src/seismic_hazard_forecasting.py

@@ -1,9 +1,264 @@
 # -*- coding: utf-8 -*-
+from eqdist.rate import datenum_to_datetime
+import Rbeast as rb;
+from scipy.stats import bootstrap
+from matplotlib.dates import DateFormatter, AutoDateLocator
+from matplotlib.ticker import MultipleLocator
+import matplotlib.pyplot as plt
+import numpy as np
+
+global ncp_choice, tcp_max, torder_min, torder_max
+ncp_choice = 'default'
+tcp_max = 5
+torder_min = 0
+torder_max = 1
+
+def plot_results(act_rate, bin_edges, bin_edges_dt, rt, boundaries,
+                  bin_dur, unit, multiplicator,
+                  rate_forecast, rate_unc_high, rate_unc_low,
+                  datenum_data, mag_data):
+
+    end_date = bin_edges[-1]
+
+    fig, ax = plt.subplots(figsize=(14, 6))
+    ax.plot(bin_edges_dt[1:], act_rate, '-o', linewidth=2.5, markersize=6.5, label='Activity rate')
+
+    if rate_forecast is not None:
+        next_date = end_date + (bin_dur / multiplicator)
+        ax.plot(datenum_to_datetime(next_date), rate_forecast, 
+                'ro', label='Forecasted Rate', markersize=6.5)
+        ax.plot([bin_edges_dt[-1], datenum_to_datetime(next_date)], [act_rate[-1], rate_forecast], 'r-', linewidth=2.5)
+        ax.vlines(datenum_to_datetime(next_date), rate_unc_low, rate_unc_high, colors='r',
+                  linewidth=2, label='Bootstrap uncertainty')
+
+    ax.xaxis.set_major_locator(AutoDateLocator())
+    ax.xaxis.set_major_formatter(DateFormatter('%d-%b-%Y'))
+    plt.xticks(rotation=45)
+    plt.title(f'Activity rate (Time Unit: {unit}, Bin Duration: {bin_dur} {unit})',fontsize=18)
+    # plt.title(f'Activity rate (Bin Duration: {bin_dur} {unit})',fontsize=18)
+    plt.xlabel('Time (Bin Center Date)', fontsize=16)
+    ax.set_ylabel('Activity rate per selected time period',fontsize=16)
+    plt.grid(True)
+
+    if len(rt) > 0:
+        for i in range(len(rt)):
+            ax.plot(bin_edges_dt[1:][boundaries[i]:boundaries[i+1]],
+                    [rt[i]] * (boundaries[i+1] - boundaries[i]),
+                    linewidth=2, label=f'Rate period {i+1}')
+
+    # ---- Magnitude scatter on right y-axis ----
+    ax2 = ax.twinx()
+    event_dates = [datenum_to_datetime(d) for d in datenum_data]
+
+    #-------------extract magnitude bins from data---------------------
+    mags = np.array(mag_data)
+    min_mag = mags.min()
+    max_mag = mags.max()
+
+    low_thresh = int(np.floor(min_mag))
+    high_thresh = int(np.floor(max_mag))
+
+    thresholds = list(range(low_thresh, high_thresh + 1))
+
+    base_size = 15
+    size_step = 35
+
+    bins_def = []
+    for idx, t in enumerate(thresholds):
+        low = t
+        if idx < len(thresholds) - 1:
+            high = thresholds[idx + 1]
+            label = f'{low:.1f} \u2264 M < {high:.1f}'
+        else:
+            high = np.inf
+            label = f'M \u2265 {low:.1f}'
+        size = base_size + idx * size_step
+        bins_def.append((low, high, size, label))
+
+    for low, high, size, label in bins_def:
+        mask = (mags >= low) & (mags < high)
+        if np.any(mask):
+            sel_dates = [d for d, m in zip(event_dates, mask) if m]
+            sel_mags = mags[mask]
+            ax2.scatter(sel_dates, sel_mags, s=size,
+                        facecolor='purple', edgecolor='black',
+                        alpha=0.15, linewidth=1, label=label)
+
+    ax2.set_ylabel('Magnitude', color='purple',fontsize=16)
+    ax2.yaxis.set_major_locator(MultipleLocator(0.5))
+    ax2.yaxis.set_minor_locator(MultipleLocator(0.1))
+    ax2.spines['right'].set_color('purple')
+    ax2.tick_params(axis='y', colors='purple')
+
+    h1, l1 = ax.get_legend_handles_labels()
+    h2, l2 = ax2.get_legend_handles_labels()
+    handles = h1 + h2
+    labels = l1 + l2
+    n_legend = len(handles)
+
+    ncols = max(1, int(np.ceil(n_legend / 5)))  # ~5 entries per column
+    
+    #-------add 20% headroom above the data to make space for legend------
+    ymin, ymax = ax.get_ylim()
+    ax.set_ylim(ymin, ymax * 1.20) 
+    
+    ax.legend(handles, labels, loc='best',
+          ncol=ncols, borderaxespad=0,framealpha=0.7)
+
+    ax.set_zorder(ax2.get_zorder() + 1) # put scatter plot behind the line plot
+    ax.patch.set_visible(False)
+    
+    fig.tight_layout()
+    plt.savefig("activity_rate.png", dpi=600)
+    plt.show()
+
+def bootstrap_forecast(data):
+
+    window_data=data
+
+    if len(window_data) >= 5:
+        res95 = bootstrap((window_data,), np.mean, confidence_level=0.95,
+                          method='BCa', n_resamples=1000)
+    else:
+        res95 = bootstrap((window_data,), np.mean, confidence_level=0.95,
+                          method='BCa', n_resamples=int(len(window_data) ** len(window_data)))
+
+    forecast = np.mean(res95.bootstrap_distribution)
+    bca_conf95 = res95.confidence_interval
+    return forecast, bca_conf95
+
+def calc_rates(act_rate, cps):
+    """
+    Calculates mean activity rates between changepoints.
+    cps : sorted array of changepoint indices into act_rate
