Gabriel Walton

Photogrammetry can be a valuable tool for understanding landscape evolution and natural hazards such as landslides. However, factors such as vegetation cover, shadows, and unstable ground can limit its effectiveness. Using photos across time to monitor an area with unstable or changing ground conditions results in fewer tie points between images across time, and often leads to low comparative accuracy if single-epoch (i.e., classical) photogrammetric processing approaches are used. This paper presents a study evaluating the co-alignment approach applied to fixed terrestrial timelapse photos at an active landslide site. The study explores the comparative accuracy of reconstructed surface models and the location and behavior of tie points over time in relation to increasing levels of global change due to landslide activity and rockfall. Building upon previous work, this study demonstrates that high comparative accuracy can be achieved with a relatively low number of inter-epoch tie points, highlighting the importance of their distribution across stable ground, rather than the total quantity. High comparative accuracy was achieved with as few as 0.03 percent of the overall co-alignment tie points being inter-epoch tie points. These results show that co-alignment is an effective approach for conducting change detection, even with large degrees of global changes between surveys. This study is specific to the context of geoscience applications like landslide monitoring, but its findings should be relevant for any application where significant changes occur between surveys.

Machine learning (ML) models are extensively used in spatial predictive modeling, including landslide susceptibility prediction. The performance statistics of these models are vital for assessing their reliability, which is typically obtained using the random cross-validation (R-CV) method. However, R-CV has a major drawback, i.e., it ignores the spatial autocorrelation (SAC) inherent in spatial datasets when partitioning the training and testing sets. We assessed the impact of SAC at three crucial phases of ML modeling: hyperparameter tuning, performance evaluation, and learning curve analysis. As an alternative to R-CV, we used spatial cross-validation (S-CV). This method considers SAC when partitioning the training and testing subsets. This experiment was conducted on regional landslide susceptibility prediction using different ML models: logistic regression (LR), k-nearest neighbor (KNN), linear discriminant analysis (LDA), artificial neural networks (ANN), support vector machine (SVM), random forest (RF), and C5.0. The experimental results showed that R-CV often produces optimistic performance estimates, e.g., 6–18% higher than those obtained using the S-CV. R-CV also occasionally fails to reveal the true importance of the hyperparameters of models such as SVM and ANN. Additionally, R-CV falsely portrays a considerable improvement in model performance as the number of variables increases. However, this was not the case when the models were evaluated using S-CV. The impact of SAC was more noticeable in complex models such as SVM, RF, and C5.0 (except for ANN) than in simple models such as LDA and LR (except for KNN). Overall, we recommend S-CV over R-CV for a reliable assessment of ML model performance in large-scale LSM.

Automatically identifying mine and tunnel infrastructure elements, such as rock bolts, from point cloud data improves deformation and quality control analyses and could ultimately contribute to improved safety on engineering projects. However, we hypothesize that existing methods are sensitive to small changes in object characteristics across datasets if trained insufficiently, and previous studies have only investigated single datasets. In this study, we present a cross-site training (generalization) investigation for a multi-class tunnel infrastructure classification task on terrestrial laser scanning data. In contrast to previous work, the novelty of this work is that the models are trained and tested across multiple datasets collected in different tunnels. We used two random forest (RF) implementations and one neural network (NN), as proposed in recent studies, on four datasets collected in different mines and tunnels in the US and Canada. We labeled points as belonging to one of four classes—rock, bolt, mesh, and other—and performed cross-site training experiments to evaluate accuracy differences between sites. In general, we found that the NN and RF models had similar performance to each other, and that same-site classification was generally successful, but cross-site performance was much lower and judged as not practically useful. Thus, our results indicate that standard geometric features are often insufficient for generalized classification of tunnel infrastructure, and these types of methods are most successful when applied to specific individual sites using interactive software for classification. Possible future research directions to improve generalized performance are discussed, including domain adaptation and deep learning methods.

Small communities in the Arequipa region of Peru are susceptible to rockfall hazards, which impact their lives and livelihoods. To mitigate rockfall hazards, it is first necessary to understand their locations and characteristics, which can be compiled into an inventory used in the creation of rockfall hazard rating maps. However, the only rockfall inventory available for Arequipa contains limited data of large, discrete events, which is insufficient for characterizing rockfall hazards at the community scale. A more comprehensive inventory would result in a more accurate rockfall hazard rating map—a significant resource for hazard mitigation and development planning. This study addresses this need through a remote method for rockfall hazard characterization at a community scale. Three communities located in geographically diverse areas of Arequipa were chosen for hazard inventory and characterization, with a fourth being used for validation of the method. Rockfall inventories of source zones and rockfall locations were developed using high-resolution aerial imagery, followed by field confirmation, and then predictions of runout distances using empirical models. These models closely matched the actual runout distance distribution, with all three sites having an R² value of 0.98 or above. A semi-automated method using a GIS-based model was developed that characterizes the generation and transport of rockfall. The generation component criteria consisted of source zone height, slope angle, and rockmass structural condition. Transport was characterized by rockfall runout distance, estimated rockfall trajectory paths, and hazard ratings of corresponding source zones. The representative runout distance inventory model of the validation site matched that of a nearby site with an R² of 0.98, despite inventorying less than a third of the number of rockfalls. This methodology improves upon current approaches and could be tested in other regions with similar climatic and geomorphic settings. These maps and methodology could be used by local and regional government agencies to warn residents of rockfall hazards, inform zoning regulations, and prioritize mitigation efforts.

