Dimensionality Reduction Techniques for Subsurface Modeling
<p id="p1">Dimensionality reduction is essential for subsurface modeling, where vast datasets with millions of measurements pose computational challenges. Advanced hardware and algorithms have enabled automated rock classification, seismic interpretation, and reservoir simulation, yet high-dimension...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Capítulo de libro |
| Lenguaje: | inglés |
| Publicado: |
IntechOpen
2025
|
| Materias: | |
| Acceso en línea: | https://www.intechopen.com/chapters/89820 |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | <p id="p1">Dimensionality reduction is essential for subsurface modeling, where vast datasets with millions of measurements pose computational challenges. Advanced hardware and algorithms have enabled automated rock classification, seismic interpretation, and reservoir simulation, yet high-dimensional data remain a bottleneck. Traditional feature selection helps simplify models, but dimensionality reduction techniques are often required for rapid predictions and enhanced interpretability. Inspired by computer vision, where images are compressed into meaningful features, subsurface modeling benefits from encoding techniques that extract latent representations while preserving critical information. This chapter explores popular dimensionality reduction methods, including singular value decomposition (SVD), principal component analysis (PCA), discrete wavelet transform (DWT), dictionary learning (DL), and deep learning-based autoencoders (AE). These techniques optimize storage, reduce computational costs, and improve predictive accuracy and can be applied to complex workflows such as reservoir simulation, history matching, and geologic modeling. By transforming complex geospatial data into lower-dimensional space, they enhance uncertainty quantification and accelerate machine learning workflows. Hence, the chapter provides insights on different dimensionality reduction techniques for subsurface applications, ensuring robust and scalable modeling for energy resource exploration and development.</p> |
|---|---|
| ISBN: | 978-1-83968-501-9 |
| DOI: | 10.5772/intechopen.115648 |