空间分析
空间生态学
自相关
比例(比率)
共同空间格局
生态学
宏观生态学
时间尺度
地理
空间相关性
统计
数学
地图学
遥感
生物地理学
生物
作者
Marie‐Josée Fortin,Mark R. T. Dale,Jay M. Ver Hoef
出处
期刊:Encyclopedia of Environmetrics
日期:2012-08-31
被引量:5
标识
DOI:10.1002/9780470057339.vas039.pub2
摘要
Abstract The first step in understanding ecological processes is to identify patterns. Ecological data are usually characterized by spatial structures due to spatial autocorrelation. Spatial autocorrelation refers to the pattern in which observations from nearby locations are more likely to have similar magnitude than by chance alone. The magnitude, intensity, as well as extent of spatial autocorrelation can be quantified using spatial statistics. Most ecological data exhibit some degree of spatial autocorrelation, depending on the scale at which the data were recorded and then analyzed. Ecological phenomena are also characterized by the multiple ecological processes that act upon them; these processes often operate at more than one spatial scale. Ecological data are a composite of several spatial scales: trends at macroscales; patches, gradients and patterns at meso‐ and local scales; and random patterns at local and microscales. The different processes and patterns at different scales are not necessarily linear or additive, and this contributes to the degree of spatial dependence in the data.
科研通智能强力驱动
Strongly Powered by AbleSci AI