def test_ReadStations(self):
base_path = os.getenv('WAVELOC_PATH')
stations_file = os.path.join(base_path, 'test_data',
'coord_stations_test')
stations = read_stations_file(stations_file)
self.assertTrue('RVL' in stations)
self.assertAlmostEqual(stations['SNE']['x'], 366.958)
def do_comp_mag(opdict):
base_path = opdict['base_path']
# dataless
dataless_glob = glob.glob(
os.path.join(base_path, 'lib', opdict['dataless']))
dataless_glob.sort()
# output directory
output_dir = os.path.join(base_path, 'out', opdict['outdir'])
# data
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
data_glob = opdict['dataglob']
# location file
locdir = os.path.join(base_path, 'out', opdict['outdir'], 'loc')
locfile = os.path.join(locdir, 'locations.dat')
locs = read_locs_from_file(locfile)
opdict = read_header_from_file(locfile, opdict)
snr_wf = np.float(opdict['snr_tr_limit'])
# Stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
paz = read_paz(dataless_glob)
vals, tdeb = {}, {}
for sta in sorted(stations):
vals[sta] = {}
tdeb[sta] = {}
cha_list = opdict['comp_list']
for cha in cha_list:
vals, tdeb, dt = fill_values(vals, tdeb, data_glob, data_dir, cha)
new_file = open(locfile, 'w')
write_header_options(new_file, opdict)
mags = []
for loc in locs:
stack_time = loc['o_time']
loc_x = loc['x_mean']
loc_y = loc['y_mean']
loc_z = -loc['z_mean']
ml = []
for sta in sorted(stations):
if vals[sta]:
paz_list, p2p_amp, tspan = [], [], []
h_dist = np.sqrt((loc_x - stations[sta]['x'])**2 +
(loc_y - stations[sta]['y'])**2 +
(loc_z - stations[sta]['elev'])**2)
for cha in cha_list:
istart = int(
round(stack_time - 0.5 - tdeb[sta][cha]) * 1. / dt)
iend = int(
round(stack_time + 5.5 - tdeb[sta][cha]) * 1. / dt)
x = vals[sta][cha][istart:iend + 1]
if x.any() and np.max(x) / np.mean(np.abs(x)) > snr_wf:
max_amp = np.max(x)
i_max_amp = np.argmax(x)
min_amp = np.abs(np.min(x))
i_min_amp = np.argmin(x)
paz_list.append(paz[sta][cha])
tspan.append(np.abs(i_max_amp - i_min_amp) * dt)
p2p_amp.append(max_amp + min_amp)
if opdict['verbose']:
fig = plt.figure()
fig.set_facecolor('white')
plt.plot(x)
plt.plot(i_min_amp, x[i_min_amp], 'ro')
plt.plot(i_max_amp, x[i_max_amp], 'ro')
plt.title('%s,%s' % (sta, cha))
plt.show()
if paz_list:
mag = estimateMagnitude(paz_list, p2p_amp, tspan, h_dist)
ml.append(mag)
new_file.write(
"Max = %.2f, %s - %.2f s + %.2f s, x= %.4f pm %.4f km, y= %.4f pm %.4f km, z= %.4f pm %.4f km, ml= %.2f pm %.2f\n"
% (loc['max_trig'], loc['o_time'].isoformat(), loc['o_err_left'],
loc['o_err_right'], loc['x_mean'], loc['x_sigma'],
loc['y_mean'], loc['y_sigma'], loc['z_mean'], loc['z_sigma'],
np.mean(ml), np.std(ml)))
if ml:
mags.append(np.mean(ml))
new_file.close()
r = np.arange(-3, 3, 0.1)
p, logN, i1, i2 = bvalue(mags, r)
print "b-value:", -p[0]
if opdict['verbose']:
fig = plt.figure(figsize=(10, 5))
fig.set_facecolor('white')
ax1 = fig.add_subplot(121)
ax1.hist(mags, 25)
ax1.set_xlabel('Magnitude')
ax2 = fig.add_subplot(122, title='Gutenberg Richter law')
ax2.plot(r, logN)
ax2.plot(r[i1:i2], np.polyval(p, r[i1:i2]), 'r')
ax2.set_xlabel('Magnitude')
ax2.set_ylabel('log N')
plt.show()
def do_locations_prob_setup_and_run(opdict):
# get / set info
base_path=opdict['base_path']
space_only = opdict['probloc_spaceonly']
locfile=os.path.join(base_path,'out',opdict['outdir'],'loc','locations.dat')
locfile_prob=os.path.join(base_path,'out',opdict['outdir'],'loc','locations_prob.dat')
locfile_hdf5=os.path.join(base_path,'out',opdict['outdir'],'loc','locations_prob.hdf5')
f_prob=open(locfile_prob,'w')
# if locfile does not exist then make it by running trigger location
if not os.path.exists(locfile):
logging.info('No location found at %s. Running trigger location first...'%locfile)
do_locations_trigger_setup_and_run(opdict)
# directories
grid_dir=os.path.join(base_path,'out',opdict['outdir'],'grid')
output_dir=os.path.join(base_path,'out',opdict['outdir'])
# data files
data_dir=os.path.join(base_path,'data',opdict['datadir'])
data_glob=opdict['dataglob']
kurt_glob=opdict['kurtglob']
grad_glob=opdict['gradglob']
data_files=glob.glob(os.path.join(data_dir,data_glob))
kurt_files=glob.glob(os.path.join(data_dir,kurt_glob))
grad_files=glob.glob(os.path.join(data_dir,grad_glob))
data_files.sort()
kurt_files.sort()
grad_files.sort()
# stations
stations_filename=os.path.join(base_path,'lib',opdict['stations'])
stations=read_stations_file(stations_filename)
# grids
grid_filename_base=os.path.join(base_path,'lib',opdict['time_grid'])
search_grid_filename=os.path.join(base_path,'lib',opdict['search_grid'])
# read time grid information
time_grids=get_interpolated_time_grids(opdict)
# read locations
locs=read_locs_from_file(locfile)
# prepare file for output of marginals
f_marginals = h5py.File(locfile_hdf5,'w')
# iterate over locations
for loc in locs:
# create the appropriate grid on the fly
# generate the grids
o_time=loc['o_time']
if space_only:
start_time=o_time
end_time =o_time
else:
start_time=o_time-3*loc['o_err_left']
end_time=o_time+3*loc['o_err_right']
# make a buffer for migration
start_time_migration = start_time - 10.0
end_time_migration = end_time + 10.0
# re-read grid info to ensure clean copy
grid_info=read_hdr_file(search_grid_filename)
# read data
grad_dict,delta = read_data_compatible_with_time_dict(grad_files,
time_grids, start_time_migration, end_time_migration)
# do migration (all metadata on grid is added to grid_info)
do_migration_loop_continuous(opdict, grad_dict, delta,
start_time_migration, grid_info, time_grids, keep_grid=True)
# integrate to get the marginal probability density distributions
# get required info
grid_starttime=grid_info['start_time']
nx,ny,nz,nt=grid_info['grid_shape']
dx,dy,dz,dt=grid_info['grid_spacing']
x_orig,y_orig,z_orig=grid_info['grid_orig']
# we are only interested in the time around the origin time of the event
it_left = np.int(np.round((start_time - grid_starttime)/dt))
it_right = np.int(np.round((end_time - grid_starttime)/dt))
it_true = np.int(np.round((o_time - grid_starttime)/dt))
nt=(it_right-it_left)+1
# set up integration axes (wrt reference)
x=np.arange(nx)*dx
y=np.arange(ny)*dy
z=np.arange(nz)*dz
if not space_only:
t=np.arange(nt)*dt
# open the grid file
grid_filename=grid_info['dat_file']
f=h5py.File(grid_filename,'r')
stack_grid=f['stack_grid']
# extract the portion of interest (copy data)
if space_only:
stack_3D=np.empty((nx,ny,nz))
stack_3D[:] = stack_grid[:,it_true].reshape(nx,ny,nz)
else:
stack_4D=np.empty((nx,ny,nz,nt))
stack_4D[:] = stack_grid[:,it_left:it_right+1].reshape(nx,ny,nz,nt)
# close the grid file
f.close()
# Get expected values (normalizes grid internally)
if space_only:
exp_x, exp_y, exp_z, cov_matrix, prob_dict = \
compute_expected_coordinates3D(stack_3D,x,y,z,return_2Dgrids=True)
else:
exp_x, exp_y, exp_z, exp_t, cov_matrix, prob_dict = \
compute_expected_coordinates4D(stack_4D,x,y,z,t,return_2Dgrids=True)
# put reference location back
exp_x = exp_x + x_orig
exp_y = exp_y + y_orig
exp_z = exp_z + z_orig
if space_only:
exp_t = o_time
else:
exp_t = start_time + exp_t
# extract uncertainties from covariance matrix
if space_only:
sig_x,sig_y,sig_z = np.sqrt(np.diagonal(cov_matrix))
sig_t = (loc['o_err_left']+loc['o_err_right'])/2.
