EP-4737950-A1 - SATELLITE PRECIPITATION DATA BIAS CORRECTION

EP4737950A1EP 4737950 A1EP4737950 A1EP 4737950A1EP-4737950-A1

Abstract

A method to train a diffusion regression model for satellite-based precipitation data bias correction may include obtaining satellite observation precipitation data for a training geographic region. The method may include obtaining corresponding ground observation precipitation data for the training geographic region, the corresponding ground observation precipitation data having a same resolution as the satellite observation precipitation data. The method may include generating training residuals from the satellite observation precipitation data and the corresponding ground observation precipitation data. The method may include adding noise to the training residuals. The method may include de-noising the noisy training residuals using a diffusion regression model to generate predicted residuals. The method may include updating the diffusion regression model using a loss function that depends on the training residuals and the predicted residuals.

Inventors

USHIJIMA-MWESIGWA, Hayato
WONG, Hon Yung
DAI, Ting-yu

Assignees

FUJITSU LIMITED

Dates

Publication Date: 20260506
Application Date: 20250509

Claims (20)

A method to train a diffusion regression model for satellite-based precipitation data bias correction, the method comprising: obtaining satellite observation precipitation data for a training geographic region; obtaining corresponding ground observation precipitation data for the training geographic region, the corresponding ground observation precipitation data having a same resolution as the satellite observation precipitation data; generating training residuals from the satellite observation precipitation data and the corresponding ground observation precipitation data; adding noise to the training residuals; de-noising the noisy training residuals using a diffusion regression model to generate predicted residuals; and updating the diffusion regression model using a loss function that depends on the training residuals and the predicted residuals.
The method of claim 1, wherein the diffusion regression model comprises an equivariant diffusion model (EDM).
The method of claim 1, wherein updating the diffusion regression model using the loss function comprises backpropagating loss using a weighted mean square error (MSE) loss function.
The method of claim 3, wherein backpropagating loss comprises, for each training residual and corresponding predicted residual: based on the training residual and the corresponding predicted residual, calculating an error value for the corresponding predicted residual using the weighted MSE loss function; and updating learnable parameters of the diffusion regression model based on the weighted MSE loss function.
The method of claim 1, further comprising, fine-tuning the diffusion regression model for a target geographic region that is different than the training geographic region using past satellite observation precipitation data for the target geographic region and past limited ground observation precipitation data for the target geographic region.
The method of claim 5, wherein the past limited ground observation precipitation data for the target geographic region comprises past rain gauge precipitation data from one or more rain gauges within the target geographic region.
The method of claim 5, wherein fine-tuning the diffusion regression model comprises: obtaining satellite observation precipitation data for the target geographic region; obtaining corresponding limited ground observation precipitation data for the target geographic region; generating second training residuals from the satellite observation precipitation data for the target geographic region and the corresponding limited ground observation precipitation data for the target geographic region; adding noise to the second training residuals; de-noising the noisy second training residuals using the diffusion regression model to generate second predicted residuals; and updating the diffusion regression model using the loss function that depends on the second training residuals and the second predicted residuals.
The method of claim 5, further comprising, bias correcting new satellite observation precipitation data for the target geographic region using the fine-tuned diffusion regression model and new limited ground observation precipitation data for the target geographic region.
The method of claim 8, wherein bias correcting the new satellite observation precipitation data for the target geographic region using the fine-tuned diffusion regression model and the new limited ground observation precipitation data comprises: inputting combined precipitation data into the diffusion regression model to generate a bias correction residual, the combined precipitation data generated from the new satellite observation precipitation data and the new limited ground observation precipitation data; and combining the bias correction residual with the combined precipitation data to produce bias-corrected satellite observation precipitation data for the target geographic region.
The method of claim 9, further comprising, generating the combined precipitation data from the new satellite observation precipitation data and the new limited ground observation precipitation data including applying an inverse distance weighting algorithm.
A non-transitory computer-readable storage medium comprising computer-readable instructions that are executable by a processor to perform or control performance of the method of claim 1.
A method to correct bias in satellite observation precipitation data, the method comprising: obtaining new satellite observation precipitation data for a target geographic region; obtaining new limited ground observation precipitation data for the target geographic region; generating combined precipitation data from the new satellite observation precipitation data and the new limited ground observation precipitation data; adding noise to the combined precipitation data to generate noisy combined precipitation data; inputting the noisy combined precipitation data into a diffusion regression model to generate a bias correction residual; and combining the bias correction residual with the combined precipitation data to generate bias-corrected satellite observation precipitation data for the target geographic region.
The method of claim 12, wherein generating the combined precipitation data from the new satellite observation precipitation data and the new limited ground observation precipitation data comprises applying an inverse distance weighting algorithm.
The method of claim 12, wherein the diffusion regression model comprises an equivariant diffusion model (EDM).
The method of claim 12, further comprising training the diffusion regression model using satellite observation precipitation data for a training geographic region and ground observation precipitation data for the training geographic region, the satellite observation precipitation data and the ground observation precipitation data having a same resolution.
The method of claim 15, wherein training the diffusion regression model comprises: obtaining the satellite observation precipitation data for the training geographic region; obtaining the ground observation precipitation data for the training geographic region; generating training residuals from the satellite observation precipitation data and the ground observation precipitation data; adding noise to the training residuals; de-noising the noisy training residuals using the diffusion regression model to generate predicted residuals; and updating the diffusion regression model using a loss function that depends on the training residuals and the predicted residuals.
The method of claim 15, further comprising fine-tuning the trained diffusion regression model using past satellite observation precipitation data for the target geographic region and past limited ground observation precipitation data for the target geographic region.
The method of claim 12, further comprising, downscaling the bias-corrected satellite observation precipitation data for the target geographic region using a downscale model and the new limited ground observation precipitation data for the target geographic region.
The method of claim 18, wherein downscaling the bias-corrected satellite observation precipitation data for the target geographic region using the downscale model and the new limited ground observation precipitation data comprises: inputting combined upsampled precipitation data into the downscale model to generate a downscaled residual, the combined upsampled precipitation data generated from the bias-corrected satellite observation precipitation data and the new limited ground observation precipitation data; and combining the downscaled residual with the combined upsampled precipitation data to produce a HR precipitation estimate for the target geographic region.
A non-transitory computer-readable storage medium comprising computer-readable instructions that are executable by a processor to perform or control performance of the method of claim 12.

