parameters.yaml

# //////////////////////////////////////////////////////////////////////////////
#
#                        SeisFlows YAML Parameter File
#
# //////////////////////////////////////////////////////////////////////////////
#
# Modules correspond to the structure of the source code, and determine
# SeisFlows' behavior at runtime. Each module requires its own sub-parameters.
#
# .. rubric::
#   - Determine available options for modules by running:
#       > seisflows print modules
#   - Auto-fill with docstrings and default values (recommended) by running:
#       > seisflows configure
#   - Swap out module parameters for a configured parameter file by running:
#       > seisflows swap {module} {name} (e.g., seisflows swap solver specfem3d)
#   - To set values as NoneType, use: null
#   - To set values as infinity, use: inf
#
#                                    MODULES
#                                    ///////
# workflow (str):    The types and order of functions for running SeisFlows
# system (str):      Computer architecture of the system being used
# solver (str):      External numerical solver to use for waveform simulations
# preprocess (str):  Preprocessing schema for waveform data
# optimize (str):    Optimization algorithm for the inverse problem
# ==============================================================================
workflow: inversion
system: workstation
solver: specfem2d
preprocess: dispersion
optimize: LBFGS
# =============================================================================
#
#    Forward Workflow
#    ----------------
#    Defines foundational structure for Workflow module. When used standalone 
#    is in charge of running forward solver in parallel and (optionally) 
#    calculating data-synthetic misfit and adjoint sources.
#
#    Parameters
#    ----------
#    :type modules: list of module
#    :param modules: instantiated SeisFlows modules which should have been
#        generated by the function `seisflows.config.import_seisflows` with a
#        parameter file generated by seisflows.configure
#    :type data_case: str
#    :param data_case: How to address 'data' in the workflow, available options:
#        'data': real data will be provided by the user in
#        `path_data/{source_name}` in the same format that the solver will
#        produce synthetics (controlled by `solver.format`) OR
#        synthetic': 'data' will be generated as synthetic seismograms using
#        a target model provided in `path_model_true`. If None, workflow will
#        not attempt to generate data.
#    :type stop_after: str
#    :param stop_after: optional name of task in task list (use
#        `seisflows print tasks` to get task list for given workflow) to stop
#        workflow after, allowing user to prematurely stop a workflow to explore
#        intermediate results or debug.
#    :type export_traces: bool
#    :param export_traces: export all waveforms that are generated by the
#        external solver to `path_output`. If False, solver traces stored in
#        scratch may be discarded at any time in the workflow
#    :type export_residuals: bool
#    :param export_residuals: export all residuals (data-synthetic misfit) that
#        are generated by the external solver to `path_output`. If False,
#        residuals stored in scratch may be discarded at any time in the 
#        workflow
#
#        
#    Migration Workflow
#    ------------------
#    Run forward and adjoint solver to produce event-dependent misfit kernels.
#    Sum and postprocess kernels to produce gradient. In seismic exploration
#    this is 'reverse time migration'.
