section plot updated

Gradio_app.ipynb

@@ -2,178 +2,27 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Inventory created at 2023-03-31T20:48:41.380800Z\n",
-      "\tCreated by: IRIS WEB SERVICE: fdsnws-station | version: 1.1.52\n",
-      "\t\t    http://service.iris.edu/fdsnws/station/1/query?starttime=2019-07-...\n",
-      "\tSending institution: IRIS-DMC (IRIS-DMC)\n",
-      "\tContains:\n",
-      "\t\tNetworks (7):\n",
-      "\t\t\t8P, CI, LB, NN, NP, PB, SY\n",
-      "\t\tStations (85):\n",
-      "\t\t\t8P.CAU08 (Monache Meadows, CA, USA)\n",
-      "\t\t\tCI.APL (Apollo)\n",
-      "\t\t\tCI.CCA (California City Airport)\n",
-      "\t\t\tCI.CCC (Christmas Canyon China Lake)\n",
-      "\t\t\tCI.CGO (Cerro Gordo)\n",
-      "\t\t\tCI.CLC (China Lake)\n",
-      "\t\t\tCI.CWC (Cottonwood Creek)\n",
-      "\t\t\tCI.DAW (Darwin)\n",
-      "\t\t\tCI.DTP (Desert Tortoise Park)\n",
-      "\t\t\tCI.GSC (Goldstone)\n",
-      "\t\t\tCI.HAR (Harper Dry Lake bed)\n",
-      "\t\t\tCI.ISA (Isabella)\n",
-      "\t\t\tCI.JRC2 (Joshua Ridge: China Lake)\n",
-      "\t\t\tCI.LMR2 (Leuhmann Ridge Extension)\n",
-      "\t\t\tCI.LRL (Laurel Mtn)\n",
-      "\t\t\tCI.MPM (Manuel Prospect Mine)\n",
-      "\t\t\tCI.MRS (Mars)\n",
-      "\t\t\tCI.Q0068 (Redwood Blvd, California City CA)\n",
-      "\t\t\tCI.Q0072 (Lakeland Street, Ridgecrest CA)\n",
-      "\t\t\tCI.SLA (Slate Mountain)\n",
-      "\t\t\tCI.SRT (Snort)\n",
-      "\t\t\tCI.TEH (Cattani Ranch)\n",
-      "\t\t\tCI.TOW2 (Tower 2)\n",
-      "\t\t\tCI.WAS2 (Alta Sierra 2)\n",
-      "\t\t\tCI.WBM (Bowman Road)\n",
-      "\t\t\tCI.WBS (Bird Springs)\n",
-      "\t\t\tCI.WCS2 (Coso Hot Springs 2)\n",
-      "\t\t\tCI.WHF (Hanning Flat)\n",
-      "\t\t\tCI.WLH2 (Little Horse 2)\n",
-      "\t\t\tCI.WMF (Mccloud Flat)\n",
-      "\t\t\tCI.WNM (Nine Mile Canyon)\n",
-      "\t\t\tCI.WOR (Onyx Ranch)\n",
-      "\t\t\tCI.WRC2 (Renegade Canyon)\n",
-      "\t\t\tCI.WRV2 (Rose Valley Canyon 2)\n",
-      "\t\t\tCI.WVP2 (Volcano Peak 2)\n",
-      "\t\t\tLB.DAC (Inyo County, Darwin, CA, USA)\n",
-      "\t\t\tNN.GWY (Greenwater Valley, CA. (GPS 12/06/2000) w84gm)\n",
-      "\t\t\tNN.PAN (Panamint Range. (GPS 12/06/2000) w84gm)\n",
-      "\t\t\tNN.QSM (Queen of Sheba Mine, CA. (GPS 01/17/2001)   w84gm)\n",
-      "\t\t\tNP.1035 (CA:Lake Isabella Dam)\n",
-      "\t\t\tNP.1809 (CA:Haiwee Rsvr;Pump Pl)\n",
-      "\t\t\tNP.5419 (CA:China Lake;Nav Weapon Ctr)\n",
-      "\t\t\tPB.B916 (marips916bcs2008, China Lake, CA, USA)\n",
-      "\t\t\tPB.B917 (tonyso917bcs2008, China Lake, CA, USA)\n",
-      "\t\t\tPB.B918 (mtsprn918bcs2008, China Lake, CA, USA)\n",
-      "\t\t\tPB.B921 (randsb921bcs2008, China Lake, CA, USA)\n",
-      "\t\t\tSY.CCA (CCA synthetic)\n",
-      "\t\t\tSY.CCC (CCC synthetic)\n",
-      "\t\t\tSY.CGO (CGO synthetic)\n",
-      "\t\t\tSY.CLC (CLC synthetic)\n",
-      "\t\t\tSY.CWC (CWC synthetic)\n",
-      "\t\t\tSY.DAC (DAC synthetic)\n",
-      "\t\t\tSY.DAW (DAW synthetic)\n",
-      "\t\t\tSY.DTP (DTP synthetic)\n",
-      "\t\t\tSY.FPC (FPC synthetic)\n",
-      "\t\t\tSY.FSR (FSR synthetic)\n",
-      "\t\t\tSY.GPO (GPO synthetic)\n",
-      "\t\t\tSY.GSC (GSC synthetic)\n",
-      "\t\t\tSY.HAR (HAR synthetic)\n",
