core.py 15.8 KB
Newer Older
Sebastian Heimann's avatar
Sebastian Heimann committed
1
import os
2
import math
Sebastian Heimann's avatar
Sebastian Heimann committed
3
4
import logging
import os.path as op
5
import shutil
Sebastian Heimann's avatar
Sebastian Heimann committed
6

7
8
from collections import defaultdict

Sebastian Heimann's avatar
Sebastian Heimann committed
9
10
11
12
import numpy as num

from pyrocko import pile, trace, util, io
from pyrocko.parstack import parstack
13
from pyrocko.guts import Object, Timestamp, String, Float
Sebastian Heimann's avatar
Sebastian Heimann committed
14

Sebastian Heimann's avatar
flake8    
Sebastian Heimann committed
15
from lassie import common, plot, grid as gridmod, geo
Sebastian Heimann's avatar
Sebastian Heimann committed
16
17
18
19

logger = logging.getLogger('lassie.core')


20
21
22
23
24
25
26
class Detection(Object):
    id = String.T()
    time = Timestamp.T()
    location = geo.Point.T()
    ifm = Float.T()


27
28
def check_data_consistency(p, config):
    receivers = config.get_receivers()
29
30
31
32
33
34
    nslc_ids = p.nslc_ids.keys()
    nsl_ids = [nslc_id[:3] for nslc_id in nslc_ids]
    r_ids = [r.codes for r in receivers]

    r_not_in_p = []
    t_not_in_r = []
35
36
    to_be_blacklisted = []

37
38
39
    for r in receivers:
        if r.codes[:3] not in nsl_ids:
            r_not_in_p.append(r.codes)
40
41
        if '.'.join(r.codes[:3]) in config.blacklist:
            to_be_blacklisted.append('.'.join(r.codes))
42
43
44
45
46
47

    for nsl_id in nsl_ids:
        if nsl_id not in r_ids:
            t_not_in_r.append(nsl_id)

    if len(r_not_in_p) != 0.:
48
        logger.warn('Following receivers have no traces in data set:')
49
        for nsl_id in r_not_in_p:
50
51
            logger.warn('  %s' % '.'.join(nsl_id))
        logger.warn('-' * 40)
52
53

    if len(t_not_in_r) != 0.:
54
        logger.warn('Following traces have no associated receivers:')
55
        for nsl_id in t_not_in_r:
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
            logger.warn('  %s' % '.'.join(nsl_id))
        logger.warn('-' * 40)

    if len(to_be_blacklisted):
        logger.info('Blacklisted receivers:')
        for code in to_be_blacklisted:
            logger.info('  %s' % code)
        logger.info('-' * 40)

    if len(config.blacklist) and\
            len(to_be_blacklisted) != len(config.blacklist):
        logger.warn('Blacklist NSL codes that did not match any receiver:')
        for code in config.blacklist:
            if code not in to_be_blacklisted:
                logger.warn('  %s' % code)
        logger.info('-' * 40)
72
73


74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
def zero_fill(trs, tmin, tmax):
    trs = trace.degapper(trs)

    d = defaultdict(list)
    for tr in trs:
        d[tr.nslc_id].append(tr)

    trs_out = []
    for nslc, trs_group in d.iteritems():
        if not all(tr.deltat == trs_group[0].deltat for tr in trs_group):
            logger.warn('inconsistent sample rate, cannot merge traces')
            continue

        if not all(tr.ydata.dtype == trs_group[0].ydata.dtype
                   for tr in trs_group):

            logger.warn('inconsistent data type, cannot merge traces')
            continue

        tr_combi = trs_group[0].copy()
        tr_combi.extend(tmin, tmax, fillmethod='zeros')

        for tr in trs_group[1:]:
            tr_combi.add(tr)

        trs_out.append(tr_combi)

