# PROJECT # Give this workflow a name and set the project root. Relative paths below are # resolved from the directory that contains this config file unless you use # {root_dir} or {config_dir} explicitly. project: name: example_ground_motion_validation root_dir: ../../.. # PATHS # Point Spatial-VTK to the input files you already have on disk. # Templates can use {root_dir}, {config_dir}, {model}, and {event_id}. paths: observed_root: data/observed synthetic_template: data/synthetics/{model}/{event_id}.mseed station_metadata: data/metadata/stations.csv event_metadata: data/metadata/events.csv event_station_table: data/metadata/event_station_records.csv region_geojson: data/metadata/regions.geojson # OUTPUTS # Choose where generated tables, figures, maps, and dashboard files should go. outputs: root: outputs tables: outputs/tables prepared_inputs: outputs/prepared preprocessed_waveforms: outputs/preprocessed_waveforms qc: outputs/qc metrics: outputs/metrics/metrics_long.parquet spatial: outputs/spatial figures: outputs/figures dashboards: outputs/dashboards # NOTEBOOKS # Set this to false if you do not want tutorial cells to print run-time lines. notebooks: show_cell_timing: true # COMPUTE # Optional SLURM settings for long-running workflows. Task-specific sections # such as qc.slurm or metrics.slurm can override any value below. compute: slurm: python_command: python # environment_setup: # - module load mamba # - mamba activate spatial-vtk-py312 partition: account: walltime: "12:00:00" memory: 16G cpus_per_task: 1 max_concurrent: 10 log_dir: outputs/logs # BOUNDS # Named bounds let you reuse map windows or station/event subsets. # Bounds are always [lon_min, lon_max, lat_min, lat_max]. bounds: presets: study_area: lon_min: -119.5 lon_max: -116.5 lat_min: 33.0 lat_max: 35.0 specific_area_of_interest: lon_min: -118.8 lon_max: -117.8 lat_min: 33.5 lat_max: 34.5 # Optional: load more named bounds from a CSV with columns # keyword, lon_min, lon_max, lat_min, lat_max. presets_csv: data/metadata/bounds_presets.csv # METRICS # Choose either groups OR individual metrics. Do not set both in one run. metrics: # Group options: all, duration, amplitude, spectral, intensity, # delay, cross_correlation. # duration: arias_duration, energy_duration # amplitude: PGA, PGV, PGD # spectral: PSA, FAS # intensity: arias_intensity, energy_intensity, CAV # delay: traveltime_delay # cross_correlation: original_cc, delay_corrected_cc groups: [amplitude, spectral, cross_correlation] # If you prefer to select individual metrics, comment out groups above and # use metrics instead. Metric options: all, PGA, PGV, PGD, PSA, FAS, CAV, # arias_duration, energy_duration, arias_intensity, energy_intensity, # traveltime_delay, original_cc, delay_corrected_cc. # metrics: [PGA, PGV, PSA, original_cc] # Transform options: residual, log2_residual, ln_residual, # anderson_2004_gof, olsen_mayhew_gof. transforms: [log2_residual, anderson_2004_gof] # Output mode options: observed, synthetic, residual, gof, full. output_mode: full # Component examples: Z, N, E, R, T. components: [R, T, Z] # Passbands are period bands in seconds. passbands: - [1, 2] - [2, 3] - [3, 5] models: [example_model] spectral: # Periods, in seconds, where PSA/FAS values should be stored. periods_s: [1.0, 2.0, 3.0, 5.0] # A period passes spectral QC only if its amplitude is at least this # fraction of the maximum supported spectral amplitude. relative_amplitude_threshold: 0.25 # Require this many cycles in the record before accepting a period. min_cycles_in_record: 3.0 # Optional SLURM overrides for metric task arrays. slurm: job_name: svtk-metrics walltime: "24:00:00" memory: 32G # SYNTHETICS # Set the maximum valid synthetic frequency in Hz. Synthetic spectral periods # shorter than 1 / max_frequency_hz will be rejected. synthetics: max_frequency_hz: 0.5 # WAVEFORMS # Optional project-specific preprocessing applied to observed and synthetic # waveforms before QC, metric calculations, and waveform figures. # Leave values empty when your inputs are already filtered/sampled as needed. # Use either bandpass_low_hz/bandpass_high_hz OR highpass_hz/lowpass_hz. waveforms: preprocessing: lowpass_hz: highpass_hz: bandpass_low_hz: bandpass_high_hz: resample_hz: filter_order: 4 # QC # These automatic checks are used when waveform-level QC is requested. qc: automatic: min_record_length_s: 60.0 min_end_after_origin_s: 60.0 snr_threshold: 3.0 # Optional SLURM overrides for building qc_trace_summary and qc_inventory. slurm: job_name: svtk-qc walltime: "24:00:00" memory: 32G # RUN SCENARIOS # Optional named scenarios let you reuse focused overrides without editing the # main defaults above. Select one with --run-scenario or run_scenario="...". run_scenarios: tutorial: # This scenario expects the companion five-event LA Basin waveform bundle # under data/examples/example_five_event_subset/. The repo keeps the # metadata tables in git and ignores the large MiniSEED products. paths: observed_root: "{root_dir}/data/examples/example_five_event_subset/observed" synthetic_root: "{root_dir}/data/examples/example_five_event_subset/synthetics/cvmsi_20260506_material_0p6x1p2_asdf" synthetic_template: "{root_dir}/data/examples/example_five_event_subset/synthetics/{model}/{event_id}.mseed" station_metadata: "{root_dir}/data/examples/example_five_event_subset/metadata/selected_stations.csv" event_metadata: "{root_dir}/data/examples/example_five_event_subset/metadata/events.csv" event_station_table: "{root_dir}/data/examples/example_five_event_subset/metadata/selected_event_stations.csv" site_metadata: "{root_dir}/data/examples/data_formats/example_site_metadata.csv" region_geojson: "{root_dir}/data/examples/example_five_event_subset/metadata/example_path_regions.geojson" metric_snapshot: "{root_dir}/data/examples/data_formats/example_metrics_snapshot.csv" metric_figure_snapshot: "{root_dir}/data/examples/data_formats/example_metrics_large_qc_passed.parquet" outputs: tutorials_root: "{root_dir}/outputs/tutorials" root: "{root_dir}/outputs/tutorials" tables: "{root_dir}/outputs/tutorials/tables" preprocessed_waveforms: "{root_dir}/outputs/tutorials/preprocessed_waveforms" figures: "{root_dir}/outputs/tutorials/figures" dashboards: "{root_dir}/outputs/tutorials/dashboards" metrics: groups: [amplitude, spectral] transforms: [log2_residual, anderson_2004_gof] output_mode: full components: [Z, R, T] models: [cvmsi_20260506_material_0p6x1p2_asdf] passbands: - [1, 2] - [2, 3] spectral: periods_s: [1.0, 2.0, 3.0, 5.0] synthetics: max_frequency_hz: 1.0 waveforms: preprocessing: lowpass_hz: 1.0 highpass_hz: bandpass_low_hz: bandpass_high_hz: resample_hz: filter_order: 4 qc: automatic: min_record_length_s: 60.0 min_end_after_origin_s: 60.0 snr_threshold: 3.0 spatial: metric: all field_mode: log2_residual value_column: log2_residual min_stations_per_event: 2 min_events_per_station: 1 moran_neighbors: 2 moran_permutations: 99 distance_bin_width_km: 20 cluster_min_k: 2 cluster_max_k: 4 pca_components: 2 # Compare average residuals between these geology class sets. # The reported contrast is mean(geology_left_values) - mean(geology_right_values). geology_group_column: mapped_region_type geology_left_values: [Basin] geology_right_values: [Mountains] geology_statistic: mean # The tutorial subset is small; use a larger value for full datasets. geology_min_stations_per_group: 1 geology_bootstrap_samples: 100 random_seed: 42 quick_amplitude_check: metrics: groups: [amplitude] transforms: [log2_residual] outputs: metrics: outputs/metrics/quick_amplitude_metrics.parquet spectral_period_review: metrics: metrics: [PSA, FAS] transforms: [log2_residual, anderson_2004_gof] spectral: periods_s: [1.0, 2.0, 3.0, 5.0, 7.5]