Browsing by Author "Nieber, John"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Minnesota Guide for Stream Connectivity and Aquatic Organism Passage through Culverts
    (Minnesota Department of Transportation, 2019-01) Hernick, Matthew; Lenhart, Christian; Kozarek, Jessica; Nieber, John
    This guide assists Minnesota culvert designers in identifying, selecting, and implementing appropriate designs for maintaining aquatic organism passage (AOP) and stream connectivity at road-stream intersections. It was synthesized from existing literature and culvert design documents, a survey of Minnesota practitioners, research, and input from local, regional, and national experts. Culvert designs that create excessive velocity, physical barriers, or shallow depth can disrupt AOP and may be detrimental to the continuity of water flow, sediment, and debris transport vital to stream health. Conversely, the recommended culvert designs in this guide account for stream parameters such as slope and substrate that vary across Minnesota landscapes. A set of best practices captures critical design elements based on stream characteristics, which can be summarized as follows: 1.) Design the culvert to be similar to the stream channel (reference reach) by matching its slope, alignment, bankfull width, and flow depth to maximize AOP; 2.) Provide a continuous sediment bed with roughness similar to the channel, while maintaining continuity of sediment transport and debris passage, and; 3.) Design for public safety, longevity, and resilience. Culvert design that improves AOP and accounts for sediment transport is expected to reduce long-term maintenance costs and increase culvert life span.
  • Thumbnail Image
    Item
    Source Aware Modulation for leveraging limited data from heterogeneous sources
    (2021) Li, Xiang; Khandelwal, Ankush; Ghosh, Rahul; Renganathan, Arvind; Willard, Jared; Xu, Shaoming; Jia, Xiaowei; Shu, Lele; Teng, Victor; Steinbach, Michael; Nieber, John; Duffy, Christopher; Kumar, Vipin
    In many personalized prediction applications, sharing information between entities/tasks/sources is critical to address data scarcity. Furthermore, inherent characteristics of sources distinguish relationships between input drivers and response variables across entities. For example, for the same amount of rainfall (input driver), two different basins will have very different streamflow (response variable) values depending on the basin characteristics (e.g., soil porosity, slope, …). Given such heterogeneity, a trivial merging of data without source characteristics would lead to poor personalized predictions. In recent years, meta-learning has become a very popular framework to learn generalized global models that can be easily adapted (fine-tuned) for individual sources. In this talk, we present an exhaustive analysis of the source-aware modulation based meta-learning approach. Source-aware modulation adjusts the shared hidden features based on source characteristics. The adjusted hidden features are then used to calculate the response variable for individual sources. Although this strategy shows promising prediction improvement, its applicability is limited in certain applications where source characteristics might not be available (especially due to privacy concerns). In this work, we show that robust personalized predictions can be achieved even in the absence of explicit source characteristics. We investigated the performance of different modulation strategies under various data sparsity settings on two datasets. We demonstrate that source-aware modulation is a very viable solution (with or without known characteristics) compared to traditional meta-learning methods such as model agnostic meta-learning.