Constraining the Multiscale Structure of Geophysical Fields in Machine Learning: The Case of Precipitation
C Guilloteau, PVV Le… - IEEE Geoscience and …, 2023 - ieeexplore.ieee.org
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 …
remotely sensed information is rapidly expanding. The typical objective function minimized …
Preserving Extremes in Satellite Quantitative Precipitation Estimates: A Matter of Scale
C Guilloteau… - IGARSS 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
Alternative metrics to the mean squared error (MSE) are assessed as optimization criteria for
geophysical remote sensing applications. While the MSE promotes smooth solutions with …
geophysical remote sensing applications. While the MSE promotes smooth solutions with …