Greenhouse industry has been growing in many countries due to both the advantage of stable year-round crop production and increased demand for fresh vegetables. In greenhouse cultivation, $CO_2$ concentration plays an essential role in the photosynthesis process of crops. Continuous and accurate monitoring of $CO_2$ level in the greenhouse would improve profitability and reduce environmental impact, through optimum control of greenhouse $CO_2$ enrichment and efficient crop production, as compared with the conventional management practices without monitoring and control of $CO_2$ level. In this study, a mathematical model was developed to estimate the $CO_2$ emission from soil as affected by environmental factors in greenhouses. Among various model types evaluated, a linear regression model provided the best coefficient of determination. Selected predictor variables were solar radiation and relative humidity and exponential transformation of both. As a response variable in the model, the difference between $CO_2$ concentrations at the soil surface and 5-cm depth showed are latively strong relationship with the predictor variables. Segmented regression analysis showed that better models were obtained when the entire daily dataset was divided into segments of shorter time ranges, and best models were obtained for segmented data where more variability in solar radiation and humidity were present (i.e., after sun-rise, before sun-set) than other segments. To consider time delay in the response of $CO_2$ concentration, concept of time lag was implemented in the regression analysis. As a result, there was an improvement in the performance of the models as the coefficients of determination were 0.93 and 0.87 with segmented time frames for sun-rise and sun-set periods, respectively. Validation tests of the models to predict $CO_2$ emission from soil showed that the developed empirical model would be applicable to real-time monitoring and diagnosis of significant factors for $CO_2$ enrichment in a soil-based greenhouse.