+    Returns rt (list of rates) and segment boundaries
+    """
+    boundaries = [0] + list(cps.astype(int)) + [len(act_rate)]
+    rt = [np.mean(act_rate[boundaries[i]:boundaries[i+1]]) 
+          for i in range(len(boundaries)-1)]
+    return rt, boundaries
+
+def apply_beast(act_rate):
+    """
+    Applies BEAST to the smmothed rate data using different smoothing windows.
+    Input
+    act_rate : The activity rate data array to smooth and apply BEAST.
+    Output
+    out : A list of BEAST results for each smoothed rate array.
+    prob : A list of probabilities and change points extracted from BEAST results.
+    """
+
+    #mirror_len = int(np.ceil(0.20 * len(act_rate)))
+    #left_mirror = act_rate[:mirror_len][::-1]
+    #right_mirror = act_rate[-mirror_len:][::-1]
+    #act_rate_mirrored = np.concatenate([left_mirror, act_rate, right_mirror])
+
+    mcmc_th = int(np.clip(np.ceil(len(act_rate) / 100), 2, 15))
+    beast_result = rb.beast(act_rate, period=0,
+                            tcp_minmax=[0, tcp_max],
+                            torder_minmax=[torder_min, torder_max],
+                            tseg_minlength=2, mcmc_chains=10,
+                            mcmc_thin=mcmc_th, mcmc_seed=10)
+
+    # User-driven ncp selection
+    if ncp_choice == 'median':
+        ncp = beast_result.trend.ncp_median
+        if np.isnan(ncp) or ncp == 0:
+            return beast_result, np.array([])
+    elif ncp_choice == 'mode':
+        ncp = beast_result.trend.ncp_mode
+        if np.isnan(ncp) or ncp == 0:
+            return beast_result, np.array([])   
+    elif ncp_choice == 'pct90':
+        ncp = beast_result.trend.ncp_pct90
+        if np.isnan(ncp) or ncp == 0:
+            return beast_result, np.array([])
+    else:  # default: median with mode and pct90 fallback
+        ncp = beast_result.trend.ncp_median
+        if np.isnan(ncp) or ncp == 0:
+            ncp = beast_result.trend.mode
+        if np.isnan(ncp) or ncp == 0:
+            ncp = beast_result.trend.ncp_pct90
+        if np.isnan(ncp) or ncp == 0:    
+            return beast_result, np.array([])
+
+    ncp = int(ncp)
+    # Filter NaNs first — BEAST fills unused cp slots with nan
+    # valid_cps = beast_result.trend.cp[~np.isnan(beast_result.trend.cp)]
+    cps = beast_result.trend.cp[:ncp]
+
+    # Discard mirrored zone changepoints and correct indices
+    #valid_mask = (cps > mirror_len) & (cps <= mirror_len + len(act_rate))
+    #cps = cps[valid_mask] - mirror_len
+
+    # Discard changepoints too close to the start or end (artifacts of mirroring).
+    # bins_after_cp / bins_before_cp set the minimum buffer bins required at each end.
+    #bins_before_cp = 2
+    #bins_after_cp = 2
+    #if len(cps) > 0:
+    #    cps = cps[(cps >= bins_before_cp) & (cps <= len(act_rate) - bins_after_cp)]
+
+    return beast_result, np.sort(cps)
+
+def bins_and_beast(dates, unit, bin_dur, multiplicator):
+    start_date = dates.min()
+    end_date = dates.max()
+
+    valid_units = ['hours', 'days']
+    if unit not in valid_units:
+        unit = 'days'
+        bin_dur = 15
+    if (end_date - start_date) < 15 and unit == 'days':
+        unit = 'hours'
+        bin_dur = 12
+
+    bin_edges = [end_date]
+    while bin_edges[-1] > start_date:
+        bin_edges.append(bin_edges[-1] - (bin_dur / multiplicator))
+    bin_edges = bin_edges[::-1]
+
+    #-------Drop first bin or keep it if >80% of set duration------
+    first_width_days = bin_edges[1] - start_date
+    first_width_units = first_width_days * multiplicator
+
+    if first_width_units >= 0.8 * bin_dur:
+        bin_edges[0] = start_date  # edge of first bin is at data start
+    else:
+        bin_edges = bin_edges[1:]  # drop bin 0 (and its events)
+    
+    #------------Error if remaining bins are fewer than 2------------
+    if len(bin_edges) < 2:
+        raise ValueError(
+            f"Not enough data to form at least one full bin of duration "
+            f"{bin_dur} {unit}(s) after dropping the partial first bin "
+            f"({first_width_units:.2f} {unit}(s), below the 80% threshold). "
+            f"Try a shorter bin_dur or check your input data range."
+        )
+    
+    bin_edges_dt = [datenum_to_datetime(d) for d in bin_edges]
+    bin_counts, _ = np.histogram(dates, bins=bin_edges)
+
+    act_rate = [count / ((bin_edges[i + 1] - bin_edges[i]) * multiplicator / bin_dur)
+                for i, count in enumerate(bin_counts)]
+
+    out, cps = apply_beast(act_rate)
+
+    if len(cps) > 0:
+        rt, boundaries = calc_rates(act_rate, cps)
+        print(f'Changepoints detected at bins: {cps}')
+    else:
+        rt = []
+        boundaries = []
+        print('-----------------------------------------------------')
+        print('No changepoints detected by BEAST (Zhao et al., 2019)')
+        print('-----------------------------------------------------')
+
+    return act_rate, bin_counts, bin_edges, bin_edges_dt, out, cps, rt, boundaries, bin_dur, unit
 