#
#    Parameters
#    ----------
#    :type export_gradient: bool
#    :param export_gradient: export the gradient after it has been generated
#        in the scratch directory. If False, gradient can be discarded from
#        scratch at any time in the workflow
#    :type export_kernels: bool
#    :param export_kernels: export each sources event kernels after they have
#        been generated in the scratch directory. If False, gradient can be
#        discarded from scratch at any time in the workflow
#
#        
#    Inversion Workflow
#    ------------------
#    Peforms iterative nonlinear inversion using the machinery of the Forward
#    and Migration workflows, as well as a built-in optimization library.
#
#    Parameters
#    ----------
#    :type start: int
#    :param start: start inversion workflow at this iteration. 1 <= start <= inf
#    :type end: int
#    :param end: end inversion workflow at this iteration. start <= end <= inf
#    :type iteration: int
#    :param iteration: The current iteration of the workflow. If NoneType, takes
#        the value of `start` (i.e., first iteration of the workflow). User can
#        also set between `start` and `end` to resume a failed workflow.
#    :type thrifty: bool
#    :param thrifty: a thrifty inversion skips the costly intialization step
#        (i.e., forward simulations and misfit quantification) if the final
#        forward simulations from the previous iterations line search can be
#        used in the current one. Requires L-BFGS optimization.
#    :type export_model: bool
#    :param export_model: export best-fitting model from the line search to disk.
#        If False, new models can be discarded from scratch at any time.
#
#        
# =============================================================================
data_case       : synthetic # 'data' or 'synthetic'
stop_after      : null      # 在多少炮之后停止
export_traces   : False      # 导出所有由外部求解器生成的波形
export_residuals: False     # 导出由外部求解器生成的所有残差
export_gradient : True      # 在临时目录中生成梯度后导出梯度
export_kernels  : False      # 在临时目录中生成每个源事件内核后导出梯度
start           : 1         # 在此迭代中启动反演工作流
end             : 50         # 在此迭代中结束反演工作流
export_model    : True      # 将线搜索中的最佳拟合模型导出到磁盘
thrifty         : False     # 节俭反演会跳过昂贵的初始化步骤
iteration       : 1         # 工作流的当前迭代
# =============================================================================
#
#    Workstation System
#    ------------------
#    Defines foundational structure for System module. When used standalone,
#    runs solver tasks either in serial (if `nproc`==1; i.e., without MPI) or in
#    parallel (if `nproc`>1; i.e., with MPI). All other tasks are run in serial.
#
#    Parameters
#    ----------
#    :type ntask: int
#    :param ntask: number of individual tasks/events to run during workflow.
#        Must be <= the number of source files in `path_specfem_data`
#    :type nproc: int
#    :param nproc: number of processors to use for each simulation. Choose 1 for
#        serial simulations, and `nproc`>1 for parallel simulations.
#    :type mpiexec: str
#    :param mpiexec: MPI executable on system. Defaults to 'mpirun -n ${NPROC}'
#    :type log_level: str
#    :param log_level: logger level to pass to logging module.
#        Available: 'debug', 'info', 'warning', 'critical'
#    :type verbose: bool
#    :param verbose: if True, formats the log messages to include the file
#        name, line number and message type. Useful for debugging but
#        also very verbose.
#
#        
# =============================================================================
ntask    : 3      # 工作流期间要运行的单个任务/事件的数量
nproc    : 40      # 每次模拟要使用的处理器数量
mpiexec  : mpirun # 系统上的 MPI 可执行文件
log_level: DEBUG  # 传递给日志模块的记录器级别, 'debug', 'info', 'warning', 'critical'
