By Saad Iqbal

Seven days before a gas well dies, nothing looks like an emergency. The chart on the SCADA screen shows casing pressure drifting down a little faster than last week. Tubing pressure is doing something similar. A field engineer glancing at the daily report might not even flag it, production is down a few percent, well within the noise band.
Then, sometime in the second week, the decline stops being gradual. The well starts heading: pressure builds, slugs of water and condensate lurch up the tubing, rates spike and crash. A few days after that, it goes quiet. No flow, no noise, just a well sitting dead until someone can get a rig or a plunger crew out to it.
That slow slide and sudden death is liquid loading, and it is one of the most common ways a gas well stops paying for itself. It is also, increasingly, a problem being caught earlier by machine learning models reading the same SCADA trends an engineer would glance at, except continuously, at scale, and without waiting for a scheduled check. This is the case for AI liquid loading prediction as something more than a research curiosity, and why the decades old model most engineers still use to catch it is starting to show its age.
Table of Contents
What Liquid Loading Actually Does to a Well
A gas well only stays unloaded if the gas is moving fast enough to carry liquids, condensate, formation water, or both, up and out of the tubing. As reservoir pressure depletes over the life of the well, gas velocity drops. Once it falls below the speed needed to keep droplets airborne, liquid starts falling back instead of lifting out. It accumulates at the bottom of the tubing, adds hydrostatic backpressure against the formation, and chokes the well’s own deliverability. The well produces less gas, which drops velocity further, which loads the well further, a feedback loop that ends, if nothing intervenes, with the well dying completely.
Recovering a loaded up or dead well is never free. Depending on the well and the field, the fix is some combination of installing a plunger lift, running a velocity string to shrink the effective tubing diameter, or a full workover, and every day the well sits underperforming or fully dead before that intervention happens is deferred production, with any permanently lost recovery depending on reservoir and operating conditions. That combination of intervention cost and lost deliverability is why catching liquid loading early, not just eventually, has real economic weight.
Turner’s Model: A Good Answer to the Wrong Shaped Question
For decades, the standard tool for this has been the Turner critical velocity model, published in 1969 and still the default check most engineers run by hand or in a spreadsheet. Turner’s model calculates the minimum gas velocity needed to lift the largest stable liquid droplet against gravity, using surface pressure, gas gravity, and liquid density.
Compare that critical velocity to the well’s actual velocity at a point in time, and you get a yes or no answer: loaded, or not loaded. Li and others later proposed modified droplet shape assumptions, and models from Turner, Zhang, and Barnea remain the standard critical velocity correlations engineers reach for first. If you want to see that calculation built out step by step, Gas Well Liquid Loading: Automate the Turner Check walks through automating it in Python.
The trouble is what that calculation leaves out. Turner’s model is a single point physics check: plug in today’s surface pressure and rate, get today’s answer. It does not look at the trend, does not adapt well to deviated or horizontal trajectories where liquid film behavior departs from the vertical droplet model it was built on, and was calibrated against a specific, fairly narrow dataset of field conditions. That is also why so many modified versions exist, Li Turner, Zhang, Barnea, Shu Luo, each trying to patch the same underlying limitation: a static snapshot model standing in for a dynamic, trending phenomenon.
AI liquid loading prediction: classification versus forecasting
AI liquid loading prediction can classify current well conditions or forecast a future loading event. These are different tasks. A classification study based on individual field observations does not demonstrate advance warning merely because its accuracy exceeds a critical velocity correlation. A forecasting claim requires a chronological test with labels and usable lead time measured before the event. Compare models on the same wells, observation periods and operating conditions.
The physics correlations remain valuable screening references for AI liquid loading prediction. Their limits should be considered explicitly, including well inclination, liquid properties and the mechanism of film reversal. A data driven model can add context from operating history, but may generalize poorly outside its training field. Use both approaches to investigate disagreement rather than automatically trusting the higher score.
AI liquid loading prediction from continuous SCADA data
The practical difference this makes in the field comes down to what data each approach actually uses. A manual Turner check is run when someone runs it, weekly, maybe daily on a watched well, using whatever surface pressure and rate reading was available at that moment. A machine learning model built for gas well deliverability AI instead runs continuously against the SCADA stream, watching how the signals move rather than just where they sit right now:
- Casing and tubing pressure decline rate, not just the pressure itself, but how fast it’s falling and whether that rate is accelerating
- Flowing gradient (dP/dz), pressure loss along the wellbore, which shifts as liquid holdup increases
- Flow stability signature, the onset of the casing heading, sawtooth pattern that shows up in rate and pressure data before a well fully unloads to loaded
- Gas rate trend against historical decline, deviation from the well’s expected deliverability curve

Random forests, gradient boosting and temporal models are possible candidates for AI liquid loading prediction. Select the approach against the available labels, sampling and field validation. An observation based classifier cannot establish a warning horizon by itself. A temporal model should be evaluated using future periods and unseen wells, with missed events and false alerts reported alongside lead time.
AI liquid loading prediction trends and thresholds
AI liquid loading prediction can produce a continuous risk trend, while a periodic Turner check evaluates the current operating condition. A continuous Turner calculation can also be automated, so the comparison should separate model skill from monitoring frequency. Compare both systems at the same sampling rate before attributing an earlier alert to machine learning.

