Reconstruction of incomplete wildfire data using deep generative models
نویسندگان
چکیده
We present our submission to the Extreme Value Analysis 2021 Data Challenge in which teams were asked accurately predict distributions of wildfire frequency and size within spatio-temporal regions missing data. For this competition, we developed a variant powerful variational autoencoder models, call Conditional Missing data Importance-Weighted Autoencoder (CMIWAE). Our deep latent variable generative model requires little no feature engineering does not necessarily rely on specifics scoring Challenge. It is fully trained incomplete data, with single objective maximize log-likelihood observed information. mitigate effects relatively low number training samples by stochastic sampling from distribution, as well ensembling set CMIWAE models validated different splits provided
منابع مشابه
Learning Deep Generative Models
Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many artificial intelligence–related tasks, including object recognition, speech perception, and language understanding. Theoretical and biological arguments strongly suggest that building such systems requires models with deep architectures that ...
متن کاملAuxiliary Deep Generative Models
Deep generative models parameterized by neural networks have recently achieved state-ofthe-art performance in unsupervised and semisupervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive. Inspired by the structure...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Extremes
سال: 2023
ISSN: ['1386-1999', '1572-915X']
DOI: https://doi.org/10.1007/s10687-022-00459-1