Claude Skill

mcda-suitability-analysis

Always invoke for spatial suitability, site selection, AHP, criteria weights, or weighted-overlay work, including audits of inconsistent pairwise judgments and requests for only a final map. Covers consistency, standardization, constraints, ranked surfaces, shortlists, and sensit

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download muend-geoai-skills-skills_mcda-suitability-analysis-096e5d4.zip · 5 KB

muend/geoai-skills 24 2 forks MIT Updated 21d ago

Part of muend/geoai-skills — 18 skills

Install

skills CLI npx skills add https://github.com/muend/geoai-skills/tree/main/skills/mcda-suitability-analysis

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install muend-geoai-skills@llmmart

Git git clone https://github.com/muend/geoai-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole muend/geoai-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

MCDA & Suitability Analysis

Purpose: produce suitability maps whose weights, scales, and assumptions are explicit, consistent, and stress-tested. A suitability map without a sensitivity analysis is an opinion with a legend.

Workflow

Structure: goal → criteria (factors) → constraints. Constraints are binary masks (legal exclusions, water bodies, slope > threshold) applied at the END by multiplication; factors are continuous and weighted. Keep them apart — encoding a constraint as a heavily-weighted factor is a classic error that lets forbidden areas score "acceptable".
Criteria layers: each factor as a raster on a COMMON grid (same CRS, extent, cell size, snap). Resample categorical layers with nearest, continuous with bilinear; document each.
Standardization to a common suitability scale (0-1 or 0-255):
- Linear min-max for monotonic "more is better/worse".
- Fuzzy membership (sigmoid/linear with control points) when suitability saturates — justify control points from domain knowledge.
- Categorical layers: explicit reclass table, shown to the user. Direction check: confirm for EVERY layer whether high raw value means high or low suitability (slope: low=good; distance-to-road: usually low=good). Direction bugs survive to the final map invisibly.
Weights (AHP below, or direct/ranked methods with rationale).
Aggregation: weighted linear combination (WLC) default; OWA when the decision-maker's risk attitude (AND-like vs OR-like) matters.
Constraint mask multiply; classify the result (equal interval or quantiles — say which and why); sensitivity analysis; validate against known good/bad sites if any exist.

AHP with consistency enforcement

Pairwise comparisons on Saaty's 1-9 scale; weights from the principal eigenvector; consistency ratio (CR) must be < 0.10 or the matrix goes back for revision. Run scripts/ahp_weights.py to compute weights + CR from a reciprocal comparison matrix (it validates reciprocity and reports λ_max).

Practices: elicit comparisons pair by pair with verbal anchors ("moderately more important" = 3); with multiple experts, aggregate judgments by geometric mean BEFORE computing weights; report the full matrix, weights, λ_max and CR in the deliverable. If CR ≥ 0.10, identify the most inconsistent triad and ask the expert to revisit it — do not silently massage numbers.

Aggregation

suit = np.zeros_like(factors[0], dtype="float32")
for w_i, f in zip(weights, factors):   # factors already standardized 0-1
    suit += w_i * f
suit *= constraint_mask                 # binary 0/1, applied last

OWA variant: sort factor values per cell and apply order weights — full AND (min) to full OR (max) continuum; use when stakeholders disagree on risk tolerance and show 2-3 scenarios.

Sensitivity analysis — mandatory

A result that flips with a small weight change is not a result:

One-at-a-time: perturb each weight ±20% (renormalize), recompute, report % of area changing suitability class and a stability map (cells that never change class across perturbations).
Scenario: 2-3 alternative weight sets from different stakeholder priorities; present side-by-side.
If a Monte Carlo budget exists: sample weights from Dirichlet around the AHP vector; per-cell probability of "highly suitable" is a far stronger product than a single map.

Deliverable standard

Suitability map (classified + continuous), constraint mask map, weights table with CR, standardization functions per criterion (with direction), sensitivity/stability summary, and limitations paragraph (data currency, resolution, criteria omitted). Route cartography to cartography-geoviz; network-access criteria come from network-accessibility-analysis.

Pitfalls checklist

Direction inversion on a criterion (the silent killer — double-check distance-based factors).
Mixing resolutions without declaring the resampling rule.
CR ignored or unreported.
Constraints blended as weights → forbidden zones scored medium.
Classifying with quantiles then reading them as absolute suitability.
No sensitivity analysis; single map presented as truth.

Execution contract

Workflow: define decision and stakeholders; separate constraints from factors; standardize criteria; elicit and validate weights; aggregate; test sensitivity; communicate uncertainty.
Decision rules: use MCDA for transparent criteria-ranked surfaces, network analysis for route-constrained access, and optimization when discrete placement or capacity decisions dominate.
Verification protocol: check criterion direction and alignment, AHP consistency, constraint enforcement, weight and threshold perturbations, and stable-versus-fragile areas.
Failure modes: reject the model when criteria double-count the same construct, weights lack provenance, constraints leak into compensation, or rankings collapse under plausible perturbations.
Deliverables: continuous and classified suitability maps, constraints, criteria transformations, weights and consistency ratio, sensitivity results, and limitations.
Source freshness: consult the authoritative source registry before applying methods or implementation APIs and record the checked date.

