Abstract. This paper introduces the Landslide Susceptibility Assessment Tools – Project Manager Suite (LSAT PM), an open-source, easy-to-use software written in Python. Primarily developed to conduct landslide susceptibility analysis (LSA), it is not limited to this issue and applies to any other research dealing with supervised spatial binary classification. LSAT PM provides efficient interactive data management supported by handy tools in a standardized project framework. The application utilizes open standard data formats, ensuring data transferability to all geographic information systems. LSAT PM has a modular structure that allows extending the existing toolkit by additional tools. The LSAT PM v1.0.0b implements heuristic and data-driven methods: analytical hierarchy process, weights of evidence, logistic regression, and artificial neural networks. The software was developed and tested over the years in different projects dealing with landslide susceptibility assessment. The emphasis on model uncertainties and statistical model evaluation makes the software a practical modeling tool to explore and evaluate different native and foreign LSA models. The software distribution package includes comprehensive documentation. A dataset for testing purposes of the software is available. LSAT PM is subject to continuous further development.

Abstract. This paper introduces the Landslide Susceptibility Assessment Tools – Project Manager Suite (LSAT PM), an open-source, easy-to-use software written in Python. Primarily developed to conduct landslide susceptibility analyses (LSA), it is not limited to this issue and applies to any other research dealing with supervised spatial binary classification. With its standardized project framework, LSAT PM provides efficient interactive data management supported by handy tools. The application utilizes standard data formats ensuring data transferability to all geographic information systems. LSAT PM has a modular structure allowing to extend the existing toolkit by additional analyses. The LSAT PM v1.0.0b implements heuristic and data-driven methods such as the analytical hierarchy process, weights of evidence, logistic regression, and artificial neural networks. The software was developed and tested over the years in different projects dealing with landslide susceptibility assessment. The emphasis on model uncertainties and statistical model evaluation makes the software a practical modeling tool. Also, it provides the possibility to explore and evaluate different LSA models, even those not created with LSAT PM. The software distribution package includes comprehensive documentation. A dataset for testing purposes of the software is available. LSAT PM is subject to continuous further development.

<p>In the presented study, we investigate the possibilities of performing tasks related to landslide susceptibility assessment (LSA) on the provided benchmark dataset. The slope unit-based dataset consists of aggregated predisposing factors and two label sets. Although initially introduced as a dataset for binary classification task<em>s</em>, it is also suitable for zoning and regression analysis in combination with the underlying landslide inventory. Zoning ranks slope units to delineate the study area in susceptibility zones. In the regression analysis, we try to predict a numeric target value (e.g.,  landslide count) by the slope unit's attributes.</p> <p>We explored the benchmark dataset using bivariate and multivariate statistical visualization techniques to understand the data relations better. We found the dataset at this stage insufficient for achieving a well-explainable high-performance classification using linear models. Most attributes are not specific to linearly separate the given labels. The chosen central tendency statistics (mean and standard deviation) may not characterize the parameter distributions inside the slope unit sufficiently.</p> <p>We propose a theoretical concept for zonation analysis to assess the best possible performance on the given discrete dataset using the success rate curve as the model evaluation metric. Because any applied algorithm cannot modify the geometry of the discrete slope units, the evaluation metric only depends on the relative ranking of slope units. The best performance is obtainable without computing a predictive model. For frequency-related models (weighting of factors with landslide count statistics), a simple direct computation of conditional probabilities or frequency ratio on the slope units as a ranking factor provides the best possible ranking. Combining the label and slope unit's area provides the best slope unit ranking for binary labels.</p> <p>We conducted a regression and classification analysis with artificial neural networks (ANN) testing different combinations of parameters (sensitivity analysis) architectures allowing for modeling nonlinear relations. In both analyses, initial results show that a complex net architecture can boost the model fit on the training dataset by losing predictive performance on test data. Also, the dataset pre-exploration corresponds well with the sensitivity analysis with ANN. The number of parameters is reducible to few effective predictors without losing much accuracy in classification, which is poor-to-moderate depending on the utilized label set.</p> <p>While slope units as an aggregation for geomorphological analyses remain undisputed, the proposed aggregation of predisposing factors in slope units at the analysis's entry point needs further discussion. Aggregating the results of a raster-based LSA to overcome deviances in landslide susceptibility patterns caused by data uncertainties or different methods could be more suitable at this point. Slope units should be analyzed with regression analysis in LSA to consider their different spatial extents during the calculation.</p> <p>We provide our scripts, visualizations, and results as a Jupyter Notebook on our GitHub: https://github.com/BGR-EGHA/EGU23_GM3.3_ls_benchmark.</p>

The eastern slope of Garmaksla, a flat-topped mountain at the western margin of Billefjorden, Svalbard, is affected by mass movements of different types. Rotational rock slides, rock fall and a rock avalanche affecting the coastal cliff are shallow surface expressions covering a larger rock mass instability that is bordered to the west by the Balliolbreen Fault. This structural feature is part of the Billefjorden Fault Zone and accommodated multi-phase deformation since Devonian time. Based on a comprehensive morpho-structural analysis, the mapped surface features and rock slope failures are explained by a compound rock slide model that reveals a litho-structural control on the type and mechanism of slope instability. The Balliolbreen fault serves as an inherited zone of weakness that is re-activated as the rear rupture surface of the rock slide. In addition, favorably oriented bedding planes and pre-existing fault zones serve as prime conditioning factors for the compound rock slide. A postglacial age of at least 6 ka is derived from 14 C dated sediments of Garmaksla Lake, a perennial sag pond along the main scarp. While the current state of activity of the compound rock slide is unclear, an increase of shallow slope instabilities is expected due to climate warming.