    return trs_out

103

Sebastian Heimann's avatar
Sebastian Heimann committed
104
105
def scan(
        config,
106
107
        override_tmin=None,
        override_tmax=None,
Sebastian Heimann's avatar
Sebastian Heimann committed
108
109
        show_detections=False,
        show_movie=False,
110
        show_window_traces=False,
Sebastian Heimann's avatar
Sebastian Heimann committed
111
        force=False,
Marius Kriegerowski's avatar
Marius Kriegerowski committed
112
113
        stop_after_first=False,
        nparallel=None):
Sebastian Heimann's avatar
Sebastian Heimann committed
114
115
116
117
118

    if config.detections_path:
        if op.exists(config.detections_path):
            if force:
                os.unlink(config.detections_path)
119
120
121
122
                if config.stackmax_path:
                    if op.exists(config.stackmax_path):
                        shutil.rmtree(config.stackmax_path)
                        os.mkdir(config.stackmax_path)
Sebastian Heimann's avatar
Sebastian Heimann committed
123
124
            else:
                raise common.LassieError(
125
126
                    'detections file already exists: %s'
                    % config.detections_path)
Sebastian Heimann's avatar
Sebastian Heimann committed
127
128
129

        util.ensuredirs(config.detections_path)

130
131
132
133
134
135
136
    else:
        if config.stackmax_path:
            if op.exists(config.stackmax_path):
                if force:
                    shutil.rmtree(config.stackmax_path)
                else:
                    raise common.LassieError(
Sebastian Heimann's avatar
Sebastian Heimann committed
137
138
                        'stackmax directory already exists: %s' %
                        config.stackmax_path)
139
140
141

            util.ensuredirs(config.stackmax_path)

142
143
144
145
    ifcs = config.image_function_contributions
    for ifc in ifcs:
        ifc.setup(config)

Sebastian Heimann's avatar
Sebastian Heimann committed
146
147
148
149
150
    grid = config.get_grid()
    receivers = config.get_receivers()

    norm_map = gridmod.geometrical_normalization(grid, receivers)

151
152
153
154
155
156
157
158
159
160
161
    for data_path in config.data_paths:
        if not op.exists(data_path):
            raise common.LassieError(
                'waveform data path does not exist: %s' % data_path)

    p = pile.make_pile(config.data_paths, fileformat='detect')
    if p.is_empty():
        raise common.LassieError('no usable waveforms found')

    for ifc in ifcs:
        ifc.prescan(p)
162

Sebastian Heimann's avatar
Sebastian Heimann committed
163
    shift_tables = []
164
    tshift_minmaxs = []
165
    for ifc in ifcs:
Sebastian Heimann's avatar
Sebastian Heimann committed
166
        shift_tables.append(ifc.shifter.get_table(grid, receivers))
167
168
        tshift_minmaxs.append(num.nanmin(shift_tables[-1]))
        tshift_minmaxs.append(num.nanmax(shift_tables[-1]))
Sebastian Heimann's avatar
Sebastian Heimann committed
169

170
171
    fsmooth_min = min(ifc.get_fsmooth() for ifc in ifcs)

172
173
    tshift_min = min(tshift_minmaxs)
    tshift_max = max(tshift_minmaxs)
Sebastian Heimann's avatar
Sebastian Heimann committed
174

175
    tpeaksearch = (tshift_max - tshift_min) + 1.0 / fsmooth_min
Sebastian Heimann's avatar
Sebastian Heimann committed
176

177
178
    tpad = max(ifc.get_tpad() for ifc in ifcs) + \
        (tshift_max - tshift_min) + tpeaksearch
Sebastian Heimann's avatar
Sebastian Heimann committed
179