else:
sig_x,sig_y,sig_z,sig_t = np.sqrt(np.diagonal(cov_matrix))
# save the marginals to a hdf5 file in loc subdirectory (f_marginals)
# each event becomes a group in this one file
grp = f_marginals.create_group(exp_t.isoformat())
grp.create_dataset('x',data=x+x_orig)
grp.create_dataset('y',data=y+y_orig)
grp.create_dataset('z',data=z+z_orig)
grp.create_dataset('prob_x',data=prob_dict['prob_x0'])
grp.create_dataset('prob_y',data=prob_dict['prob_x1'])
grp.create_dataset('prob_z',data=prob_dict['prob_x2'])
grp.create_dataset('prob_xy',data=prob_dict['prob_x0_x1'])
grp.create_dataset('prob_xz',data=prob_dict['prob_x0_x2'])
grp.create_dataset('prob_yz',data=prob_dict['prob_x1_x2'])
if not space_only:
grp.create_dataset('t',data=t-(o_time - start_time))
grp.create_dataset('prob_t',data=prob_dict['prob_x3'])
grp.create_dataset('prob_xt',data=prob_dict['prob_x0_x3'])
grp.create_dataset('prob_yt',data=prob_dict['prob_x1_x3'])
grp.create_dataset('prob_zt',data=prob_dict['prob_x2_x3'])
# write the expected values to a plain text locations file
f_prob.write("PROB DENSITY : T = %s s pm %.2f s, x= %.4f pm %.4f km, \
y= %.4f pm %.4f km, z= %.4f pm %.4f km\n" % (exp_t.isoformat(), sig_t, \
exp_x, sig_x, exp_y, sig_y, exp_z, sig_z))
# close location files
f_prob.close()
f_marginals.close()
def do_clustering_setup_and_run(opdict):
base_path=opdict['base_path']
verbose=opdict['verbose']
# stations
stations_filename=os.path.join(base_path,'lib',opdict['stations'])
# output directory
output_dir=os.path.join(base_path,'out',opdict['outdir'])
# data
data_dir=os.path.join(base_path,'data',opdict['datadir'])
data_glob=opdict['dataglob']
data_files=glob.glob(os.path.join(data_dir,data_glob))
data_files.sort()
# location file
locdir=os.path.join(base_path,'out',opdict['outdir'],'loc')
loc_filename=os.path.join(locdir,'locations.dat')
# file containing correlation values
coeff_file=os.path.join(locdir,opdict['xcorr_corr'])
# Read correlation values
b=BinaryFile(coeff_file)
coeff=b.read_binary_file()
# file containing time delays
delay_file=os.path.join(locdir,opdict['xcorr_delay'])
# INPUT PARAMETERS
nbmin=int(opdict['nbsta'])
if nbmin > len(coeff.keys()):
raise Error('the minimum number of stations cannot be > to the number of stations !!')
event=len(coeff.values()[0])
tplot=float(opdict['clus']) # threshold for which we save and plot
cluster_file="%s/cluster-%s-%s"%(locdir,str(tplot),str(nbmin))
corr=[opdict['clus']]
#corr=np.arange(0,1.1,0.1)
for threshold in corr:
threshold=float(threshold)
nbsta=compute_nbsta(event,coeff,threshold)
CLUSTER = do_clustering(event,nbsta,nbmin)
if threshold == tplot:
print "----------------------------------------------"
print "THRESHOLD : ",threshold," # STATIONS : ",nbmin
print "# CLUSTERS : ",len(CLUSTER)
print CLUSTER
c=BinaryFile(cluster_file)
c.write_binary_file(CLUSTER)
print "Written in %s"%cluster_file
if verbose: # PLOT
# Read location file
locs=read_locs_from_file(loc_filename)
# Read station file
stations=read_stations_file(stations_filename)
# Look at the waveforms
plot_traces(CLUSTER, delay_file, coeff, locs, stations, data_dir, data_files, threshold)
def generateSyntheticDirac(opdict, time_grids=None):
# Creates the synthetic dataset for us to work with
from NllGridLib import read_stations_file, read_hdr_file
from migration import migrate_4D_stack, extract_max_values
from hdf5_grids import get_interpolated_time_grids
load_time_grids = False
if time_grids == None: load_time_grids = True
#define length and sampling frequency of synthetic data
s_amplitude = opdict['syn_amplitude']
s_data_length = opdict['syn_datalength']
s_sample_freq = opdict['syn_samplefreq']
s_filename = opdict['syn_filename']
s_npts = int(s_data_length * s_sample_freq)
s_delta = 1 / s_sample_freq
s_kwidth = opdict['syn_kwidth']
s_nkwidth = int(round(s_kwidth * s_sample_freq))
# define origin time
s_t0 = opdict['syn_otime']
base_path = opdict['base_path']
outdir = opdict['outdir']
test_grid_file = os.path.join(base_path, 'out', opdict['outdir'], 'grid',
s_filename)
test_stack_file = os.path.join(base_path, 'out', opdict['outdir'], 'stack',
'stack_all_' + s_filename)
test_info_file = os.path.join(base_path, 'out', opdict['outdir'], 'grid',
'%s.info' % s_filename)
fig_path = os.path.join(base_path, 'out', outdir, 'fig')
# get filenames for time-grids and search grids
grid_filename_base = os.path.join(base_path, 'lib', opdict['time_grid'])
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
if opdict.has_key('sta_list'):
sta_list = opdict['sta_list'].split(',')
else:
sta_list = stations.keys()
# get parameters for noise etc
syn_addnoise = opdict['syn_addnoise']
#################################
# start setting up synthetic data
#################################
grid_info = read_hdr_file(search_grid_filename)
if load_time_grids:
time_grids = get_interpolated_time_grids(opdict)
#################################
# create synthetic data
#################################
# choose hypocenter
nx = grid_info['nx']
ny = grid_info['ny']
nz = grid_info['nz']
dx = grid_info['dx']
dy = grid_info['dy']
dz = grid_info['dz']
x_orig = grid_info['x_orig']
y_orig = grid_info['y_orig']
z_orig = grid_info['z_orig']
ix = opdict['syn_ix']
iy = opdict['syn_iy']
iz = opdict['syn_iz']
it = int(round(s_t0 / s_delta))
# retrieve travel times for chosen hypocenter
# and station list
ib = ix * ny * nz + iy * nz + iz
n_buf = nx * ny * nz
logging.debug('ib for true hypocenter = %d' % ib)
ttimes = {}
for sta in sta_list:
if time_grids.has_key(sta):
ttimes[sta] = time_grids[sta].grid_data[ib]
else:
logging.info(
'Missing travel-time information for station %s. Ignoring station...'