 
 def main(catalog_file, mc_file, pdf_file, m_file, m_select, mag_label, mc, m_max,
          m_kde_method, xy_select, grid_dim, xy_win_method, rate_select, time_win_duration,
-         forecast_select, custom_rate, forecast_len, time_unit, model, products_string, verbose):
+         forecast_select, custom_rate, forecast_len, time_unit, AOI_extent, model, products_string, verbose):
     """
     Python application that reads an earthquake catalog and performs seismic hazard forecasting.
     Arguments:
@@ -33,6 +288,8 @@ def main(catalog_file, mc_file, pdf_file, m_file, m_select, mag_label, mc, m_max
                     forecasting.
         forecast_len: Length of the forecast for seismic hazard assessment.
         time_unit: Times units for the inputs Time Window Duration, Custom Activity Rate, and Forecast Length.
+        AOI_extent: The forecast geographical area of interest specified as a latitude and longitude range in decimal degrees
+                    in the form [lat_min, lat_max, lon_min, lon_max].
         model: Select from the following ground motion models available. Other models in the Openquake library are
                     available but have not yet been tested.
         products_string: The ground motion intensity types to output. Use a space between names to select more than
@@ -49,26 +306,23 @@ def main(catalog_file, mc_file, pdf_file, m_file, m_select, mag_label, mc, m_max
     import logging
     from base_logger import getDefaultLogger
     from timeit import default_timer as timer
-    from math import ceil, floor, isnan
     import numpy as np
     import dask
     import kalepy as kale
-    import utm
-    from skimage.transform import resize
     import igfash
-    from igfash.io import read_mat_cat, read_mat_m, read_mat_mc, read_mat_pdf, read_csv
+    from igfash.io import read_mat_cat, read_mat_m, read_mat_mc, read_mat_pdf
-    from igfash.window import win_CTL, win_CNE
+    from igfash.window import win_CNE
     import igfash.kde as kde
     from igfash.gm import compute_IMT_exceedance
-    from igfash.compute import get_cdf, hellinger_dist, cols_to_rows
+    from igfash.compute import get_cdf
-    from igfash.rate import lambda_probs, calc_bins, bootstrap_forecast_rolling
-    from igfash.mc import estimate_mc
     import matplotlib.pyplot as plt
     from matplotlib.ticker import MultipleLocator
     from matplotlib.contour import ContourSet
     import xml.etree.ElementTree as ET
     import json
     import multiprocessing as mp
+    import geopandas as gpd
+    import shapely
 
     logger = getDefaultLogger('igfash')
 
@@ -88,8 +342,8 @@ def main(catalog_file, mc_file, pdf_file, m_file, m_select, mag_label, mc, m_max
     else:
         logger.setLevel(logging.INFO)
 
-    exclude_low_fxy = True # skip low probability areas of the map
+    AOI_lat = np.array(AOI_extent[:2]) 
-    thresh_fxy = 1e-3  # minimum fxy value (location PDF) needed to do PGA estimation (to skip low probability areas); also should scale according to number of grid points
+    AOI_lon = np.array(AOI_extent[2:])
     
