Understanding source rocks' organic content and thermal maturity is crucial in assessing their hydrocarbon potential. To address this, our study focused on developing an accurate artificial neural network (ANN) model for estimating total organic carbon (TOC) content and a complete set of pyrolysis parameters from conventional well logs. The accuracy of the ANN-based technique in estimating TOC content was found to be significantly higher (correlation coefficient of 0.95) compared to the results obtained using Passey's method (correlation coefficient of 0.44). Additionally, the ANN model provided highly accurate predictions for the pyrolysis parameters S1, S2, S3, and Tmax, with correlation coefficients of 0.85, 0.90, 0.86, and 0.93, respectively. The study focused on the Abu Gabra Formation in the Hamra field, and the ANN data analysis revealed that the source rock in this area is of fair to good quality. The assessment of kerogen type indicated a mixed kerogen type II and type III, suggesting the potentiality for oil and gas generation. The predicted parameters further confirmed that the Abu Gabra source rock is thermally mature and capable of generating indigenous hydrocarbons. The results of the ANN-based modeling were consistent with laboratory measurements, demonstrating the reliability of the predictions for comprehensive source rock evaluation using well logs.

了解烃源岩的有机含量和热成熟度对于评估其油气潜力至关重要。为了解决这个问题，我们的研究重点是开发一个准确的人工神经网络（ANN）模型，用于估计总有机碳（TOC）含量和来自传统测井的一整套热解参数。与使用 Passey 方法获得的结果（相关系数为 0.44）相比，基于 ANN 的技术估算 TOC 含量的准确性明显更高（相关系数为 0.95）。此外，ANN 模型对热解参数 S1、S2、S3 和 Tmax 提供了高度准确的预测，相关系数分别为 0.85、0.90、0.86 和 0.93。研究重点是哈姆拉油田的 Abu Gabra 组，ANN 数据分析显示该地区的烃源岩质量中等至良好。干酪根类型评价表明为II型和III型混合干酪根，表明具有生油、生气潜力。预测参数进一步证实 Abu Gabra 烃源岩处于热成熟状态，能够产生原生碳氢化合物。基于人工神经网络的建模结果与实验室测量结果一致，证明了利用测井曲线进行综合烃源岩评价预测的可靠性。