











摘要:針對傳統相干體屬性和機器學習在復雜斷裂識別能力差的問題, 提出一種基于UNet++卷積神經網絡的斷層識別方法。該方法采用加權交叉熵損失函數做目標函數, 使網絡模型訓練過程中避免了數據樣本不平衡的問題, 引入注意力機制和密集卷積塊, 以及更多的跳躍連接, 更好地實現深層次斷層語義信息和淺層次斷層空間信息之間的特征融合, 進而可以使UNet++網絡模型更好地實現斷層識別。實驗結果表明, 該網絡模型將F1值提高到了92.38%, loss降低到0.012 0, 可以更好地學習斷層特征信息。將該模型應用于西南莊斷層的識別中, 結果表明, 該方法可以更準確預測斷層位置, 在識別連續斷層的準確率上有所提高, 有效防止了地下噪音對于斷層識別的不利影響, 從而驗證了UNet++網絡模型在斷層識別上具有一定的研究價值。
關鍵詞:斷層識別; UNet++網絡模型; 加權交叉熵損失函數; 注意力機制; 特征融合
中圖分類號: TP391 文獻標志碼: A
Fault Recognition Based on UNet++ Network Model
AN Zhiwei1, LIU Yumin2, YUAN Shuo1, WEI Haijun1
(1. School of Electrical and Information Engineering, Northeast Petroleum University, Daqing 163318, China;2. School of Electrical Engineering, Chongqing University of Science and Technology, Chongqing 401331, China)
Abstract:Fault identification plays an important role in geological exploration, reservoir description, structural trap and well placement. Aiming at the problem that traditional coherence attribute and machine learning are poor in complex fault recognition, a fault recognition method based on UNet++ convolutional neural network is proposed. The weighted cross entropy loss function is used as the objective function to avoid the problem of data sample imbalance in the training process of the network model. Attention mechanism and dense convolution blocks are introduced, and more jump connections are introduced to better realize the feature fusion between the semantic information of deep faults and the spatial information of shallow faults. Furthermore, the UNet++ network model can realize fault identification better. The experimental results show that the F1 value increased to 92.38% and the loss decreased to 0.012 0, which can better learn fault characteristic information. The model is applied to the identification of the XiNanZhuang fault. The results show that this method can accurately predict the fault location and improve the fault continuity. It is proved that the UNet++ network model has certain research value in fault identification.
Key words:fault identification; UNet++ network model; weighted cross entropy loss function; attention mechanism; feature fusion
0 引 言
斷層是地下巖層沿一個破裂面或破裂帶兩側發生脆性形變而導致巖石層發生相對錯位的突出地質特征[1]。斷層在地質勘探中對地質分析和油氣的聚集與移動都有十分重要的意義, 斷層測繪可以幫助人們預測油氣田的分布和規模, 所以斷層識別在地質勘探中起著十分重要的作用。
近年來, 人工智能技術不斷發展, 出現了越來越多的深度學習算法應用于斷層識別過程中, 這些算法包括BP(Back Propagation Neural Network)混合神經網絡[2]、 AlexNet[3]、 全卷積神經……