A novel Machine Learning-based gap-filling of fine-resolution remotely sensed snow cover fraction data by combining downscaling and regression

View More View Less
  • 1 1 Earth System Science Interdisciplinary Center, University of Maryland, College Park, MD 20742, USA
  • | 2 2 Hydrological Sciences Laboratory, NASA Goddard Space Flight Center, Greenbelt, MD 20771, USA
© Get Permissions Rent on DeepDyve
Restricted access

Abstract

Satellite-based remotely-sensed observations of snow cover fraction (SCF) can have data gaps in spatially distributed coverage from sensor and orbital limitations. We mitigate these limitations in the example fine-resolution Moderate Resolution Imaging Spectroradiometer (MODIS) data by gap-filling using auxiliary 1-km datasets that either aid in downscaling from coarser-resolution (5 km) MODIS SCF wherever not fully covered by clouds, or else by themselves via regression wherever fully cloud-covered. This study’s prototype predicts a 1-km version of the 500 m MOD10A1 SCF target. Due to non-collocatedness of spatial gaps even across input and auxiliary datasets, we consider a recent gap-agnostic advancement of partial convolution in computer vision for both training and predictive gap-filling. Partial convolution accommodates spatially consistent gaps across the input images, effectively implementing a 2-dimensional masking. To overcome reduced usable data from non-collocated spatial gaps across inputs, we innovate a fully generalized 3-dimensional masking in this partial convolution. This enables a valid output value at a pixel even if only a single valid input variable and its value exist in the neighborhood covered by the convolutional filter zone centered around that pixel. Thus our gap-agnostic technique can use significantly more examples for training (~67%) and prediction (~100%), instead of only less than 10% for the previous partial convolution. We train an example simple 3-layer legacy Super-Resolution Convolutional Neural Network (SRCNN) to obtain downscaling and regression component performances that are better than baseline values of either climatology or MOD10C1 SCF as relevant. Our generalized partial convolution can enable multiple earth science applications like downscaling, regression, classification and segmentation that were hindered by data gaps.

Corresponding author: soni.yatheendradas@nasa.gov, +1 (301) 286-9135

This article is included in the 2019 NOAA Workshop on AI for Earth Observations and NWP Special Collection.

Abstract

Satellite-based remotely-sensed observations of snow cover fraction (SCF) can have data gaps in spatially distributed coverage from sensor and orbital limitations. We mitigate these limitations in the example fine-resolution Moderate Resolution Imaging Spectroradiometer (MODIS) data by gap-filling using auxiliary 1-km datasets that either aid in downscaling from coarser-resolution (5 km) MODIS SCF wherever not fully covered by clouds, or else by themselves via regression wherever fully cloud-covered. This study’s prototype predicts a 1-km version of the 500 m MOD10A1 SCF target. Due to non-collocatedness of spatial gaps even across input and auxiliary datasets, we consider a recent gap-agnostic advancement of partial convolution in computer vision for both training and predictive gap-filling. Partial convolution accommodates spatially consistent gaps across the input images, effectively implementing a 2-dimensional masking. To overcome reduced usable data from non-collocated spatial gaps across inputs, we innovate a fully generalized 3-dimensional masking in this partial convolution. This enables a valid output value at a pixel even if only a single valid input variable and its value exist in the neighborhood covered by the convolutional filter zone centered around that pixel. Thus our gap-agnostic technique can use significantly more examples for training (~67%) and prediction (~100%), instead of only less than 10% for the previous partial convolution. We train an example simple 3-layer legacy Super-Resolution Convolutional Neural Network (SRCNN) to obtain downscaling and regression component performances that are better than baseline values of either climatology or MOD10C1 SCF as relevant. Our generalized partial convolution can enable multiple earth science applications like downscaling, regression, classification and segmentation that were hindered by data gaps.

Corresponding author: soni.yatheendradas@nasa.gov, +1 (301) 286-9135

This article is included in the 2019 NOAA Workshop on AI for Earth Observations and NWP Special Collection.

Save