Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386721531> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386721531 abstract "Precipitation nowcasting (up to a few hours) remains a challenge due to the highly complex local interactions that need to be captured accurately. Convolutional Neural Networks rely on convolutional kernels convolving with grid data and the extracted features are trapped by limited receptive field, typically expressed in excessively smooth output compared to ground truth. Thus they lack the capacity to model complex spatial relationships among the grids. Geometric deep learning aims to generalize neural network models to non-Euclidean domains. Such models are more flexible in defining nodes and edges and can effectively capture dynamic spatial relationship among geographical grids. Motivated by this, we explore a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value during the training procedure. Then, the spatial relationship is refined by GCN layers while the temporal information is extracted by 1D convolution with various kernel lengths. The neighboring information is fed as auxiliary input layers to improve the final result. We test the model on sequences of radar reflectivity maps over the Trento/Italy area. The results show that GCNs improves the effectiveness of modeling the local details of the cloud profile as well as the prediction accuracy by achieving decreased error measures." @default.
- W4386721531 created "2023-09-14" @default.
- W4386721531 creator A5000663216 @default.
- W4386721531 creator A5007745122 @default.
- W4386721531 creator A5022524675 @default.
- W4386721531 creator A5068384981 @default.
- W4386721531 creator A5083424027 @default.
- W4386721531 date "2023-09-11" @default.
- W4386721531 modified "2023-09-30" @default.
- W4386721531 title "Exploring Geometric Deep Learning For Precipitation Nowcasting" @default.
- W4386721531 doi "https://doi.org/10.48550/arxiv.2309.05828" @default.
- W4386721531 hasPublicationYear "2023" @default.
- W4386721531 type Work @default.
- W4386721531 citedByCount "0" @default.
- W4386721531 crossrefType "posted-content" @default.
- W4386721531 hasAuthorship W4386721531A5000663216 @default.
- W4386721531 hasAuthorship W4386721531A5007745122 @default.
- W4386721531 hasAuthorship W4386721531A5022524675 @default.
- W4386721531 hasAuthorship W4386721531A5068384981 @default.
- W4386721531 hasAuthorship W4386721531A5083424027 @default.
- W4386721531 hasBestOaLocation W43867215311 @default.
- W4386721531 hasConcept C108583219 @default.
- W4386721531 hasConcept C110484373 @default.
- W4386721531 hasConcept C11413529 @default.
- W4386721531 hasConcept C114614502 @default.
- W4386721531 hasConcept C132525143 @default.
- W4386721531 hasConcept C146849305 @default.
- W4386721531 hasConcept C153180895 @default.
- W4386721531 hasConcept C153294291 @default.
- W4386721531 hasConcept C154945302 @default.
- W4386721531 hasConcept C160633673 @default.
- W4386721531 hasConcept C187691185 @default.
- W4386721531 hasConcept C205649164 @default.
- W4386721531 hasConcept C2524010 @default.
- W4386721531 hasConcept C2781013037 @default.
- W4386721531 hasConcept C33923547 @default.
- W4386721531 hasConcept C41008148 @default.
- W4386721531 hasConcept C45374587 @default.
- W4386721531 hasConcept C554190296 @default.
- W4386721531 hasConcept C62649853 @default.
- W4386721531 hasConcept C74193536 @default.
- W4386721531 hasConcept C76155785 @default.
- W4386721531 hasConcept C80444323 @default.
- W4386721531 hasConcept C81363708 @default.
- W4386721531 hasConceptScore W4386721531C108583219 @default.
- W4386721531 hasConceptScore W4386721531C110484373 @default.
- W4386721531 hasConceptScore W4386721531C11413529 @default.
- W4386721531 hasConceptScore W4386721531C114614502 @default.
- W4386721531 hasConceptScore W4386721531C132525143 @default.
- W4386721531 hasConceptScore W4386721531C146849305 @default.
- W4386721531 hasConceptScore W4386721531C153180895 @default.
- W4386721531 hasConceptScore W4386721531C153294291 @default.
- W4386721531 hasConceptScore W4386721531C154945302 @default.
- W4386721531 hasConceptScore W4386721531C160633673 @default.
- W4386721531 hasConceptScore W4386721531C187691185 @default.
- W4386721531 hasConceptScore W4386721531C205649164 @default.
- W4386721531 hasConceptScore W4386721531C2524010 @default.
- W4386721531 hasConceptScore W4386721531C2781013037 @default.
- W4386721531 hasConceptScore W4386721531C33923547 @default.
- W4386721531 hasConceptScore W4386721531C41008148 @default.
- W4386721531 hasConceptScore W4386721531C45374587 @default.
- W4386721531 hasConceptScore W4386721531C554190296 @default.
- W4386721531 hasConceptScore W4386721531C62649853 @default.
- W4386721531 hasConceptScore W4386721531C74193536 @default.
- W4386721531 hasConceptScore W4386721531C76155785 @default.
- W4386721531 hasConceptScore W4386721531C80444323 @default.
- W4386721531 hasConceptScore W4386721531C81363708 @default.
- W4386721531 hasLocation W43867215311 @default.
- W4386721531 hasOpenAccess W4386721531 @default.
- W4386721531 hasPrimaryLocation W43867215311 @default.
- W4386721531 hasRelatedWork W2731899572 @default.
- W4386721531 hasRelatedWork W2999805992 @default.
- W4386721531 hasRelatedWork W3011074480 @default.
- W4386721531 hasRelatedWork W3116150086 @default.
- W4386721531 hasRelatedWork W3133861977 @default.
- W4386721531 hasRelatedWork W3192840557 @default.
- W4386721531 hasRelatedWork W4200173597 @default.
- W4386721531 hasRelatedWork W4291897433 @default.
- W4386721531 hasRelatedWork W4312417841 @default.
- W4386721531 hasRelatedWork W4321369474 @default.
- W4386721531 isParatext "false" @default.
- W4386721531 isRetracted "false" @default.
- W4386721531 workType "article" @default.