Related papers: Cloud-top infrared observations reveal the four-di…
In climate science and meteorology, high-resolution local precipitation (rain and snowfall) predictions are limited by the computational costs of simulation-based methods. Statistical downscaling, or super-resolution, is a common workaround…
Climate change is intensifying rainfall extremes, making high-resolution precipitation projections crucial for society to better prepare for impacts such as flooding. However, current Global Climate Models (GCMs) operate at spatial…
4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…
Reliable nowcasting of extreme precipitation remains difficult because convective systems are strongly nonlinear, multiscale, and nonstationary in 3D. Radar is the backbone of nowcasting, yet existing methods struggle to predict extremes:…
We introduce the Quartet of Diffusions, a structure-aware point cloud generation framework that explicitly models part composition and symmetry. Unlike prior methods that treat shape generation as a holistic process or only support part…
Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider…
We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates…
The evolution of a single raindrop falling below a cloud is governed by fluid dynamics and thermodynamics fundamentally transferable to planetary atmospheres beyond modern Earth's. Here, we show how three properties that characterize…
Improving the representation of precipitation in Earth system models (ESMs) is critical for assessing the impacts of climate change and especially of extreme events like floods and droughts. In existing ESMs, precipitation is not resolved…
Cloud types, as a type of meteorological data, are of particular significance for evaluating changes in rainfall, heatwaves, water resources, floods and droughts, food security and vegetation cover, as well as land use. In order to…
Being able to effectively identify clouds and monitor their evolution is one important step toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation technique is…
Accurate rainfall forecasting is critical because it has a great impact on people's social and economic activities. Recent trends on various literatures show that Deep Learning (Neural Network) is a promising methodology to tackle many…
Accurate precipitation forecasting is indispensable for informed decision-making across various industries. However, the computational demands of current models raise environmental concerns. We address the critical need for accurate…
Information spreads across social and technological networks, but often the network structures are hidden from us and we only observe the traces left by the diffusion processes, called cascades. Can we recover the hidden network structures…
Accurate precipitation estimates at individual locations are crucial for weather forecasting and spatial analysis. This study presents a paradigm shift by leveraging Deep Neural Networks (DNNs) to surpass traditional methods like Kriging…
Precipitation prediction has undergone a profound transformation. A notable limitation of traditional NWP is the need for extensive statistical post-processing. To address this challenge, neural network-based approaches were developed.…
As a primitive 3D data representation, point clouds are prevailing in 3D sensing, yet short of intrinsic structural information of the underlying objects. Such discrepancy poses great challenges on directly establishing correspondences…
Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy. While estimating the scene flow from LiDAR has progressed recently, it remains largely…
Precipitation nowcasting is an important spatio-temporal prediction task to predict the radar echoes sequences based on current observations, which can serve both meteorological science and smart city applications. Due to the chaotic…
Precipitation plays a critical role in the Earth's hydrological cycle, directly affecting ecosystems, agriculture, and water resource management. Accurate precipitation estimation and prediction are crucial for understanding climate…