{
  "protocol": {
    "honesty": "100% synthetic hydraulic/SCADA simulation (see src/pipelinewatch/simulate.py). Pipeline length (60 km), pressure-wave speed (1.1 km/s), and the friction/pressure relationship are ASSUMED textbook-typical values -- NOT calibrated to any real, named pipeline or customer asset. A real pilot deployment must replace/calibrate these constants against actual SCADA historian data from the specific line before any number below, especially the NPW localization error, is trusted for field use.",
    "n_episodes": 180,
    "n_train_episodes": 126,
    "n_test_episodes": 54,
    "sample_interval_s": 5,
    "severity_bands_pct_of_nominal_flow": {
      "small": [
        1,
        3
      ],
      "medium": [
        3,
        8
      ],
      "large": [
        8,
        20
      ]
    },
    "mass_balance_calibration": {
      "window_samples": 36,
      "persist_windows": 6,
      "k": 3.0,
      "threshold": 1.7525218250941839,
      "note": "mu/sigma/k calibrated on normal-only TRAIN episodes only; detection_rate/false_alarm below is measured on held-out TEST episodes."
    }
  },
  "mass_balance": {
    "small": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 91.25,
      "median_ttd_s": 82.5
    },
    "medium": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 66.25,
      "median_ttd_s": 70.0
    },
    "large": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 52.5,
      "median_ttd_s": 52.5
    },
    "overall": {
      "n_episodes": 24,
      "detection_rate": 1.0,
      "mean_ttd_s": 70.0,
      "median_ttd_s": 67.5
    },
    "false_alarm": {
      "n_normal_episodes": 30,
      "episodes_with_false_alarm_fraction": 0.16666666666666666,
      "mean_false_alarms_per_hour": 0.3557202408522464
    }
  },
  "lstm_ae": {
    "small": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 50.0,
      "median_ttd_s": 52.5
    },
    "medium": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 43.125,
      "median_ttd_s": 42.5
    },
    "large": {
      "n_episodes": 8,
      "detection_rate": 1.0,
      "mean_ttd_s": 30.625,
      "median_ttd_s": 35.0
    },
    "overall": {
      "n_episodes": 24,
      "detection_rate": 1.0,
      "mean_ttd_s": 41.25,
      "median_ttd_s": 40.0
    },
    "false_alarm": {
      "n_normal_episodes": 30,
      "episodes_with_false_alarm_fraction": 0.7,
      "mean_false_alarms_per_hour": 3.8418079096045186
    },
    "training_history": {
      "best_val_mse": 0.03187253326177597,
      "epochs_ran": 25.0
    },
    "threshold": 0.0505700446665287,
    "window_samples": 36
  },
  "npw_localization": {
    "n_localized": 24,
    "mean_abs_error_km": 13.373748620341866,
    "median_abs_error_km": 8.42794804230748,
    "by_severity": {
      "small": {
        "n": 8,
        "mean_abs_error_km": 12.681819882133222,
        "median_abs_error_km": 15.265277817152366
      },
      "medium": {
        "n": 8,
        "mean_abs_error_km": 13.716801975487986,
        "median_abs_error_km": 7.878984101297062
      },
      "large": {
        "n": 8,
        "mean_abs_error_km": 13.722624003404391,
        "median_abs_error_km": 5.783308992666312
      }
    },
    "method": "Cross-correlation of high-pass-filtered inlet/outlet pressure around the detection time; location_km_from_inlet = 0.5*(L + c*dt).",
    "based_on_detector": "mass_balance",
    "caveat": "Best-effort/demo-grade estimator, not a calibrated field system. Accuracy degrades substantially for small leaks (weak signal-to-noise) -- see by_severity breakdown."
  },
  "primary_detector": "mass_balance",
  "primary_detector_rationale": "detection_rate tied (1.00); mass_balance has a lower false-alarm rate (0.36/h vs lstm_ae 3.84/h) on held-out normal test episodes, so it is recommended as the primary/first-line trigger. lstm_ae detects leaks faster on average (lower time-to-detect) and is recommended as a fast corroborating secondary signal, not as the sole trigger, given its higher false-alarm rate on this synthetic data.",
  "published_baselines": [
    {
      "method": "Statistical volume/mass balance LDS (field deployment survey)",
      "finding": "Reported sensitivity/response ranges from a 0.5% leak detected within 5 minutes on a short, well-instrumented segment, down to a 12% leak in 180 minutes on a >400 km large-separation offshore segment (sensitivity is strongly limited by sensor spacing and transient operations, not a single fixed number).",
      "citation": "Atmosi, 'The challenges for effective leak detection on large diameter pipelines' (field deployment case studies). https://www.atmosi.com/us/news-events/blogs/the-challenges-for-effective-leak-detection-on-large-diameter-pipelines/"
    },
    {
      "method": "Mass-balance leak detection with packing-term correction (transient flow)",
      "finding": "Detection threshold of about 3% of mass flow over several minutes, contingent on pressure-wave-velocity uncertainty being minimized.",
      "citation": "Pipeline leak detection based on mass balance: Importance of the packing term (transient-flow mass-balance LDS study). https://www.academia.edu/17624416/Pipeline_leak_detection_based_on_mass_balance_Importance_of_the_packing_term"
    },
    {
      "method": "Unsupervised autoencoder-integrated model (TKAN-AE) on real urban pipeline field data",
      "finding": "93.1% segment-wise precision detecting simulated leaks injected into real urban water-pipeline SCADA data (Shanghai field experiments).",
      "citation": "Temporal Kolmogorov-Arnold Network with Autoencoder Integration for unsupervised pipeline leak detection. Sensors 2025, 25(2), 384. https://www.mdpi.com/1424-8220/25/2/384"
    }
  ],
  "pipeline_seconds": 113.9
}