180
    tinc = (tshift_max - tshift_min) * 10. + 3.0 * tpad
181
182
183
184
185
186
187
188
    tavail = p.tmax - p.tmin
    tinc = min(tinc, tavail - 2.0 * tpad)

    if tinc <= 0:
        raise common.LassieError(
            'available waveforms too short \n'
            'required: %g s\n'
            'available: %g s\n' % (2.*tpad, tavail))
Sebastian Heimann's avatar
Sebastian Heimann committed
189
190

    blacklist = set(tuple(s.split('.')) for s in config.blacklist)
191
192
193
194
    whitelist = set(tuple(s.split('.')) for s in config.whitelist)

    distances = grid.distances(receivers)
    distances_to_grid = num.min(distances, axis=0)
Sebastian Heimann's avatar
Sebastian Heimann committed
195

196
197
198
    distance_min = num.min(distances)
    distance_max = num.max(distances)

Sebastian Heimann's avatar
Sebastian Heimann committed
199
200
    station_index = dict(
        (rec.codes, i) for (i, rec) in enumerate(receivers)
201
202
203
204
        if rec.codes not in blacklist and (
            not whitelist or rec.codes in whitelist) and (
            config.distance_max is None or
                distances_to_grid[i] <= config.distance_max))
Sebastian Heimann's avatar
Sebastian Heimann committed
205

206
207
208
209
210
    for data_path in config.data_paths:
        if not op.exists(data_path):
            raise common.LassieError(
                'waveform data path does not exist: %s' % data_path)

Sebastian Heimann's avatar
Sebastian Heimann committed
211
    p = pile.make_pile(config.data_paths, fileformat='detect')
212
213
    if p.is_empty():
        raise common.LassieError('no usable waveforms found')
Sebastian Heimann's avatar
Sebastian Heimann committed
214

Marius Kriegerowski's avatar
Marius Kriegerowski committed
215
    check_data_consistency(p, config)
216

217
218
219
220
221
222
223
224
225
    deltat_cf = max(p.deltats.keys())
    assert deltat_cf > 0.0

    while True:
        if not all(ifc.deltat_cf_is_available(deltat_cf * 2) for ifc in ifcs):
            break

        deltat_cf *= 2

226
227
    logger.info('CF sampling interval (rate): %g s (%g Hz)' % (
        deltat_cf, 1.0/deltat_cf))
228

Sebastian Heimann's avatar
Sebastian Heimann committed
229
230
    ngridpoints = grid.size()

231
232
233
234
235
236
    logger.info('number of grid points: %i' % ngridpoints)
    logger.info('minimum source-receiver distance: %g m' % distance_min)
    logger.info('maximum source-receiver distance: %g m' % distance_max)
    logger.info('minimum travel-time: %g s' % tshift_min)
    logger.info('maximum travel-time: %g s' % tshift_max)

Sebastian Heimann's avatar
Sebastian Heimann committed
237
238
    idetection = 0

239
240
    tmin = override_tmin or config.tmin or p.tmin + tpad
    tmax = override_tmax or config.tmax or p.tmax - tpad
Sebastian Heimann's avatar
Sebastian Heimann committed
241

242
243
244
245
246
247
    events = config.get_events()
    twindows = []
    if events is not None:
        for ev in events:
            if tmin <= ev.time <= tmax:
                twindows.append((
248
249
250
251
                    ev.time + tshift_min - (tshift_max - tshift_min) *
                    config.event_time_window_factor,
                    ev.time + tshift_min + (tshift_max - tshift_min) *
                    config.event_time_window_factor))
Sebastian Heimann's avatar
Sebastian Heimann committed
252

253
254
    else:
        twindows.append((tmin, tmax))
Sebastian Heimann's avatar
Sebastian Heimann committed
255

256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
    for iwindow_group, (tmin_win, tmax_win) in enumerate(twindows):

        nwin = int(math.ceil((tmax_win - tmin_win) / tinc))

        logger.info('start processing time window group %i/%i: %s - %s' % (
            iwindow_group + 1, len(twindows),
            util.time_to_str(tmin_win),
            util.time_to_str(tmax_win)))

        logger.info('number of time windows: %i' % nwin)
        logger.info('time window length: %g s' % (tinc + 2.0*tpad))
        logger.info('time window payload: %g s' % tinc)
        logger.info('time window padding: 2 x %g s' % tpad)
        logger.info('time window overlap: %g%%' % (
            100.0*2.0*tpad / (tinc+2.0*tpad)))

        iwin = -1
273
274
        for trs in p.chopper(
                tmin=tmin_win, tmax=tmax_win, tinc=tinc, tpad=tpad,
275
                want_incomplete=config.fill_incomplete_with_zeros,
276
                trace_selector=lambda tr: tr.nslc_id[:3] in station_index):
Sebastian Heimann's avatar
Sebastian Heimann committed
277

