Worldwide, there is an ever-increasing interest and concern about the destructive affects of air pollution on the ecological system. The growing awareness of these effects has revealed the need to take adequate measures to monitor and control the emissions of air pollutants. Process heaters contribute a major percent to the industrially formed emissions, particularly of NO, and CO. The conventional approach was to monitor these emissions using on-line analyzers on a regular basis called continuous emission monitors (CEMS). Predictive emission monitors (PEMS) have been proven to be as accurate as the GEMS and are in fact more economical from the cost and maintenance point of view. This paper presents a PEMS developed based on the emission data collected on a 5 MMkcal h(-1) pilot plant furnace. The NOx kinetic parameters were tuned using a heuristic optimizer genetic algorithm (GA) which minimizes the least squared error between the model and experimental data. The model thus tuned could be used to predict O-2, NOx, CO, CO2 emissions with reasonable accuracy as also for model predictive control of these emissions.