Google Earth Engine（GEE）——将城区、森林区和水域实现光谱分离！

光谱分离是在地球引擎中实现的image.unmix()方法。以下是将 Landsat 5 与预先确定的城市、植被和水端元混合的示例：

unmix(endmembers, sumToOne, nonNegative)

Unmix each pixel with the given endmembers, by computing the pseudo-inverse and multiplying it through each pixel. Returns an image of doubles with the same number of bands as endmembers.

通过计算伪逆并将其乘以每个像素，将每个像素与给定的端元分开。返回具有与末端成员相同数量的带图像。

Arguments:

this:image (Image):

The input image.

endmembers (List):

The endmembers to unmix with.

sumToOne (Boolean, default: false):

Constrain the outputs to sum to one.

nonNegative (Boolean, default: false):

Constrain the outputs to be non-negative.

Returns: Image

 直接上代码：

  

   

    

     

    
    

     

      // 加载影像并且选择波段，之后选择位置显示中心和加载影像
     
    
   

    

     

    
    

     

      var bands = ['B1', 'B2', 'B3', 'B4', 'B5', 'B6', 'B7'];
     
    
   

    

     

    
    

     

      var image = ee.Image('LANDSAT/LT05/C01/T1/LT05_044034_20080214')
     
    
   

    

     

    
    

     

        .select(bands);
     
    
   

    

     

    
    

     

      Map.setCenter(-122.1899, 37.5010, 10); 
     
    
   

    

     

    
    

     

      Map.addLayer(image, {bands: ['B4', 'B3', 'B2'], min: 0, max: 128}, 'image');
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      // 定义光谱端元，这个参数具体要看更加详细的光谱内容
     
    
   

    

     

    
    

     

      var urban = [88, 42, 48, 38, 86, 115, 59];
     
    
   

    

     

    
    

     

      var veg = [50, 21, 20, 35, 50, 110, 23];
     
    
   

    

     

    
    

     

      var water = [51, 20, 14, 9, 7, 116, 4];
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      // 取消混合，这样就进行了分解
     
    
   

    

     

    
    

     

      var fractions = image.unmix([urban, veg, water]);
     
    
   

    

     

    
    

     

      Map.addLayer(fractions, {}, 'unmixed');
     
    
  
 

文章来源: blog.csdn.net，作者：此星光明2021年博客之星云计算Top3，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/qq_31988139/article/details/119302820