Files (geoai-skills)

agents

openai.yaml 229 B

interface:
  display_name: "MCDA Suitability Analysis"
  short_description: "Build transparent spatial suitability models"
  default_prompt: "Use $mcda-suitability-analysis to create and stress-test this site suitability model."

references

authoritative-sources.md 867 B

# Authoritative sources

- Last verified: 2026-07-19
- Review cadence: every 12 months
- Refresh triggers: weighting method change, decision-policy change, or implementation dependency release

## Canonical sources

- [Saaty, The Analytic Hierarchy Process](https://doi.org/10.1016/0270-0255(87)90473-8) — primary AHP scale and consistency foundation.
- [JRC sensitivity analysis resources](https://joint-research-centre.ec.europa.eu/sensitivity-analysis-samo_en) — European Commission guidance and tools for sensitivity analysis.
- [NumPy linear algebra documentation](https://numpy.org/doc/stable/reference/routines.linalg.html) — implementation behavior for the bundled weight calculator.

Document stakeholder provenance and the exact pairwise matrix. A mathematically consistent matrix does not make criteria, preferences, or policy assumptions objective.

scripts

ahp_weights.py 2.8 KB

"""AHP weights + consistency ratio from a pairwise comparison matrix.

Run:    python ahp_weights.py matrix.csv        (n x n CSV, no header)
Import: from ahp_weights import ahp_weights
"""
from __future__ import annotations

import argparse
from pathlib import Path

import numpy as np

# Saaty's random consistency index by matrix order
RI = {1: 0.0, 2: 0.0, 3: 0.58, 4: 0.90, 5: 1.12, 6: 1.24, 7: 1.32, 8: 1.41, 9: 1.45, 10: 1.49}


def ahp_weights(A: np.ndarray) -> tuple[np.ndarray, float]:
    """Principal-eigenvector AHP weights and consistency ratio.

    Args:
        A: n x n positive reciprocal pairwise comparison matrix
           (Saaty 1-9 scale).

    Returns:
        (weights summing to 1, CR). CR >= 0.10 means judgments are too
        inconsistent to use — revise the most discordant comparison.

    Raises:
        ValueError: If the matrix is not finite, positive, square, reciprocal,
            or supported by the bundled random consistency index table.
    """
    A = np.asarray(A, dtype=float)
    if A.ndim != 2 or A.shape[0] != A.shape[1]:
        raise ValueError("AHP matrix must be a square 2D array.")

    n = A.shape[0]
    if n not in RI:
        raise ValueError(f"AHP matrix order {n} is unsupported; expected 1–10.")
    if not np.isfinite(A).all():
        raise ValueError("AHP matrix must contain only finite values.")
    if np.any(A <= 0):
        raise ValueError("AHP matrix values must be strictly positive.")
    if not np.allclose(np.diag(A), 1.0, rtol=0.0, atol=1e-8):
        raise ValueError("AHP matrix diagonal must contain only 1 values.")
    if not np.allclose(A * A.T, np.ones_like(A), rtol=1e-6):
        raise ValueError("Matrix is not reciprocal (A[i,j] must equal 1/A[j,i]).")

    eigvals, eigvecs = np.linalg.eig(A)
    k = int(np.argmax(eigvals.real))
    if abs(eigvals[k].imag) > 1e-8:
        raise ValueError("Principal eigenvalue is unexpectedly complex.")

    w = eigvecs[:, k].real
    if w.sum() < 0:
        w = -w
    if np.any(w <= 0):
        raise ValueError("Principal eigenvector did not produce positive weights.")
    w /= w.sum()
    lam_max = eigvals[k].real
    ci = max(0.0, (lam_max - n) / (n - 1)) if n > 2 else 0.0
    cr = ci / RI[n] if RI.get(n, 0) > 0 else 0.0
    return w, float(cr)


def main() -> None:
    """Read a headerless CSV matrix and print weights plus consistency."""
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("matrix", type=Path)
    args = parser.parse_args()

    matrix = np.loadtxt(args.matrix, delimiter=",")
    weights, cr = ahp_weights(matrix)
    for i, wi in enumerate(weights):
        print(f"criterion_{i + 1}: {wi:.4f}")
    verdict = "OK" if cr < 0.10 else "REVISE — inconsistent judgments"
    print(f"CR = {cr:.4f}  [{verdict}]")


if __name__ == "__main__":
    main()

SKILL.md 5.8 KB

---
name: mcda-suitability-analysis
description: >-
  Always invoke for spatial suitability, site selection, AHP, criteria
  weights, or weighted-overlay work, including audits of inconsistent
  pairwise judgments and requests for only a final map. Covers consistency,
  standardization, constraints, ranked surfaces, shortlists, and sensitivity.
  Route travel-time placement and location-allocation to
  network-accessibility-analysis.
license: MIT
metadata:
  author: Muhammed Enes Duran
---

# MCDA & Suitability Analysis

Purpose: produce suitability maps whose weights, scales, and assumptions are
explicit, consistent, and stress-tested. A suitability map without a
sensitivity analysis is an opinion with a legend.

