on a large and very active instability located in the Swiss Alps, i.e., the Moosfluh rock slope. In the late summer 2016, a sudden acceleration was reported at this location, with surface velocity rates passing from maximum values of 0.2 cm/day to 80 cm/day. A dense pattern of uphill-facing scarps and tension cracks formed within the instability and rock fall activity started to become very pronounced. This evolution of the rock mass may suggest that the most active portion of the slope could fail catastrophically. Here we discuss advantages and limitations of the use of spaceborne methods for hazard analyses and early warningbyusingtheESASentinels,andshowthatincriticalscenariostheyareoftennotsufficientto reliably interpret the evolution of surface deformation. The insights obtained from this case study are relevant for similar scenarios in the Alps and elsewhere., Remote Sensing, 10 (5), ISSN:2072-4292

Geophysical Research Abstracts, 20, ISSN:1029-7006, ISSN:1607-7962

Scientific data 5, 180269 (2018). doi:10.1038/sdata.2018.269, Published by Nature Publ. Group, London

In this contribution we present a review of scientific research results that address seismo-hydro-mechanical coupled processes relevant for the development of a sustainable heat exchanger in low permeability crystalline rock and introduce the design of the In-situ Stimulation and Circulation (ISC) experiment at the Grimsel Test Site dedicated to study such processes under controlled conditions. The review shows that research on reservoir stimulation for deep geothermal energy exploitation has been largely based on laboratory observations, large-scale projects and numerical models. Observations of full-scale reservoir stimulations have yielded important results. However, the limited access to the reservoir and limitations in the control on the experimental conditions during deep reservoir stimulations is insufficient to resolve the details of the hydro-mechanical processes that would enhance process understanding in a way that aids future stimulation design. Small scale laboratory experiments provide a fundamental insights into various processes relevant for enhanced geothermal energy, but suffer from 1) difficulties and uncertainties in upscaling the results to the field-scale and 2) relatively homogeneous material and stress conditions that lead to an over-simplistic fracture flow and/or hydraulic fracture propagation behaviour that is not representative for a heterogeneous reservoir. Thus, there is a need for intermediate-scale hydraulic stimulation experiments with high experimental control that bridge the various scales, and for which access to the target rock mass with a comprehensive monitoring system is possible. Only few intermediate-scale hydro-shearing and hydro-fracturing experiments have recently been performed in a densely instrumented rock mass. No such measurements have been performed on faults in crystalline basement rocks. The In-situ Stimulation and Circulation (ISC) experiment currently performed in a naturally fractured and faulted crystalline rock mass at the Grimsel Test Site (Switzerland) is designed to address open research questions, which could not be investigated in the required detail so far. Two hydraulic injection phases were executed to enhance the permeability of the rock mass: a hydro-shearing phase and then a hydraulic fracturing phase. During the injection phases the rock mass deformation across fractures and within intact rock, the pore pressure distribution and propagation and the micro-seismic response were monitored at a high spatial and temporal resolution., Solid Earth Discussions, ISSN:1869-9537

ISSN:0148-0227 ISSN:2169-9003 ISSN:2169-9011

EGU General Assembly 2016, EGU2016, Vienna, Austria, 17 Apr 2016 - 22 Apr 2016; Geophysical research abstracts : GRA 18, EGU2016-12475 (2016). special issue: "EGU General Assembly 2016", Published by European Geophysical Society, Katlenburg-Lindau