     # log user selections
     logger.debug(f"User input files\n Catalog: {catalog_file}\n Mc: {mc_file}\n Mag_PDF: {pdf_file}\n Mag: {m_file}")
@@ -98,7 +352,7 @@ def main(catalog_file, mc_file, pdf_file, m_file, m_select, mag_label, mc, m_max
 xy_select: {xy_select}\n grid_dim: {grid_dim}\n xy_win_method: {xy_win_method}\n rate_select: {rate_select}\n time_win_duration: {time_win_duration}\n \
 forecast_select: {forecast_select}\n custom_rate: {custom_rate}\n forecast_len: {forecast_len}\n time_unit: {time_unit}\n model: {model}\n products: {products_string}\n \
 verbose: {verbose}")
-
+    logger.debug(f"Area of interest selected by user - Latitude: {AOI_lat}, Longitude: {AOI_lon}")
     # print key package version numbers
     logger.debug(f"Python version {sys.version}")
     logger.debug(f"Numpy version {version('numpy')}")
@@ -207,44 +461,65 @@ verbose: {verbose}")
 
         time, mag, lat, lon, depth = read_mat_cat(catalog_file)
 
-        # convert to UTM
+        # Create a GeoDataFrame for the catalog data (initially WGS84 EPSG:4326)
-        u = utm.from_latlon(lat, lon)
+        catalog_gdf = gpd.GeoDataFrame(
-        x = u[0]
+            {'depth': depth, 'time': time},
-        y = u[1]
+            geometry=gpd.points_from_xy(lon, lat),
-        utm_zone_number = u[2]
+            crs="EPSG:4326"
-        utm_zone_letter = u[3]
+        )
-        logger.debug(f"Latitude / Longitude coordinates correspond to UTM zone {utm_zone_number}{utm_zone_letter}")
 
-        # define corners of grid based on global dataset
+        utm_crs = catalog_gdf.estimate_utm_crs() # Find the UTM EPSG code for this location                
-        x_min = x.min()
+        catalog_gdf_utm = catalog_gdf.to_crs(utm_crs) # Convert the catalog entirely to UTM meters
-        y_min = y.min()
+        logger.debug(f"Latitude / Longitude event coordinates converted to UTM zone {utm_crs}")
-        x_max = x.max()
-        y_max = y.max()
         
-        grid_x_max = int(ceil(x_max / grid_dim) * grid_dim)
+        # Extract event coordinates directly from the vector geometry
-        grid_x_min = int(floor(x_min / grid_dim) * grid_dim)
+        x = catalog_gdf_utm.geometry.x.values
-        grid_y_max = int(ceil(y_max / grid_dim) * grid_dim)
+        y = catalog_gdf_utm.geometry.y.values
-        grid_y_min = int(floor(y_min / grid_dim) * grid_dim)
 
-        grid_lat_max, grid_lon_max = utm.to_latlon(grid_x_max, grid_y_max, utm_zone_number, utm_zone_letter)
+        # Handle Area of Interest (AOI)
-        grid_lat_min, grid_lon_min = utm.to_latlon(grid_x_min, grid_y_min, utm_zone_number, utm_zone_letter)
+        if (None not in AOI_lat) and (None not in AOI_lon):
+            use_AOI = True
             
-        # rectangular grid
+            # Create an AOI GeoDataFrame and project it to the same UTM CRS
-        nx = int((grid_x_max - grid_x_min) / grid_dim) + 1
+            aoi_gdf_utm = gpd.GeoDataFrame(
-        ny = int((grid_y_max - grid_y_min) / grid_dim) + 1
+                geometry=gpd.points_from_xy(AOI_lon, AOI_lat),
+                crs="EPSG:4326"
+            ).to_crs(utm_crs)
                         
-        # ensure a square grid is used
+            # Combine dataframes to extract the collective bounding box limits
-        if nx > ny:  # enlarge y dimension to match x
+            combined_gdf = gpd.GeoDataFrame(geometry=gpd.pd.concat([catalog_gdf_utm.geometry, aoi_gdf_utm.geometry]))
-            ny = nx
+            x_min, y_min, x_max, y_max = combined_gdf.total_bounds    
-            grid_y_max = int(grid_y_min + (ny - 1) * grid_dim)
+        else:
+            use_AOI = False
+            x_min, y_min, x_max, y_max = catalog_gdf_utm.total_bounds
 
-        else:  # enlarge x dimension to match y
+        # round up grid dimensions 
-            nx = ny
+        grid_x_min = (x_min // grid_dim) * grid_dim
-            grid_x_max = int(grid_x_min + (nx - 1) * grid_dim)
+        grid_x_max = ((x_max + grid_dim - 1) // grid_dim) * grid_dim
+        grid_y_min = (y_min // grid_dim) * grid_dim
+        grid_y_max = ((y_max + grid_dim - 1) // grid_dim) * grid_dim
         
