The continuous improvement of spark-ignition direct-injection (SIDI) engines is largely attributed to the enhanced understanding of air-fuel mixing and combustion processes. The intricate interaction between transient spray behavior and the ambient flow field is important to unveil the airflow dynamics during the spray injection process. This study investigates the fuel-spray boundary interactions under different superheated conditions by analyzing the ambient flow field pattern with constraint-based modeling (CBM). In the experimental setup, superheated conditions are facilitated by adjusting different fuel temperatures and ambient pressures. By adding the tracer particles containing Rhodamine 6G to the ambient air, the combined diagnostic of fluorescent particle image velocimetry (FPIV) and Mie-scattering is implemented to measure the velocity distribution and flow trajectory of the air surrounding the spray formation and propagation. For analytical analysis, a data-driven approximation method is developed by utilizing the spatiotemporal characteristics of spray-air boundary interaction. Specifically, a piecewise exponential regression model is proposed with 6 model coefficients and three segment boundaries. The segment boundaries of the piecewise expression align well with the boundary position between the entrainment, recirculation, and spray-tip regions. Further analysis of the coefficients of the regression model reveals different time-evolving flow field patterns under sub-cooled and flash-boiling conditions. For most non and transitional flash-boiling conditions, the model reaches over 90% reconstruction accuracy compared to the experimental result. Moreover, detailed model coefficient analysis suggests that the temporal development of ambient flow field pattern could be accurately captured from an explicit exponential expression. For flare flash-boiling conditions, more intense atomization near the injector would result in more intense entrainment velocity near the injection region. Besides, flare flash-boiling would increase the area of the recirculation region and subsequently decrease entrainment and spray-tip area. Furthermore, the momentum of the ambient flow is primarily aggregated within the recirculation region, resulting in lower entrainment and diffusion intensity at the other two regions. In conclusion, this work proposes an innovative CBM approach to investigate the spatiotemporal flow field patterns and sheds light on the potentials of low-latency time-series flow field prediction.