UPstream Regional LiDAR Model for Extent of Trout (UPRLIMET) model training and prediction data

We present a novel model development and evaluation framework, wherein we compare 26 models to predict upper distribution limits of trout in streams in Oregon using observational data collected in 2017. The models used machine learning, logistic regression, and a sophisticated nested spatial cross-validation routine to evaluate predictive performance while accounting for spatial autocorrelation. The model resulting in the best predictive performance, termed UPstream Regional LiDAR Model for Extent of Trout (UPRLIMET), is a two-stage model that uses a logistic regression algorithm calibrated to observations of Coastal Cutthroat Trout (Oncorhynchus clarkii clarkii) occurrence and variables representing hydro-topographic characteristics of the landscape. We predict trout presence along reaches throughout a stream network and include a stopping rule to identify a discrete upper limit point above which all stream reaches are classified as fishless. This data publication contains the geospatial data used for training, validation, and prediction by UPRLIMET (UPstream Regional LiDAR Model for Extent of Trout). Data are provided as two geodatabases with streamline (flowline) hydrography and include spatially explicit full-detail (predictions + covariates) prediction features separated by HUC12 watersheds and layers with pertinent prediction outputs merged into single spatial data layers for rapid rendering. Additionally, tabular data files are included that provide definitions of the covariates used in the model as well as the location and habitat barrier information for each stream and mainstem or tributary.

本项研究提出了一种创新的模型开发与评估框架，该框架通过比较26种模型，以预测俄勒冈州溪流中鲑鱼的上限分布。所采用的模型运用机器学习、逻辑回归以及复杂的嵌套空间交叉验证程序来评估预测性能，同时考虑空间自相关性。在预测性能最佳的模型中，即所谓的UPstream Regional LiDAR Model for Extent of Trout (UPRLIMET)模型，该模型为两阶段模型，运用逻辑回归算法进行校准，以观测到的海岸红点鲑鱼（Oncorhynchus clarkii clarkii）的分布情况以及代表景观水陆特征的变量。我们预测了溪流网络中各河段鲑鱼的存在情况，并设立了一个停止规则，以识别一个离散的上限点，在此点之上，所有溪流河段均被归类为无鱼。本数据出版物包含了用于UPRLIMET（UPstream Regional LiDAR Model for Extent of Trout）训练、验证和预测的地理空间数据。数据以两个地理数据库的形式提供，包括流线（流量线）水文学和空间显式的全细节（预测+协变量）预测特征，这些特征由HUC12流域和将相关预测输出合并为单一空间数据层的图层分隔。此外，还包括了表格数据文件，提供了模型中使用的协变量的定义以及每条溪流和主河道或支流的位置和栖息地障碍信息。