🪙 MET-AL

Coordination Bond Stability in Transition Metals Under Extreme Environments

Overview

MET-AL introduces the first physics-informed AI framework for quantitative characterization of coordination bond stability in transition metal complexes operating under extreme environmental conditions — the Coordination Bond Stability Index (CBSI). Built on seven orthogonal physico-chemical descriptors, MET-AL elevates the study of transition metal behavior from empirical materials testing to rigorous AI-driven predictive science.

Core Contributions

Validated Results

Installation

pip install metal

Quick Start

CBSI Framework

from metal import CBSI, CBSIParameters

# Initialize with 7 parameters
params = CBSIParameters(
    eta_hp=0.74,    # Hydrostatic compression
    ea=0.67,        # Adaptive resilience
    pec=0.57,       # Electrochemical density
    sigma_nav=0.73, # Stress navigation
    lxf=0.91,       # Ligand exchange fidelity
    klatt=1.74,     # Lattice expansion (Df)
    aci=0.43        # Corrosion inhibition
)

# Compute CBSI
cbsi = CBSI.compute(params)
print(f"CBSI: {cbsi:.3f}")

AI Prediction

from metal import MetalPredictor

predictor = MetalPredictor()
result = predictor.predict(impedance_data, xrd_data)
print(f"Failure probability: {result.probability:.3f}")
print(f"Early warning: {result.days_to_failure} days")

Documentation

Resource Link Website https://met-al-science.netlify.app Research Paper DOI: 10.5281/zenodo.19566418 API Reference https://metal.readthedocs.io OSF Registration https://osf.io/6v4xt

Project Structure

MET-AL/
│
├── metal/
│   ├── __init__.py
│   ├── cbsi.py           # CBSI composite formula
│   ├── parameters.py     # 7 physico-chemical parameters
│   ├── ai_models.py      # 1D-CNN, XGBoost, LSTM, PINN
│   ├── data_loader.py    # Dataset loader (3,847 CCUs)
│   └── utils.py          # Utilities & helpers
│
├── tests/
│   ├── test_cbsi.py
│   ├── test_parameters.py
│   ├── test_ai_models.py
│   └── test_utils.py
│
├── examples/
│   ├── example_cbsi.py
│   ├── example_prediction.py
│   └── example_parameters.py
│
├── results/
│   ├── daily_report_2026-03-xx.txt
│   ├── weekly_report_week12_2026.txt
│   ├── monthly_report_march_2026.txt
│   ├── alerts.log
│   └── coverage_report_2026-03-xx.txt
│
├── docs/
│   ├── conf.py
│   ├── index.rst
│   └── api.rst
│
├── Netlify/
│   ├── index.html
│   ├── dashboard.html
│   ├── reports.html
│   └── documentation.html
│
├── bin/
│   └── run_prediction.py
│
├── scripts/
├── data/
│
├── pyproject.toml
├── requirements.txt
├── requirements-dev.txt
├── Dockerfile
├── Makefile
├── VERSION
├── CITATION.cff
├── AUTHORS.md
├── CHANGELOG.md
├── CONTRIBUTING.md
├── SECURITY.md
├── DEPLOY.md
├── INSTALL.md
└── COMPLETION.md

Codebase Statistics

Metric Value Python modules 6 Test files 4 Dataset 3,847 CCUs Sites 52 Environment types 5 Time span 14 years (2012–2026) Governing equations 7+

Dataset

Metric Value Coordination Complexes 3,847 CCUs Sites 52 Environment Types 5 Time Span 14 years (2012–2026) Paired Samples 284 intact/damaged pairs Bond Trajectories 1,840 tracking events

Environment Categories

Environment Sites Pressure Range Temperature Range Deep-Sea Hydrothermal 11 20–35 MPa 2°C–380°C Abyssal Plain Cold Water 13 35–110 MPa 1.5°C–4°C Cryogenic Space Simulation 10 10⁻⁸ Pa vacuum -196°C to -20°C Radiation-Exposed Orbital 9 Ambient–5 MPa -80°C to +150°C High-Temperature Autoclave 9 5–30 MPa 300°C–900°C

Case Studies

Kermadec Trench (10,900m depth)

· Ni²⁺ maintains Df = 1.88 at 109 MPa · Fe²⁺ shows higher pressure sensitivity · CBSI identifies specific engineering interventions

Enceladus Ocean Analog

· 68-hour coordinated impedance burst · Propagation velocity: 1.8 mm/s · 22-day warning before visible damage

International Space Station

· Orbital navigation orphaning phenomenon · σ_nav = 0.62–0.67 (below ground reference) · Radiation disrupts crystallographic order

Citation

@software{baladi2026metal,
  author    = {Samir Baladi},
  title     = {MET-AL: Coordination Bond Stability in Transition Metals
               Under Extreme Environments},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.19566418},
  note      = {Physics-Informed AI Framework},
  url       = {https://doi.org/10.5281/zenodo.19566418}
}

License

MIT License © 2026 Samir Baladi Ronin Institute / Rite of Renaissance · ORCID 0009-0003-8903-0029

"The metal speaks. MET-AL translates. Coordination bond networks are not passive structural elements — they are active information processing systems that sense, integrate, respond to, and transmit information about environmental state across spatial scales from individual bond lengths to macroscopic fracture networks spanning centimeters."