Seismic lithology prediction: Insights from seismic attributes and continuous wavelet transform using CNN and ML Algorithms

Abstract Predicting lithology from seismic attribute data plays an important role in characterizing subsurface properties, including stratigraphy, sedimentary facies, and hydrocarbon potential, particularly in areas with limited well data. One of the main challenges in seismic interpretation arises from the limited resolution, which hinders the ability to detect thin and geologically complex layers. To overcome these limitations, machine learning (ML)-driven approaches offer a robust methodology for establishing correlations between seismic attributes and lithological variations, using well data as a reference. In this study, advanced ML algorithms are employed to identify complex trends in seismic data and their relationships with lithology distribution. The proposed approach was tested on 3D seismic data from the “TGF” Field in the North Kalimantan Basin. The methodologies applied include convolutional neural networks (CNN), random forest (RF), and K-nearest neighbors (KNN). Seismic datasets were transformed into multiple attributes such as RMS amplitude, chaos, envelope, gradient magnitude, sweetness, instantaneous frequency, dominant frequency, instantaneous bandwidth, and instantaneous quality which were subsequently utilized as inputs for gamma ray and lithology prediction. To enhance frequency information, the Continuous Wavelet Transform (CWT) was implemented to derive a time–frequency representation as CNN input. While RF and KNN estimate lithology by analysing statistical relationships between the attributes, CNN evaluates image-based trends across a range of seismic frequency data. The findings demonstrate that the CNN approach with CWT methods can be predicted lithology however with limitations data get overfitting result. Random forest has achieved the highest R2 score 0.84 with lowest MAE 3.15 lowest error rates based on established evaluation metrics. CNN reveals higher sensitivity detect pattern frequency CWT compared to RF and KNN as a result of its effectiveness in modelling detailed spatial dependencies present in seismic images.