Njord is a probabilistic GNN model using latent variables and adaptive K-means meshes that produces ensemble forecasts and outperforms deterministic ML baselines on global OceanBench and Baltic Sea domains.
Magneto-thermoelectric current induced by phonon drag in low-dimensional junctions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We examine splitting the heat flow in a low-dimensional junction under influence an external d.c. magnetic field. The junction is a crossing between the narrow single atomic layer stripe (or a nanotube) of a semiconductor C with a metal stripe N (C/N-knot). External source of heat injects the non-equilibrium (NE) phonons, electrons, and holes into C which then propagate in direction the C/N-knot. Most of the heat is carried by NE phonons which drag additional electron and hole excitations along C. In vicinity the C/N-knot, the Lorentz force pulls the charge carriers from C to N thus inducing a substantial lateral magneto-thermoelectric electric current (MTEC) along N.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
Njord is a probabilistic GNN model using latent variables and adaptive K-means meshes that produces ensemble forecasts and outperforms deterministic ML baselines on global OceanBench and Baltic Sea domains.