In practice, teams building this kind of monitoring are pulling SCADA history into pandas, training and validating loading classifiers with scikit learn, and scoring new SCADA reads against that model on a recurring basis, daily at minimum, ideally against every new polling interval. Field data platforms like Corva are increasingly where that real time SCADA stream already lives, which makes them a natural place to wire in a loading risk score rather than building a separate data pipe from scratch.
None of this replaces the physics, a flagged well still gets evaluated the way it always has, including with a Turner style check as a sanity reference, but it changes when that evaluation happens, from “whenever someone next looks” to “the moment the trend says to.”
AI liquid loading prediction economics
It’s worth being precise about what’s at stake, because “liquid loading” can sound like a minor operational nuisance until you’ve watched a well go through it. A well that loads up doesn’t just produce a little less gas, it enters the feedback loop described above, where reduced velocity causes more loading, which causes less velocity, until the well is intermittent (flowing in surges, then dying, then unloading and flowing again) or fully dead.
Every day in that state reduces current production. Some gas may be recovered later; permanent recovery loss should be assessed separately rather than assumed. Getting the well back typically means a deliquification intervention: a plunger lift system sized and installed for the well’s specific rate and depth, a velocity string run to shrink tubing diameter and restore critical velocity at lower rates, or, in worse cases, a full workover.
Each of those is a planned, budgeted event when it’s caught early, and a more expensive, more urgent one when the well has already died and sat dead waiting for a crew.

That’s the real case for treating this as a monitoring problem rather than a periodic checklist problem. The cost driver isn’t the Turner calculation itself, it’s the gap between when loading actually begins and when someone happens to notice.
AI liquid loading prediction in a flow assurance workflow
Liquid loading prediction doesn’t sit in isolation. It’s one signal among several that a well is drifting out of stable, efficient operation, alongside things like casing heading in gas lifted wells, if you’re seeing cyclic instability on a gas lift well rather than a naturally flowing one, AI Gas Lift Instability Detection: Stop Casing Heading covers the related but distinct diagnostic pattern.
The point of building liquid loading machine learning into a monitoring stack isn’t to replace engineering judgment, Turner, Li Turner, and the rest remain useful physical sanity checks, and nobody is deciding to mobilize a plunger crew purely because a classifier crossed a threshold. It’s to make sure that judgment gets applied while there’s still time to choose the response, instead of after the well has already made the choice by going intermittent or dying outright.
The wells worth watching this way are the ones already showing early decline signatures: mature gas wells past peak rate, wells with a history of marginal critical velocity, or wells on fields where deliquification interventions are a recurring, budgeted line item rather than a rare event. For those wells, the question isn’t whether Turner’s model is wrong. It’s whether checking it once a week is still good enough, and for a well whose pressure trend is already telling a different story between checks, the research increasingly says it isn’t.
Five AI liquid loading prediction checks before deployment
1. Define loading consistently. Specify whether AI liquid loading prediction targets observed loading, intermittent production or a confirmed intervention need. Record how field evidence establishes each label. A low gas rate alone does not distinguish loading from a choke change, network restriction or declining reservoir pressure. Labels should reflect the diagnostic question, not simply a convenient spreadsheet category.
2. Align measurements. Reconcile pressure, gas rate and liquid measurements to the same timestamps and reporting intervals. Separate instantaneous sensor values from daily allocated production. Record well status, shut ins and telemetry gaps. A missing rate must not be converted to zero without a reason; otherwise AI liquid loading prediction may learn communications failures as physical loading events.
3. Evaluate transfer to new wells. Hold out complete wells or pads, then test later periods. Report performance for different tubing diameters, inclinations and pressure ranges. An AI liquid loading prediction model trained on vertical wells may fail on a horizontal section where film behavior differs. Keep model validation and correlation applicability as separate documented checks.
4. Measure usable warning. For every confirmed event, record the first sustained alert and the time when an operator could reasonably act. Count alerts per well month and the proportion that led to a confirmed condition. Report missed events and how many wells were observed. AI liquid loading prediction should improve the decision window, rather than merely identify a well after it has already stopped flowing.
5. Tie alerts to an engineering response. Use a review workflow to inspect pressures, rates, recent controls and well geometry. Evaluate plunger lift, velocity strings, surfactant or other deliquification options against field conditions. An AI liquid loading prediction alert should trigger a documented assessment; it is not sufficient by itself to choose equipment or override operating limits.