2007 Environmental Protection Agency (EPA) National Lakes Assessment dataset plus derived data and additional spatially explicit ancillary environmental data.

Lake water quality is known to be affected by local and regional drivers, including lake physical characteristics, hydrology, landscape position, land cover, land use, geology, and climate. Here, we demonstrate the utility of hypothesis testing within the landscape limnology conceptual framework using a random forest algorithm on large, national-scale, spatially explicit dataset, the United States Environmental Protection Agency 2007 National Lakes Assessment. For 1026 lakes, we tested the relative importance of water quality drivers across spatial scales, the importance of hydrologic connectivity in mediating water quality drivers, and how the importance of both spatial scale and connectivity differ across response variables for five important in-lake water quality metrics (total phosphorus, total nitrogen, dissolved organic carbon, turbidity, and conductivity).众所周知，湖泊水质受局地与区域驱动因子影响，这些驱动因子包括湖泊物理特性、水文状况、景观位置、土地覆被、土地利用、地质条件与气候。本研究以美国环境保护署（United States Environmental Protection Agency）2007年全国湖泊评估项目的大型国家级空间显式数据集为支撑，结合随机森林（Random Forest）算法，在景观湖沼学（Landscape Limnology）的概念框架内，验证了假设检验的应用效用。针对1026个湖泊，本研究分析了三类核心内容：一是不同空间尺度下水质驱动因子的相对重要性；二是水文连通性在调控水质驱动因子过程中的关键作用；三是针对总磷（Total Phosphorus）、总氮（Total Nitrogen）、溶解性有机碳（Dissolved Organic Carbon）、浊度（Turbidity）与电导率（Conductivity）这5项关键湖内水质指标，空间尺度与水文连通性的重要性随响应变量的变化差异。