Random forest Classificaption


How can I kown the best number of tress? please help me,thank you!

generally, more trees make your classifier more robust and more accurate. However, when you reach a certain point, the accuracy does no longer increase with more trees. So you can test step wise:
10 > 25 > 50 > 100 > 200 > 400
and compare the resulting training accuracies. Once there is no longer a significant increase of accuracy, you don’t need more trees.

But: This all depends on the number of input features (rasters used for training) and training samples (polygons used for training). If these are too small, the random forest classifier becomes ineffective, because every tree is calculated based on the same training data. For example, if you only use 2 input rasters (VV and VH) and very small training polyons), it does not make a difference if you process 5 trees or 5000, they will all produce the same result, and therefore make the classifier ineffective.

1 Like

Thank you!
I have another question, I have two Images,I want to use Create Stack tools to merge S1 and S2,add S1 first ,or S2 first ?
The order in which this is added makes any difference to the result.

the order won’t affect the result, because the variables are shuffled by the Random Forest anyway.

Have you seen this tutorial? Synergetic use of S1 (SAR) and S2 (optical) data and use of analysis tools

nice user name by the way :wink: Looking forward to the new album.

1 Like

Aha :slightly_smiling_face:,Thank you very much again!