278
279
            iwin += 1

280
281
282
283
284
            trs_ok = []
            for tr in trs:
                if tr.ydata.size == 0:
                    logger.warn(
                        'skipping empty trace: %s.%s.%s.%s' % tr.nslc_id)
Sebastian Heimann's avatar
Sebastian Heimann committed
285

286
                    continue
Sebastian Heimann's avatar
Sebastian Heimann committed
287

288
289
290
291
                if not num.all(num.isfinite(tr.ydata)):
                    logger.warn(
                        'skipping trace because of invalid values: '
                        '%s.%s.%s.%s' % tr.nslc_id)
Sebastian Heimann's avatar
Sebastian Heimann committed
292

293
                    continue
Sebastian Heimann's avatar
Sebastian Heimann committed
294

295
                trs_ok.append(tr)
Sebastian Heimann's avatar
Sebastian Heimann committed
296

297
            trs = trs_ok
Sebastian Heimann's avatar
Sebastian Heimann committed
298

299
            if not trs:
Sebastian Heimann's avatar
Sebastian Heimann committed
300
301
                continue

302
303
            logger.info('processing time window %i/%i: %s - %s' % (
                iwin + 1, nwin,
304
305
                util.time_to_str(trs[0].wmin),
                util.time_to_str(trs[0].wmax)))
Sebastian Heimann's avatar
Sebastian Heimann committed
306

307
308
            wmin = trs[0].wmin
            wmax = trs[0].wmax
Sebastian Heimann's avatar
Sebastian Heimann committed
309

310
311
            if config.fill_incomplete_with_zeros:
                trs = zero_fill(trs, wmin - tpad, wmax + tpad)
Sebastian Heimann's avatar
Sebastian Heimann committed
312

313
314
315
316
317
            frames = None
            pdata = []
            trs_debug = []
            shift_maxs = []
            for iifc, ifc in enumerate(ifcs):
318
                dataset = ifc.preprocess(
319
                    trs, wmin-tpeaksearch, wmax+tpeaksearch,
320
                    tshift_max - tshift_min, deltat_cf)
Sebastian Heimann's avatar
Sebastian Heimann committed
321

322
323
                if not dataset:
                    continue
Sebastian Heimann's avatar
Sebastian Heimann committed
324

325
                nstations_selected = len(dataset)
Sebastian Heimann's avatar
Sebastian Heimann committed
326

327
                nsls_selected, trs_selected = zip(*dataset)
Sebastian Heimann's avatar
Sebastian Heimann committed
328

Sebastian Heimann's avatar
Sebastian Heimann committed
329
330
331
                for tr in trs_selected:
                    tr.meta = {'tabu': True}

332
                trs_debug.extend(trs + list(trs_selected))
Sebastian Heimann's avatar
Sebastian Heimann committed
333

334
                t0 = (wmin / deltat_cf) * deltat_cf
Sebastian Heimann's avatar
Sebastian Heimann committed
335

336
337
338
                istations_selected = num.array(
                    [station_index[nsl] for nsl in nsls_selected],
                    dtype=num.int)
Sebastian Heimann's avatar
Sebastian Heimann committed
339

340
                arrays = [tr.ydata.astype(num.float) for tr in trs_selected]
Sebastian Heimann's avatar
Sebastian Heimann committed
341

