Seamless high-resolution transboundary dynamic landcover map of the Sonoran and Mojave Desert ecoregion within Bird Conservation Region 33

These data were compiled for the creation of a continuous, high-resolution transboundary land cover map of the Sonoran and Mojave Desert ecoregion within Bird Conservation Region 33 (BCR 33). Objective(s) of our study were to, 1) develop a machine learning algorithm trained to classify vegetation land cover using remote sensing spectral data and phenology metrics from 2013-2021, over the Sonoran and Mojave Deserts BCR 33; 2) calibrate, validate, and refine the final machine learning derived vegetation map using a collection of openly sourced remote sensing and ground-based ancillary data, images, and limited fieldwork; and 3) harmonize a new transboundary classification system by expanding existing land cover mapping resources from the United States portion of BCR 33 into Mexico. These data represent the final land cover maps produced using a Random Forest Classifier (RF), with additional ancillary labels for urban and agriculture areas. These data were created within BCR33 which spans an extent from Nevada, in the United States to Sinaloa, in Mexico for the time period from April 2013 to December 2021. These data were created by researchers at the University of Arizona, Vegetation Index and Phenology Lab who collected, processed, and analyzed all data and developed the random forest model used to produce the final continuous, high-resolution transboundary land cover map. These data can be used to guide land management and conservation decisions within the Sonoran and Mojave Desert ecoregion within BCR 33.

本数据集为制作鸟类保护区域33（Bird Conservation Region 33，BCR 33）内索诺兰沙漠与莫哈韦沙漠生态区的连续高分辨率跨界土地覆盖图而汇编。本研究的目标包括：1）基于2013-2021年的遥感光谱数据与物候指标，开发针对索诺兰沙漠与莫哈韦沙漠BCR 33区域的植被土地覆盖分类机器学习算法；2）通过公开获取的遥感、地面辅助数据、影像资料及有限野外调查数据，对机器学习生成的最终植被图进行校准、验证与优化；3）将美国境内BCR 33区域的现有土地覆盖制图资源拓展至墨西哥境内，以统一新的跨界分类体系。本数据集为采用随机森林分类器（Random Forest Classifier, RF）生成的最终土地覆盖图，附带城镇与农业区域的额外辅助标签。数据集覆盖范围为BCR 33区域，北至美国内华达州，南抵墨西哥锡那罗亚州，时间跨度为2013年4月至2021年12月。本数据集由亚利桑那大学植被指数与物候实验室的研究人员创建，该团队完成了所有数据的采集、处理与分析，并开发了用于生成最终连续高分辨率跨界土地覆盖图的随机森林模型。本数据集可用于指导BCR 33区域内索诺兰沙漠与莫哈韦沙漠生态区的土地管理与保护决策。