Announcement: All noncommercial projects registered to use Earth Engine before
April 15, 2025 must
verify noncommercial eligibility to maintain Earth Engine access.
ee.Model.predictImage
Stay organized with collections
Save and categorize content based on your preferences.
Make predictions from pixel tiles of an image. The predictions are merged as bands with the input image.
The model will receive 0s in place of masked pixels. The masks of predicted output bands are the minimum of the masks of the inputs.
Usage | Returns | Model.predictImage(image) | Image |
Argument | Type | Details | this: model | Model | |
image | Image | The input image. |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[[["\u003cp\u003ePredicts pixel values within image tiles and integrates these predictions as new bands into the original image.\u003c/p\u003e\n"],["\u003cp\u003eAccepts images with masked pixels, representing them as 0 values, and generates output masks based on input masks.\u003c/p\u003e\n"],["\u003cp\u003eOffers a \u003ccode\u003epredictImage\u003c/code\u003e function that takes an image as input and returns an image with the predicted bands.\u003c/p\u003e\n"]]],["The model predicts pixel values from an input image, merging these predictions as new bands within the image. Masked pixels in the input are treated as 0s. The output bands' masks are determined by taking the minimum mask of the input bands. The `predictImage` function takes an `image` as input and returns a modified `image` with the new predicted bands.\n"],null,["# ee.Model.predictImage\n\nMake predictions from pixel tiles of an image. The predictions are merged as bands with the input image.\n\n\u003cbr /\u003e\n\nThe model will receive 0s in place of masked pixels. The masks of predicted output bands are the minimum of the masks of the inputs.\n\n| Usage | Returns |\n|-----------------------------|---------|\n| Model.predictImage`(image)` | Image |\n\n| Argument | Type | Details |\n|---------------|-------|------------------|\n| this: `model` | Model | |\n| `image` | Image | The input image. |"]]