-        # new x and y range
+        # expand extent until it is square
-        x_range = np.linspace(grid_x_min, grid_x_max, nx)
+        ext_w, ext_h = grid_x_max - grid_x_min, grid_y_max - grid_y_min
-        y_range = np.linspace(grid_y_min, grid_y_max, ny)
+        delta = abs(ext_w - ext_h) / 2
+        
+        # Shift the shorter axis outward symmetrically
+        grid_x_min, grid_x_max = (grid_x_min - delta, grid_x_max + delta) if ext_w < ext_h else (grid_x_min, grid_x_max)
+        grid_y_min, grid_y_max = (grid_y_min - delta, grid_y_max + delta) if ext_h < ext_w else (grid_y_min, grid_y_max)
+        
+        # make grid points
+        x_range = np.arange(grid_x_min, grid_x_max + grid_dim, grid_dim)
+        nx = len(x_range)
+        y_range = np.arange(grid_y_min, grid_y_max + grid_dim, grid_dim)
+        ny = len(y_range)
+
+        X, Y = np.meshgrid(x_range, y_range)
+        cells = shapely.box(X, Y, X + grid_dim, Y + grid_dim)
+        grid_gdf_utm = gpd.GeoDataFrame(geometry=cells.flatten(), crs=utm_crs)
+        grid_gdf_latlon = grid_gdf_utm.to_crs("EPSG:4326")
+
+        logger.debug(f"Grid extent in UTM XY {grid_gdf_utm.total_bounds}")
+        logger.debug(f"Grid extent in lat lon {grid_gdf_latlon.total_bounds}")
                 
         t_windowed = time
         r_windowed = [[x, y]]
@@ -268,6 +543,7 @@ verbose: {verbose}")
 
         xy_kale = output_kale[0]
         xy_kde = output_kde[0]
+        grid_gdf_latlon['location_PDF'] = xy_kde[0].flatten() # insert location PDF as a column of the latlon GDF
         
         # plot location PDF
         xy_kale_km = type(xy_kale)(xy_kale.dataset / 1000)
@@ -321,9 +597,12 @@ verbose: {verbose}")
     elif rate_select:
         logger.info(f"Activity rate modeling selected")
                 
-        time, mag_dummy, lat_dummy, lon_dummy, depth_dummy = read_mat_cat(catalog_file, output_datenum=True)
+        datenum_data, mag_data, lat_dummy, lon_dummy, depth_dummy = read_mat_cat(catalog_file, mag_label=mag_label, output_datenum=True)
 
-        datenum_data = time  # REMEMBER THE DECIMAL DENOTES DAYS
+        if trim_to_mc:
+            indices = np.argwhere(mag_data < mc)
+            mag_data = np.delete(mag_data, indices)
+            datenum_data = np.delete(datenum_data, indices)
         
         if time_unit == 'hours':
             multiplicator = 24
@@ -340,32 +619,46 @@ verbose: {verbose}")
             logger.error(msg)
             raise Exception(msg)
 
-        # Selects dates in datenum format and procceeds to forecast value
+        #-----------data are sorted in case they were not-----------------
-        start_date = datenum_data[-1] - (2 * time_win_duration / multiplicator)
+        sorted_pairs = sorted(zip(datenum_data, mag_data), key=lambda x: x[0])
-        dates_calc = [date for date in datenum_data if start_date <= date <= datenum_data[-1]]
+        datenum_data, mag_data = map(list, zip(*sorted_pairs))
-        forecasts, bca_conf95, rate_mean = bootstrap_forecast_rolling(dates_calc, multiplicator)
 
-        # FINAL VALUES OF RATE AND ITS UNCERTAINTY IN THE 5-95 PERCENTILE
+        #-------split the data into bins and apply BEAST for changepoint detection--------------------
-        unc_bca05 = [ci.low for ci in bca_conf95];
+        act_rate, bin_counts, bin_edges, bin_edges_dt, out, cps, rt, boundaries, bin_dur, time_unit = bins_and_beast(
-        unc_bca95 = [ci.high for ci in bca_conf95]
+            np.array(datenum_data), time_unit, time_win_duration, multiplicator)
-        rate_unc_high = multiplicator / np.array(unc_bca05);
-        rate_unc_low = multiplicator / np.array(unc_bca95);
-        rate_forecast = multiplicator / np.median(forecasts)  # [per time unit]
         
-        # Plot of forecasted activity rate with previous binned activity rate
+        #------Forecasted rate is taken from BEAST or is equal to last value if no changepoints detected-----
-        act_rate, bin_counts, bin_edges, out, pprs, rt, idx, u_e = calc_bins(np.array(datenum_data), time_unit,
+        if len(cps) > 0:
-                                                                             time_win_duration, dates_calc,
+            rate_forecast = rt[-1]
+            last_cp_bin = int(cps[-1])
+        else:
+            rate_forecast = act_rate[-1]
+            last_cp_bin = len(act_rate) - 1
+
+        last_cp_datenum = bin_edges[last_cp_bin]
+        dates_calc = [date for date in datenum_data if last_cp_datenum <= date <= datenum_data[-1]]
+        interevent_times = np.diff(dates_calc)
+
+        #------------Use BCa for uncertainty intervals-----------------
+        forecast, bca_conf95 = bootstrap_forecast(interevent_times)
+        rate_unc_high = bin_dur / (bca_conf95.low * multiplicator)
+        rate_unc_low = bin_dur / (bca_conf95.high * multiplicator)
+
+        #----------------------Plot------------------------------------
+        plot_results(act_rate, bin_edges, bin_edges_dt, rt, boundaries,
+                      bin_dur, time_unit, multiplicator,
                       rate_forecast, rate_unc_high, rate_unc_low,
-                                                                             multiplicator, quiet=True, figsize=(14,9))
+                      datenum_data, mag_data)
 