342
343
344
345
                offsets = num.array(
                    [int(round((tr.tmin-t0) / deltat_cf))
                     for tr in trs_selected],
                    dtype=num.int32)
Sebastian Heimann's avatar
Sebastian Heimann committed
346

Marius Kriegerowski's avatar
Marius Kriegerowski committed
347
                w = ifc.get_weights(nsls_selected)
Sebastian Heimann's avatar
Sebastian Heimann committed
348

349
350
351
                weights = num.ones((ngridpoints, nstations_selected))
                weights *= w[num.newaxis, :]
                weights *= ifc.weight
352

353
                shift_table = shift_tables[iifc]
Sebastian Heimann's avatar
Sebastian Heimann committed
354

Sebastian Heimann's avatar
Sebastian Heimann committed
355
356
357
                ok = num.isfinite(shift_table[:, istations_selected])
                bad = num.logical_not(ok)

358
359
360
                shifts = -num.round(
                    shift_table[:, istations_selected] /
                    deltat_cf).astype(num.int32)
Sebastian Heimann's avatar
Sebastian Heimann committed
361

Sebastian Heimann's avatar
Sebastian Heimann committed
362
363
364
                weights[bad] = 0.0
                shifts[bad] = num.max(shifts[ok])

365
                pdata.append((list(trs_selected), shift_table, ifc))
Sebastian Heimann's avatar
Sebastian Heimann committed
366

367
368
                iwmin = int(round((wmin-tpeaksearch-t0) / deltat_cf))
                iwmax = int(round((wmax+tpeaksearch-t0) / deltat_cf))
Sebastian Heimann's avatar
Sebastian Heimann committed
369

370
                lengthout = iwmax - iwmin + 1
Sebastian Heimann's avatar
Sebastian Heimann committed
371

372
                shift_maxs.append(num.max(-shifts) * deltat_cf)
Sebastian Heimann's avatar
Sebastian Heimann committed
373

374
375
376
377
378
379
380
                frames, ioff = parstack(
                    arrays, offsets, shifts, weights, 0,
                    offsetout=iwmin,
                    lengthout=lengthout,
                    result=frames,
                    nparallel=nparallel,
                    impl='openmp')
Sebastian Heimann's avatar
Sebastian Heimann committed
381

382
            shift_max = max(shift_maxs)
Sebastian Heimann's avatar
Sebastian Heimann committed
383

384
385
386
387
388
            if config.sharpness_normalization:
                frame_maxs = frames.max(axis=0)
                frame_means = num.abs(frames).mean(axis=0)
                frames *= (frame_maxs / frame_means)[num.newaxis, :]
                frames *= norm_map[:, num.newaxis]
389

390
            frame_maxs = frames.max(axis=0)
Sebastian Heimann's avatar
Sebastian Heimann committed
391

392
            tmin_frames = t0 + ioff * deltat_cf
Sebastian Heimann's avatar
Sebastian Heimann committed
393

394
395
396
397
398
            tr_stackmax = trace.Trace(
                '', 'SMAX', '', '',
                tmin=tmin_frames,
                deltat=deltat_cf,
                ydata=frame_maxs)
Sebastian Heimann's avatar
Sebastian Heimann committed
399

Sebastian Heimann's avatar
Sebastian Heimann committed
400
401
            tr_stackmax.meta = {'tabu': True}

402
            trs_debug.append(tr_stackmax)
Sebastian Heimann's avatar
Sebastian Heimann committed
403

404
405
            if show_window_traces:
                trace.snuffle(trs_debug)
Sebastian Heimann's avatar
Sebastian Heimann committed
406

407
408
            ydata_window = tr_stackmax.chop(
                wmin, wmax, inplace=False).get_ydata()
Sebastian Heimann's avatar
Sebastian Heimann committed
409

410
411
412
413
            logger.info('CF stats: min %g, max %g, median %g' % (
                num.min(ydata_window),
                num.max(ydata_window),
                num.median(ydata_window)))
414

