Depth to top of root or water soil restrictive layer (resdept) soil maps of the Upper Colorado River Basin

UPDATE: AN ERROR WAS FOUND IN THE TRAINING DATA PREPARATION. AN UPDATED VERSION HAS BEEN CREATED. THIS VERSION SIGNIFICANTLY UNDERESTIMATES VALUES, BUT REPRESENTS TRENDS DECENTLY, PLEASE SEE THE UPDATED VERSION OF THIS REPOSITORY FOR BETTER PREDICTIONS. Repository includes maps describing the depth (cm) to the top of any water or root soil restrictive layer (resdept) as defined by United States soil survey program. These data are preliminary or provisional and are subject to revision. They are being provided to meet the need for timely best science. The data have not received final approval by the U.S. Geological Survey (USGS) and are provided on the condition that neither the USGS nor the U.S. Government shall be held liable for any damages resulting from the authorized or unauthorized use of the data. The creation and interpretation of this data is documented in the following article. Please note this article has not been reviewed yet and this citation will be updated as the peer review process proceeds. Nauman, T. W., Duniway, M. C., In Preparation. Predictive reconstruction of soil survey property maps for field scale adaptive land management. Soil Science Society of America Journal. File Name Details: ACCURACY!! Please see manuscript and Github repository (https://github.com/naumi421/SoilReconProps) for full details on accuracy. We do provide cross validation (CV) accuracy plots in this repository for the training sample (file ending _CV_plots.tif). These plots compare CV predictions with observed values relative to a 1:1 line. Values plotted near the 1:1 line are more accurate. Note that values are plotted in hex-bin density scatter plots because of the large number of observations (most are >3000). Elements are separated by underscore (_) in the following sequence: property_r_depth_cm_geometry_model_additional_elements.extension Example: resdept_r_cm_2D_QRF.tif Indicates depth to top of restriction (resdept; in cm) using a 2D model (separate model for each depth) employing a quantile regression forest. This file is the raster prediction map for this model. There may be additional GIS files associated with this file (e.g. pyramids) that have the same file name, but different extensions. The following elements may also exist on the end of filenames indicating other spatial files that characterize a given model's uncertainty (see below). _95PI_h: Indicates the layer is the upper 95% prediction interval value. _95PI_l: Indicates the layer is the lower 95% prediction interval value. _95PI_relwidth: Indicates the layer is the 95% relative prediction interval (RPI). The RPI is a standardization of the prediction interval that indicates that model is constraining uncertainty relative to the original sample. RPI values less than one represent uncertainty is being improved by the model relative to the original sample, and values less than 0.5 indicate low uncertainty in predictions. See paper listed above and also Nauman and Duniway (In revision) for more details on RPI. References Nauman, T. W., and Duniway, M. C., In Revision, Relative prediction intervals reveal larger uncertainty in 3D approaches to predictive digital soil mapping of soil properties with legacy data: Geoderma更新说明：训练数据制备环节发现一处错误，现已推出更新版本。原版本存在数值显著低估的问题，但尚能较好反映变化趋势。如需获得更精准的预测效果，请参阅本仓库的更新版本。 本仓库包含由美国土壤调查计划定义的、描述任意水体或根系限制土层顶部深度（单位：厘米，resdept）的地图数据。 本数据集属于初步或暂定版本，仍有可能进行修订。发布此类数据旨在满足及时获取最优科学成果的需求。本数据尚未经过美国地质调查局（United States Geological Survey, USGS）的最终审核，发布时附带以下免责条款：无论因授权或非授权使用本数据引发任何损害，美国地质调查局及美国政府均不承担相关责任。 本数据集的构建与解读可参阅下述论文。请注意该论文尚未经过同行评审，后续将随着同行评审流程的推进更新引用信息。Nauman, T. W.、Duniway, M. C.，待刊. 面向田块尺度适应性土地管理的土壤调查属性地图预测重建. 美国土壤学会期刊（Soil Science Society of America Journal）. 文件名说明：关于精度的重要说明！如需了解完整的精度细节，请参阅随附手稿及GitHub仓库（https://github.com/naumi421/SoilReconProps）。本仓库中提供了训练样本的交叉验证（Cross Validation, CV）精度图（文件名后缀为_CV_plots.tif）。此类图表以1:1直线为基准，对比交叉验证预测值与实测值，点位越靠近1:1直线则代表预测精度越高。由于观测样本量庞大（多数样本量超过3000），因此采用六边形分箱密度散点图进行可视化。 文件名中的元素以下划线（_）分隔，顺序如下：属性_深度（厘米）_几何模型_附加元素.扩展名。示例：resdept_r_cm_2D_QRF.tif，代表采用分位数回归森林构建的二维模型（针对各深度分别构建独立模型）得到的限制层顶部深度（resdept，单位：厘米）栅格预测图。此类文件为对应模型的栅格预测地图。可能存在与该文件关联的其他GIS文件（例如影像金字塔文件），其文件名一致但扩展名不同。 下述后缀可附加至文件名后，用于表征对应模型的不确定性（详见下文）： _95PI_h：代表图层为95%预测区间的上限值； _95PI_l：代表图层为95%预测区间的下限值； _95PI_relwidth：代表图层为95%相对预测区间（Relative Prediction Interval, RPI）。相对预测区间是对预测区间的标准化处理，用于衡量模型相较于原始样本集对不确定性的约束效果。若RPI值小于1，代表模型相较原始样本集有效降低了不确定性；若RPI值小于0.5，则代表预测的不确定性较低。有关相对预测区间的更多细节，请参阅上述论文及Nauman与Duniway（待修回）的相关研究。 参考文献 Nauman, T. W. 与 Duniway, M. C.，待修回. 相对预测区间揭示了利用遗留数据进行土壤属性预测性数字制图的三维方法存在更大不确定性：Geoderma