Hybrid neural parameterization of biophysical models plus multi-task learning improves phenology prediction accuracy by 60% and cold hardiness by 40% over deployed biophysical models.
Prediction Under Uncertainty with Error-Encoding Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future state which are predictable from those which are inherently unpredictable, and encoding the unpredictable components into a low-dimensional latent variable which is fed into a forward model. Our method uses a supervised training objective which is fast and easy to train. We evaluate it in the context of video prediction on multiple datasets and show that it is able to consistently generate diverse predictions without the need for alternating minimization over a latent space or adversarial training.
verdicts
UNVERDICTED 2representative citing papers
LMVP is a GAN-based video prediction model that introduces a motion guider component and information leakage from the discriminator to achieve claimed state-of-the-art results on synthetic and real videos without labeled data.
citing papers explorer
-
A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning
Hybrid neural parameterization of biophysical models plus multi-task learning improves phenology prediction accuracy by 60% and cold hardiness by 40% over deployed biophysical models.
-
LMVP: Video Predictor with Leaked Motion Information
LMVP is a GAN-based video prediction model that introduces a motion guider component and information leakage from the discriminator to achieve claimed state-of-the-art results on synthetic and real videos without labeled data.