黄铁矿作为页岩体系中最具代表性的重矿物之一，对其进行微观特征识别对于页岩沉积环境研究具有重要意义。以四川盆地泸州Ι区五峰组—龙一₁亚段为例，通过岩心矿物实验、扫描电镜观测、网络模型优化和特征参数统计，构建了适用于黄铁矿扫描电镜图像分割的网络模型，实现了基于草莓状黄铁矿参数对研究区沉积环境的判断。结果表明： \mathrm{①} 优化后的UNet-Im模型对草莓状黄铁矿扫描电镜图像的分割精度可达0.863，证明了改进措施的优越性； \mathrm{②} 对比黄铁矿含量，龙一 {}_{\mathrm{1}}^{\mathrm{1}~\mathrm{3}} 小层黄铁矿含量最高，为2.95%，随后降低至龙一 {}_{\mathrm{1}}^{\mathrm{4}} 小层的2.03%以及五峰组的0.83%； \mathrm{③} 基于草莓状黄铁矿特征参数，推断出黄铁矿沉积环境为深水硫化环境、深水强还原环境、深水强—弱还原环境以及深水还原—次氧化环境。实现了黄铁矿扫描电镜图像的精准化分割，对于提升行业勘探开发智能化具有借鉴意义。

Pyrite, a significant heavy mineral in shale, aids in the comprehension of shale depositional environments. Referencing the Wufeng-Long₁ subsection Formation of the Luzhou Block in Sichuan Basin, a network model for pyrite SEM image segmentation was established via core mineral experiments, SEM observations, network model refinement, and feature parameter analysis. The model assesses the sedimentary environment of the study block using pyrite framboid parameters. \mathrm{①} Our findings indicated that enhancement of the UNet-Im model for pyrite framboid SEM images resulted in a segmentation precision of 0.863, demonstrating the effectiveness of the enhancement measures. \mathrm{②} Pyrite content varied from 2.95% in the Long {}_{\mathrm{1}}^{\mathrm{1}~\mathrm{3}} minor layer to 0.83% in the Wufeng Formation, with the Long {}_{\mathrm{1}}^{\mathrm{4}} minor layer at 2.03%. \mathrm{③} Pyrite depositional environments are deduced as deep-water sulfide environments, strong reducing environments, strong-weak reduction environments, and reductive-suboxidative environments based on pyrite framboid characteristics. This study accurately segmented pyrite SEM images to enhance the exploration and development of intelligence in this industry.