Tensile Fractures and in situ Stress Measurement Data Constraints on Cretaceous-Present Tectonic Stress Field Evolution of the Tanlu Fault Zone in Shandong Province,North China Craton

Tectonic stress fields are the key drivers of tectonic events and the evolution of regional structures.The tectonic stress field evolution of the Tanlu fault zone in Shandong Province,located in the east of the North China Craton(NCC),may have preserved records of the NCC’s tectonic history.Borehole television survey and hydraulic fracturing were conducted to analyze the paleo and present tectonic stress fields.Three groups of tensile fractures were identified via borehole television,their azimuths being NNW-SSE,NW-SE and NE-SW,representing multiple stages of tectonic events.Hydraulic fracturing data indicates that the study region is experiencing NEE-SWW-oriented compression and nearly-N-Soriented extension,in accordance with strike-slip and compression.Since the Cretaceous,the orientation of the extensional stress has evolved counterclockwise and sequentially from nearly-NW-SE-oriented to NE-SW-oriented and even nearly N-S-oriented,the stress state having transitioned from strike-slip-extension to strike-slip-compression,in association with the rotating and oblique subduction of the Pacific Plate beneath the NCC,with the participation of the Indian Plate.

Comparative analysis of twelve transfer learning models for the prediction and crack detection in concrete dams,based on borehole images

Disaster-resilient dams require accurate crack detection,but machine learning methods cannot capture dam structural reaction temporal patterns and dependencies.This research uses deep learning,convolutional neural networks,and transfer learning to improve dam crack detection.Twelve deep-learning models are trained on 192 crack images.This research aims to provide up-to-date detecting techniques to solve dam crack problems.The finding shows that the EfficientNetB0 model performed better than others in classifying borehole concrete crack surface tiles and normal(undamaged)surface tiles with 91%accuracy.The study’s pre-trained designs help to identify and to determine the specific locations of cracks.