-      "\t\t\tSY.ISA (ISA synthetic)\n",
-      "\t\t\tSY.JRC (JRC synthetic)\n",
-      "\t\t\tSY.JRC2 (JRC2 synthetic)\n",
-      "\t\t\tSY.KRV3 (KRV3 synthetic)\n",
-      "\t\t\tSY.LMR (LMR synthetic)\n",
-      "\t\t\tSY.LMR2 (LMR2 synthetic)\n",
-      "\t\t\tSY.LRL (LRL synthetic)\n",
-      "\t\t\tSY.MPM (MPM synthetic)\n",
-      "\t\t\tSY.OVRO (OVRO synthetic)\n",
-      "\t\t\tSY.RRC (RRC synthetic)\n",
-      "\t\t\tSY.SEV (SEV synthetic)\n",
-      "\t\t\tSY.SLA (SLA synthetic)\n",
-      "\t\t\tSY.SRT (SRT synthetic)\n",
-      "\t\t\tSY.TEH (TEH synthetic)\n",
-      "\t\t\tSY.TOW2 (TOW2 synthetic)\n",
-      "\t\t\tSY.WAS2 (WAS2 synthetic)\n",
-      "\t\t\tSY.WBM (WBM synthetic)\n",
-      "\t\t\tSY.WBP (WBP synthetic)\n",
-      "\t\t\tSY.WBS (WBS synthetic)\n",
-      "\t\t\tSY.WCS2 (WCS2 synthetic)\n",
-      "\t\t\tSY.WHF (WHF synthetic)\n",
-      "\t\t\tSY.WLH2 (WLH2 synthetic)\n",
-      "\t\t\tSY.WMF (WMF synthetic)\n",
-      "\t\t\tSY.WNM (WNM synthetic)\n",
-      "\t\t\tSY.WOR (WOR synthetic)\n",
-      "\t\t\tSY.WRC2 (WRC2 synthetic)\n",
-      "\t\tChannels (0):\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "import obspy\n",
-    "from obspy.clients.fdsn import Client\n",
-    "\n",
-    "client_name = 'SCEDC'\n",
-    "radius_km = 100\n",
-    "timestamp = '2019-07-04 17:33:49'\n",
-    "eq_lat = 35.766\n",
-    "eq_lon = -117.605\n",
-    "\n",
-    "origin_time = obspy.UTCDateTime(timestamp)\n",
-    "\n",
-    "client = Client(\"IRIS\")\n",
-    "inventory = client.get_stations(network=\"*\", station=\"*\", channel=\"*\",\n",
-    "                                starttime=origin_time, endtime=origin_time + 120,\n",
-    "                                latitude=eq_lat, longitude=eq_lon, maxradius=radius_km/111.2)\n",
-    "print(inventory)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "\n",
-    "client = Client(client_name)\n",
-    "window = radius_km / 111.2\n",
-    "\n",
-    "assert eq_lat - window > -90 and eq_lat + window < 90, \"Latitude out of bounds\"\n",
-    "assert eq_lon - window > -180 and eq_lon + window < 180, \"Longitude out of bounds\"\n",
-    "\n",
-    "starttime = obspy.UTCDateTime(timestamp)\n",
-    "endtime = starttime + 120\n",
-    "\n",
-    "inv = client.get_stations(network=\"*\", station=\"*\", location=\"*\", channel=\"*H*\", \n",
-    "                        starttime=starttime, endtime=endtime, \n",
-    "                        minlatitude=(eq_lat-window), maxlatitude=(eq_lat+window),\n",
-    "                        minlongitude=(eq_lon-window), maxlongitude=(eq_lon+window), \n",
-    "                        level='station')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 't0s' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[75], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mpandas\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mpd\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m pd\u001b[39m.\u001b[39mdate_range(start\u001b[39m=\u001b[39mt0s[i], periods\u001b[39m=\u001b[39mwaveforms[i][\u001b[39m0\u001b[39m]\u001b[39m.\u001b[39mshape[\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m], freq\u001b[39m=\u001b[39m\u001b[39m'\u001b[39m\u001b[39m1s\u001b[39m\u001b[39m'\u001b[39m)\n",