Large-scale rock formations, referred to as “rockmasses”, consist of intact rock separated by pre-existing discontinuities (i.e., joints). The mechanical behavior of rockmasses is difficult to directly test in the laboratory due to the required specimen scale. Instead, Synthetic Rockmass Modeling (SRM) is often used to simulate field-scale rockmass behavior. SRM requires a calibrated discrete element model (DEM) of intact rock combined with a Discrete Fracture Network (DFN). While the SRM concept has been informally determined to provide reasonable results based on practitioner experience, detailed and peer-reviewed validation is lacking. The goal of this study was to evaluate the predictive capabilities of the SRM method. Previously available data on intact and rockmass analog laboratory specimens of Blanco Mera granite containing DFNs with two joint sets were used as a basis for the SRM created in this study. Specifically, the intact DEM was a Bonded Block Model (BBM), generated to match the grain structure and composition of Blanco Mera granite and the model’s input parameters were calibrated so that the behavior of the BBM matched that of the intact laboratory specimens. The predictive capabilities of the model were evaluated by recreating the DFN from the jointed laboratory specimens within the intact BBM and comparing the behavior of the jointed models back to the jointed laboratory specimens, which has not been previously studied in the literature. The BBM was found capable of approximately predicting the behavior of rockmass analog specimens containing a pre-existing DFN without further calibration, which shows potential for the use of SRM in both industry and academia. Specifically, the BBM predicted the strength, dilatancy, and microfracturing behavior of the jointed laboratory specimens.

Research on high-temporal-resolution rock slope monitoring has tended to focus on scenarios where spatial resolution is also high. Accordingly, there is a lack of understanding of the implications for rock slope monitoring results in cases with high temporal resolution but low spatial resolution, which is the focus of this study. This study uses automatically captured photos taken at a daily frequency by five fixed-base cameras in conjunction with multi-epoch Structure-from-Motion (SfM) photogrammetric processing techniques to evaluate changes in a rock slope in Majes, Arequipa, Peru. The results of the monitoring campaign demonstrate that there are potential issues with the common notion that higher frequency change detection is always superior. For lower spatial resolutions or when only large changes are of concern, using a high-frequency monitoring method may cause small volume changes that eventually aggrade into larger areas of change to be missed, whereas most of the total volume change would be captured with lower-frequency monitoring intervals. In this study, daily change detection and volume calculation resulted in a cumulative rockfall volume of 4300 m³ over about 14 months, while change detection and volume calculation between dates at the start and end of the 14-month period resulted in a total rockfall volume of 12,300 m³. High-frequency monitoring is still the most accurate approach for evaluating slope evolution from a rockfall frequency and size distribution perspective, and it allows for the detection of short accelerations and pre-failure deformations, but longer-term comparison intervals may be required in cases where spatial resolution is low relative to temporal resolution to more accurately reflect the total volume change of a given rock slope over a long period of time.

Discontinuum Bonded Block Modeling (BBM) represents a potential tool for support design, as these models can reproduce both the rock fracturing process and the influence of reinforcement on unsupported ground. Despite their strengths, discontinuum models are seldom used for mining design due to their computationally intensive nature. This study is an application of an integrated 3D continuum–2D discontinuum approach, in which the mine-wide stress distribution process is modeled using a continuum software, and the local deformation behavior in response to a strain path from the continuum model is simulated with a 2D discontinuum software. In June 2017, two multi-point borehole extensometers were installed in a longwall chain pillar to record ground displacements as a function of the longwall face position. The data from one of the extensometers were employed to calibrate a panel-scale FLAC3D model. The boundary conditions along the pillar slice containing the extensometer were extracted from the FLAC3D model and applied to a 2D BBM, and the input parameters were modified to match the extensometer data. The calibrated BBM was able to reproduce the unsupported rib deformation and depth of the fracturing well. Subsequently, a few support schemes were tested to demonstrate how the incorporation of support might affect rib deformation.