Systems Safety & Engineering (AI-augmented) · Version 1.1.1 · May 2026

DAMS-SLIP

Dynamic AI-Augmented Monitoring System for Seepage, Limit-state Integrity, and Piping
A Critical Framework for Seepage Control, AI-Augmented Piping Prediction,
and Structural Integrity Governance in Earth-Fill Dams

"A dam is not a static earth structure. It is a continuously evolving dissipative boundary
interacting with its own hydraulic gradient field. DAMS-SLIP formalizes and governs this
interaction, ensuring structural integrity against internal erosion and shear instability."

↗ View on GitHub 📦 PyPI Package 🔬 Zenodo DOI 📄 Documentation

Real-Time Safety Governance

Three-Level HGCL Signal Classification

Every dam state evaluated by DAMS-SLIP receives a continuous safety signal with full hydraulic and stability diagnostics.

F_s ≥ 1.45 · SCI ≥ 98%

🟢 STABILITY CERTIFIED

All hydraulic gradient constraints satisfied. Factor of Safety certified by global SOS polynomial optimizer. Maintenance mode active — continuous monitoring.

SCI < 98% or F_s < 1.55

🟠 MONITORING PHASE

Gradient elevation or stability margin narrowing detected. HGCL Level 1–2: drainage activation and reservoir regulation recommendation issued to operator.

F_s < 1.45 · SCI < 96%

🔴 CRITICAL ALERT

Safety threshold breach. HGCL Level 3: critical alert dispatched with full diagnostic report — seepage field, critical surface, PINN forecast, emergency action sequence.

Governance Architecture

Three Constructs · One Continuum · Three AI Modules

Fully coupled hydro-mechanical simulation augmented by real-time AI inference. No decoupled seepage-then-stability paradigm.

CONSTRUCT 01

SMEC — Seepage Mechanics & Continuity Engine

SCI ≥ 98.0%

Solves modified Richards equation in anisotropic K(x,y,z) field at N_mesh = 10⁶ elements. Tracks phreatic surface position and monitors hydraulic gradient field in real time.

∂θ/∂t = ∇·[K(ψ)·∇(ψ+z)] + S(x,t)
SCI = |{x: i_cr−i ≥ 0}| / |Ω| × 100%

CONSTRUCT 02

GSSE — Geotechnical Slip Stability Evaluator

F_s ≥ 1.45

Morgenstern–Price equilibrium solver over 10⁴ candidate surfaces + Sum-of-Squares global optimizer for provably certified F_s lower bound. Satisfies both force and moment equilibrium.

F_s* = min_{surface∈A} F_s(surface)
σ(x) ≥ 0 certifies global lower bound F_s,LB

CONSTRUCT 03

HGCL — Hydraulic Gradient Consistency Lock

3-Level Governance

Enforces exit gradient constraint at downstream boundary. Activates Level 1 drainage, Level 2 drawdown recommendation, or Level 3 critical alert in real time.

i_exit(x,t) ≤ i_cr(x) ∀ x ∈ ∂Ω_down
i_cr = (G_s − 1) / (1 + e) ≈ 1.03

AI MODULE 01

CNN Gradient Detector

Prec. 0.94 · Rec. 0.91

Convolutional neural network trained on 847 simulations + 23 historical piping incidents. Classifies gradient field into {normal, elevated, critical} at each time step.

Input: ∇h(x,y,t) 128×128 spatial grid
Output: P ∈ {0, 1, 2} · AUC = 0.97

AI MODULE 02

PINN Pore Pressure Forecaster

24h MAE: 1.67 kPa

Physics-Informed Neural Network embedding Biot consolidation equation as training constraint. Forecasts full spatial pore pressure field at T+6/12/24/48 hours from sensor data.

L = λ_data·L_data + λ_phys·L_phys
λ_data=0.7 · λ_phys=0.3

AI MODULE 03

XGBoost Stability Ensemble

24h F_s MAE: 0.024

500-tree gradient boosting ensemble providing 24-hour F_s forecast with calibrated uncertainty. Seeds the SOS solver — reduces computation time by 67%.

F_s(T+24h) = μ ± σ · 47-dim features
FAR = 3.8% · Shapley: PINN P95 = 0.31

Experimental Validation

Four Canonical Benchmark Scenarios

Validated across homogeneous fill, zoned embankment, rapid drawdown, and seismic coupling conditions.

Case	Scenario	SCI	F_s (SOS cert.)	Stability Time	AI Lead Time
S1	Homogeneous dam	97.4%	1.58	1.2 τ_H	28.4 h
S2	Zoned embankment	99.1%	1.74	0.8 τ_H	34.1 h
S3	Rapid drawdown	96.8%	1.48	2.1 τ_H	18.3 h
S4	Seismic coupling	98.2%	1.51	1.5 τ_H	22.7 h
Mean	—	98.2%	1.57	1.4 τ_H	25.9 h

τ_H = hydraulic time constant. AI Lead Time = hours of warning before projected safety threshold breach.