% sta)
logging.debug('Travel-times for true hypocenter = %s' % ttimes)
# construct data with these travel times
data = {}
for key, delay in ttimes.iteritems():
if syn_addnoise:
s_snr = opdict['syn_snr']
s = np.random.rand(s_npts) * s_amplitude / s_snr
else:
s = np.zeros(s_npts)
atime = s_t0 + delay
i_atime = np.int(atime / s_delta)
if i_atime + s_nkwidth > len(s):
logging.error(
'syn_datalength is too small compared with geographical size of network '
)
s[i_atime:i_atime +
s_nkwidth] = s_amplitude - np.arange(s_nkwidth) * (s_amplitude /
float(s_nkwidth))
data[key] = s
# DO MIGRATION
logging.info('Doing migration to %s' % test_grid_file)
f = h5py.File(test_grid_file, 'w')
stack_grid = f.create_dataset('stack_grid', (n_buf, s_npts),
'f',
chunks=(1, s_npts))
stack_shift_time = migrate_4D_stack(data, s_delta, time_grids, stack_grid)
n_buf, nt = stack_grid.shape
# add useful information to dataset
for key, value in grid_info.iteritems():
stack_grid.attrs[key] = value
stack_grid.attrs['dt'] = s_delta
stack_grid.attrs['start_time'] = -stack_shift_time
# extract max-stack
logging.info('Extracting max_val etc. to %s' % test_stack_file)
f_stack = h5py.File(test_stack_file, 'w')
# extract maxima
extract_max_values(stack_grid, grid_info, f_stack)
for name in f_stack:
dset = f_stack[name]
logging.debug('After extract_max_values : %s %f %f' %
(name, np.max(dset), np.sum(dset)))
dset.attrs['start_time'] = -stack_shift_time
dset.attrs['dt'] = s_delta
# close the stack and grid files
f_stack.close()
f.close()
logging.info('Saved 4D grid to file %s' % test_grid_file)
shifted_it = it + int(round(stack_shift_time / s_delta))
# SETUP information to pass back
test_info = {}
test_info['dat_file'] = test_grid_file
test_info['stack_file'] = test_stack_file
test_info['grid_shape'] = nx, ny, nz, nt
test_info['grid_spacing'] = dx, dy, dz, s_delta
test_info['grid_orig'] = x_orig, y_orig, z_orig
test_info['true_indexes'] = (ix, iy, iz, shifted_it)
test_info['start_time'] = -stack_shift_time
logging.debug(test_info)
f = open(test_info_file, 'w')
f.write(str(test_info))
return test_info
def do_comp_mag(opdict):
base_path=opdict['base_path']
# dataless
dataless_glob=glob.glob(os.path.join(base_path,'lib',opdict['dataless']))
dataless_glob.sort()
# output directory
output_dir=os.path.join(base_path,'out',opdict['outdir'])
# data
data_dir=os.path.join(base_path,'data',opdict['datadir'])
data_glob=opdict['dataglob']
# location file
locdir=os.path.join(base_path,'out',opdict['outdir'],'loc')
locfile=os.path.join(locdir,'locations.dat')
locs=read_locs_from_file(locfile)
opdict=read_header_from_file(locfile,opdict)
snr_wf=np.float(opdict['snr_tr_limit'])
# Stations
stations_filename=os.path.join(base_path,'lib',opdict['stations'])
stations=read_stations_file(stations_filename)
paz=read_paz(dataless_glob)
vals,tdeb={},{}
for sta in sorted(stations):
vals[sta]={}
tdeb[sta]={}
cha_list=opdict['comp_list']
for cha in cha_list:
vals,tdeb,dt=fill_values(vals,tdeb,data_glob,data_dir,cha)
new_file=open(locfile,'w')
write_header_options(new_file,opdict)
mags=[]
for loc in locs:
stack_time=loc['o_time']
loc_x=loc['x_mean']
loc_y=loc['y_mean']
loc_z=-loc['z_mean']
ml=[]
for sta in sorted(stations):
if vals[sta]:
paz_list,p2p_amp,tspan=[],[],[]
h_dist=np.sqrt((loc_x-stations[sta]['x'])**2+(loc_y-stations[sta]['y'])**2+(loc_z-stations[sta]['elev'])**2)
for cha in cha_list:
istart=int(round(stack_time-0.5-tdeb[sta][cha])*1./dt)
iend=int(round(stack_time+5.5-tdeb[sta][cha])*1./dt)
x=vals[sta][cha][istart:iend+1]
if x.any() and np.max(x)/np.mean(np.abs(x)) > snr_wf:
max_amp=np.max(x)
i_max_amp=np.argmax(x)
min_amp=np.abs(np.min(x))
i_min_amp=np.argmin(x)
paz_list.append(paz[sta][cha])
tspan.append(np.abs(i_max_amp-i_min_amp)*dt)
p2p_amp.append(max_amp+min_amp)
if opdict['verbose']:
fig=plt.figure()
fig.set_facecolor('white')
plt.plot(x)
plt.plot(i_min_amp,x[i_min_amp],'ro')
plt.plot(i_max_amp,x[i_max_amp],'ro')
plt.title('%s,%s'%(sta,cha))
plt.show()
if paz_list:
mag=estimateMagnitude(paz_list,p2p_amp,tspan,h_dist)
ml.append(mag)
new_file.write("Max = %.2f, %s - %.2f s + %.2f s, x= %.4f pm %.4f km, y= %.4f pm %.4f km, z= %.4f pm %.4f km, ml= %.2f pm %.2f\n"%(loc['max_trig'],loc['o_time'].isoformat(),loc['o_err_left'], loc['o_err_right'],loc['x_mean'],loc['x_sigma'],loc['y_mean'],loc['y_sigma'],loc['z_mean'],loc['z_sigma'],np.mean(ml),np.std(ml)))
if ml:
mags.append(np.mean(ml))
new_file.close()
r=np.arange(-3,3,0.1)
p,logN,i1,i2 = bvalue(mags,r)
print "b-value:",-p[0]
if opdict['verbose']:
fig=plt.figure(figsize=(10,5))
fig.set_facecolor('white')
ax1 = fig.add_subplot(121)
ax1.hist(mags,25)
ax1.set_xlabel('Magnitude')
ax2 = fig.add_subplot(122,title='Gutenberg Richter law')
ax2.plot(r,logN)
ax2.plot(r[i1:i2],np.polyval(p,r[i1:i2]),'r')
ax2.set_xlabel('Magnitude')
ax2.set_ylabel('log N')
plt.show()
def do_plotting_setup_and_run(opdict, plot_wfm=True, plot_grid=True):
# get / set info
base_path = opdict['base_path']
locfile = os.path.join(base_path, 'out', opdict['outdir'], 'loc',
'locations.dat')
stackfile = os.path.join(base_path, 'out', opdict['outdir'], 'stack',
'combined_stack_all.hdf5')
grid_dir = os.path.join(base_path, 'out', opdict['outdir'], 'grid')
output_dir = os.path.join(base_path, 'out', opdict['outdir'])
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
data_glob = opdict['dataglob']
data_files = glob.glob(os.path.join(data_dir, data_glob))
data_files.sort()
kurt_glob = opdict['kurtglob']
kurt_files = glob.glob(os.path.join(data_dir, kurt_glob))
kurt_files.sort()
mig_files = kurt_files
if opdict['kderiv']:
grad_glob = opdict['gradglob']
grad_files = glob.glob(os.path.join(data_dir, grad_glob))
grad_files.sort()
mig_files = grad_files
if opdict['gauss']:
gauss_glob = opdict['gaussglob']
gauss_files = glob.glob(os.path.join(data_dir, gauss_glob))
gauss_files.sort()
mig_files = gauss_files
figdir = os.path.join(base_path, 'out', opdict['outdir'], 'fig')
# stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
# grids
grid_filename_base = os.path.join(base_path, 'lib', opdict['time_grid'])
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
# read time grid information
time_grids = get_interpolated_time_grids(opdict)
# read locations
locs = read_locs_from_file(locfile)
# open stack file
f_stack = h5py.File(stackfile, 'r')
max_val = f_stack['max_val_smooth']
stack_start_time = UTCDateTime(max_val.attrs['start_time'])
for loc in locs:
# generate the grids
o_time = loc['o_time']
start_time = o_time - opdict['plot_tbefore']
end_time = o_time + opdict['plot_tafter']
# re-read grid info to ensure clean copy
grid_info = read_hdr_file(search_grid_filename)
nx = grid_info['nx']
ny = grid_info['ny']
nz = grid_info['nz']
dx = grid_info['dx']
dy = grid_info['dy']
dz = grid_info['dz']
x = loc['x_mean']
y = loc['y_mean']
z = loc['z_mean']
# get the corresponding travel-times for time-shifting
ttimes = {}
for sta in time_grids.keys():
ttimes[sta] = time_grids[sta].value_at_point(x, y, z)
tshift_migration = max(ttimes.values())
start_time_migration = start_time - tshift_migration
end_time_migration = end_time + tshift_migration
if plot_grid:
logging.info('Plotting grid for location %s' % o_time.isoformat())