verbose  : True   # 如果为 True，则格式化日志消息以包含文件名称、行号和消息类型
# =============================================================================
#
#    Solver SPECFEM
#    --------------
#    Defines foundational structure for Specfem-based solver module. 
#    Generalized SPECFEM interface to manipulate SPECFEM2D/3D/3D_GLOBE w/ Python
#
#    Parameters
#    ----------
#    :type syn_data_format: str
#    :param syn_data_format: data format for reading synthetic traces into memory.
#        Available: ['SU': seismic unix format, 'ASCII': human-readable ascii]
#    :type materials: str
#    :param materials: Material parameters used to define model. Available:
#        ['ELASTIC': Vp, Vs, 'ACOUSTIC': Vp, 'ISOTROPIC', 'ANISOTROPIC']
#    :type density: bool
#    :param density: How to treat density during inversion. If True, updates
#        density during inversion. If False, keeps it constant.
#        TODO allow density scaling during an inversion
#    :type attenuation: bool
#    :param attenuation: How to treat attenuation during inversion.
#        if True, turns on attenuation during forward simulations only. If
#        False, attenuation is always set to False. Requires underlying
#        attenution (Q_mu, Q_kappa) model
#    :type smooth_h: float
#    :param smooth_h: Gaussian half-width for horizontal smoothing in units
#        of meters. If 0., no smoothing applied. Only applicable for workflows:
#        ['migration', 'inversion'], ignored for 'forward' workflow.
#        SPECFEM3D_GLOBE only: if `smooth_type`=='laplacian' then this is just 
#        the X and Y extent of the applied smoothing
#    :type smooth_h: float
#    :param smooth_v: Gaussian half-width for vertical smoothing in units
#        of meters. Only applicable for workflows: ['migration', 'inversion'],
#        ignored for 'forward' workflow.
#        SPECFEM3D_GLOBE only: if `smooth_type`=='laplacian' then this is just 
#        the Z extent of the applied smoothing
#    :type components: str
#    :param components: components to search for synthetic data with. None by
#        default which uses a wildcard when searching for synthetics. If
#        provided, User only wants to use a subset of components generated by
#        SPECFEM. In that case, `components` should be string of letters such
#        as 'ZN' (for up and north components)
#    :type solver_io: str
#    :param solver_io: format of model/kernel/gradient files expected by the
#        numerical solver. Available: ['fortran_binary': default .bin files].
#        TODO: ['adios': ADIOS formatted files]
#    :type source_prefix: str
#    :param source_prefix: prefix of source/event/earthquake files. If None,
#        will attempt to guess based on the specific solver chosen.
#    :type mpiexec: str
#    :param mpiexec: MPI executable used to run parallel processes. Should also
#        be defined for the system module
#
#        
#    Solver SPECFEM2D
#    ----------------
#    SPECFEM2D-specific alterations to the base SPECFEM module
#
#    Parameters
#    ----------
#    :type source_prefix: str
#    :param source_prefix: Prefix of source files in path SPECFEM_DATA. Defaults
#        to 'SOURCE'
#    :type multiples: bool
#    :param multiples: set an absorbing top-boundary condition
#
#        
# =============================================================================
syn_data_format: ascii          # 用于将合成轨迹读入内存的数据格式
materials      : elastic        # 用于定义模型的材料参数, acoustic,elastic,isotropic, anisotropic
