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 language | English |
---|---|
Article number | 7503405 |
Journal | IEEE Geoscience and Remote Sensing Letters |
Volume | 20 |
DOIs | |
State | Published - 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