-        # Assign probabilities 
+        logger.info("\n----------------- Forecast Summary -----------------")
-        lambdas, lambdas_perc = lambda_probs(act_rate, dates_calc, bin_edges)
+        logger.info(f"Forecasted activity rate (next {bin_dur} {time_unit}(s)): {rate_forecast:.4f}")
-        lambdas = np.array(lambdas, dtype='d')
+        logger.info(f"95% BCa confidence interval: [{rate_unc_low:.4f}, {rate_unc_high:.4f}]")
-        lambdas_perc = np.array(lambdas_perc, dtype='d')
+        logger.info("------------------------------------------------------")
         
-        # print("Forecasted activity rates: ", lambdas, "events per", time_unit[:-1])
+        lambdas = np.array([rate_forecast/bin_dur], dtype='d')
-        logger.info(f"Forecasted activity rates: {lambdas} events per {time_unit} with percentages {lambdas_perc}")
+        lambdas_perc = np.array([1], dtype='d')
-        np.savetxt('activity_rate.csv', np.vstack((lambdas, lambdas_perc)).T, header="lambda, percentage",
+        
+        np.savetxt('activity_rate.csv', lambdas, header=f"Activity Rate (Events per {time_unit[:-1]})",
                    delimiter=',', fmt='%1.4f')
 
     if forecast_select:
@@ -392,7 +685,7 @@ verbose: {verbose}")
             logger.error(msg)
             raise Exception(msg)
         
-        if lambdas[0] == None:
+        if lambdas == None:
             msg = "Activity rate modeling was not selected and custom activity rate was not provided; cannot continue..."
             logger.error(msg)
             raise Exception(msg)
@@ -407,52 +700,41 @@ verbose: {verbose}")
 
         m_cdf = get_cdf(m_pdf)
 
-        fxy = xy_kde[0]
+        centroids_utm = grid_gdf_utm.geometry.centroid.values #extract the centroid of each cell
-        logger.debug(f"Normalization check; sum of all f(x,y) values = {np.sum(fxy)}")
+        num_points = len(grid_gdf_utm)
 
-        xx, yy = np.meshgrid(x_range, y_range, indexing='ij')  # grid points
+        distances = np.array([shapely.distance(centroids_utm[i], centroids_utm) for i in range(num_points)]) #compute distance between every grid point
+        grid_gdf_latlon['distance_matrix'] = [distances[i] for i in range(num_points)] #store the distance matrix in the GDF
 
-        # set every grid point to be a receiver
+        # Select only cells of the grid that are inside the AOI
-        x_rx = xx.flatten()
+        if use_AOI:
-        y_rx = yy.flatten()
+            centroids_latlon = grid_gdf_latlon.geometry.centroid
             
-        # compute distance matrix for each receiver
+            # Mark grid cells that are within the AOI using vectorized boundary checks
-        distances = np.zeros(shape=(nx * ny, nx, ny))
+            grid_gdf_latlon['AOI'] = (
-        rx_lat = np.zeros(nx * ny)
+                (centroids_latlon.x >= AOI_lon[0]) & (centroids_latlon.x <= AOI_lon[1]) &
-        rx_lon = np.zeros(nx * ny)
+                (centroids_latlon.y >= AOI_lat[0]) & (centroids_latlon.y <= AOI_lat[1])
+            )                               
+        else:
+            grid_gdf_latlon['AOI']=True #set entire grid to be the area of interest
 
-        for i in range(nx * ny):
+        distances_sel = grid_gdf_latlon.loc[grid_gdf_latlon['AOI']]['distance_matrix'].to_numpy()
-            # Compute the squared distances directly using NumPy's vectorized operations
+        centroids_sel = grid_gdf_latlon.loc[grid_gdf_latlon['AOI']].centroid
-            squared_distances = (xx - x_rx[i]) ** 2 + (yy - y_rx[i]) ** 2
-            distances[i] = np.sqrt(squared_distances)
         
-            # create context object for receiver and append to list
+        loc_pdf = grid_gdf_latlon['location_PDF'].to_numpy() # extract the previously created location PDF from the GDF 
-            rx_lat[i], rx_lon[i] = utm.to_latlon(x_rx[i], y_rx[i], utm_zone_number,
-                                                 utm_zone_letter)  # get receiver location as lat,lon
        
         # convert distances from m to km because openquake ground motion models take input distances in kilometres
-        distances = distances/1000.0
+        #distances_sel = distances_sel/1000.0
-
-        # compute ground motion only at grid points that have minimum probability density of thresh_fxy
-        if exclude_low_fxy:
-            indices = list(np.where(fxy.flatten() > thresh_fxy)[0])
-        else:
-            indices = range(0, len(distances))
-
-        fr = fxy.flatten()
 
