The Methodology

What the engine computes,
and what it doesn't.

The Liquefaction Hazard Engine computes one triggering procedure: Boulanger & Idriss (2014), CPT-based, deterministic. It plots the result against three published reference curves for visual comparison, nothing more. It draws on 8,634 in-situ test records from the Next Generation Liquefaction (NGL) database. This page states exactly what that means: what the engine computes, what it plots, what the data record is, and where it applies.

The Models

One implemented procedure. Three reference curves.

The engine does not implement a proprietary model, and it does not implement three models at once. It computes one published, peer-reviewed triggering procedure. It then plots that result against three additional published boundary curves so the engineer can see, visually, where other established procedures would draw the line.

The implemented procedure

Boulanger & Idriss (2014)

Semi-empirical, CPT-based liquefaction triggering procedure, computed in its deterministic form. This is the only triggering computation the engine runs in production: every cyclic stress ratio, cyclic resistance ratio, and factor of safety on the platform comes from this procedure. No other model is computed.

Boulanger, R.W. & Idriss, I.M. (2014), “CPT and SPT Based Liquefaction Triggering Procedures,” Report UCD/CGM-14/01, UC Davis.

Reference boundary curves

These are plotted for visual comparison. The engine does not compute them, does not run their equations against the site's input, and does not average them with the implemented procedure.

Cetin et al. (2004)

Plotted as a 9-point digitized boundary curve, pinned at a probability of liquefaction PL = 15%, moment magnitude Mw = 7.5, effective overburden stress σ′v = 1 atm, and fines content FC = 0%. Described as probabilistic in the original publication; the curve shown here is a single fixed slice of that model, not a live computation.

Cetin, K.O. et al. (2004), “Standard Penetration Test-Based Probabilistic and Deterministic Assessment of Seismic Soil Liquefaction Potential,” J. Geotech. Geoenviron. Eng., 130(12).

Moss et al. (2006)

A CPT-based triggering correlation, probabilistic in the literature, plotted here as a reference boundary curve for comparison against the implemented procedure, not computed by the engine.

Moss, R.E.S., Seed, R.B., Kayen, R.E., Stewart, J.P., Der Kiureghian, A. & Cetin, K.O. (2006), “CPT-Based Probabilistic and Deterministic Assessment of In Situ Seismic Soil Liquefaction Potential,” J. Geotech. Geoenviron. Eng., 132(8).

Idriss & Boulanger (2008)

An earlier semi-empirical triggering procedure from the same research lineage as the implemented procedure. Plotted as a reference boundary curve for comparison, not computed.

Idriss, I.M. & Boulanger, R.W. (2008), Soil Liquefaction During Earthquakes, EERI Monograph MNO-12, Earthquake Engineering Research Institute.

Reference Curves

Why we show the disagreement

Published triggering procedures do not always agree. At real sites, with real CPT and SPT profiles, Boulanger & Idriss, Cetin et al., Moss et al., and Idriss & Boulanger (2008) can draw different boundaries for the same soil column and the same shaking. This is not a defect in any one procedure. It is what happens when independent research groups build triggering correlations from overlapping but non-identical case-history records, using different functional forms and different corrections.

Most tools hide that disagreement before the engineer ever sees it, by picking one model as the house standard and presenting its output as the answer. The engine computes one procedure, Boulanger & Idriss (2014), and plots the site's position against the three reference curves alongside it. It does not average them. It does not compute them. It shows them, so the engineer can see where the published literature would disagree with the implemented result.

That visual disagreement is information: it tells the engineer where the case-history record underlying these procedures is thin, where the site sits near a triggering threshold, and where professional judgment, not another decimal place, is what the decision actually turns on.

The Data Record

8,634 in-situ test records

The engine draws on 8,634 in-situ test records (670 CPT soundings and 7,964 SPT samples) across 354 sites and 31 earthquakes, from the Next Generation Liquefaction (NGL) database (Brandenberg et al., 2020). Each record carries the test profile, groundwater depth, and shaking parameters documented for that site.

The engine searches this record for the test profiles most similar to the site under assessment and surfaces them alongside the computed result. This is a statement about the depth of the case-history record behind the engine, not a benchmarking claim, not a validation claim, and not a comparison against any other tool.

The NGL database is the same field-observation record the geotechnical community already builds on. GeoLiquefy cites it; GeoLiquefy does not own it.

Affiliation GeoLiquefy LLC is an independent, for-profit company. The Liquefaction Hazard Engine cites the Next Generation Liquefaction (NGL) database as a data source but is not affiliated with, endorsed by, or sponsored by the NGL project, its principal investigators, host institutions, or funding agencies. All NGL data is used in accordance with the NGL project's published terms of use.
Where the AI Sits

The procedure computes. The AI drafts.