density        : False          # 如何在反演过程中处理密度
attenuation    : False          # 如何在反演过程中处理衰减
smooth_h       : 10.0            # 水平平滑的高斯半宽度
smooth_v       : 10.0            # 垂直平滑的高斯半宽度
components     : XZ             # 考虑的分量并标记数据
source_prefix   : SOURCE         # 震源文件的前缀
multiples      : True           # 设置吸收顶部边界条件
# =============================================================================
#
#    Pyaflowa Preprocess
#    -------------------
#    Preprocessing and misfit quantification using Python's Adjoint Tomography
#    Operations Assistant (Pyatoa)
#
#    Parameters
#    ----------
#    :type min_period: float
#    :param min_period: Minimum filter corner in unit seconds. Bandpass
#    filter if set with `max_period`, highpass filter if set without
#    `max_period`, no filtering if not set and `max_period also not set
#    :type max_period: float
#    :param max_period: Maximum filter corner in unit seconds. Bandpass
#        filter if set with `min_period`, lowpass filter if set without
#        `min_period`, no filtering if not set and `min_period also not set
#   :type filter_corners: int
#    :param filter_corners: number of filter corners applied to filtering
#    :type client: str
#    :param client: Client name for ObsPy FDSN data gathering. Pyatoa will
#        attempt to collect waveform and metadata based on network and
#        station codes provided in the SPECFEM STATIONS file. If set None,
#        no FDSN gathering will be attempted
#    :type rotate: bool
#    :param rotate: Attempt to rotate waveform components from NEZ -> RTZ
#    :type pyflex_preset: str
#    :param pyflex_preset: Parameter map for misfit window configuration
#        defined by Pyflex. IF None, misfit and adjoint sources will be
#        calculated on whole traces. For available choices, see Pyatoa docs
#        page (pyatoa.rtfd.io)
#    :type fix_windows: bool or str
#    :param fix_windows: How to address misfit window evaluation at each
#        evaluation. Options to re-use misfit windows collected during an
#        inversion, available options:
#        [True, False, 'ITER', 'ONCE']
#        True: Re-use windows after first evaluation (i01s00);
#        False: Calculate new windows each evaluation;
#        'ITER': Calculate new windows at first evaluation of
#        each iteration (e.g., i01s00... i02s00...
#        'ONCE': Calculate new windows at first evaluation of
#        the workflow, i.e., at self.par.BEGIN
#    :type adj_src_type: str
#    :param adj_src_type: Adjoint source type to evaluate misfit, defined by
#        Pyadjoint. See `pyadjoint.config.ADJSRC_TYPES` for available options.
#        Listed below, they are:
#        
#        - 'waveform': waveform misfit function
#        - 'convolution': convolution misfit function
#        - 'exponentiated_phase': exponentiated phase from Yuan et al. 2020
#        - 'cc_traveltime': cross-correlation traveltime misfit
#        - 'multitaper': multitaper misfit function
#    :type plot: bool
#    :param plot: plot waveform figures and source receiver maps during
#        the preprocessing stage
#    :type pyatoa_log_level: str
#    :param pyatoa_log_level: Log level to set Pyatoa, Pyflex, Pyadjoint.
#        Available: ['null': no logging, 'warning': warnings only,
#        'info': task tracking, 'debug': log all small details (recommended)]
#    :type unit_output: str
#    :param unit_output: Data units. Must match the synthetic output of
#        external solver. Available: ['DISP': displacement, 'VEL': velocity,
#        'ACC': acceleration]
#    :type export_datasets: bool
#    :param export_datasets: periodically save the output ASDFDataSets which
#        contain data, metadata and results collected during the
#        preprocessing procedure
#    :type export_figures: bool
#    :param export_figures: periodically save the output basemaps and
#        data-synthetic waveform comparison figures
#    :type export_log_files: bool
#    :param export_log_files: periodically save log files created by Pyatoa
#
#        
# =============================================================================
obs_data_format: ascii      # 读取观测轨迹的数据格式,'su','ascii','sac'
unit_output    : disp       # 数据单位, disp, vel, acc
misfit          : waveform   # 波形比较的不匹配函数, waveform,envelope,instantaneous_phase,traveltime,
adjoint        : waveform   # 偏移的反投影函数或 FWI中的目标函数
normalize      : []         # 规范化波形振幅的数据规范化参数, enorml1,enorml2,tnorml1,tnorml2
filter          : null       # 数据过滤类型, bandpass,lowpass,highpass
min_period     : null
max_period     : null
min_freq       : null       # 最小过滤频率, 0.1
max_freq       : null       # 最大过滤频率, 30.0
mute           : []         # 数据mute参数, early,late,short,long
early_slope    : null       # 应用于源接收器距离以mute到达的斜率
early_const    : null       # 用于随时间移动掩码的恒定时间偏移
late_slope     : null
late_const     : null
short_dist     : null       # cutoff distance, 截止距离
long_dist      : null

