Search

Introduction: The Indian Himalayas' susceptibility to landslides, particularly as a location where climate change effects may be event catalysts, necessitates the development of dependable landslide susceptibility maps (LSM). Method: This study diverges from traditional binary classification models, framing LSM as a positive-unlabeled learning problem. This approach acknowledges that regions without recorded landslides are not necessarily at low risk but could simply have not experienced landslides yet. The study utilizes novel positive-unlabeled learning-enhanced algorithms—Random Forest, K-Nearest Neighbor, and Decision Tree—to create LSM for Chamoli district, India. Eleven causative factors for landslides are identified, including elevation, aspect, slope, geology, geomorphology, distance to lineament, lithology, NDVI, distance to river, distance to road and residential land use. To address spatial correlation biases, instead of randomly splitting the dataset, the study adopts spatial splitting to get the training and testing datasets. Conclusion: The study reveals that positive-unlabeled learning substantially improves the Area Under Curve and recall, leading to a more conservative LSM compared to binary classification methods. Analysis shows that the southern region of Chamoli exhibits high recall but lower accuracy, suggesting a latent high landslide susceptibility despite a lack of historical landslides in this region. The study also quantifies the impact of human activity on landslide risk, indicating an elevated threat to life and the local economy, especially in Chamoli's southwestern areas. [ABSTRACT FROM AUTHOR]

Quantification of particle shape features to characterize granular materials remains an open problem till date, owing to the complexity involved in obtaining the geometrical parameters necessary to adequately compute the shape components (sphericity, roundness and roughness). A new computational method based on image analysis and filter techniques is proposed in this paper to overcome this difficulty. In this method, operations are performed on binary images of particles obtained from raster images (collection of pixels) by the process of image segmentation. The boundary of particles captured in 2D images consist of micro, meso and macro scale features on which filter techniques are applied to remove the micro level features for the quantification of particle roughness and to obtain a roughness free boundary. A robust algorithm is then written and implemented in MATLAB to obtain the complete geometry of the particle boundary (free from roughness features) and to identify the precise corner and non-corner regions along the boundary. This information is used to quantify the roundness (as per Wadell in J Geol 40:443-451, 1932) and sphericity of particles. The proposed methodology to measure roundness and sphericity is compared against standard visual charts provided by earlier researchers. Finally, the methodology is demonstrated on real soil particles falling across a wide range of sizes, shapes and mineralogical compositions. Also, an idea to comprehend the kinematics of particle motion based on its concavo-convex features is discussed with two proposed novel descriptors and a visual classification chart. [ABSTRACT FROM AUTHOR]

Manually grading D3 data visualizations is a challenging endeavor, and is especially difficult for large classes with hundreds of students. Grading an interactive visualization requires a combination of interactive, quantitative, and qualitative evaluation that are conventionally done manually and are difficult to scale up as the visualization complexity, data size, and number of students increase. We present VISGRADER, a first-of-its kind automatic grading method for D3 visualizations that scalably and precisely evaluates the data bindings, visual encodings, interactions, and design specifications used in a visualization. Our method enhances students' learning experience, enabling them to submit their code frequently and receive rapid feedback to better inform iteration and improvement to their code and visualization design. We have successfully deployed our method and auto-graded D3 submissions from more than 4000 students in a visualization course at Georgia Tech, and received positive feedback for expanding its adoption.