-      "\u001b[0;31mNameError\u001b[0m: name 't0s' is not defined"
-     ]
+     "data": {
+      "text/plain": [
+       "'hi!'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "import pandas as pd\n"
+    "'hi!'"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 114,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -188,7 +37,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7935\n",
+      "Running on local URL:  http://127.0.0.1:7862\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -196,7 +45,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7935/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7862/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -209,7 +58,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 114,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -238,6 +87,8 @@
     "import matplotlib.pyplot as plt\n",
     "import matplotlib.dates as mdates\n",
     "\n",
+    "from glob import glob\n",
+    "\n",
     "def make_prediction(waveform):\n",
     "    waveform = np.load(waveform)\n",
     "    processed_input = prepare_waveform(waveform)\n",
@@ -297,6 +148,15 @@
     "    plt.close(fig)\n",
     "    return image\n",
     "\n",
+    "def variance_coefficient(residuals):\n",
+    "    # calculate the variance of the residuals\n",
+    "    var = residuals.var()\n",
+    "    \n",
+    "    # scale the variance to a coefficient between 0 and 1\n",
+    "    coeff = 1 - (var / (residuals.max() - residuals.min()))\n",
+    "    \n",
+    "    return coeff\n",
+    "\n",
     "def predict_on_section(client_name, timestamp, eq_lat, eq_lon, radius_km, source_depth_km, velocity_model):\n",
     "    distances, t0s, st_lats, st_lons, waveforms = [], [], [], [], []\n",
     "    \n",
@@ -318,6 +178,8 @@
     "                          level='station')\n",
     "    \n",
     "    waveforms = []\n",
+    "    cached_waveforms = glob(\"data/cached/*.mseed\")\n",
+    "\n",
     "    for network in inv:\n",
     "        for station in network:\n",
     "            try:\n",
@@ -332,8 +194,12 @@
     "                    starttime = obspy.UTCDateTime(timestamp) + arrivals[0].time - 15\n",
     "                    endtime = starttime + 60\n",
     "\n",
-    "                    waveform = client.get_waveforms(network=network.code, station=station.code, location=\"*\", channel=\"*\", \n",
-    "                                                starttime=starttime, endtime=endtime)\n",
+    "                    if f\"data/cached/{network.code}_{station.code}_{starttime}.mseed\" not in cached_waveforms:\n",
+    "                        waveform = client.get_waveforms(network=network.code, station=station.code, location=\"*\", channel=\"*\", \n",
+    "                                                    starttime=starttime, endtime=endtime)\n",
+    "                        waveform.write(f\"data/cached/{network.code}_{station.code}_{starttime}.mseed\", format=\"MSEED\")\n",
+    "                    else:\n",
+    "                        waveform = obspy.read(f\"data/cached/{network.code}_{station.code}_{starttime}.mseed\")\n",
     "                    \n",
     "                    waveform = waveform.select(channel=\"H[BH][ZNE]\")\n",
