Hajime NARUSE

Another new paper alert! We experimentally validate a deep-learning–based 2D inverse model for turbidity currents, enabling flow reconstruction over complex seafloor topography.
#TurbidityCurrents #DeepLearning #Sedimentology #Geohazards
dx.doi.org/10.1029/2025...

Are river deltas morphologically continuous, or do they occupy discrete stable states?
Using unsupervised deep learning on global delta images, we identify 8 delta morphotypes, showing antagonistic controls of rivers and waves on delta geometry.
doi.org/10.1038/s432...

I am thrilled to announce @myharisma's new research paper! A novel cluster analysis method for clastic zircon age distributions clarified the pre-collision location of the Kuril Arc and shed light on the Paleogene ridge subduction in the North Pacific.
rdcu.be/dDapP

I just returned from Kendari, Indonesia. During my stay, we discussed future collaborations at Halu Oleo University. It was a pleasure to have discussions with active and kind faculty members and enthusiastic students. Thank you very much for the invitation.

I am currently visiting Halu Oleo University, Indonesia, to discuss our future collaboration. Beautiful place!

Dr. Kazuki Kikuchi at Chuo Univ. received the Best Paper Award from the Palaeontological Society of Japan for his paper "Morphological function of trace fossil Paleodictyon: an approach from fluid simulation." Congratulations!

www.palaeo-soc-japan.jp/awards/

doi.org/10.2517/PR21...

Understanding flow characteristics from tsunami deposits at Odaka, Joban Coast, using a deep neural network (DNN) inverse model Abstract. The 2011 Tohoku-oki tsunami inundated the Joban coastal area in the Odaka region of the city of Minamisoma, up to 2818 m from the shoreline. In this study, the flow characteristics of the tsunami were reconstructed from deposits using the DNN (deep neural network) inverse model, suggesting that the tsunami inundation occurred in the Froude supercritical condition. The DNN inverse model effectively estimated the tsunami flow parameters in the Odaka region, including the maximum inundation distance, flow velocity, maximum flow depth, and sediment concentration. Despite having a few topographical anthropogenic undulations that caused the inundation height to fluctuate greatly, the reconstructed maximum flow depth and flow velocity were reasonable and close to the values reported in the field observations. The reconstructed data around the Odaka region were characterized by an extremely high velocity (12.1 m s−1). This study suggests that the large fluctuation in flow depths on the Joban Coast compared with the stable flow depths in the Sendai Plain can be explained by the inundation in the supercritical flow condition.

This is my first post on Bluesky!
Inverse analysis of tsunami deposits implied that the 2011 Tohoku-oki tsunami in Minamisoma, Fukushima, inundated as a Fr-supercritical flow with much higher velocity than in the Sendai Plain. See more details at: doi.org/10.5194/nhes...