Customized Reservoir Characterization and Interpretation:

1）High-resolution Reservoir Prediction for Thin-layer Reservoirs

- Wave Field Forwarding Based on Wave Equation

- High-resolution&litude-preserved Conditioning for Reservoir Prediction

- High-resolution Poststack&prestack Inversion Based on Geostatistics

2）Quantitative Prediction of Porosity and Permeability for Tight Reservoirs

- NMR&Imaging Processing Technique for Quantitative Evaluation of Porosity and Permeability

- Fracture and Stress-induced Anisotropic Rock Physical Modeling

- Direct Inversion Based on Prestack Porosity and Permeability Attributes

3）Quantitative Reservoir Characterization for Complex Carbonate Reservoirs

- Seismic Faces Prediction Based on Convolutional Neural Network Algorithm

- Quantitative Porosity Prediction Based on Equivalent Porosity in Carbonate Reservoirs

- Seismic Prediction of Reservoir Permeability Based on Pore Structure Factor

4）Reservoir Prediction for Complex Lithological Igneous Targets

- Logging Litho-stratigraphic Classification Based on Convolutional Neural Network

- Complex Lithological Seismic Prediction Based on Geological-constrained Deep Learning Algorithm

5） Multi-scale Anisotropic Seismic Fracture Prediction

- Fault and Fracture Characterization Based on Deep Learning Algorithm

- Fracture Prediction Based on Reinforced Coherence and other Geometric Properties

- Amplitude Inversion for Micro-cracks Based on Wide-azimuth Seismic Data

- Multi-scale Fusion Technique Based on Clustering Analysis

6） Integrated Evaluation Technique of Geological&Engineering Target for Shale oil/gas Reservoirs

- Logging Geomechanical Modeling

- Logging Formation Evaluation for Shale-gas/oil Reservoir with Complex Mineral Composition

- Orthotropic Rock Physical Modeling and Seismic Forward Modeling

- Quantitative Prediction of TOC Content Based on Seismic Inversion

- Quantitative Prediction and Analysis for Rock Brittle Mineral Content

- 3D Geomechanical Modeling Based on Seismic data