misfit: traveltime
adjoint: traveltime
fmin: 3.0
fmax: 50.0
dx: 0.1
df: 0.1
dk: 0.1
minrec: 10          # 最小多少个检波器来提频散曲线
dfpara: 0.1
dkpara: 0.1
nt: 5000
nx: 40
dt: 6.e-2
syn_data_format: ascii
obs_data_format: ascii
channel: XZ
# =============================================================================
#
#    Gradient Optimization
#    ---------------------
#    Defines foundational structure for Optimization module. Applies a 
#    gradient/steepest descent optimization algorithm.
#
#    Parameters
#    ----------
#    :type line_search_method: str
#    :param line_search_method: chosen line_search algorithm. Currently available
#        are 'bracket' and 'backtrack'. See seisflows.plugins.line_search
#        for all available options
#    :type preconditioner: str
#    :param preconditioner: algorithm for preconditioning gradients. Currently
#        available: 'diagonal'. Requires `path_preconditioner` to point to a
#        set of files that define the preconditioner, formatted the same as the
#        input model
#    :type step_count_max: int
#    :param step_count_max: maximum number of trial steps to perform during
#        the line search before a change in line search behavior is
#        considered, or a line search is considered to have failed.
#    :type step_len_init: float
#    :param step_len_init: initial line search step length guess, provided
#        as a fraction of current model parameters.
#    :type step_len_max: float
#    :param step_len_max: maximum allowable step length during the line
#        search. Set as a fraction of the current model parameters
#
#        
#    L-BFGS Optimization
#    -------------------
#    Limited memory BFGS nonlienar optimization algorithm
#
#    Parameters
#    ----------
#    :type lbfgs_mem: int
#    :param lbfgs_mem: L-BFGS memory. Max number of previous gradients to
#        retain in local memory for approximating the objective function.
#    :type lbfgs_max: L-BFGS periodic restart interval. Must be
#        1 <= lbfgs_max <= infinity.
#    :type lbfgs_thresh: L-BFGS angle restart threshold. If the angle between
#        the current and previous search direction exceeds this value,
#        optimization algorithm will be restarted.
#
#        
# =============================================================================
preconditioner: null
step_count_max: 10
step_len_init: 0.05
step_len_max: 0.5
line_search_method: Backtrack
LBFGS_mem: 3
LBFGS_max: inf
LBFGS_thresh: 0.0
# =============================================================================
#
#	 Paths
#	 -----
#    :type workdir: str
#    :param workdir: working directory in which to perform a SeisFlows workflow.
#        SeisFlows internal directory structure will be created here. Default cwd
#    :type path_output: str
#    :param path_output: path to directory used for permanent storage on disk.
#        Results and exported scratch files are saved here.
#    :type path_data: str
#    :param path_data: path to any externally stored data required by the solver
#    :type path_state_file: str
#    :param path_state_file: path to a text file used to track the current
#        status of a workflow (i.e., what functions have already been completed),
#        used for checkpointing and resuming workflows
#    :type path_model_init: str
#    :param path_model_init: path to the starting model used to calculate the
#        initial misfit. Must match the expected `solver_io` format.
#    :type path_model_true: str
#    :param path_model_true: path to a target model if `case`=='synthetic' and
#        a set of synthetic 'observations' are required for workflow.
#    :type path_eval_grad: str
#    :param path_eval_grad: scratch path to store files for gradient evaluation,
#        including models, kernels, gradient and residuals.
#        :type path_mask: str
#    :param path_mask: optional path to a masking function which is used to
#        mask out or scale parts of the gradient. The user-defined mask must
#        match the file format of the input model (e.g., .bin files).
#        :type path_eval_func: str
#    :param path_eval_func: scratch path to store files for line search objective
#        function evaluations, including models, misfit and residuals
#        
#    :type path_output_log: str
#    :param path_output_log: path to a text file used to store the outputs of
#        the package wide logger, which are also written to stdout
#    :type path_par_file: str
#    :param path_par_file: path to parameter file which is used to instantiate
#        the package
#    :type path_log_files: str
#    :param path_log_files: path to a directory where individual log files are
#        saved whenever a number of parallel tasks are run on the system.
#        
#    :type path_data: str
#    :param path_data: path to any externally stored data required by the solver
#    :type path_specfem_bin: str
#    :param path_specfem_bin: path to SPECFEM bin/ directory which
#        contains binary executables for running SPECFEM
#    :type path_specfem_data: str
#    :param path_specfem_data: path to SPECFEM DATA/ directory which must
#        contain the CMTSOLUTION, STATIONS and Par_file files used for
#        running SPECFEM
#            
#    :type path_preprocess: str
#    :param path_preprocess: scratch path for preprocessing related steps
#        
#    :type path_preconditioner: str
#    :param path_preconditioner: optional path to a set of preconditioner files
#        formatted the same as the input model (or output model of solver).
#        Required to exist and contain files if `preconditioner`==True
#            
# =============================================================================
path_workdir       : .
path_par_file       : parameters.yaml
path_specfem_data  : specfem2d_workdir/DATA
# path_model_init    : specfem2d_workdir/Init
path_model_init    : specfem2d_workdir/MODEL_15
path_model_true    : specfem2d_workdir/True 
# path_specfem_data: /home/zhangzhiyu/MyProjects/sf1/specfem2d_workdir/DATA
# path_model_init: /home/zhangzhiyu/MyProjects/sf1/specfem2d_workdir/OUTPUT_FILES_INIT
# path_model_true: /home/zhangzhiyu/MyProjects/sf1/specfem2d_workdir/OUTPUT_FILES_TRUE
path_data          : null
path_mask          : null

path_scratch       : scratch
path_solver        : scratch/solver
path_eval_grad     : scratch/eval_grad
path_eval_func     : scratch/eval_func
path_output        : output
path_log_files      : logs
path_output_log    : sflog.txt
path_state_file     : sfstate.txt
path_specfem_bin   : /home/zhangzhiyu/MyProjects/Seisflows/specfem2d/bin
path_preconditioner: null