Dong Zhicheng, Tang Pan, Chen Gongyang, Yin Senlin
Research Institute of Mud Logging Technology and Engineering, Yangtze University, Jingzhou, 434023, China.
Hubei Key Laboratory of Complex Shale Oil and Gas Geology and Development in Southern China, Yangtze University, Jingzhou, 434023, China.
Sci Rep. 2024 Oct 3;14(1):22948. doi: 10.1038/s41598-024-74903-6.
In order to meet the needs of geologists for the analysis of data characterizing field outcrops (rock sections or formations exposed on the ground surface), this study developed a field digital outcrop visualization platform based on Cesium (a 3D geospatial visualization technology) digital outcrop characterization technology. The platform was developed based on WebGL (a protocol for rendering interactions on web pages), which overcame the shortcomings of traditional software in terms of visualization, cross-device, cross-platform, and ease of use. Firstly, UAV inclined photography is used for data collection, which transforms a large amount of geological data into an intuitive 3D geological model, while the visualization platform provides rich measurement and mapping tools for the identified features, which more intuitively displays the outcrop information, helps geological explorers to understand the geological conditions in the field more quickly and comprehensively, and improves the analysis efficiency and ease-of-use of outcrop characterization data. Combined with the improved VGG19 (a deep convolutional neural network architecture) algorithm model, it has excellent performance in dealing with the fine texture and complex structure of rocks, which significantly improves the accuracy of lithology identification. The synergistic application of this technology provides geologists with a faster and more comprehensive means to understand the geological conditions in the field. The reliability of combining the Cesium digital outcrop characterization technology with the VGG19 lithology identification algorithm in geological exploration is verified through case studies. The synergistic application of this technology will greatly enhance the efficiency and ease of analysis of outcrop characterization in the field, and provide new perspectives for future research in geosciences.
为满足地质学家对表征野外露头（地面暴露的岩石剖面或地层）数据进行分析的需求，本研究基于Cesium（一种3D地理空间可视化技术）数字露头表征技术开发了一个野外数字露头可视化平台。该平台基于WebGL（一种用于在网页上渲染交互的协议）开发，克服了传统软件在可视化、跨设备、跨平台和易用性方面的缺点。首先，利用无人机倾斜摄影进行数据采集，将大量地质数据转化为直观的3D地质模型，同时可视化平台为识别出的特征提供丰富的测量和绘图工具，更直观地展示露头信息，帮助地质勘探人员更快、更全面地了解野外地质条件，提高露头表征数据的分析效率和易用性。结合改进的VGG19（一种深度卷积神经网络架构）算法模型，在处理岩石的精细纹理和复杂结构方面具有优异性能，显著提高了岩性识别的准确性。该技术的协同应用为地质学家提供了一种更快、更全面地了解野外地质条件的手段。通过案例研究验证了Cesium数字露头表征技术与VGG19岩性识别算法在地质勘探中结合的可靠性。该技术的协同应用将大大提高野外露头表征分析的效率和易用性，并为地球科学未来的研究提供新的视角。