## Workflow

1. **Structure**: goal → criteria (factors) → constraints. Constraints are
   binary masks (legal exclusions, water bodies, slope > threshold) applied
   at the END by multiplication; factors are continuous and weighted.
   Keep them apart — encoding a constraint as a heavily-weighted factor is
   a classic error that lets forbidden areas score "acceptable".
2. **Criteria layers**: each factor as a raster on a COMMON grid (same CRS,
   extent, cell size, snap). Resample categorical layers with nearest,
   continuous with bilinear; document each.
3. **Standardization** to a common suitability scale (0-1 or 0-255):
   - Linear min-max for monotonic "more is better/worse".
   - Fuzzy membership (sigmoid/linear with control points) when suitability
     saturates — justify control points from domain knowledge.
   - Categorical layers: explicit reclass table, shown to the user.
   Direction check: confirm for EVERY layer whether high raw value means
   high or low suitability (slope: low=good; distance-to-road: usually
   low=good). Direction bugs survive to the final map invisibly.
4. **Weights** (AHP below, or direct/ranked methods with rationale).
5. **Aggregation**: weighted linear combination (WLC) default; OWA when
   the decision-maker's risk attitude (AND-like vs OR-like) matters.
6. **Constraint mask** multiply; classify the result (equal interval or
   quantiles — say which and why); **sensitivity analysis**; validate
   against known good/bad sites if any exist.

## AHP with consistency enforcement

Pairwise comparisons on Saaty's 1-9 scale; weights from the principal
eigenvector; consistency ratio (CR) must be < 0.10 or the matrix goes back
for revision. Run `scripts/ahp_weights.py` to compute weights + CR from a
reciprocal comparison matrix (it validates reciprocity and reports λ_max).

Practices: elicit comparisons pair by pair with verbal anchors ("moderately
more important" = 3); with multiple experts, aggregate judgments by
geometric mean BEFORE computing weights; report the full matrix, weights,
λ_max and CR in the deliverable. If CR ≥ 0.10, identify the most
inconsistent triad and ask the expert to revisit it — do not silently
massage numbers.

## Aggregation

```python
suit = np.zeros_like(factors[0], dtype="float32")
for w_i, f in zip(weights, factors):   # factors already standardized 0-1
    suit += w_i * f
suit *= constraint_mask                 # binary 0/1, applied last
```

OWA variant: sort factor values per cell and apply order weights — full
AND (min) to full OR (max) continuum; use when stakeholders disagree on
risk tolerance and show 2-3 scenarios.

## Sensitivity analysis — mandatory

A result that flips with a small weight change is not a result:

- **One-at-a-time**: perturb each weight ±20% (renormalize), recompute,
  report % of area changing suitability class and a stability map (cells
  that never change class across perturbations).
- **Scenario**: 2-3 alternative weight sets from different stakeholder
  priorities; present side-by-side.
- If a Monte Carlo budget exists: sample weights from Dirichlet around the
  AHP vector; per-cell probability of "highly suitable" is a far stronger
  product than a single map.

## Deliverable standard

Suitability map (classified + continuous), constraint mask map, weights
table with CR, standardization functions per criterion (with direction),
sensitivity/stability summary, and limitations paragraph (data currency,
resolution, criteria omitted). Route cartography to `cartography-geoviz`;
network-access criteria come from `network-accessibility-analysis`.

## Pitfalls checklist

- Direction inversion on a criterion (the silent killer — double-check
  distance-based factors).
- Mixing resolutions without declaring the resampling rule.
- CR ignored or unreported.
- Constraints blended as weights → forbidden zones scored medium.
- Classifying with quantiles then reading them as absolute suitability.
- No sensitivity analysis; single map presented as truth.

## Execution contract

- **Workflow:** define decision and stakeholders; separate constraints from factors; standardize criteria; elicit and validate weights; aggregate; test sensitivity; communicate uncertainty.
- **Decision rules:** use MCDA for transparent criteria-ranked surfaces, network analysis for route-constrained access, and optimization when discrete placement or capacity decisions dominate.
- **Verification protocol:** check criterion direction and alignment, AHP consistency, constraint enforcement, weight and threshold perturbations, and stable-versus-fragile areas.
- **Failure modes:** reject the model when criteria double-count the same construct, weights lack provenance, constraints leak into compensation, or rankings collapse under plausible perturbations.
- **Deliverables:** continuous and classified suitability maps, constraints, criteria transformations, weights and consistency ratio, sensitivity results, and limitations.
- **Source freshness:** consult [the authoritative source registry](references/authoritative-sources.md) before applying methods or implementation APIs and record the checked date.