         # For each receiver compute estimated ground motion values
-        logger.info(f"Estimating ground motion intensity at {len(indices)} grid points...")
+        logger.info(f"Estimating ground motion intensity at {len(distances_sel)} grid points...")
-
-        PGA = np.zeros(shape=(nx * ny))
-
-        start = timer()
 
         use_pp = True
         
+        start = timer()
         if use_pp:         # use dask parallel computing
             mp.set_start_method("fork", force=True)
-            iter = indices
+            iter = range(0,len(distances_sel))
             iml_grid_raw = []  # raw ground motion grids
             for imt in products:
                 logger.info(f"Estimating {imt}")
@@ -462,7 +744,7 @@ verbose: {verbose}")
                 else:
                     IMT_max = 2.0 # search interval max for acceleration (g)
 
-                imls = [dask.delayed(compute_IMT_exceedance)(rx_lat[i], rx_lon[i], distances[i].flatten(), fr, p, lambdas,
+                imls = [dask.delayed(compute_IMT_exceedance)(centroids_sel.iloc[i].y, centroids_sel.iloc[i].x, distances_sel[i].flatten(), loc_pdf, p, lambdas,
                                                             forecast_len, lambdas_perc, m_range, m_pdf, m_cdf, model,
                                                             log_level=logging.DEBUG, imt=imt, IMT_min=0.0, IMT_max=IMT_max, rx_label=i,
                                                             rtol=0.1, use_cython=True) for i in iter]
@@ -471,9 +753,9 @@ verbose: {verbose}")
 
         else:
             iml_grid_raw = []
-            iter = indices
+            iter = range(0,len(distances_sel))
-            for imt in products:
             
+            for imt in products:
                 if imt == "PGV":
                     IMT_max = 200 # search interval max for velocity (cm/s)
                 else:
@@ -481,7 +763,7 @@ verbose: {verbose}")
 
                 iml = []
                 for i in iter:
-                    iml_i = compute_IMT_exceedance(rx_lat[i], rx_lon[i], distances[i].flatten(), fr, p, lambdas, forecast_len, 
+                    iml_i = compute_IMT_exceedance(centroids_sel.iloc[i].y, centroids_sel.iloc[i].x, distances_sel[i].flatten(), loc_pdf, p, lambdas, forecast_len, 
                                                     lambdas_perc, m_range, m_pdf, m_cdf, model, imt=imt, IMT_min = 0.0,
                                                     IMT_max = IMT_max, rx_label = i, rtol = 0.1, use_cython=True)
                     iml.append(iml_i)
@@ -491,71 +773,51 @@ verbose: {verbose}")
         end = timer()
         logger.info(f"Ground motion exceedance computation time: {round(end - start, 1)} seconds")
 
+        
+        
         if np.isnan(iml_grid_raw).all():
             msg = "No valid ground motion intensity measures were forecasted. Try a different ground motion model."
             logger.error(msg)
             raise Exception(msg)
         
-        # create list of one empty list for each imt
+        for j, imt in enumerate(products): #generate image overlay for each IMT product
-        iml_grid = [[] for _ in range(len(products))]  # final ground motion grids
+            logger.debug(f"{products[j]} values: {iml_grid_raw[j]}")
-        iml_grid_prep = iml_grid.copy()  # temp ground motion grids
+            grid_gdf_latlon.loc[grid_gdf_latlon['AOI'], imt] = iml_grid_raw[j] # insert computed imt grid into GDF
 
-        if exclude_low_fxy:
+            grid_gdf_latlon_clean = grid_gdf_latlon.dropna(subset=[imt]) # remove null values from grid
-            for i in range(0, len(distances)):
-                if i in indices:
-                    for j in range(0, len(products)):
-                        iml_grid_prep[j].append(iml_grid_raw[j].pop(0))
-                else:
-                    list(map(lambda lst: lst.append(np.nan),
-                             iml_grid_prep))  # use np.nan to indicate grid point excluded
-        else:
-            iml_grid_prep = iml_grid_raw
 
-        for j in range(0, len(products)):
+            x_plot = grid_gdf_latlon_clean.geometry.centroid.x.values
-            vmin = min(x for x in iml_grid_prep[j] if x is not np.nan)
+            y_plot = grid_gdf_latlon_clean.geometry.centroid.y.values
-            vmax = max(x for x in iml_grid_prep[j] if x is not np.nan)
+            z_plot = grid_gdf_latlon_clean[imt].values
-            iml_grid[j] = np.reshape(iml_grid_prep[j], (nx, ny)).astype(
-                dtype=np.float64)  # this reduces values to 8 decimal places
-            iml_grid_tmp = np.nan_to_num(iml_grid[j])  # change nans to zeroes
 
-            # upscale the grid, trim, and interpolate if there are at least 10 grid values with range greater than 0.1
+            vmin = np.nanmin(z_plot)
-            if np.count_nonzero(iml_grid_tmp) >= 10 and vmax-vmin > 0.1:
+            vmax = np.nanmax(z_plot)
-                up_factor = 4
-                iml_grid_hd = resize(iml_grid_tmp, (up_factor * len(iml_grid_tmp), up_factor * len(iml_grid_tmp)),
-                                    mode='reflect', anti_aliasing=False)
-                trim_thresh = vmin
-                iml_grid_hd[iml_grid_hd < trim_thresh] = np.nan
-            else:
-                iml_grid_hd = iml_grid_tmp
             
