BlackBox: generalizable reconstruction of extremal values from incomplete spatio-temporal data

DOI10.1007/s10687-020-00396-xzbMath1469.62391arXiv2005.02140OpenAlexW3094340151MaRDI QIDQ2028575

Domagoj Vlah, Tomislav Ivek

Publication date: 1 June 2021

Published in: Extremes (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.02140

zbMATH Keywords

data reconstructionensembledeep learningconvolutional neural networkextreme value analysis conference challengespation-temporal extremes

Mathematics Subject Classification ID

Applications of statistics to environmental and related topics (62P12) Artificial neural networks and deep learning (68T07) Statistics of extreme values; tail inference (62G32) Geostatistics (86A32)

Related Items

Ranks of elliptic curves and deep neural networks

Uses Software

• PyTorch
• ImageNet
• Adam
• GitHub
• Tensor2Tensor
• fastai
• U-Net
• AlexNet
• BRITS
• MisGAN

Cites Work

• Unnamed Item
• Unnamed Item
• BRITS
• MisGAN
• Hierarchical neural networks for image interpretation.
• Handbook of Environmental and Ecological Statistics
• Statistical modeling of spatial extremes