     "                    waveform = waveform.merge(fill_value=0)\n",
@@ -365,29 +231,39 @@
     "    p_phases = output[:, 0]\n",
     "    s_phases = output[:, 1]\n",
     "\n",
-    "    fig, ax = plt.subplots(nrows=1, figsize=(10, 3), sharex=True)\n",
+    "    # Max confidence - min variance     \n",
+    "    p_max_confidence = np.min([p_phases[i::len(waveforms)].std() for i in range(len(waveforms))]) \n",
+    "    s_max_confidence = np.min([s_phases[i::len(waveforms)].std() for i in range(len(waveforms))])\n",
+    "\n",
+    "    fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(10, 3), sharex=True)\n",
     "    for i in range(len(waveforms)):\n",
     "        current_P = p_phases[i::len(waveforms)]\n",
     "        current_S = s_phases[i::len(waveforms)]\n",
+    "\n",
     "        x = [t0s[i] + pd.Timedelta(seconds=k/100) for k in np.linspace(0,6000,6000)]\n",
     "        x = mdates.date2num(x)\n",
-    "        ax.plot(x, waveforms[i][0, 0]+distances[i]*111.2, color='black', alpha=0.5)\n",
-    "        ax.scatter(x[int(current_P.mean()*waveforms[i][0].shape[-1])], waveforms[i][0, 0].mean()+distances[i]*111.2, color='r')\n",
-    "        ax.scatter(x[int(current_S.mean()*waveforms[i][0].shape[-1])], waveforms[i][0, 0].mean()+distances[i]*111.2, color='b')\n",
-    "        ax.set_ylabel('Z')\n",
     "\n",
-    "        ax.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M:%S'))\n",
-    "        ax.xaxis.set_major_locator(mdates.SecondLocator(interval=10))\n",
+    "        # Normalize confidence for the plot\n",
+    "        p_conf = 1/(current_P.std()/p_max_confidence).item()\n",
+    "        s_conf = 1/(current_S.std()/s_max_confidence).item()\n",
     "\n",
-    "        # for a in ax:\n",
-    "        #     a.axvline(current_P.mean()*waveforms[i][0].shape[-1], color='r', linestyle='--', label='P')\n",
-    "        #     a.axvline(current_S.mean()*waveforms[i][0].shape[-1], color='b', linestyle='--', label='S')\n",
+    "        ax[0].plot(x, waveforms[i][0, 0]*10+distances[i]*111.2, color='black', alpha=0.5, lw=1)\n",
     "\n",
-    "        # ax[-1].set_xlabel('Time, samples')\n",
-    "        # ax[-1].set_ylabel('Uncert.')\n",
-    "        # ax[-1].legend()\n",
+    "        ax[0].scatter(x[int(current_P.mean()*waveforms[i][0].shape[-1])], waveforms[i][0, 0].mean()+distances[i]*111.2, color='r', alpha=p_conf, marker='|')\n",
+    "        ax[0].scatter(x[int(current_S.mean()*waveforms[i][0].shape[-1])], waveforms[i][0, 0].mean()+distances[i]*111.2, color='b', alpha=s_conf, marker='|')\n",
+    "        ax[0].set_ylabel('Z')\n",
     "\n",
-    "        plt.subplots_adjust(hspace=0., wspace=0.)\n",
+    "        ax[0].xaxis.set_major_formatter(mdates.DateFormatter('%H:%M:%S'))\n",
+    "        ax[0].xaxis.set_major_locator(mdates.SecondLocator(interval=5))\n",
+    "        \n",
+    "    ax[0].scatter(None, None, color='r', marker='|', label='P')\n",
+    "    ax[0].scatter(None, None, color='b', marker='|', label='S')\n",
+    "    ax[0].legend()\n",
+    "\n",
+    "    ax[1].scatter(st_lats, st_lons, color='b', marker='d', label='Stations')\n",
+    "    ax[1].scatter(eq_lat, eq_lon, color='r', marker='*', label='Earthquake')\n",
+    "    ax[1].legend()\n",