# TODO implement a rough estimation of the stack shift based on propagation time across the whole network
# read data
mig_dict, delta = read_data_compatible_with_time_dict(
mig_files, time_grids, start_time_migration,
end_time_migration)
# do migration
do_migration_loop_continuous(opdict,
mig_dict,
delta,
start_time_migration,
grid_info,
time_grids,
keep_grid=True)
# plot
plotLocationGrid(loc, grid_info, figdir,
opdict['plot_otime_window'])
if plot_wfm:
logging.info('Plotting waveforms for location %s' %
o_time.isoformat())
# get the index of the location
# ix=np.int(np.round((loc['x_mean']-grid_info['x_orig'])/dx))
# iy=np.int(np.round((loc['y_mean']-grid_info['y_orig'])/dy))
# iz=np.int(np.round((loc['z_mean']-grid_info['z_orig'])/dz))
# ib= ix*ny*nz + iy*nz + iz
# read data
data_dict, delta = read_data_compatible_with_time_dict(
data_files, time_grids, start_time_migration,
end_time_migration)
mig_dict, delta = read_data_compatible_with_time_dict(
mig_files, time_grids, start_time_migration,
end_time_migration)
# cut desired portion out of data
for sta in data_dict.keys():
tmp = data_dict[sta]
istart = np.int(
np.round(
(start_time + ttimes[sta] - start_time_migration) /
delta))
iend = istart + np.int(
np.round((opdict['plot_tbefore'] + opdict['plot_tafter']) /
delta))
# sanity check in case event is close to start or end of data
if istart < 0: istart = 0
if iend > len(tmp): iend = len(tmp)
data_dict[sta] = tmp[istart:iend]
# do slice
tmp = mig_dict[sta]
mig_dict[sta] = tmp[istart:iend]
# retrieve relevant portion of stack max
istart = np.int(
np.round((o_time - opdict['plot_tbefore'] - stack_start_time) /
delta))
iend = istart + np.int(
np.round(
(opdict['plot_tbefore'] + opdict['plot_tafter']) / delta))
# sanity check in case event is close to start or end of data
if istart < 0:
start_time = start_time + np.abs(istart) * dt
istart = 0
if iend > len(max_val): iend = len(max_val)
# do slice
stack_wfm = max_val[istart:iend]
# plot
plotLocationWaveforms(loc, start_time, delta, data_dict, mig_dict,
stack_wfm, figdir)
f_stack.close()
def do_double_diff_setup_and_run(opdict):
"""
Do double difference (outer routine). Takes options from a
WavelocOptions.opdict dictionary.
:param opdict: Dictionary of parameters and options
"""
base_path = opdict['base_path']
verbose = opdict['verbose']
dd_loc = opdict['dd_loc']
# Station
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
# Location file
locdir = os.path.join(base_path, 'out', opdict['outdir'], 'loc')
loc_filename = os.path.join(locdir, 'locations.dat')
locs = read_locs_from_file(loc_filename)
opdict = read_header_from_file(loc_filename, opdict)
# ------------------------------------------------------------------------
# search grid
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
# traveltimes grid
grid_info = read_hdr_file(search_grid_filename)
time_grids = get_interpolated_time_grids(opdict)
# Extract the UTM coordinates of the area of study
xstart = grid_info['x_orig']
xend = xstart+grid_info['nx']*grid_info['dx']
ystart = grid_info['y_orig']
yend = ystart+grid_info['ny']*grid_info['dy']
zend = -grid_info['z_orig']
zstart = -(-zend+grid_info['nz']*grid_info['dz'])
area = [xstart, xend, ystart, yend, zstart, zend]
# ------------------------------------------------------------------------
nbmin = int(opdict['nbsta'])
threshold = float(opdict['clus'])
# Correlation, time delay and cluster files
corr_file = os.path.join(locdir, opdict['xcorr_corr'])
cfile = BinaryFile(corr_file)
coeff = cfile.read_binary_file()
delay_file = os.path.join(locdir, opdict['xcorr_delay'])
dfile = BinaryFile(delay_file)
delay = dfile.read_binary_file()
cluster_file = os.path.join(locdir, 'cluster-%s-%s' % (str(threshold),
str(nbmin)))
clfile = BinaryFile(cluster_file)
cluster = clfile.read_binary_file()
# ------------------------------------------------------------------------
# Input parameters
len_cluster_min = 2
if dd_loc:
new_loc_filename = os.path.join(locdir, 'relocations.dat')
new_loc_file = open(new_loc_filename, 'w')
write_header_options(new_loc_file, opdict)
# ------------------------------------------------------------------------
# Iterate over clusters
for i in cluster.keys():
print "CLUSTER %d:" % i, cluster[i], len(cluster[i])
N = len(cluster[i])
# Hypocentral parameters to be changed
x, y, z, z_ph, to = coord_cluster(cluster[i], locs)
# Replace bad locations by the centroid coordinates
centroid_x = np.mean(x)
centroid_y = np.mean(y)
centroid_z = np.mean(z)
for ii in range(len(cluster[i])):
if np.abs(x[ii]-centroid_x) > .75:
x[ii] = centroid_x
if np.abs(y[ii]-centroid_y) > .75:
y[ii] = centroid_y
if np.abs(z[ii]-centroid_z) > .75:
z[ii] = centroid_z
if N > len_cluster_min:
# Theroretical traveltimes and arrival times
t_th, arr_times = traveltimes(x, y, z, to, stations, time_grids)
# do double difference location
x, y, z, to = do_double_diff(x, y, z, to, stations, coeff, delay,
cluster[i], threshold, t_th,
arr_times)
if verbose:
from clustering import compute_nbsta
nbsta = compute_nbsta(len(locs), coeff, threshold)
plot_events(cluster, locs, stations, x, y, z, i, threshold, nbmin,
area, nbsta)
if dd_loc:
ind = 0
for j in cluster[i]:
locs[j-1]['x_mean'] = x[ind]
locs[j-1]['y_mean'] = y[ind]
locs[j-1]['z_mean'] = z[ind]
locs[j-1]['o_time'] = to[ind]
locs[j-1]['x_sigma'] = 0
locs[j-1]['y_sigma'] = 0
locs[j-1]['z_sigma'] = 0
locs[j-1]['o_err_right'] = 0
locs[j-1]['o_err_left'] = 0
ind += 1
new_loc_file.write("Max = %.2f, %s - %.2f s + %.2f s, x= %.4f pm\
%.4f km, y= %.4f pm %.4f km, z= %.4f pm %.4f km\n" %
(locs[j-1]['max_trig'], locs[j-1]['o_time'].isoformat(),
locs[j-1]['o_err_left'], locs[j-1]['o_err_right'],
locs[j-1]['x_mean'], locs[j-1]['x_sigma'],
locs[j-1]['y_mean'], locs[j-1]['y_sigma'],
locs[j-1]['z_mean'], locs[j-1]['z_sigma']))
if dd_loc:
new_loc_file.close()
def do_locations_prob_setup_and_run(opdict):
# get / set info
base_path = opdict['base_path']
space_only = opdict['probloc_spaceonly']
locfile = os.path.join(base_path, 'out', opdict['outdir'], 'loc',
'locations.dat')
locfile_prob = os.path.join(base_path, 'out', opdict['outdir'], 'loc',
'locations_prob.dat')
locfile_hdf5 = os.path.join(base_path, 'out', opdict['outdir'], 'loc',
'locations_prob.hdf5')
f_prob = open(locfile_prob, 'w')
# if locfile does not exist then make it by running trigger location
if not os.path.exists(locfile):
logging.info(
'No location found at %s. Running trigger location first...' %
locfile)
do_locations_trigger_setup_and_run(opdict)
# directories
grid_dir = os.path.join(base_path, 'out', opdict['outdir'], 'grid')
output_dir = os.path.join(base_path, 'out', opdict['outdir'])
# data files
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
data_glob = opdict['dataglob']
kurt_glob = opdict['kurtglob']
grad_glob = opdict['gradglob']
data_files = glob.glob(os.path.join(data_dir, data_glob))
kurt_files = glob.glob(os.path.join(data_dir, kurt_glob))
grad_files = glob.glob(os.path.join(data_dir, grad_glob))
data_files.sort()
kurt_files.sort()
grad_files.sort()
# stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
# grids
grid_filename_base = os.path.join(base_path, 'lib', opdict['time_grid'])
