Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fusing Climate Data Products using a Spatially Varying Autoencoder

Jacob A. Johnson, Matthew J. Heaton, William F. Christensen, Lynsie R. Warr, Summer B. Rupper

TL;DR

The proposed autoencoder utilizes a Bayesian statistical framework, allowing for probabilistic interpretations while also varying spatially to capture useful spatial patterns across the various data products.

Abstract

Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on creating an identifiable and interpretable autoencoder that can be used to meld and combine climate data products. The proposed autoencoder utilizes a Bayesian statistical framework, allowing for probabilistic interpretations while also varying spatially to capture useful spatial patterns across the various data products. Constraints are placed on the autoencoder as it learns patterns in the data, creating an interpretable consensus that includes the important features from each input. We demonstrate the utility of the autoencoder by combining information from multiple precipitation products in High Mountain Asia.

Fusing Climate Data Products using a Spatially Varying Autoencoder

TL;DR

The proposed autoencoder utilizes a Bayesian statistical framework, allowing for probabilistic interpretations while also varying spatially to capture useful spatial patterns across the various data products.

Abstract

Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on creating an identifiable and interpretable autoencoder that can be used to meld and combine climate data products. The proposed autoencoder utilizes a Bayesian statistical framework, allowing for probabilistic interpretations while also varying spatially to capture useful spatial patterns across the various data products. Constraints are placed on the autoencoder as it learns patterns in the data, creating an interpretable consensus that includes the important features from each input. We demonstrate the utility of the autoencoder by combining information from multiple precipitation products in High Mountain Asia.
Paper Structure (10 sections, 6 equations, 7 figures)

This paper contains 10 sections, 6 equations, 7 figures.

Table of Contents

  1. Introduction
  2. Problem Background
  3. Statistical Model
  4. Model Structure
  5. Model Fitting and Tuning
  6. Application to HMA Data
  7. Setup and Model Fit
  8. Fused Data Product
  9. Sensitivity and Comparison with Alternative Methods
  10. Conclusions

Figures (7)

  • Figure 1: World map showing the HMA region.
  • Figure 2: Four different digital precipitation data products for July 2015.
  • Figure 3: Autoencoder structure with a single neuron consensus.
  • Figure 4: Consensus Data Product for July 2015.
  • Figure 5: 95% Credible Interval on Autoencoder Consensus.
  • ...and 2 more figures