公告：所有在
2025 年 4 月 15 日之前注册使用 Earth Engine 的非商业项目都必须
验证是否符合非商业性质的资格条件，才能继续使用 Earth Engine。
ee.Reducer.covariance
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
创建一个归约器，用于将一些长度相同的 1D 数组归约为形状为 NxN 的协方差矩阵。此 reducer 使用 Sandia National Laboratories 技术报告 SAND2008-6212 中的单次协方差公式，如果值范围较大，可能会降低准确性。
| 用法 | 返回 |
|---|
ee.Reducer.covariance() | 缩减器 |
无实参。
如未另行说明，那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可，并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情，请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC)：2025-07-26。
[null,null,["最后更新时间 (UTC)：2025-07-26。"],[[["\u003cp\u003eCreates a reducer for calculating the covariance matrix from multiple 1-D arrays.\u003c/p\u003e\n"],["\u003cp\u003eUtilizes a one-pass covariance formula which may be less accurate with large value ranges.\u003c/p\u003e\n"],["\u003cp\u003eOutput is an NxN covariance matrix where N is the length of the input arrays.\u003c/p\u003e\n"],["\u003cp\u003eThe reducer is created using \u003ccode\u003eee.Reducer.covariance()\u003c/code\u003e.\u003c/p\u003e\n"]]],["This describes a reducer function that computes a covariance matrix from multiple 1-D arrays of identical length. The output is an NxN covariance matrix. It employs a one-pass covariance formula, as detailed in Sandia National Laboratories Technical Report SAND2008-6212. The key action is reducing multiple arrays into a single matrix, and the critical information is the use of a specific formula which can result in decreased accuracy if the input data contains a broad range of values.\n"],null,["# ee.Reducer.covariance\n\nCreates a reducer that reduces some number of 1-D arrays of the same length N to a covariance matrix of shape NxN. This reducer uses the one-pass covariance formula from Sandia National Laboratories Technical Report SAND2008-6212, which can lose accuracy if the values span a large range.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Usage | Returns |\n|---------------------------|---------|\n| `ee.Reducer.covariance()` | Reducer |\n\n**No arguments.**"]]
