The São Francisco Craton (SFC) and its marginal Araçuaí and Brasília orogens exhibit a significant diversity in their lithospheric architecture. These orogens were shaped during the Neoproterozoic–Cambrian amalgamation of West Gondwana. The rigid cratonic lithosphere of the SFC and the relatively weak lithosphere of the Araçuaí Orogen were disrupted during the Cretaceous opening of the South Atlantic Ocean, whereas the Brasília Orogen remained in the continental hinterland. In earlier research, the thermal effects of the Phanerozoic reactivations in the shallow crust of the Araçuaí Orogen have been revealed by low-temperature thermochronology, mainly by apatite fission track (AFT) analysis. However, analyses from the continental interior are scarce. We present new AFT data from forty-three samples from the Brasília Orogen, the SFC and the Araçuaí Orogen, far from the passive margin of the Atlantic coast (~150 to 800 km). Three main periods of basement exhumation were identified: (i) Paleozoic, recorded both by samples from the SFC and Brasília Orogen; (ii) Early Cretaceous to Cenomanian, recorded by samples from the Araçuaí Orogen; and (iii) Late Cretaceous to Paleocene, inferred in samples from all domains. We compare the differential exhumation pattern of the different geotectonic provinces with their lithospheric strengths. We suggest that the SFC likely concentrated the Meso-Cenozoic reactivations in narrow weak zones while the Araçuaí Orogen displayed a far-reaching Meso-Cenozoic deformation. The Brasília Orogen seems to be an example of a stronger orogenic lithosphere, inhibiting reworking, confirmed by our new AFT data. Understanding the role of the lithosphere rigidity may be decisive to comprehend the processes of differential denudation and the tectonic–morphological evolution over Phanerozoic events.

Abstract A new method for automatic counting of etched fission tracks in minerals is developed and recently published in Geochronology (see Nachtergaele and De Grave, 2021). Artificial intelligence techniques such as deep neural networks and computer vision were trained to detect fission surface semi-tracks on images. The deep neural networks can be used in an open source computer program for semi-automated fission track dating called “AI-Track-tive”. Our custom-trained deep neural networks use YOLOv3 object detection algorithm, which is currently one of the most powerful and fastest object recognition algorithms. Two Deep Neural Networks were trained for both apatite and mica using our training dataset with images from the available microscope. The developed program successfully finds most of the fission tracks in the microscope images, however, the user still needs to supervise the automatic counting. The presented deep neural networks have high precision for apatite (97%) and mica (98%). Recall values are lower for apatite (86%) than for mica (91%). These high values have been obtained on images using the same microscope that provided the training images. The application can be used online on the web page https://ai-track-tive.ugent.be or after download as an offline application for Windows. The online application can be used to analyse captured images and does not require installation or download. The offline application can be used for both live track recognition on live microscopy images and captured images of apatite or mica. AI-Track-tive is written in Python and can be downloaded on https://github.com/SimonNachtergaele.