Manning’s roughness coefficients (Manning’s n) are numerical values which represent the resistance to flows in river channels and floodplains. Field surveys and land use land cover (LULC) maps are commonly used to infer these Manning’s n values. Field surveys can be time and labour intensive while the LULC maps derived from Landsat and RadarSat-2 are often too coarse and may produce inaccurate representations of true surface roughness, leading to errors in the outputs from hydraulic models. In this work we tested two approaches to generate high resolution surfaces depicting Manning’s n. The first is using unclassified LiDAR point clouds and a voxel/connection (VC) based approach in combination with a rule-based table to set the roughness values. In the second method, we created training data for several land use categories and trained an Image Segmentation (IS) U-Net model to predict the category of each pixel and then applied a Manning's n value to each category. Our results indicate the LiDAR based approach is able to label all pixels within the study region, but the reclass table needs more attention. The IS method has the capability to cover a larger area more efficiently, but many pixels did not fit the existing training labels, leaving the output data incomplete. Future work is needed before either of these techniques can be reliably implemented.

The Oxford English Dictionary is a valuable source of lexical information and a rich testing ground for mining highly structured text. Each entry is organized into a hierarchy of senses, which include definitions, labels and cited quotations. Subject labels distinguish the subject classification of a sense, for example they signal how a word may be used in anthropology, music or computing. Unfortunately subject labeling in the dictionary is incomplete. To overcome this incompleteness, we attempt to classify the senses (i.e., definitions) in the dictionary by their subjects, using the citations as an information guide. We report on four different approaches: k nearest neighbors, a standard classification technique; term weighting, an information retrieval method dealing with text; naive Bayes, a probabilistic method; and expectation maximization, an iterative probabilistic method. Experimental performance of these methods is compared based on standard classification metrics.