Quick Start

Deploy Safety Governance in 60 Seconds

pip install dams-slip-engine

from dams_slip import DAMSGovernor

# Initialize with dam configuration and current reservoir head
governor = DAMSGovernor(
    dam_config="configs/zoned_embankment.yaml",
    reservoir_head=42.0,  # meters
    sensor_stream="live"
)

result = governor.evaluate()

print(result.signal)          # "STABILITY_CERTIFIED" | "MONITORING" | "CRITICAL_ALERT"
print(result.factor_of_safety) # SOS-certified global min F_s
print(result.sci)              # Seepage Containment Index (%)
print(result.ai_lead_time_hours) # Warning horizon (hours)
print(result.hgcl_action)      # "none" | "level_1" | "level_2" | "level_3"

from dams_slip import DAMSGovernor
from dams_slip.ai import CNNGradientDetector, PINNPoreForecaster, XGBStabilityEnsemble

governor = DAMSGovernor(
    dam_config="configs/zoned_embankment.yaml",
    ai_modules={
        "gradient_cnn":  CNNGradientDetector.from_pretrained("default"),
        "pore_pinn":     PINNPoreForecaster.from_pretrained("default"),
        "stability_xgb": XGBStabilityEnsemble.from_pretrained("default"),
    }
)

result = governor.evaluate(horizon_hours=[6, 12, 24, 48])
print(result.pore_forecast_24h)  # full spatial pore pressure field at T+24h
print(result.fs_forecast_24h)    # predicted F_s: mean ± std
print(result.piping_risk)        # CNN: "normal" | "elevated" | "critical"

from dams_slip import DAMSGovernor
from dams_slip.simulation import DrawdownScenario

# Rapid drawdown from 42m to 14m over 7 days (S3 benchmark)
scenario = DrawdownScenario(
    initial_head=42.0, final_head=14.0, drawdown_days=7,
    dam_config="configs/zoned_embankment.yaml"
)

governor = DAMSGovernor(dam_config="configs/zoned_embankment.yaml")
results = governor.run_transient(scenario, dt_hours=0.25, T_max_days=14)

print(results.min_fs)            # 1.48 (S3 validation result)
print(results.min_sci)           # 96.8% — triggers HGCL Level 2
print(results.ai_warning_hours)  # 18.3 h before projected F_s minimum

# Launch real-time Streamlit safety monitoring dashboard
# Live seepage heatmap · F_s evolution · PINN forecast · 🔴🟠🟢 signals

$ streamlit run examples/streamlit_live.py

# Dashboard at: http://localhost:8501
# Panels:
#   · 2D seepage field & gradient heatmap (SMEC live output)
#   · Critical failure surface overlay (GSSE SOS result)
#   · PINN pore pressure forecast at T+6/12/24/48h
#   · F_s time-series with 1.45 threshold line
#   · 🔴🟠🟢 SAM safety signal status panel
#   · JSON/CSV archive with SHA-256 checksums

Citation

Cite DAMS-SLIP in Your Research

If DAMS-SLIP contributes to your research, please use one of the citation formats below.

@software{baladi2026damsslip_pypi,
  author    = {Baladi, Samir},
  title     = {{DAMS-SLIP}: Dynamic AI-Augmented Monitoring System
               for Seepage, Limit-state Integrity, and Piping},
  year      = {2026},
  version   = {1.0.0},
  publisher = {Python Package Index},
  url       = {https://pypi.org/project/dams-slip-engine},
  note      = {Python package, MIT License,
               Systems Safety & Engineering (AI-augmented)}
}

@dataset{baladi2026damsslip_zenodo,
  author    = {Baladi, Samir},
  title     = {{DAMS-SLIP}: Dynamic AI-Augmented Monitoring System
               for Seepage, Limit-state Integrity, and Piping —
               Research Paper and Simulation Data},
  year      = {2026},
  publisher = {Zenodo},
  version   = {1.0.0},
  doi       = {10.5281/zenodo.20370291},
  url       = {https://doi.org/10.5281/zenodo.20370291},
  note      = {Geotechnical Engineering Core · FSI · Systems Safety}
}

@misc{baladi2026damsslip_osf,
  author    = {Baladi, Samir},
  title     = {{DAMS-SLIP} Framework: Pre-registered Study Protocol for
               AI-Augmented Structural Integrity Governance
               in Earth-Fill Dams},
  year      = {2026},
  publisher = {Open Science Framework},
  doi       = {10.17605/OSF.IO/PW7QZ},
  url       = {https://doi.org/10.17605/OSF.IO/PW7QZ},
  note      = {OSF Preregistration}
}

@article{baladi2026damsslip,
  author  = {Baladi, Samir},
  title   = {{DAMS-SLIP}: A Critical Framework for Seepage Control,
             AI-Augmented Piping Phenomenon Prediction, and Structural
             Integrity Governance in Earth-Fill Dams},
  year    = {2026},
  month   = {May},
  version = {1.0.0},
  doi     = {10.5281/zenodo.20370291},
  url     = {https://doi.org/10.5281/zenodo.20370291},
  note    = {Ronin Institute / Rite of Renaissance}
}

Baladi, S. (2026). DAMS-SLIP: A Critical Framework for Seepage
Control, AI-Augmented Piping Phenomenon Prediction, and
Structural Integrity Governance in Earth-Fill Dams
(Version 1.1.1). Zenodo.
https://doi.org/10.5281/zenodo.20370291