The implemented triggering procedure computes the cyclic stress ratio (CSR), the cyclic resistance ratio (CRR), and the factor of safety against triggering. That arithmetic belongs entirely to Boulanger & Idriss (2014): the engine does not substitute an AI estimate for any of it, and the reference curves plotted alongside it are not recomputed by the AI either.

AI's role is to draft the assessment memo and the engineering-readable explanation that accompanies it: which in-situ test records are most similar to the site in question, how the site's result sits against the published reference curves, and what the numbers mean in plain language. Every number that appears in that memo comes from the triggering procedure and the test-record search, not from the AI.

The draft is reviewed and sealed by the engineer of record. This is a computation and drafting instrument that sits in front of published methods, not a system that outputs a verdict on its own authority.

Domain of Applicability & Limitations

Where this applies, and where it doesn't

The case-history record has a shape

The implemented triggering procedure is calibrated on field case histories drawn predominantly from a limited set of well-instrumented earthquakes and regions. Applying it outside those conditions requires local validation: the procedure carries no automatic license to extend to geology or seismicity it was not built from.

A screening and assessment instrument

The engine is a screening and assessment instrument. It does not replace site investigation, site response analysis, or the judgment of a licensed engineer. It exists to make published methods faster to apply and easier to defend, not to remove the steps that require a stamp.

Bounded by input quality

Output quality is bounded by input quality. A CPT or SPT profile with sparse sampling, unclear groundwater conditions, or uncertain fines content will produce an assessment no more reliable than that profile deserves, regardless of which procedure is run against it.

Point estimates, not probabilities

Every output is a deterministic point estimate. The engine does not currently propagate input uncertainty, run Monte Carlo simulation, or produce confidence intervals. A factor of safety is a single number computed from a single set of inputs, not a probability of outcome.

Triggering only

The engine assesses triggering: whether liquefaction is expected to initiate. It does not model lateral-spread displacement or settlement. Consequence assessment beyond triggering remains the engineer's work.

Open Validation

India validation program

The case-history record that underlies published triggering procedures is concentrated in a relatively small number of well-instrumented earthquakes, mostly outside India. GeoLiquefy is running an open research initiative to validate the implemented triggering procedure against Indian SPT and CPT profiles with known liquefaction outcomes.

This is research in progress, not a completed validation. We are not claiming Indian-specific calibration today. If your organization holds SPT or CPT profiles with documented liquefaction outcomes (from Bhuj, Sikkim, or any other Indian earthquake) and is willing to contribute them to this record, we would like to hear from you.

Contribute Data →

The Priors of Liquefaction Engineering

Tiwari, A., Moss, R. & Gupta, A.K. (2026). On why the factor of safety compresses a multidimensional problem into a single, false-precision number, and how matching a site to documented in-situ test records in the NGL database restores the information that compression discards.

Download the Paper →

Responsibility

Critical decisions require professional engineering review. Our platform augments, not replaces, human expertise.

Transparent assumptions

Every assumption behind an assessment (which procedure, which test records, which input values) is documented and visible to the engineer, not buried in the output.

Disagreement, shown honestly

The engine shows where the site's result sits against the published reference curves, instead of hiding the comparison or collapsing it into a single score.

Human-in-the-loop

The AI-drafted memo is a starting point. The engineer of record reviews the reasoning behind every number and seals the final work.

Frequently asked questions

Does the Liquefaction Hazard Engine predict liquefaction with AI?

No. The Boulanger & Idriss (2014) procedure computes the triggering result. AI drafts the assessment memo and the plain-language explanation around that result; it does not compute the number.

Which liquefaction triggering models does the engine run?

One implemented procedure: Boulanger & Idriss (2014), CPT-based and deterministic. Three published boundary curves, Cetin et al. (2004), Moss et al. (2006), and Idriss & Boulanger (2008), are plotted alongside it for visual comparison, not computed.

Does the engine give a probability of liquefaction?

No. Every output is a deterministic point estimate. The engine does not propagate input uncertainty, run Monte Carlo simulation, or produce confidence intervals.

Does the engine model lateral spread or settlement?

No. The engine assesses triggering, whether liquefaction is expected to initiate. It does not model lateral-spread displacement or settlement.

What data is the engine's assessment grounded in?

8,634 in-situ test records (670 CPT soundings and 7,964 SPT samples) from 354 sites across 31 earthquakes in the Next Generation Liquefaction (NGL) database (Brandenberg et al., 2020).

Does this replace a geotechnical engineer's judgment?

No. It is a screening and assessment instrument. It does not replace site investigation, site response analysis, or the judgment of a licensed engineer. The engineer of record reviews the reasoning behind every number and seals the final work.