I want to run the graphcast by my own gribfile downloaded from ERA5,i select the needed var correctly,but i meet a bug,how to slove it?

[1301970063]

2024-04-14 17:12:09,858 INFO Building model: 0.6 second.
2024-04-14 17:12:50,841 INFO Creating forcing variables: 40 seconds.
2024-04-14 17:13:01,958 INFO Converting GRIB to xarray: 11 seconds.
2024-04-14 17:13:13,666 INFO Reindexing: 11 seconds.
2024-04-14 17:13:14,930 INFO Creating training data: 1 minute 5 seconds.
2024-04-14 17:13:38,654 INFO Extracting input targets: 23 seconds.
2024-04-14 17:13:38,655 INFO Creating input data (total): 1 minute 28 seconds.
2024-04-14 17:13:38,655 INFO Total time: 1 minute 39 seconds.
Traceback (most recent call last):
File "/data1/home/songrj/anaconda3/envs/am/lib/python3.10/site-packages/xarray/core/dataset.py", line 1408, in _copy_listed
variables[name] = self._variables[name]
KeyError: 'geopotential_at_surface'

[mchantry]

You are missing one of the variables, specifically the geopotential_at_surface. Are you sure your file contains the variable?

[1301970063]

Thank you, I have resolved the issue. GraphCast requires the 'landmask' variable to be provided in the GRIB file, which I had not provided. Thank you for your response.
But running this large model requires a significant amount of memory compared to other major meteorological models, and my computer is not quite up to the task.

[kasProg]

Curious to know how did you use --file option from graphcast or any other model. If I download ERA5, I get surface pressure levels and pressure levels separately. Did you combine these two files somehow?

[1301970063]

Curious to know how did you use --file option from graphcast or any other model. If I download ERA5, I get surface pressure levels and pressure levels separately. Did you combine these two files somehow?

No need to combine,you can repalce the [--input cds] by this option：
[--file '../FourcastNet_*.grib']