EPA approves Software CEM to monitor a paper mill turbine's NOx

EPA found that a neural network's NOx estimates for a mill turbine passed all three federal statistical tests. It estimated that two such systems cost less than half as much as hardware monitors.

  • 1 an organization

    EPA estimated that two such systems at the mill would cost less than half as much a year as two continuous emission monitoring systems.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Two continuous emission monitoring systems (CEMS), the next least costly option under EPA's cost model. Assumed without a measurement.

Without the system
$125,400 a year for two CEMS
With it
approximately $51,700 a year for two PEMS with in-house audits
The system’s part
EPA compared the model's hourly NOx estimates with reference measurements taken at the same time, which isolates the software's accuracy. EPA describes the system as neural network software trained on the unit's operating conditions. The cost comparison is EPA's estimate.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Task Cost
System
Pavilion Technologies Software CEM predictive emission monitoring system (PEMS)
Made by
Pavilion Technologies
Used by
MeadWestvaco Coated Board, Inc. (Mahrt Mill)
Where
Cottonton, Alabama, United States
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Monitoring Processes, Materials, or Surroundings
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Environmental Protection Agency, Clean Air Markets Division. Final Approval of the Predictive Emission Monitoring Systems Installed on Units X022 and Z008 at the Mahrt Paper Mill (Facility ID (ORISPL) 54802). Letter to MeadWestvaco Coated Board, Inc., 5 April 2006, with Attachments A to C.

    The PEMS NO x ppm, dry output passed all three statistics.

Details

AI system

Workflow

The model estimated NOx from turbine sensor inputs such as gas flow, load and temperatures. MeadWestvaco compared the model's hourly output with certified reference measurements over 889 operating hours.

Money

Kind of value

Estimated yearly saving of two PEMS over two CEMS at the mill, even if outside contractors run the audits

Amount

Estimate: $36,650

Recipients and payers

MeadWestvaco (Mahrt Mill)

Follow-up

Conditions for replication

The unit's input parameters stay within the operating envelope on which the model was trained. The mill runs monthly accuracy audits with a portable analyzer in the ozone season.

Entry details

Sector

Air emissions monitoring.

Purpose

Pavilion Technologies built Software CEM to estimate NOx and oxygen emissions from a combustion unit's sensor readings with a neural network.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, currency and prices, period and unit, realization, gross or net, included costs, comparison, method, return and payback, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). EPA approves Software CEM to monitor a paper mill turbine's NOx (AIBD-0895). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0895.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions