相关实验视频

Updated: Jan 20, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

使用卷积神经网络-双向长短记忆神经网络模型对页岩油水平井的生产预测

Xuanrui Zhang^1,2, Lin Yan², Fengpeng Lai¹

¹School of Energy Resources, China University of Geosciences (Beijing), Beijing 100083, China.

|January 19, 2026

概括

一个新的CNN-BiLSTM模型准确地预测了从水平井中生产页岩油的情况. 这种先进的方法改善了对非传统资源的预测,提高了能源安全.

科学领域:

石油工程是石油工程中的一个.
人工智能在能源中的作用
非传统资源非传统资源

背景情况:

页岩油对于全球能源安全至关重要,但由于储备的复杂性,难以预测.
传统的方法在页岩水库中的低孔径/透性和复杂的断裂网络方面扎.
准确的产量预测对于优化非传统石油和天然气开发至关重要.

研究的目的:

为页岩油水平井开发一种新且准确的生产预测模型.
整合卷积神经网络 (CNN) 进行空间特征提取和双向长短期记忆 (BiLSTM) 网络进行时间依赖.
用现实世界生产数据验证拟议的CNN-BiLSTM模型.

主要方法:

开发了一种混合CNN-BiLSTM模型用于页岩油产量预测.
利用奥尔多斯盆地7成员水平井的生产数据进行验证.
将CNN-BiLSTM模型与支持向量回归 (SVR),随机森林 (RF),XGBoost,LSTM和BiLSTM进行了对比.

主要成果:

CNN-BiLSTM模型在所有基准算法中表现出卓越的性能.
实现了0.3103的根-平均-平方误差 (RMSE) 和0.1731.1的平均绝对误差 (MAE).
获得了3.2333%的平均绝对百分比误差 (MAPE) 和0.8856.2的确定系数 (R2).

结论:

CNN-BiLSTM模型为页岩油水平井生产预测提供了一个有效和强大的解决方案.
该模型的协同方法提高了复杂的非常规水库的预测准确性.
这些发现为开发非传统石油和天然气资源提供了宝贵的见解.

更多相关视频

Visualization of Neural and Vascular Networks in a Chicken Embryo

Visualization of Neural and Vascular Networks in a Chicken Embryo

Published on: June 17, 2025

Developing a Micro-Tissue-Engineered Neural Network Using a Hydrogel-Based Micro-column

Developing a Micro-Tissue-Engineered Neural Network Using a Hydrogel-Based Micro-column

Published on: August 7, 2025

相关概念视频

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

The present protocol describes a novel end-to-end salient object detection algorithm. It leverages deep neural networks to enhance the precision of salient object detection within intricate environmental...

Visualization of Neural and Vascular Networks in a Chicken Embryo

Visualization of Neural and Vascular Networks in a Chicken Embryo

Source: Delalande, J., et.al. Dual Labeling of Neural Crest Cells and Blood Vessels Within Chicken Embryos Using ChickGFP Neural Tube Grafting and Carbocyanine Dye DiI Injection. J. Vis. Exp. (2015)This video demonstrates the transplantation of a GFP-labeled donor neural tube from a stage-matched transgenic chicken embryo into a recipient embryo at the level of somites one to seven, followed by vascular labeling using a lipophilic fluorescent dye. The combined approach allows for direct...

Developing a Micro-Tissue-Engineered Neural Network Using a Hydrogel-Based Micro-column

Developing a Micro-Tissue-Engineered Neural Network Using a Hydrogel-Based Micro-column

Source: Struzyna, L. A. et. al., Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling. J. Vis. Exp. (2017)This video demonstrates the development of micro-tissue-engineered neural networks using a hydrogel micro-column with an extracellular matrix core. Seeded neuronal aggregates adhere, extend projections, and form structured neural networks, contributing to advancements in neurodevelopment and...

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

The goal of the work presented in this article is to develop technology for automated recognition of food and beverage items from images taken by mobile devices. The technology comprises of two different approaches - the first one performs food image recognition while the second one performs food image...

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Here, we present a protocol for non-invasive assessment of oocyte developmental competence performed during their in vitro maturation from the germinal vesicle to the metaphase II stage. This method combines time-lapse imaging with particle image velocimetry (PIV) and neural network...

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

This manuscript details the fabrication of micro-tissue engineered neural networks: three-dimensional micron-sized constructs comprised of long aligned axonal tracts spanning aggregated neuronal population(s) encased in a tubular hydrogel. These living scaffolds can serve as functional relays to reconstruct or modulate neural circuitry or as biofidelic test-beds mimicking gray-white matter...