Geophysical Research Abstracts, 17, ISSN:1029-7006, ISSN:1607-7962

With micro-strain resolution and the capability to sample at rates of 100 Hz and higher, fiber optic (FO) strain sensors offer exciting new possibilities for in-situ landslide monitoring. Here we describe a new FO monitoring system based on long-gauge fiber Bragg grating sensors installed at the Randa Rockslide Laboratory in southern Switzerland. The new FO monitoring system can detect sub-micrometer scale deformations in both triggered-dynamic and continuous measurements. Two types of sensors have been installed: (1) fully embedded borehole sensors and (2) surface extensometers. Dynamic measurements are triggered by sensor deformation and recorded at 100 Hz, while continuous data are logged every 5 min. Deformation time series for all sensors show displacements consistent with previous monitoring. Accelerated shortening following installation of the borehole sensors is likely related to long-term shrinkage of the grout. A number of transient signals have been observed, which in some cases were large enough to trigger rapid sampling. The combination of short- and long-term observation offers new insight into the deformation process. Accelerated surface crack opening in spring is shown to have a diurnal trend, which we attribute to the effect of snowmelt seeping into the crack void space and freezing at night to generate pressure on the crack walls. Controlled-source tests investigated the sensor response to dynamic inputs, which compared an independent measure of ground motion against the strain measured across a surface crack. Low frequency signals were comparable but the FO record suffered from aliasing, where undersampling of higher frequency signals generated spectral peaks not related to ground motion., Natural Hazards and Earth System Sciences, 10 (2), ISSN:1561-8633, ISSN:1684-9981

Hydrogeology Journal, 20 (1), ISSN:1431-2174, ISSN:1435-0157

Journal of Geophysical Research: Earth Surface, 122 (4), ISSN:0148-0227, ISSN:2169-9003, ISSN:2169-9011

A comprehensive surface displacement monitoring system installed in the recently deglaciated bedrock slopes of the Aletsch Valley shows systematic reversible motions at the annual scale. We explore potential drivers for this deformation signal and demonstrate that the main driver is pore pressure changes of groundwater in fractured granitic mountain slopes. The spatial pattern of these reversible annual deformations shows similar magnitudes and orientations for adjacent monitoring points, leading to the hypothesis that the annually reversible deformation is caused by slope-scale groundwater elevation changes and rock mass properties. Conversely, we show that the ground reaction to infiltration from snowmelt and summer rainstorms can be highly heterogeneous at local scale, and that brittle-ductile fault zones are key features for the groundwater pressure-related rock mass deformations. We also observe irreversible long-term trends (over the 6.5 yr dataset) of deformation in the Aletsch valley composed of a larger uplift than observed at our reference GNSS station in the Rhone valley, and horizontal displacements of the slopes towards the valley. These observations can be attributed respectively to the elastic bedrock rebound in response to current glacier mass downwasting of the Great Aletsch Glacier and gravitational slope deformations enabled by cyclic groundwater pressure-related rock mass fatigue in the fractured rock slopes., Journal of Geophysical Research: Earth Surface, 126 (12), ISSN:0148-0227, ISSN:2169-9003, ISSN:2169-9011