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
# read time grid information
time_grids = get_interpolated_time_grids(opdict)
# read locations
locs = read_locs_from_file(locfile)
# prepare file for output of marginals
f_marginals = h5py.File(locfile_hdf5, 'w')
# iterate over locations
for loc in locs:
# create the appropriate grid on the fly
# generate the grids
o_time = loc['o_time']
if space_only:
start_time = o_time
end_time = o_time
else:
start_time = o_time - 3 * loc['o_err_left']
end_time = o_time + 3 * loc['o_err_right']
# make a buffer for migration
start_time_migration = start_time - 10.0
end_time_migration = end_time + 10.0
# re-read grid info to ensure clean copy
grid_info = read_hdr_file(search_grid_filename)
# read data
grad_dict, delta = read_data_compatible_with_time_dict(
grad_files, time_grids, start_time_migration, end_time_migration)
# do migration (all metadata on grid is added to grid_info)
do_migration_loop_continuous(opdict,
grad_dict,
delta,
start_time_migration,
grid_info,
time_grids,
keep_grid=True)
# integrate to get the marginal probability density distributions
# get required info
grid_starttime = grid_info['start_time']
nx, ny, nz, nt = grid_info['grid_shape']
dx, dy, dz, dt = grid_info['grid_spacing']
x_orig, y_orig, z_orig = grid_info['grid_orig']
# we are only interested in the time around the origin time of the event
it_left = np.int(np.round((start_time - grid_starttime) / dt))
it_right = np.int(np.round((end_time - grid_starttime) / dt))
it_true = np.int(np.round((o_time - grid_starttime) / dt))
nt = (it_right - it_left) + 1
# set up integration axes (wrt reference)
x = np.arange(nx) * dx
y = np.arange(ny) * dy
z = np.arange(nz) * dz
if not space_only:
t = np.arange(nt) * dt
# open the grid file
grid_filename = grid_info['dat_file']
f = h5py.File(grid_filename, 'r')
stack_grid = f['stack_grid']
# extract the portion of interest (copy data)
if space_only:
stack_3D = np.empty((nx, ny, nz))
stack_3D[:] = stack_grid[:, it_true].reshape(nx, ny, nz)
else:
stack_4D = np.empty((nx, ny, nz, nt))
stack_4D[:] = stack_grid[:, it_left:it_right + 1].reshape(
nx, ny, nz, nt)
# close the grid file
f.close()
# Get expected values (normalizes grid internally)
if space_only:
exp_x, exp_y, exp_z, cov_matrix, prob_dict = \
compute_expected_coordinates3D(stack_3D,x,y,z,return_2Dgrids=True)
else:
exp_x, exp_y, exp_z, exp_t, cov_matrix, prob_dict = \
compute_expected_coordinates4D(stack_4D,x,y,z,t,return_2Dgrids=True)
# put reference location back
exp_x = exp_x + x_orig
exp_y = exp_y + y_orig
exp_z = exp_z + z_orig
if space_only:
exp_t = o_time
else:
exp_t = start_time + exp_t
# extract uncertainties from covariance matrix
if space_only:
sig_x, sig_y, sig_z = np.sqrt(np.diagonal(cov_matrix))
sig_t = (loc['o_err_left'] + loc['o_err_right']) / 2.
else:
sig_x, sig_y, sig_z, sig_t = np.sqrt(np.diagonal(cov_matrix))
# save the marginals to a hdf5 file in loc subdirectory (f_marginals)
# each event becomes a group in this one file
grp = f_marginals.create_group(exp_t.isoformat())
grp.create_dataset('x', data=x + x_orig)
grp.create_dataset('y', data=y + y_orig)
grp.create_dataset('z', data=z + z_orig)
grp.create_dataset('prob_x', data=prob_dict['prob_x0'])
grp.create_dataset('prob_y', data=prob_dict['prob_x1'])
grp.create_dataset('prob_z', data=prob_dict['prob_x2'])
grp.create_dataset('prob_xy', data=prob_dict['prob_x0_x1'])
grp.create_dataset('prob_xz', data=prob_dict['prob_x0_x2'])
grp.create_dataset('prob_yz', data=prob_dict['prob_x1_x2'])
if not space_only:
grp.create_dataset('t', data=t - (o_time - start_time))
grp.create_dataset('prob_t', data=prob_dict['prob_x3'])
grp.create_dataset('prob_xt', data=prob_dict['prob_x0_x3'])
grp.create_dataset('prob_yt', data=prob_dict['prob_x1_x3'])
grp.create_dataset('prob_zt', data=prob_dict['prob_x2_x3'])
# write the expected values to a plain text locations file
f_prob.write("PROB DENSITY : T = %s s pm %.2f s, x= %.4f pm %.4f km, \
y= %.4f pm %.4f km, z= %.4f pm %.4f km\n" % (exp_t.isoformat(), sig_t, \
exp_x, sig_x, exp_y, sig_y, exp_z, sig_z))
# close location files
f_prob.close()
f_marginals.close()
def do_migration_setup_and_run(opdict):
base_path = opdict['base_path']
verbose = opdict['verbose']
runtime = opdict['time']
reloc = opdict['reloc']
# stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
# output directory
output_dir = os.path.join(base_path, 'out', opdict['outdir'])
stack_dir = os.path.join(output_dir, 'stack')
# data
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
if opdict['kderiv']:
data_glob = opdict['gradglob']
if opdict['gauss']:
data_glob = opdict['gaussglob']
else:
data_glob = opdict['kurtglob']
data_files = glob.glob(os.path.join(data_dir, data_glob))
data_files.sort()
if len(data_files) == 0:
logging.error('No data files found for %s and %s' %
(data_dir, data_glob))
raise UserWarning
# grids
grid_filename_base = os.path.join(base_path, 'lib', opdict['time_grid'])
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
time_grids = get_interpolated_time_grids(opdict)
#start and end times
starttime = opdict['starttime']
endtime = opdict['endtime']
data_length = opdict['data_length']
data_overlap = opdict['data_overlap']
initial_start_time = utcdatetime.UTCDateTime(starttime)
initial_end_time = initial_start_time + data_length
final_end_time = utcdatetime.UTCDateTime(endtime)
time_shift_secs = data_length - data_overlap
######### FOR EACH TIME SPAN - DO MIGRATION #############
# start loop over time
start_time = initial_start_time
end_time = initial_end_time
if runtime:
t_ref = time()
while (start_time < final_end_time):
# read data
logging.info("Reading data : %s - %s." %
(start_time.isoformat(), end_time.isoformat()))
data, delta = read_data_compatible_with_time_dict(
data_files, time_grids, start_time, end_time)
print len(data_files)
if reloc:
tr_glob = opdict['kurtglob']
files = glob.glob(os.path.join(data_dir, tr_glob))
traces, delta = read_data_compatible_with_time_dict(
files, time_grids, start_time, end_time)
sta_list = sorted(traces)
for staname in sta_list:
snr = np.max(traces[staname]) / np.mean(np.abs(
traces[staname]))
if snr < opdict['reloc_snr']:
data[staname] = np.zeros(len(data[staname]))
# re-read grid_info at each iteration to make sure it is a clean copy
grid_info = read_hdr_file(search_grid_filename)
# do migration if have enough data (3 is bare minimum)
if len(data.keys()) >= 3:
logging.info("Migrating data : %s - %s." %
(start_time.isoformat(), end_time.isoformat()))
do_migration_loop_continuous(opdict, data, delta, start_time,
grid_info, time_grids)
elif len(data.keys()) == 0:
logging.warn('No data found between %s and %s.' %
(start_time.isoformat(), end_time.isoformat()))
else:
logging.warn('Insufficient data found between %s and %s.' %
(start_time.isoformat(), end_time.isoformat()))
# Reset the start and end times to loop again
start_time = start_time + time_shift_secs
end_time = end_time + time_shift_secs
if runtime:
t = time() - t_ref
logging.info("Time for migrating all time slices : %.2f s\n" % (t))
def do_double_diff_setup_and_run(opdict):
"""
Do double difference (outer routine). Takes options from a
WavelocOptions.opdict dictionary.
