prl900

module load cdo
module load nco
module load gdal/2.2.2

cdo -b I16 select,name=maxPV /g/data/ub8/au/LandCover/DEA_ALC/17_-25/fc_metrics_17_-25_2014.nc out.nc
ncpdq -a y,x out.nc out_swap.nc
gdal_translate -ot Byte NETCDF:"out_swap.nc":maxPV test.tiff -co TILED=YES -co COMPRESS=DEFLATE
gdaladdo test.tiff 2 4 8 16 32

prl900

import xarray as xr
import numpy as np
import matplotlib.pyplot as plt

print("Jan")
ds = xr.open_dataset("era5_prec_2018H1.nc")
prec = ds.tp.sel(dict(time=slice('2018-01-01', '2018-01-31'))).data * 1000
ds.close()
print(prec.shape)

prl900

import numpy as np
import netCDF4

x = netCDF4.Dataset("/datasets/work/D61_CPSR_A_INPUT/ERA5_global/press_levels_201501.nc")["z"][:]
x = np.moveaxes(x,1,-1)

topo = netCDF4.Dataset("/datasets/work/D61_CPSR_A_INPUT/ERA5_global/ERA5_orography.nc")['z'][:]
topo = np.tile(topo, (x.shape[0],1,1,1))

prl900

from __future__ import print_function, division

from keras.layers import concatenate, Input, Concatenate, BatchNormalization
from keras.layers.convolutional import UpSampling2D, Conv2D
from keras.models import Model
from keras.optimizers import Adam

import xarray as xr
import numpy as np
import pickle

prl900

import tensorflow as tf
import numpy as np
import pandas as pd
import imageio

im_orig = imageio.imread("cameraman.jpg")[::4,::4].astype(np.float32) / 255

im_orig_df = pd.DataFrame(im_orig)

im_df_masked = im_orig_df.copy()

prl900

prl900

prl900

import datacube
from datacube.storage import masking
import matplotlib.pyplot as plt
import numpy as np

dc = datacube.Datacube(app='load-data-example')

query = {
        'lat': (-35.27, -35.33),
        'lon': (149.07, 149.15),

prl900

import numpy as np
import xarray as xr

# Load ERA5 geopotential levels
era5_ds1 = xr.open_dataset("./datasets/GEOP1000_GAN_2017.nc")
era5_ds2 = xr.open_dataset("./datasets/GEOP800_GAN_2017.nc")
era5_ds3 = xr.open_dataset("./datasets/GEOP500_GAN_2017.nc")
era5_times = era5_ds1.time[:].data

# Load ERA5 total precipitation

prl900