Key Takeaways

  • Acid-base accounting (ABA) itself is a standard, decades-old static/kinetic lab test — there’s no AI in the test protocol.
  • PHREEQC, the free USGS geochemical modeling engine, is the standard open-source tool for extending raw ABA results into predictive geochemical models.
  • The INAP GARD Guide is the industry-standard methodology reference for how to run and interpret ABA/ARD programs.
  • This is genuinely “Emerging” for AI specifically — the AI opportunity is in predicting long-term drainage chemistry from ABA + mineralogy data, not in the test itself.

TL;DR

Run standard static and kinetic (humidity cell) ABA testing per the INAP GARD Guide methodology, then use PHREEQC to model the resulting geochemistry — with genuine AI upside still emerging in using ML to predict long-term drainage behavior from that data rather than relying purely on kinetic cell extrapolation.

How Do I Predict Acid Rock Drainage With AI?

Acid-base accounting exists to answer one question before you move a single tonne of waste rock: will this material generate acid drainage over its operational and post-closure life? The core test is not something AI touches — it’s a static test (net acid-producing potential vs. neutralizing potential) followed, where the static result is ambiguous, by kinetic humidity-cell testing that runs for months to years. The methodology for how to design and interpret that program is codified in the INAP GARD Guide, the closest thing the industry has to a standard reference.

Where modeling comes in is translating those lab results into a predictive geochemical model of what actually happens in a waste rock pile or tailings facility over decades. PHREEQC — free, USGS-maintained, and the de facto standard in this space — handles the aqueous equilibria, mineral dissolution/precipitation, and kinetic reaction modeling needed to extend a handful of lab data points into a defensible long-term prediction.

The honest state of AI here: it’s not mature. The real opportunity being explored right now is using machine learning to predict long-term acid-generation behavior directly from ABA results plus mineralogical data (automated mineralogy output, hyperspectral alteration data), which would shortcut the multi-year kinetic testing that’s currently the bottleneck. That’s active research territory, not a product you can buy — if a vendor pitches you a mature “AI ABA prediction” tool, treat that claim skeptically.

Try It With Geocluster

Tracking the actual state of ML-based acid-drainage prediction research — separating genuine progress from vendor hype — is exactly the kind of literature and landscape research Geocluster is built to run.