:param opdict: Dictionary of parameters and options
"""
base_path = opdict['base_path']
verbose = opdict['verbose']
dd_loc = opdict['dd_loc']
# Station
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
stations = read_stations_file(stations_filename)
# Location file
locdir = os.path.join(base_path, 'out', opdict['outdir'], 'loc')
loc_filename = os.path.join(locdir, 'locations.dat')
locs = read_locs_from_file(loc_filename)
opdict = read_header_from_file(loc_filename, opdict)
# ------------------------------------------------------------------------
# search grid
search_grid_filename = os.path.join(base_path, 'lib',
opdict['search_grid'])
# traveltimes grid
grid_info = read_hdr_file(search_grid_filename)
time_grids = get_interpolated_time_grids(opdict)
# Extract the UTM coordinates of the area of study
xstart = grid_info['x_orig']
xend = xstart + grid_info['nx'] * grid_info['dx']
ystart = grid_info['y_orig']
yend = ystart + grid_info['ny'] * grid_info['dy']
zend = -grid_info['z_orig']
zstart = -(-zend + grid_info['nz'] * grid_info['dz'])
area = [xstart, xend, ystart, yend, zstart, zend]
# ------------------------------------------------------------------------
nbmin = int(opdict['nbsta'])
threshold = float(opdict['clus'])
# Correlation, time delay and cluster files
corr_file = os.path.join(locdir, opdict['xcorr_corr'])
cfile = BinaryFile(corr_file)
coeff = cfile.read_binary_file()
delay_file = os.path.join(locdir, opdict['xcorr_delay'])
dfile = BinaryFile(delay_file)
delay = dfile.read_binary_file()
cluster_file = os.path.join(locdir,
'cluster-%s-%s' % (str(threshold), str(nbmin)))
clfile = BinaryFile(cluster_file)
cluster = clfile.read_binary_file()
# ------------------------------------------------------------------------
# Input parameters
len_cluster_min = 2
if dd_loc:
new_loc_filename = os.path.join(locdir, 'relocations.dat')
new_loc_file = open(new_loc_filename, 'w')
write_header_options(new_loc_file, opdict)
# ------------------------------------------------------------------------
# Iterate over clusters
for i in cluster.keys():
print "CLUSTER %d:" % i, cluster[i], len(cluster[i])
N = len(cluster[i])
# Hypocentral parameters to be changed
x, y, z, z_ph, to = coord_cluster(cluster[i], locs)
# Replace bad locations by the centroid coordinates
centroid_x = np.mean(x)
centroid_y = np.mean(y)
centroid_z = np.mean(z)
for ii in range(len(cluster[i])):
if np.abs(x[ii] - centroid_x) > .75:
x[ii] = centroid_x
if np.abs(y[ii] - centroid_y) > .75:
y[ii] = centroid_y
if np.abs(z[ii] - centroid_z) > .75:
z[ii] = centroid_z
if N > len_cluster_min:
# Theroretical traveltimes and arrival times
t_th, arr_times = traveltimes(x, y, z, to, stations, time_grids)
# do double difference location
x, y, z, to = do_double_diff(x, y, z, to, stations, coeff, delay,
cluster[i], threshold, t_th,
arr_times)
if verbose:
from clustering import compute_nbsta
nbsta = compute_nbsta(len(locs), coeff, threshold)
plot_events(cluster, locs, stations, x, y, z, i, threshold, nbmin,
area, nbsta)
if dd_loc:
ind = 0
for j in cluster[i]:
locs[j - 1]['x_mean'] = x[ind]
locs[j - 1]['y_mean'] = y[ind]
locs[j - 1]['z_mean'] = z[ind]
locs[j - 1]['o_time'] = to[ind]
locs[j - 1]['x_sigma'] = 0
locs[j - 1]['y_sigma'] = 0
locs[j - 1]['z_sigma'] = 0
locs[j - 1]['o_err_right'] = 0
locs[j - 1]['o_err_left'] = 0
ind += 1
new_loc_file.write(
"Max = %.2f, %s - %.2f s + %.2f s, x= %.4f pm\
%.4f km, y= %.4f pm %.4f km, z= %.4f pm %.4f km\n" %
(locs[j - 1]['max_trig'], locs[j - 1]['o_time'].isoformat(),
locs[j - 1]['o_err_left'], locs[j - 1]['o_err_right'],
locs[j - 1]['x_mean'], locs[j - 1]['x_sigma'],
locs[j - 1]['y_mean'], locs[j - 1]['y_sigma'],
locs[j - 1]['z_mean'], locs[j - 1]['z_sigma']))
if dd_loc:
new_loc_file.close()
def do_migration_setup_and_run(opdict):
base_path=opdict['base_path']
verbose=opdict['verbose']
runtime=opdict['time']
reloc=opdict['reloc']
# stations
stations_filename=os.path.join(base_path,'lib',opdict['stations'])
stations=read_stations_file(stations_filename)
# output directory
output_dir=os.path.join(base_path,'out',opdict['outdir'])
stack_dir=os.path.join(output_dir,'stack')
# data
data_dir=os.path.join(base_path,'data',opdict['datadir'])
if opdict['kderiv']:
data_glob=opdict['gradglob']
if opdict['gauss']:
data_glob=opdict['gaussglob']
else:
data_glob=opdict['kurtglob']
data_files=glob.glob(os.path.join(data_dir,data_glob))
data_files.sort()
if len(data_files)==0:
logging.error('No data files found for %s and %s'%(data_dir,data_glob))
raise UserWarning
# grids
grid_filename_base=os.path.join(base_path,'lib',opdict['time_grid'])
search_grid_filename=os.path.join(base_path,'lib',opdict['search_grid'])
time_grids=get_interpolated_time_grids(opdict)
#start and end times
starttime=opdict['starttime']
endtime=opdict['endtime']
data_length=opdict['data_length']
data_overlap=opdict['data_overlap']
initial_start_time=utcdatetime.UTCDateTime(starttime)
initial_end_time=initial_start_time+data_length
final_end_time=utcdatetime.UTCDateTime(endtime)
time_shift_secs=data_length-data_overlap
######### FOR EACH TIME SPAN - DO MIGRATION #############
# start loop over time
start_time=initial_start_time
end_time=initial_end_time
if runtime:
t_ref=time()
while (start_time < final_end_time):
# read data
logging.info("Reading data : %s - %s."%(start_time.isoformat(), end_time.isoformat()))
data,delta=read_data_compatible_with_time_dict(data_files,time_grids,start_time,end_time)
print len(data_files)
if reloc:
tr_glob=opdict['kurtglob']
files=glob.glob(os.path.join(data_dir,tr_glob))
traces,delta=read_data_compatible_with_time_dict(files,time_grids,start_time,end_time)
sta_list=sorted(traces)
for staname in sta_list:
snr=np.max(traces[staname])/np.mean(np.abs(traces[staname]))
if snr < opdict['reloc_snr']:
data[staname]=np.zeros(len(data[staname]))
# re-read grid_info at each iteration to make sure it is a clean copy
grid_info=read_hdr_file(search_grid_filename)
# do migration if have enough data (3 is bare minimum)
if len(data.keys())>=3:
logging.info("Migrating data : %s - %s."%(start_time.isoformat(), end_time.isoformat()))
do_migration_loop_continuous(opdict, data, delta, start_time, grid_info, time_grids)
elif len(data.keys())==0:
logging.warn('No data found between %s and %s.'%(start_time.isoformat(),end_time.isoformat()))
else:
logging.warn('Insufficient data found between %s and %s.'%(start_time.isoformat(),end_time.isoformat()))
# Reset the start and end times to loop again
start_time=start_time+time_shift_secs
end_time=end_time+time_shift_secs
if runtime:
t=time()-t_ref
logging.info("Time for migrating all time slices : %.2f s\n" % (t))
def do_clustering_setup_and_run(opdict):
base_path = opdict['base_path']
verbose = opdict['verbose']
# stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
# output directory
output_dir = os.path.join(base_path, 'out', opdict['outdir'])
# data
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
data_glob = opdict['dataglob']
data_files = glob.glob(os.path.join(data_dir, data_glob))
data_files.sort()
# location file
locdir = os.path.join(base_path, 'out', opdict['outdir'], 'loc')
loc_filename = os.path.join(locdir, 'locations.dat')
# file containing correlation values
coeff_file = os.path.join(locdir, opdict['xcorr_corr'])
# Read correlation values
b = BinaryFile(coeff_file)
coeff = b.read_binary_file()
# file containing time delays
delay_file = os.path.join(locdir, opdict['xcorr_delay'])
# INPUT PARAMETERS
nbmin = int(opdict['nbsta'])
if nbmin > len(coeff.keys()):
raise Error(
'the minimum number of stations cannot be > to the number of stations !!'
