US 12,423,952 B1
Method for classifying geological section, storage medium and device
Shan Dong, Hubei (CN); Jingrui Jiang, Hubei (CN); Jiacheng Hou, Hubei (CN); Xi Hu, Hubei (CN); and Lianke Li, Hubei (CN)
Assigned to China University of Geosciences, Wuhan (CN)
Filed by China University of Geosciences, Hubei (CN)
Filed on May 30, 2025, as Appl. No. 19/224,711.
Int. Cl. G06V 10/764 (2022.01); G06V 10/72 (2022.01); G06V 10/77 (2022.01); G06V 20/13 (2022.01)
CPC G06V 10/765 (2022.01) [G06V 10/72 (2022.01); G06V 10/7715 (2022.01); G06V 20/13 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A method for classifying a geological section, comprising the following steps:
S1, acquiring on-site exploration data and remote sensing data of a geological section, and a category label of the geological section, preprocessing the on-site exploration data and the remote sensing data, and extracting features on the basis of preprocessed data;
S2, constructing new features on the basis of extracted features, and combining the extracted features and the new features to form a feature set;
the extracted features comprising: a density, a porosity, a mineral content, a particle size distribution, a color index and a saturation; and
construction of the new features being represented as:

OG Complex Work Unit Math
where C represents rock content, a, b and c represent weight coefficients, ρ represents the density, ϕ represents the porosity, M represents the mineral content, D represents the particle size distribution, CI represents the color index of rocks, and S represents the saturation;
S3, selecting and normalizing features in the feature set, and dividing same into a training set and a validation set; and
S4, constructing a geological section classification model, using a light gradient boosting machine (LightGBM) as a model benchmark architecture, training the model using the training set and the category label of the geological section, validating the model after training using the validation set, and inputting data to be tested into the model after validating to obtain geological section classification results.