415
416
417
            tpeaks, apeaks = zip(*[(tpeak, apeak) for (tpeak, apeak) in zip(
                *tr_stackmax.peaks(config.detector_threshold, tpeaksearch)) if
                wmin <= tpeak and tpeak < wmax]) or ([], [])
418

419
            tr_stackmax_indx = tr_stackmax.copy(data=False)
420
421

            imaxs = num.zeros(len(frames))
422
            for iframe, frame in enumerate(frames.T):
423
424
                imaxs[iframe] = num.argmax(frame)

425
426
427
            tr_stackmax_indx.set_ydata(imaxs.astype(num.int32))
            tr_stackmax_indx.set_location('i')

428
            for (tpeak, apeak) in zip(tpeaks, apeaks):
Sebastian Heimann's avatar
Sebastian Heimann committed
429

430
431
432
                iframe = int(round(((tpeak-t0) - ioff*deltat_cf) / deltat_cf))
                frame = frames[:, iframe]
                imax = num.argmax(frame)
Sebastian Heimann's avatar
Sebastian Heimann committed
433

434
435
                latpeak, lonpeak, xpeak, ypeak, zpeak = \
                    grid.index_to_location(imax)
Sebastian Heimann's avatar
Sebastian Heimann committed
436

437
                idetection += 1
Sebastian Heimann's avatar
Sebastian Heimann committed
438

439
440
441
442
443
444
445
446
447
448
449
450
451
                detection = Detection(
                    id='%06i' % idetection,
                    time=tpeak,
                    location=geo.Point(
                        lat=float(latpeak),
                        lon=float(lonpeak),
                        x=float(xpeak),
                        y=float(ypeak),
                        z=float(zpeak)),
                    ifm=float(apeak))

                logger.info('detection: %s' % str(detection))

452
453
454
455
456
457
458
459
460
                if config.detections_path:
                    f = open(config.detections_path, 'a')
                    f.write('%06i %s %g %g %g %g %g %g\n' % (
                        idetection,
                        util.time_to_str(
                            tpeak,
                            format='%Y-%m-%d %H:%M:%S.6FRAC'),
                        apeak,
                        latpeak, lonpeak, xpeak, ypeak, zpeak))
Sebastian Heimann's avatar
Sebastian Heimann committed
461

462
                    f.close()
Sebastian Heimann's avatar
Sebastian Heimann committed
463

464
465
466
                if show_detections:
                    fmin = min(ifc.fmin for ifc in ifcs)
                    fmax = min(ifc.fmax for ifc in ifcs)
467
468
469
470
471
                    try:
                        plot.plot_detection(
                            grid, receivers, frames, tmin_frames,
                            deltat_cf, imax, iframe, fsmooth_min, xpeak, ypeak,
                            zpeak,
Sebastian Heimann's avatar
flake8    
Sebastian Heimann committed
472
473
                            tr_stackmax, tpeaks, apeaks,
                            config.detector_threshold,
474
475
476
477
478
479
                            wmin, wmax,
                            pdata, trs, fmin, fmax, idetection,
                            grid_station_shift_max=shift_max,
                            movie=show_movie)
                    except AttributeError as e:
                        logger.warn(e)
Sebastian Heimann's avatar
Sebastian Heimann committed
480

481
482
                if stop_after_first:
                    return
483

484
            tr_stackmax.chop(wmin, wmax)
485
            tr_stackmax_indx.chop(wmin, wmax)
486

Sebastian Heimann's avatar
Sebastian Heimann committed
487
488
489
490
491
            if config.stackmax_path:
                io.save(
                    [tr_stackmax, tr_stackmax_indx],
                    os.path.join(
                        config.stackmax_path, 'trace_%(tmin_ms)s.mseed'))
492

493
494
495
496
        logger.info('end processing time window group: %s - %s' % (
            util.time_to_str(tmin_win),
            util.time_to_str(tmax_win)))

Sebastian Heimann's avatar
Sebastian Heimann committed
497
498
499
500

__all__ = [
    'scan',
]