Many geothermal pilot projects worldwide have been forced to shutdown in the last fifteen years after triggering earthquakes by fluid injections into critically-stressed faults. This reveals that our capacity to control the migration of injected fluids is still poor and shows the importance to better understand how faults control flow to improve the safety of hydraulic stimulations. Little is known also about how deep fluid injections affect heat transport and, ultimately, the performance of enhanced geothermal systems. Here, I investigate how downscaled controlled hydraulic stimulations performed at the Grimsel Rock Laboratory, Switzerland, enhanced subsurface flow and heat transport in a highly-monitored reservoir analog. The installation of 15 boreholes to monitor fluid pressure, temperature and rock deformation in a previously unexplored area of the Grimsel Rock Laboratory, from 2015 to 2016, provided a unique opportunity to carry out experiments and observe flow and heat transport in situ at unprecedented resolution. I first investigate how the internal structure of shallow crustal faults affects flow and pore-fluid diffusion. Starting at borehole scale, I systematically test the permeability of the host rock, single fracture and fracture networks and show how brittle damage induces a power-law decay in permeability with lateral distance from faults. Building on this knowledge, I investigate cross-hole scale flow interactions to understand the nature of spatial dimensions amenable to flow. By applying a generalized flow model, I show that fractional flow dimensions systematically emerge, converging to a dimension of $n$=1.3, due to a pressure diffusion slowdown. This slowdown is inconsistent with normal diffusion and suggests that anomalous diffusion is an important flow process in shallow crustal faults, and that their hydrologic structure is fractal. For the faults tested, I obtain a fractal dimension of $d_f$=2.23, which may reflect network-scale flow channeling. Characterizing the hydrological state of these faults after stimulation shows that their permeability and internal flow structure sustained significant, multiscale changes. Locally, changes in permeability measured in stimulation wells, where high-pressure injections took place, were found to be inversely proportional to the initial permeability and scale positively with seismic magnitudes and rupture areas. This suggests a relation between permeability enhancement and induced seismicity. Several locations in the near field became also less permeable. This shows, for the first time, that permeability reduction may be an overlooked but important near-field process following stimulation. Globally, stimulated faults became more permeable and better connected hydraulically compared to their pre-injection state. Faults with poor to moderate natural connectivity experienced the largest increase in connectivity. Hence, I propose that such faults constitute better stimulation targets. Finally, heat injection experiments confirmed that the heterogeneous flow structure of faults strongly affects subsurface heat transport. Thermal breakthroughs were observed at multiple locations, yet confined to the most permeable faults. These breakthroughs were found to be better explained by heat transport through a parallel plate fracture, instead of tube-like channels. Comparing then pre- and post-stimulation thermal transfer time distribution showed that high-pressure fluid injections enhanced, but also delayed, advective heat transport. The thermal response to shear stimulation of shallow crustal faults appears, therefore, to be more complex than previously described.

Past exploration missions have revealed that the lunar topography is eroded through mass wasting processes such as rockfalls, similar to Earth. Despite the abundance of remote sensing and in–situ data many questions about the occurrence and characteristics of lunar rockfalls remain unanswered: Why do lunar rockfalls occur? What endo- and exogenic processes drive lunar rockfalls? What can these processes tell us about the geologic activity and evolution of the Moon? What can rockfall tracks teach us about the shallow lunar regolith and its interaction with the space environment? To help address these questions, we develop deep learning-driven algorithms that allow us to automate the detection and mapping of rockfalls in Lunar Reconnaissance Orbiter’s Petabyte-scale image archive - a uniquely rich resource that has barely been exploited by previous work. Our convolutional neural networks achieve human-level detection performance while reducing the required processing time by several orders of magnitude. By applying transfer learning principles we further boost the performance of our detectors and make them robust enough to map rockfalls on other bodies across the Solar System as well, such as Mars, Ceres, and comet 67P. Using such multi-domain trained algorithms we conduct the first-ever, global scan of the lunar surface and derive the global distribution of rockfalls on the Moon, identifying more than 130,000 individual rockfalls. The global distribution of rockfalls is highly heterogeneous, where the vast majority as well as the highest spatial concentrations of rockfalls occur in young impact craters and on equatorfacing slopes with large thermal gradients. This indicates that rockfall occurrence is mainly controlled by erratic impacts and continuous solar-driven thermal fatigue. We discover that rockfalls occur even in the oldest, pre-Nectarian lunar terranes, indicating that the identified processes - particularly small-scale meteoritic impacts - drive erosion over billions of years. We do not observe significant clusters of rockfalls in the proximity of visible volcanic and tectonic features which suggests that seismic activity has not been a major, global driver of lunar rockfall in the Moon’s recent geologic past. Using satellite images of rockfall boulders and their tracks, we further develop a method to estimate the regolith surface strength and geomechanical properties of yet unexplored regions, such as the polar permanently shadowed regions and large pyroclastic deposits, directly supporting humanity’s current efforts to continue the exploration of the Moon and beyond. This dissertation demonstrates the enormous potential of deep learning-driven applications for planetary science and reveals new insights about the weathering, erosion and evolution of airless planetary bodies in our solar system.