Air quality modelers often rely on regional travel demand models to estimate the vehicle activity data for emission models, however, most of the current travel demand models can only output reliable person travel activity rather than goods/service specific travel activity. This paper presents the successful application of data-driven, Spatial Regression and output optimization Truck model (SPARE-Truck) to develop truck-related activity inputs for the mobile emission model, and eventually to produce truck specific gridded emissions. To validate the proposed methodology, the Cincinnati metropolitan area in United States was selected as a case study site. From the results, it is found that the truck miles traveled predicted using traditional methods tend to underestimate — overall 32% less than proposed model— truck miles traveled. The coefficient of determination values for different truck types range between 0.82 and 0.97, except the motor homes which showed least model fit with 0.51. Consequently, the emission inventories calculated from the traditional methods were also underestimated i.e. −37% for NO_x, −35% for SO₂, -43% for VOC, −43% for BC, −47% for OC and - 49% for PM_2.5. Further, the proposed method also predicted within ∼7% of the national emission inventory for all pollutants. The bottom-up gridding methodology used in this paper could allocate the emissions to grid cell where more truck activity is expected, and it is verified against regional land-use data. Most importantly, using proposed method it is easy to segregate gridded emission inventory by truck type, which is of particular interest for decision makers, since currently there is no reliable method to test different truck-category specific travel-demand management strategies for air pollution control.