-            iml_grid_hd[iml_grid_hd == 0.0] = np.nan  # change zeroes back to nan
+            # Generate Image Overlay
-
+            fig, ax = plt.subplots()
-            #vmin_hd = min(x for x in iml_grid_hd.flatten() if not isnan(x))
+            contour = ax.tricontourf(
-            vmax_hd = max(x for x in iml_grid_hd.flatten() if not isnan(x))
+                x_plot, 
-
+                y_plot, 
-            # generate image overlay
+                z_plot, 
-            north, south = lat.max(), lat.min()  # Latitude range
+                levels=200, #linear scale 
-            east, west = lon.max(), lon.min()  # Longitude range
+                cmap="YlOrRd",
-            bounds = [[south, west], [north, east]]
+            )
-
+            ax.set_aspect('equal') # keep geographic coordinates from stretching
-            map_center = [np.mean([north, south]), np.mean([east, west])]
+            ax.set_axis_off()
-
+            fig.patch.set_visible(False); ax.patch.set_visible(False)
-            # Create an image from the grid
-            cmap_name = 'YlOrRd'
-            cmap = plt.get_cmap(cmap_name)
-            fig, ax = plt.subplots(figsize=(6, 6))
-            ax.imshow(iml_grid_hd, origin='lower', cmap=cmap, vmin=vmin, vmax=vmax, interpolation='bilinear')
-            ax.axis('off')
-
-            # Save the figure
-            fig.canvas.draw()
             overlay_filename = f"overlay_{j}.svg"
-            plt.savefig(overlay_filename, bbox_inches="tight", pad_inches=0, transparent=True)
+            plt.savefig(overlay_filename, pad_inches=0, bbox_inches="tight", transparent=True)
             plt.close(fig)
 
+            # set image map extent in geographic coordinates
+            north = grid_gdf_latlon[grid_gdf_latlon['AOI']].total_bounds[3]
+            south = grid_gdf_latlon[grid_gdf_latlon['AOI']].total_bounds[1]
+            east = grid_gdf_latlon[grid_gdf_latlon['AOI']].total_bounds[2]
+            west = grid_gdf_latlon[grid_gdf_latlon['AOI']].total_bounds[0]
+                       
             # Embed geographic bounding box into the SVG
             map_bounds = dict(zip(("south", "west", "north", "east"),
-                            map(float, (grid_lat_min, grid_lon_min, grid_lat_max, grid_lon_max))))
+                            map(float, (south, west, north, east))))
             tree = ET.parse(overlay_filename)
             tree.getroot().set("data-map-bounds", json.dumps(map_bounds))
             tree.write(overlay_filename, encoding="utf-8", xml_declaration=True)
@@ -569,17 +831,17 @@ verbose: {verbose}")
             gradient = np.vstack((gradient, gradient)).T
             gradient = np.tile(gradient, (1, width))
 
-            colorbar_title = products[j]
+            colorbar_title = imt
             if "PGA" in colorbar_title or "SA" in colorbar_title:
                 colorbar_title = colorbar_title + "  (g)"
 
             fig, ax = plt.subplots(figsize=((width + 40) / 100.0, (height + 20) / 100.0),
                                    dpi=100)  # Increase fig size for labels
             ax.imshow(gradient, aspect='auto', cmap=cmap.reversed(),
-                      extent=[0, 1, vmin, vmax_hd])  # Note: extent order is different for vertical
+                      extent=[0, 1, vmin, vmax])  # Note: extent order is different for vertical
             ax.set_xticks([])  # Remove x-ticks for vertical colorbar
             num_ticks = 11  # Show more ticks
-            tick_positions = np.linspace(vmin, vmax_hd, num_ticks)
+            tick_positions = np.linspace(vmin, vmax, num_ticks)
             ax.set_yticks(tick_positions)
             ax.set_yticklabels([f"{tick:.2f}" for tick in tick_positions])  # format tick labels
             ax.set_title(colorbar_title, loc='right', pad=15) 

src/shf_wrapper.py

@@ -32,6 +32,9 @@ def main(argv):
         else:
             raise argparse.ArgumentTypeError("Boolean value expected.")
         
+    def float_or_none(v):
+        return None if v.lower() == "none" else float(v)
+
     parser = argparse.ArgumentParser()
 
     parser.add_argument("catalog_file", help="Path to input file of type 'catalog'")
@@ -55,6 +58,7 @@ def main(argv):
     parser.add_argument("--time_unit", type=str)
     parser.add_argument("--model", type=str)
     parser.add_argument("--products_string", type=str)
+    parser.add_argument("--AOI_extent", nargs=4, type=float_or_none, default=[None] * 4, required=False)
     parser.add_argument("--verbose", type=str2bool)
 
     args = parser.parse_args()