)
event = len(coeff.values()[0])
tplot = float(opdict['clus']) # threshold for which we save and plot
cluster_file = "%s/cluster-%s-%s" % (locdir, str(tplot), str(nbmin))
corr = [opdict['clus']]
#corr=np.arange(0,1.1,0.1)
for threshold in corr:
threshold = float(threshold)
nbsta = compute_nbsta(event, coeff, threshold)
CLUSTER = do_clustering(event, nbsta, nbmin)
if threshold == tplot:
print "----------------------------------------------"
print "THRESHOLD : ", threshold, " # STATIONS : ", nbmin
print "# CLUSTERS : ", len(CLUSTER)
print CLUSTER
c = BinaryFile(cluster_file)
c.write_binary_file(CLUSTER)
print "Written in %s" % cluster_file
if verbose: # PLOT
# Read location file
locs = read_locs_from_file(loc_filename)
# Read station file
stations = read_stations_file(stations_filename)
# Look at the waveforms
plot_traces(CLUSTER, delay_file, coeff, locs, stations,
data_dir, data_files, threshold)
def generateSyntheticDirac(opdict,time_grids=None):
# Creates the synthetic dataset for us to work with
from NllGridLib import read_stations_file, read_hdr_file
from migration import migrate_4D_stack, extract_max_values
from hdf5_grids import get_interpolated_time_grids
load_time_grids = False
if time_grids==None : load_time_grids = True
#define length and sampling frequency of synthetic data
s_amplitude = opdict['syn_amplitude']
s_data_length = opdict['syn_datalength']
s_sample_freq = opdict['syn_samplefreq']
s_filename = opdict['syn_filename']
s_npts=int(s_data_length*s_sample_freq)
s_delta=1/s_sample_freq
s_kwidth=opdict['syn_kwidth']
s_nkwidth=int(round(s_kwidth*s_sample_freq))
# define origin time
s_t0 = opdict['syn_otime']
base_path=opdict['base_path']
outdir=opdict['outdir']
test_grid_file=os.path.join(base_path,'out',opdict['outdir'],'grid',s_filename)
test_stack_file=os.path.join(base_path,'out',opdict['outdir'],'stack','stack_all_'+s_filename)
test_info_file=os.path.join(base_path,'out',opdict['outdir'],'grid','%s.info'%s_filename)
fig_path = os.path.join(base_path,'out',outdir,'fig')
# get filenames for time-grids and search grids
grid_filename_base = os.path.join(base_path,'lib',opdict['time_grid'])
search_grid_filename = os.path.join(base_path,'lib',opdict['search_grid'])
stations_filename = os.path.join(base_path,'lib',opdict['stations'])
stations=read_stations_file(stations_filename)
if opdict.has_key('sta_list') :
sta_list=opdict['sta_list'].split(',')
else:
sta_list=stations.keys()
# get parameters for noise etc
syn_addnoise=opdict['syn_addnoise']
#################################
# start setting up synthetic data
#################################
grid_info=read_hdr_file(search_grid_filename)
if load_time_grids:
time_grids=get_interpolated_time_grids(opdict)
#################################
# create synthetic data
#################################
# choose hypocenter
nx=grid_info['nx']
ny=grid_info['ny']
nz=grid_info['nz']
dx=grid_info['dx']
dy=grid_info['dy']
dz=grid_info['dz']
x_orig=grid_info['x_orig']
y_orig=grid_info['y_orig']
z_orig=grid_info['z_orig']
ix=opdict['syn_ix']
iy=opdict['syn_iy']
iz=opdict['syn_iz']
it=int(round(s_t0/s_delta))
# retrieve travel times for chosen hypocenter
# and station list
ib= ix*ny*nz + iy*nz + iz
n_buf=nx*ny*nz
logging.debug('ib for true hypocenter = %d'%ib)
ttimes={}
for sta in sta_list:
if time_grids.has_key(sta):
ttimes[sta]=time_grids[sta].grid_data[ib]
else:
logging.info('Missing travel-time information for station %s. Ignoring station...'%sta)
logging.debug('Travel-times for true hypocenter = %s'%ttimes)
# construct data with these travel times
data={}
for key,delay in ttimes.iteritems():
if syn_addnoise:
s_snr=opdict['syn_snr']
s=np.random.rand(s_npts)*s_amplitude/s_snr
else:
s=np.zeros(s_npts)
atime=s_t0+delay
i_atime=np.int(atime/s_delta)
if i_atime+s_nkwidth > len(s) :
logging.error('syn_datalength is too small compared with geographical size of network ')
s[i_atime:i_atime+s_nkwidth]=s_amplitude-np.arange(s_nkwidth)*(s_amplitude/float(s_nkwidth))
data[key]=s
# DO MIGRATION
logging.info('Doing migration to %s'%test_grid_file)
f=h5py.File(test_grid_file,'w')
stack_grid=f.create_dataset('stack_grid',(n_buf,s_npts),'f',chunks=(1,s_npts))
stack_shift_time = migrate_4D_stack(data,s_delta,time_grids,stack_grid)
n_buf,nt=stack_grid.shape
# add useful information to dataset
for key,value in grid_info.iteritems():
stack_grid.attrs[key]=value
stack_grid.attrs['dt']=s_delta
stack_grid.attrs['start_time']=-stack_shift_time
# extract max-stack
logging.info('Extracting max_val etc. to %s'%test_stack_file)
f_stack = h5py.File(test_stack_file,'w')
# extract maxima
extract_max_values(stack_grid,grid_info,f_stack)
for name in f_stack:
dset=f_stack[name]
logging.debug('After extract_max_values : %s %f %f'%(name,np.max(dset),np.sum(dset)))
dset.attrs['start_time']=-stack_shift_time
dset.attrs['dt']=s_delta
# close the stack and grid files
f_stack.close()
f.close()
logging.info('Saved 4D grid to file %s'%test_grid_file)
shifted_it=it+int(round(stack_shift_time/s_delta))
# SETUP information to pass back
test_info={}
test_info['dat_file']=test_grid_file
test_info['stack_file']=test_stack_file
test_info['grid_shape']=nx,ny,nz,nt
test_info['grid_spacing']=dx,dy,dz,s_delta
test_info['grid_orig']=x_orig,y_orig,z_orig
test_info['true_indexes']=(ix,iy,iz,shifted_it)
test_info['start_time']=-stack_shift_time
logging.debug(test_info)
f=open(test_info_file,'w')
f.write(str(test_info))
return test_info
def do_clustering_setup_and_run(opdict):
"""
Does clustering by applying the depth first search algorithm and saves the result
(= a dictionary containing the event indexes forming each cluster) in a binary file.
