The sinistral Altyn Tagh strike‐slip fault demarcates the northern boundary of the Qinghai‐Tibetan Plateau; however, the significance and timing of activity along the fault are debated. Here new apatite and zircon (U‐Th)/He data are presented, revealing the exhumation history of the Altyn Tagh Mountains from crustal depths of ~2–7 km. Studies of rock samples from the Altun Shan region show that they were located close to the surface during the Early Cretaceous and remained so until about 40 Ma. Samples from the Subei and Dangjin Pass areas, on the other hand, record a period of rapid exhumation at 20 ± 2 Ma, and samples from the Qiemo area record a period of continuous exhumation between ~20 and 12 Ma at a rate of mm/year, plus a further rapid cooling event at 7–5.5 Ma. Thus, significantly more exhumation has occurred toward the southwestern section of the Altyn Tagh Fault Zone, indicating a decrease in tectonic uplift toward the northeast since the Miocene. During the late Miocene, the Tarim Block began to subduct beneath the northern Tibetan margin, resulting in rapid exhumation of the central section of the Altyn Tagh Fault Zone. In accordance with previous studies, the present results support a model of northward propagation and expansion of the Qinghai‐Tibetan Plateau during the Cenozoic.

The western North China Craton (NCC) entered a stage of craton thinning concentrated on its margin in the Cenozoic, but its Late‐Cretaceous conditions were previously deduced to be relatively quiescent. Therefore, whether the Late‐Cretaceous tectonic reactivation existed on the margin of this block is critical to understanding how the craton evolved into a thinned one. To investigate this possible margin reactivation in the Late Cretaceous, we apply zircon (U‐Th)/He thermochronology to Taibai Mountain on the southern margin of the western NCC. From an ∼3‐km‐high vertical profile with ages decreasing from 98 ± 5 Ma at the peak to 52 ± 7 Ma at the foot, the age‐elevation relationship suggests the rapid exhumation at ca. 78–71 Ma bracketed by two slow exhumation phases. This interpretation is confirmed by 1D half‐space modeling and QTQt inverse modeling, with the rapid exhumation stage having an exhumation rate of 0.1–0.6 km/Myr and a cooling rate of ∼10°C/Myr. Together with previously reported thermochronological data from the margin of the western NCC, the rapid exhumation at ca. 78–71 Ma implies a reactivated margin in the Late Cretaceous before widespread Cenozoic thinning of the craton margin. This Late‐Cretaceous reactivation likely resulted from WNW‐ESE extension expressed by thermo‐tectonic events, basin subsidence, and volcanism in East Asia. Excluding impacts from climate change, lithospheric delamination, and India subduction beneath Eurasia, we infer that the Late‐Cretaceous reactivation on the margin of the western NCC was driven by the far‐field effect of Izanagi Plate subduction beneath the Eurasian Plate during slab rollback of the subducted plate.

Building segmentation has extensive research value and application prospects in high-resolution remote sensing image (HRSI) processing. However, complex architectural contexts, varied building morphologies, and non-building occlusions make building segmentation challenging. Compared with traditional methods, deep learning-based methods present certain advantages in terms of accuracy and intelligence. At present, the most popular option is to first apply a single neural network to encode an HRSI, then perform a decoding process through up-sampling or using a transposed convolution operation, and then finally obtain the segmented building image with the help of a loss function. Although effective, this approach not only tends to lead to a loss of detail information, but also fails to fully utilize the contextual features. As an alternative, we propose a novel network called NPSFF-Net. First, using an improved pseudo-Siamese network composed of ResNet-34 and ResNet-50, two sets of deep semantic features of buildings are extracted with the support of transfer learning, and four encoded features at different scales are obtained after fusion. Then, information from the deepest encoded feature is enriched using a feature enhancement module, and the resolutions are recovered via the operations of skip connections and transposed convolutions. Finally, the discriminative features of buildings are obtained using the designed feature fusion algorithm, and the optimal segmentation model is obtained by fitting a cross-entropy loss function. Our method obtained intersection-over-union values of 89.45% for the Aerial Imagery Dataset, 71.88% for the Massachusetts Buildings Dataset, and 68.72% for the Satellite Dataset I.

Tectonics and climate are the two competitive factors sculpturing landforms. Observations on the Earth surface are affected by signals from both tectonic and climatic agents. How to clarify these signals is a key issue. We categorize factors affecting mountain growth as horizontal (extension, compression, and transpression) and vertical (mantle upwelling and climate change) forces to evaluate the driving forces of accelerated exhumation in Taibai Mountain. Based on apatite (U-Th)/He thermochronology, we document two stages of accelerated exhumation at ca. 52-46 Ma and ca. 24-19 Ma from the age-elevation relationship, confirmed by 1D half-space modeling and QTQt inverse modeling. In the framework of paleostress, the two accelerated exhumation events occurred during transpressional periods in the early Eocene and late Oligocene-early Miocene in East China. These two events were triggered by the localized contractional deformation at the intersection of the North Qinling and Fengxian-Taibai faults: The opposite-direction shearing of these two faults was responsible for the former event with an unroofing magnitude of ~1 km; the same-direction shearing of the two faults resulted in the latter event with an unroofing magnitude of ~0.6 km. The far-field effects of both India-Eurasia collision and Pacific subduction drove the accelerated exhumation at ca. 52-46 Ma. The lateral extrusion of the Tibetan Plateau acted as the main driving force for the accelerated exhumation at ca. 24-19 Ma, which may have been slightly influenced by the intensified Asian summer monsoon in the early Miocene.