topic Re: Smoothing the DEM in Water Resources Questions

Smoothing the DEM

HusamAbuOqer — Thu, 22 Jun 2023 21:33:26 GMT

Hello everyone,

I am working on the Archydro toolset and I am facing an issue with the perona malik smoothing method, the mean and median areworking normally but the perona malik is not working and showing the error below.

(I am using the DEM I generated from the LAS file data)

Re: Smoothing the DEM

GinaO_Neil — Mon, 26 Jun 2023 20:22:03 GMT

Hello @HusamAbuOqer ! Perona Malik requires the input DEM to be in the .tif format. While other formats may work with the other smoothing methods, it is highly recommended that .tif files be used as inputs anyway. Please let me know if this resolves your issue. Thanks!

-Gina

Re: Smoothing the DEM

HusamAbuOqer — Mon, 26 Jun 2023 21:13:11 GMT

Hi Gina,

Thank you for your reply.

I think that was the issue I have been running through last, now I solved it by converting the DEM to a tif format.

Currently I am running the "Run random tree step and I am getting a raster of one value only (0), any recommendations for this issue?

Thanks.

Re: Smoothing the DEM

GinaO_Neil — Mon, 26 Jun 2023 22:45:45 GMT

Great!

You may be seeing a prediction value of just the 0 class if your training data is highly imbalanced towards the 0 class. If the imbalance is the issue, you can try significantly undersampling the majority class (0) when running Train Test Split: set the sampling percent for class 0 to be much lower thanthe sampling percent for class 1

Re: Smoothing the DEM

HusamAbuOqer — Wed, 28 Jun 2023 20:54:31 GMT

Hi again Gina!

I have been trying using testing data and it worked perfectly when I used the main data I reached the train test split and I am facing this error in the screenshot below.

Any recommendations for this issue?

Thanks

Re: Smoothing the DEM

GinaO_Neil — Thu, 29 Jun 2023 18:03:45 GMT

Hi @HusamAbuOqer ,

I believe your study area is too large. I recommend working in units of watersheds and from DEM data that is 3m resolution. I've found that 3m DEMs clipped to HUC12 watersheds works well with the tool's size limits. How large is your area? And are you confident in both the wetland coverage and nonwetland coverage in this entire area?

Re: Smoothing the DEM

HusamAbuOqer — Thu, 29 Jun 2023 18:22:09 GMT

Hello @GinaO_Neil

My study area is 23 sqKM with a DEM resolution of 25 centimeters.

And I am using ground truth data for Alberta from a government data source showing the wetland and non-wetland areas.

The test data area I tried it before and it worked normally was with almost the same size (but the resolution for this DEM was 1 meter)

Is this area considered a big area for the toolset or it's because of the high resolution of the DEM I am using?

Re: Smoothing the DEM

GinaO_Neil — Thu, 29 Jun 2023 18:37:54 GMT

Yes, that's a very large dataset. Over several tests I found that wetlands were better predicted by topographic indices calcualted from 3m DEM than from a 1m (or higher res) DEM. I recommend resampling your data up to 3m and working in one HUC12 at a time - i.e., calculated predictor variables for a single HUC12 extent. That sounds like amazing ground truth data! You should have the opportunity in that case to train wetlands in one HIC12 and use the trained model to predict wetlands in a separate HUC 12

Re: Smoothing the DEM

HusamAbuOqer — Thu, 29 Jun 2023 19:23:36 GMT

@GinaO_Neil Thank you so much for your reply!

I will check on this now.

Re: Smoothing the DEM

GinaO_Neil — Thu, 29 Jun 2023 19:29:55 GMT

No problem! Let me know if you continue to run into issues. I am happy to set up a screenshare as well. Good luck!

Re: Smoothing the DEM

HusamAbuOqer — Thu, 29 Jun 2023 20:44:55 GMT

@GinaO_Neil appreciate your support

Now this issue has been solved but I am facing another issue again when I run the random trees model as I only get a raster with one or zero value.

I have tried to use different constraints area or not add the constraint and it's still the same!

Do you know what could cause this?

Re: Smoothing the DEM

GinaO_Neil — Thu, 29 Jun 2023 20:51:09 GMT

Can you include a screenshot of your training data?

Re: Smoothing the DEM

HusamAbuOqer — Thu, 29 Jun 2023 20:55:52 GMT

Sure

So this image includes the constraint I have created within the study area.

And the other screenshot indicates the train.tff after running the test split tool.

Re: Smoothing the DEM

GinaO_Neil — Thu, 29 Jun 2023 21:12:43 GMT

It looks like your constraint is capturing an area with no wetlands. I may not be fully understanding your workflow. But I recommend the following:

choose one HUC12 in your study area and clip a 3m DEM to that area
derive predictor variables for that clipped DEM
use Preprocessing Groundtruth Data to prepare your known wetlands, using the HUC12 boundaries as the extents
create a polygon feature class within your HUC12 to use as your constraint (create a polygon that encompasses a mix of both wetlands and nonwetlands)
run Train Test Split with the constraint
continue with WIM workflow

Re: Smoothing the DEM

HusamAbuOqer — Sat, 01 Jul 2023 18:47:36 GMT

I am working on a study area in Canada so no HUC12 is available.

I think the issue could be caused because we are using different data than you have used.

Can we set up a meeting so I can discuss the data I am using with you?

Thank you!

Re: Smoothing the DEM

GinaO_Neil — Thu, 06 Jul 2023 00:59:42 GMT

Sure thing. Please email me and we'll get something scheduled! goneil@ersi.com

Re: Smoothing the DEM

HusamAbuOqer — Fri, 07 Jul 2023 21:03:17 GMT

Thank you Gina!

I tried to send you an email but I got a failure message.

Did you get any emails?

Re: Smoothing the DEM

Bethf — Fri, 21 Jun 2024 15:55:15 GMT

Hello. I am receiving this error when attempting to use Perona Malik method. It is is TIFF format, 1m resolution. Any insight would be helpful.

Re: Smoothing the DEM

LeAnnaKilhoffer — Wed, 11 Dec 2024 21:12:37 GMT

I am receiving the same error as you with 3 meter DEM data downloaded from the USGS. However if I run the smooth high resolution DEM tool on a higher resolution DEM I get a different error. Any ideas on what I can do to fix these errors.

Re: Smoothing the DEM

AshleyCofrin — Thu, 21 Aug 2025 15:56:12 GMT

I am having this same error. Did you find a solution?