I am lokesh kanna from Anna University Regional Campus Tirunelveli make use of the resource you got
Machine learning is the ability of machine to understand languages to machine it is a low level language that is used by humans to give command
A variety of algorithms may be applied depending on the nature of the earth science exploration. Some algorithms may perform significantly better than others for particular objectives. For example, convolutional neural networks (CNN) are good at interpreting images, artificial neural networks (ANN) perform well in soil classification[4] but more computationally expensive to train than support-vector machine (SVM) learning. The application of machine learning has been popular in recent decades, as the development of other technologies such as unmanned aerial vehicles (UAVs),[5] ultra-high resolution remote sensing technology and high-performance computing units[6] lead to the availability of large high-quality datasets and more advanced algorithms.
1. MACHINE LEARNING FOR EARTH SYSTEM SCIENCE
ADWAY MITRA
CENTRE OF EXCELLENCE IN AI, IIT KHARAGPUR
Live Session 1: Handling Geophysical Datasets
2. CONCEPTS COVERED
⮚ Raster Data formats
⮚ Vector Data Formats
⮚ Loading and visualizing data using Python interface
⮚ Extreme values statistics using Python
3. RASTER DATA FORMAT
Formats:
NetCDF (.nc) – netCDF4 package (Python)
HDF (hierarchical data format) – also netCDF4 package
- Raster data where each “pixel” stores geophysical
variable for a specific location
GeoTIFF- Geospatial Data Abstraction Library (GDAL)
(tagged image file format)
- Georeferenced data including satellite imagery, aerial
photography, topography or digital elevation maps etc
4. LOADING DATA FROM .NC
from netCDF4 import Dataset
nc_f = 'tpw_v07r01_200910.nc4.nc' # filename
nc_fid = Dataset(nc_f, 'r') print(nc_fid)
nc_fid.close()
import netCDF4
import numpy as np
f = netCDF4.Dataset('orography.nc', 'r')
lats = f.variables['lat']
lons = f.variables['lon']
orography = f.variables['orog']
print(lats[:])
print(lons[:])
print(orography[:])
f.close()
STORING DATA IN NC FILE
import netCDF4
import numpy as np
f = netCDF4.Dataset('orography.nc', 'w')
f.createDimension('time', None)
f.createDimension('z', 3)
f.createDimension('y', 4)
f.createDimension('x', 5)
lats = f.createVariable('lat', float, ('y', ), zlib=True)
lons = f.createVariable('lon', float, ('x', ), zlib=True)
orography = f.createVariable('orog', float, ('y', 'x'), zlib=True,
least_significant_digit=1, fill_value=0)
# create latitude and longitude 1D arrays
lat_out = [60, 65, 70, 75]
lon_out = [ 30, 60, 90, 120, 150]
# Create field values for orography
data_out = np.arange(4*5) # 1d array but with dimension x*y
data_out.shape = (4,5) # reshape to 2d array
orography[:] = data_out
lats[:] = lat_out
lons[:] = lon_out
# close file to write on disk
f.close()
5. DATA VISUALIZATION USING HDF
from netCDF4 import Dataset
f=Dataset('MISR_AM1_CGLS_MAY_2007_F04_0031.hdf','r')
print("Metadata for the dataset:")
print(f)
print("List of available variables (or key): ")
f.variable.keys()
print("Metadata for 'NDVI average' variable: ")
data=f.variables['NDVI average'][:]
plt.imshow(data)
plt.show()
f.close()
f.close()