Deep Learning-Based semantic segmentation for geomorphicprocesses signals in tree-ring records

Trees encapsulate environmental changes in their growth through the records in the tree rings, but extractingthis signal proves challenging and time consuming. These challenges persist in the study of geomorphicprocesses, requiring meticulous and prolonged efforts by a specialised technician to identify and dategrowth disturbances (GD). The presence of false annual rings adds another layer of complexity to the task.Today, many classical computer vision-based techniques have been developed for the automatic detectionof annual rings. However, to the best of our knowledge, these techniques have not been applied to thedetection of GD associated with geomorphic events, which are more challenging because they do notpresent as clear visual patterns as annual rings. Deep learning-based architectures have shown greatcapacity for automatic localisation of objects in images with complex shapes.We have applied these systems to the segmentation of evidence of geomorphological processes (i) wounds(ii) callus tissue (iii) latewood (iv) traumatic resin ducts and (v) growth rings. The deep learning (DL)architectures used were Faster R-CNN with ResNet-101-FPN backbone, YOLOv8 and a U-Netarchitecture. For the application of the system, it is necessary divide the image into smaller patches, andpost-processing techniques for the correct unification of the predictions of each image. Training andevaluation of the networks was performed in Google Colaboratory. The algorithm was tested on 150 corestaken ad hoc from a debris flow cone in the Pyrenees (Pineta Valley), where historical debris flows haveoccurred. The cores were subjected to a sanding process and the images were obtained using a Canon Eos8camera. 120 were used to train and validate and 30 to test the architectures, comparing the results obtainedby a classical approach and by DL. The evaluations were performed at the pixel level using the accuracy,precision and recall metrics. After post-processing the predictions, the pixels were converted into instancesand the predictions were compared with the ground truth, and the metrics Intersection over Union (IoU),precision and recall per category were calculated.Our preliminary results suggest that, with a sufficiently large dataset, deep learning-based models cancapture sufficient information to identify the complex patterns to be classified. This implies that it ispossible to achieve a model capable of automatically identifying geomorphological event signals, therebyspeeding up the process of obtaining evidence. This opens the possibility of having proposals of eventsignals without subjective bias, obtaining in different studies, evidence datasets made with a homogeneousand systematised criterion.