Constraining the Multiscale Structure of Geophysical Fields in Machine Learning: The Case of Precipitation

Clement Guilloteau, Phong V.V. Le, Efi Foufoula-Georgiou

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

The use of deep-learning algorithms for estimating the value of geophysical variables from remotely sensed information is rapidly expanding. The typical objective function minimized in such algorithms is the mean square error (MSE), which is known to lead to smooth estimates with compressed dynamical range as compared to the true distribution of the variable of interest. Here, we introduce and evaluate alternative objective functions, focusing on the retrieval of precipitation rates from satellite passive microwave radiometric measurements using a deep convolutional neural network. For this testbed application, the results show that explicitly imposing the preservation of the statistical distribution and spatial wavelet power spectrum of the target variable allows to accurately reproduce extreme values and sharp gradients across multiple scales.

Original languageEnglish
Article number7503405
JournalIEEE Geoscience and Remote Sensing Letters
Volume20
DOIs
StatePublished - 2023

Funding

This work was supported in part by the NASA through the Global Precipitation Measurement Program under Grant 80NSSC19K0684 and Grant 80NSSC22K0597 and in part by the National Science Foundation (NSF) through the TRIPODS-X Program under Grant DMS-1839336.

Keywords

  • Machine learning
  • objective function
  • precipitation
  • remote sensing
  • satellite

Fingerprint

Dive into the research topics of 'Constraining the Multiscale Structure of Geophysical Fields in Machine Learning: The Case of Precipitation'. Together they form a unique fingerprint.

Cite this