Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics

• URL: http://arxiv.org/abs/2608.27521v1
• Date: Thu, 27 Aug 2026 12:43:03 GMT
• Title: Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics
• Abstract summary: We propose Dandelion, a spherical version of Flower, a warp-based neural PDE solver.<n> Layers of Dandelion predict a tangent-plane displacement and transport features along great circles.<n>We obtain a U-Net-like structure by implementing hierarchical pooling entirely in the spherical-harmonic domain.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a regular lat-lon grid causes problems: Cartesian convolutions become distorted at high latitude; 2D FFTs in Fourier neural operators incorrectly assume double periodicity; Cartesian positional encodings in ViTs distort spherical geodesic distances. Recent work moves towards natively spherical primitives, including spherical convolutions (e.g., DeepSphere or DISCO), Spherical Fourier Neural Operators (SFNOs), and geodesic attention. Here we propose Dandelion, a spherical version of Flower, a warp-based neural PDE solver. Layers of Dandelion predict a tangent-plane displacement and transport features along great circles. We obtain a U-Net-like structure by implementing hierarchical pooling entirely in the spherical-harmonic domain. There are thus no convolutions: spatial mixing is achieved only through spherical coordinate changes, or warps. To compare Dandelion with existing spherical architectures, we release an evolving benchmark suite of challenging, natively-spherical PDE datasets including a modified Galewsky jet, anomalous chained turbulence, Cahn-Hilliard decomposition, spherical Riemann shocks, Held-Suarez dry atmospheric transport and global ocean dynamics. This new benchmark fills the gap in existing spherical datasets which are either too small and stylized, or much too large (ERA5) for model iteration. Dandelion is best or second-best on every dataset, and the gap to non-warp baselines widens with resolution: at $256\times 512$, Dandelion and Flower2D occupy the top two slots in both single-step prediction and rollout.

Related papers

• Flowers: A Warp Drive for Neural PDE Solvers [47.10397857711356]
  We introduce Flowers, a neural architecture for learning PDE solution operators built entirely from multihead warps.<n>Flowers achieve excellent performance on a broad suite of 2D and 3D time-dependent PDE benchmarks, particularly flows and waves.
  arXiv  Detail & Related papers  (2026-02-17T15:06:28Z)
• CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs [5.854176164327896]
  Monocular 360 depth estimation is challenging due to the inherent distortion of the equirectangular projection (ERP) plane. In this paper, we propose spherical fully-connected CRFs (SF-CRFs) SF-CRFs enjoy two key components. Firstly, to involve sufficient spherical neighbors, we propose a Spherical Window Transform (SWT) module. This module aims to replicate the equator window's spherical relationships to all other windows, leveraging the rotational invariance of the sphere. Remarkably, the transformation process is highly efficient, completing the transformation of all windows in a 512
  arXiv  Detail & Related papers  (2024-05-19T14:29:06Z)
• SGFormer: Spherical Geometry Transformer for 360 Depth Estimation [52.23806040289676]
  Panoramic distortion poses a significant challenge in 360 depth estimation.<n>We propose a spherical geometry transformer, named SGFormer, to address the above issues.<n>We also present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions.
  arXiv  Detail & Related papers  (2024-04-23T12:36:24Z)
• Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation [62.258256483231484]
  LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Many works project the point cloud onto the 2D image and adopt the 2D Convolutional Neural Networks (CNNs) or vision transformer for LiDAR point cloud semantic segmentation. In this paper, we propose a novel spherical frustum structure to avoid quantized information loss.
  arXiv  Detail & Related papers  (2023-11-29T09:55:13Z)
• Spherical Feature Pyramid Networks For Semantic Segmentation [0.0]
  We develop graph-based models for representing the signal on a spherical mesh. Our models achieve state-of-the-art performance with an mIOU of 48.75, an improvement of 3.75 IoU points over the previous best spherical CNN.
  arXiv  Detail & Related papers  (2023-07-05T21:19:13Z)
• Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions [73.60788465154572]
  Current 2D and 3D location encoders are designed to model point distances in Euclidean space. We propose a multi-scale location encoder called Sphere2Vec which can preserve spherical distances when encoding point coordinates on a spherical surface.
  arXiv  Detail & Related papers  (2023-06-30T12:55:02Z)
• Towards General-Purpose Representation Learning of Polygonal Geometries [62.34832826705641]
  We develop a general-purpose polygon encoding model, which can encode a polygonal geometry into an embedding space. We conduct experiments on two tasks: 1) shape classification based on MNIST; 2) spatial relation prediction based on two new datasets - DBSR-46K and DBSR-cplx46K. Our results show that NUFTspec and ResNet1D outperform multiple existing baselines with significant margins.
  arXiv  Detail & Related papers  (2022-09-29T15:59:23Z)
• Sphere2Vec: Multi-Scale Representation Learning over a Spherical Surface for Geospatial Predictions [4.754823920235069]
  We propose a multi-scale location encoding model called Sphere2Vec. It directly encodes point coordinates on a spherical surface while avoiding the mapprojection distortion problem. We provide theoretical proof that the Sphere2Vec encoding preserves the spherical surface distance between any two points.
  arXiv  Detail & Related papers  (2022-01-25T17:34:29Z)
• PDO-e$\text{S}^\text{2}$CNNs: Partial Differential Operator Based Equivariant Spherical CNNs [77.53203546732664]
  We use partial differential operators to design a spherical equivariant CNN, PDO-e$textStext2$CNN, which is exactly rotation equivariant in the continuous domain. In experiments, PDO-e$textStext2$CNNs show greater parameter efficiency and outperform other spherical CNNs significantly on several tasks.
  arXiv  Detail & Related papers  (2021-04-08T07:54:50Z)
• Cortical surface registration using unsupervised learning [8.57142014602892]
  Non-rigid cortical registration is an important and challenging task due to the geometric complexity of the human cortex. Recent learning-based methods to surfaces yields poor results due to distortions introduced by projecting a sphere to a 2D plane. We present SphereMorph, a diffeomorphic registration framework for cortical surfaces using deep networks that addresses these issues.
  arXiv  Detail & Related papers  (2020-04-09T15:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.