+    "    plt.subplots_adjust(hspace=0., wspace=0.)\n",
     "        \n",
     "    fig.canvas.draw();\n",
     "    image = np.array(fig.canvas.renderer.buffer_rgba())\n",
@@ -401,12 +277,6 @@
     "                                    learning_rate=3e-4)\n",
     "model.eval()\n",
     "\n",
-    "\n",
-    "\n",
-    "# # Create the Gradio interface\n",
-    "# gr.Interface(mark_phases, inputs, outputs, title='PhaseHunter').launch()\n",
-    "\n",
-    "\n",
     "with gr.Blocks() as demo:\n",
     "    gr.Markdown(\"# PhaseHunter\")\n",
     "    gr.Markdown(\"\"\"This app allows one to detect P and S seismic phases along with uncertainty of the detection. \n",
@@ -467,7 +337,9 @@
     "            radius_inputs = gr.Slider(minimum=1, \n",
     "                                    maximum=150, \n",
     "                                    value=50, label=\"Radius (km)\", \n",
-    "                                    info=\"Select the radius around the earthquake to download data from\",\n",
+    "                                    step=10,\n",
+    "                                    info=\"\"\"Select the radius around the earthquake to download data from.\\n \n",
+    "                                    Note that the larger the radius, the longer the app will take to run.\"\"\",\n",
     "                                    interactive=True)\n",
     "            \n",
     "            velocity_inputs = gr.Dropdown(\n",
@@ -480,7 +352,7 @@
     "            \n",
     "            \n",
     "        button = gr.Button(\"Predict phases\")\n",
-    "        outputs_section = gr.outputs.Image(label='Waveforms with Phases Marked', type='numpy')\n",
+    "        outputs_section = gr.Image(label='Waveforms with Phases Marked', type='numpy', interactive=False)\n",
     "        \n",
     "        button.click(predict_on_section, \n",
     "                 inputs=[client_inputs, timestamp_inputs, \n",
@@ -494,41 +366,15 @@
     "        Your waveform should be sampled at 100 sps and have 3 (Z, N, E) or 1 (Z) channels.\n",
     "        \"\"\")\n",
     "\n",
-    "\n",
-    "\n",
     "demo.launch()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "DatetimeIndex(['2019-07-04 17:33:49', '2019-07-04 17:33:50',\n",
-       "               '2019-07-04 17:33:51', '2019-07-04 17:33:52',\n",
-       "               '2019-07-04 17:33:53', '2019-07-04 17:33:54',\n",
-       "               '2019-07-04 17:33:55', '2019-07-04 17:33:56',\n",
-       "               '2019-07-04 17:33:57', '2019-07-04 17:33:58',\n",
-       "               ...\n",
-       "               '2019-07-04 19:13:39', '2019-07-04 19:13:40',\n",
-       "               '2019-07-04 19:13:41', '2019-07-04 19:13:42',\n",
-       "               '2019-07-04 19:13:43', '2019-07-04 19:13:44',\n",
-       "               '2019-07-04 19:13:45', '2019-07-04 19:13:46',\n",
-       "               '2019-07-04 19:13:47', '2019-07-04 19:13:48'],\n",
-       "              dtype='datetime64[ns]', length=6000, freq='S')"
-      ]
-     },
-     "execution_count": 105,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pd.date_range(start=obspy.UTCDateTime(\"2019-07-04 17:33:49\").timestamp*1e9, periods=6000, freq='s')"
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {