Distributed fiber optic temperature sensing provides significant advantages for production monitoring in complex geological environments due to its high precision, real-time capability, and long-term stability. However, its expanding application generates increasingly complex temperature datasets that challenge conventional production profile interpretation methods. To address these challenges, in this study, the researchers developed an intelligent interpretation framework to combine physically constrained forward modeling with data-driven machine learning techniques. A forward model of wellbore temperature profiles was established based on the fundamental principles of momentum conservation, energy conservation, and two-phase flow dynamics. Sensitivity analysis was used to identify key controlling factors, including production rate, geothermal gradient, reservoir thickness, crude oil heat capacity, and crude oil density, which were then used to generate representative training datasets. Three neural network architectures, including a fully connected neural network, a radial basis function network, and a back propagation network, were systematically trained and compared. The fully connected neural network demonstrated superior prediction accuracy and generalization capability, offering a robust tool for production profiling. Field validation using actual distributed fiber optic temperature-sensing monitoring data from commingled production wells confirmed the method’s practical effectiveness, with predicted production rates strongly agreeing with the measured values across multiple reservoir layers. The proposed framework provides a reliable, efficient solution for interpreting the production profiles of multilayer wells under single-phase flow conditions. This study establishes a foundational methodology that can be extended to more complex multiphase flow scenarios in future research, thereby contributing to intelligent and automated reservoir management.

The transient flow testing of ultra-deepwater gas wells is greatly impacted by the low temperatures of seawater encountered over extended distances. This leads to a redistribution of temperature within the wellbore, which in turn influences the flow behavior. To accurately predict such a temperature distribution, in this study a comprehensive model of the flowing temperature and pressure fields is developed. This model is based on principles of fluid mechanics, heat transfer, mass conservation, and energy conservation and relies on the Runge-Kutta method for accurate integration in time of the resulting equations. The analysis includes the examination of the influence of various factors, such as gas flow production rate, thermal diffusivity of the formation, and thermal diffusivity of seawater, on the temperature and pressure profiles of the wellbore. The key findings can be summarized as follows: 1. Higher production rates during testing lead to increased flowing temperatures and decreased pressures within the wellbore. However, in the presence of a seawater thermocline, a crossover in flowing temperature is observed. 2. An increase in wellbore pressure is associated with larger pipe diameters. 3. Greater thermal diffusivity of the formation results in more rapid heat transfer from the wellbore to the formation, which causes lower flowing temperatures within the wellbore. 4. In an isothermal layer, higher thermal diffusivity of seawater leads to increased wellbore flowing temperatures. Conversely, in thermocline and mixed layer segments, lower temperatures are noted. 5. Production test data from a representative deep-water gas well in the South China Sea, used to calculate the bottom-seafloor-wellhead temperature and pressure fields across three operating modes, indicate that the average error in temperature prediction is 2.18%, while the average error in pressure prediction is 5.26%, thereby confirming the reliability of the theoretical model.