Needs to define the correlation value threshold and the minimum number of stations
where this threshold should be reached to form a cluster (should be done in the options
dictionary)
:param opdict: Dictionary of waveloc options
"""
base_path = opdict['base_path']
verbose = opdict['verbose']
# stations
stations_filename = os.path.join(base_path, 'lib', opdict['stations'])
# data
data_dir = os.path.join(base_path, 'data', opdict['datadir'])
data_glob = opdict['dataglob']
data_files = glob.glob(os.path.join(data_dir, data_glob))
data_files.sort()
# location file
locdir = os.path.join(base_path, 'out', opdict['outdir'], 'loc')
loc_filename = os.path.join(locdir, 'locations.dat')
# file containing correlation values
coeff_file = os.path.join(locdir, opdict['xcorr_corr'])
# Read correlation values
b = BinaryFile(coeff_file)
coeff = b.read_binary_file()
# INPUT PARAMETERS
nbmin = int(opdict['nbsta'])
if nbmin > len(coeff.keys()):
raise Exception('the minimum number of stations cannot be > to the\
number of stations !!')
event = len(coeff.values()[0])
tplot = float(opdict['clus']) # threshold for which we save and plot
cluster_file = "%s/cluster-%s-%s" % (locdir, str(tplot), str(nbmin))
corr = [opdict['clus']]
#corr = np.arange(0, 1.1, 0.1)
for threshold in corr:
threshold = float(threshold)
nbsta = compute_nbsta(event, coeff, threshold)
CLUSTER = do_clustering(event, nbsta, nbmin)
if threshold == tplot:
print "----------------------------------------------"
print "THRESHOLD : ", threshold, " # STATIONS : ", nbmin
print "# CLUSTERS : ", len(CLUSTER)
print CLUSTER
c = BinaryFile(cluster_file)
c.write_binary_file(CLUSTER)
print "Written in %s" % cluster_file
if verbose: # PLOT
# Read location file
locs = read_locs_from_file(loc_filename)
# Read station file
stations = read_stations_file(stations_filename)
# Look at the waveforms
#plot_traces(CLUSTER, delay_file, coeff, locs,
# data_dir, data_files, threshold)
# Plot graphs
plot_graphs(locs, stations, nbsta, CLUSTER, nbmin, threshold)
def do_plotting_setup_and_run(opdict,plot_wfm=True,plot_grid=True):
# get / set info
base_path=opdict['base_path']
locfile=os.path.join(base_path,'out',opdict['outdir'],'loc','locations.dat')
stackfile=os.path.join(base_path,'out',opdict['outdir'],'stack','combined_stack_all.hdf5')
grid_dir=os.path.join(base_path,'out',opdict['outdir'],'grid')
output_dir=os.path.join(base_path,'out',opdict['outdir'])
data_dir=os.path.join(base_path,'data',opdict['datadir'])
data_glob=opdict['dataglob']
data_files=glob.glob(os.path.join(data_dir,data_glob))
data_files.sort()
kurt_glob=opdict['kurtglob']
kurt_files=glob.glob(os.path.join(data_dir,kurt_glob))
kurt_files.sort()
mig_files=kurt_files
if opdict['kderiv']:
grad_glob=opdict['gradglob']
grad_files=glob.glob(os.path.join(data_dir,grad_glob))
grad_files.sort()
mig_files=grad_files
if opdict['gauss']:
gauss_glob=opdict['gaussglob']
gauss_files=glob.glob(os.path.join(data_dir,gauss_glob))
gauss_files.sort()
mig_files=gauss_files
figdir=os.path.join(base_path,'out',opdict['outdir'],'fig')
# stations
stations_filename=os.path.join(base_path,'lib',opdict['stations'])
stations=read_stations_file(stations_filename)
# grids
grid_filename_base=os.path.join(base_path,'lib',opdict['time_grid'])
search_grid_filename=os.path.join(base_path,'lib',opdict['search_grid'])
# read time grid information
time_grids=get_interpolated_time_grids(opdict)
# read locations
locs=read_locs_from_file(locfile)
# open stack file
f_stack=h5py.File(stackfile,'r')
max_val=f_stack['max_val_smooth']
stack_start_time=UTCDateTime(max_val.attrs['start_time'])
for loc in locs:
# generate the grids
o_time=loc['o_time']
start_time=o_time-opdict['plot_tbefore']
end_time=o_time+opdict['plot_tafter']
# re-read grid info to ensure clean copy
grid_info=read_hdr_file(search_grid_filename)
nx=grid_info['nx']
ny=grid_info['ny']
nz=grid_info['nz']
dx=grid_info['dx']
dy=grid_info['dy']
dz=grid_info['dz']
x=loc['x_mean']
y=loc['y_mean']
z=loc['z_mean']
# get the corresponding travel-times for time-shifting
ttimes={}
for sta in time_grids.keys():
ttimes[sta]=time_grids[sta].value_at_point(x,y,z)
tshift_migration=max(ttimes.values())
start_time_migration=start_time-tshift_migration
end_time_migration=end_time+tshift_migration
if plot_grid:
logging.info('Plotting grid for location %s'%o_time.isoformat())
# TODO implement a rough estimation of the stack shift based on propagation time across the whole network
# read data
mig_dict,delta = read_data_compatible_with_time_dict(mig_files,
time_grids, start_time_migration, end_time_migration)
# do migration
do_migration_loop_continuous(opdict, mig_dict, delta,
start_time_migration, grid_info, time_grids, keep_grid=True)
# plot
plotLocationGrid(loc,grid_info,figdir,opdict['plot_otime_window'])
if plot_wfm:
logging.info('Plotting waveforms for location %s'%o_time.isoformat())
# get the index of the location
# ix=np.int(np.round((loc['x_mean']-grid_info['x_orig'])/dx))
# iy=np.int(np.round((loc['y_mean']-grid_info['y_orig'])/dy))
# iz=np.int(np.round((loc['z_mean']-grid_info['z_orig'])/dz))
# ib= ix*ny*nz + iy*nz + iz
# read data
data_dict,delta = read_data_compatible_with_time_dict(data_files,
time_grids, start_time_migration, end_time_migration)
mig_dict,delta = read_data_compatible_with_time_dict(mig_files,
time_grids, start_time_migration, end_time_migration)
# cut desired portion out of data
for sta in data_dict.keys():
tmp=data_dict[sta]
istart=np.int(np.round(
(start_time + ttimes[sta] - start_time_migration) / delta))
iend=istart + np.int(np.round(
(opdict['plot_tbefore'] + opdict['plot_tafter']) / delta))
# sanity check in case event is close to start or end of data
if istart < 0 : istart=0
if iend > len(tmp) : iend = len(tmp)
data_dict[sta]=tmp[istart:iend]
# do slice
tmp=mig_dict[sta]
mig_dict[sta]=tmp[istart:iend]
# retrieve relevant portion of stack max
istart=np.int(np.round(
(o_time - opdict['plot_tbefore'] -stack_start_time) / delta))
iend=istart + np.int(np.round(
(opdict['plot_tbefore'] + opdict['plot_tafter']) / delta))
# sanity check in case event is close to start or end of data
if istart < 0 :
start_time = start_time + np.abs(istart)*dt
istart=0
if iend > len(max_val) : iend = len(max_val)
# do slice
stack_wfm=max_val[istart:iend]
# plot
plotLocationWaveforms(loc,start_time,delta,data_dict,mig_dict,stack_wfm,figdir)
f_stack.close()