Description

FIELD The present disclosure generally relates to satellite precipitation data bias correction. BACKGROUND Accurate and timely precipitation data is essential for many applications, including early warning systems for natural disasters, local water management, and agricultural planning. However, ground-based weather observation equipment like weather surveillance radar (WSR) is often lacking in remote or developing areas due to its high cost. For example, while the United States and Europe combined have over 600 WSRs, Africa has fewer than 40 despite having almost one and a half times their landmass. The subject matter claimed in the present disclosure may not be limited to embodiments that solve any disadvantages or that operate only in environments such as those described above. Rather, this background may be only provided to illustrate one example technology area where some embodiments described in the present disclosure may be practiced. SUMMARY In an example embodiment, a method to train a diffusion regression model for satellite-based precipitation data bias correction may include obtaining satellite observation precipitation data for a training geographic region. The method may include obtaining corresponding ground observation precipitation data for the training geographic region, the corresponding ground observation precipitation data having a same resolution as the satellite observation precipitation data. The method may include generating training residuals from the satellite observation precipitation data and the corresponding ground observation precipitation data. The method may include adding noise to the training residuals. The method may include de-noising the noisy training residuals using a diffusion regression model to generate predicted residuals. The method may include updating the diffusion regression model using a loss function that depends on the training residuals and the predicted residuals. The object and advantages of the embodiments will be realized and achieved at least by the elements, features, and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are explanatory and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS Example embodiments will be described and explained with additional specificity and detail through the accompanying drawings in which: FIG. 1 illustrates an example system 100 for weather data processing;FIG. 2A illustrates an example process flow to train a diffusion model for satellite data downscaling;FIG. 2B illustrates a flowchart of an example method to train the diffusion model for satellite data downscaling;FIG. 3A illustrates an example process flow to downscale satellite data;FIG. 3B illustrates a flowchart of an example method to downscale satellite data;FIG. 4A illustrates an example process flow to train a diffusion regression model for satellite data bias correction;FIG. 4B illustrates an example process flow to fine-tune the pretrained diffusion regression model of FIG. 4A for satellite data bias correction;FIG. 4C illustrates a flowchart of an example method to train the diffusion regression model for satellite data bias correction;FIG. 5A illustrates an example process flow to bias correct satellite data;FIG. 5B illustrates a flowchart of an example method to bias correct satellite data;FIG. 6 compares error distributions of original and corrected IMERG data relative to LR MRMS data;FIG. 7 compares error distributions of LR MRMS and downscaled MRMS relative to HR MRMS;FIG. 8 illustrates results of applying bias correction and downscale models sequentially to downscale IMERG data to the resolution of MRMS observations, showcasing detailed cloud-like formations and precipitation patterns;FIG. 9 compares error distributions of IMERG, bias corrected IMERG, and downscaled IMERG relative to MRMS data;FIG. 10 shows results of application of a downscale model trained using data from Seattle to data from, respectively, New York, San Jose, and Portland;FIG. 11 shows results of application of a bias correction model trained using data from Seattle to data from, respectively, New York, San Jose, and Portland; andFIG. 12 illustrates a block diagram of an example computing system, in accordance with one or more embodiments of the present disclosure. DETAILED DESCRIPTION Water-related disasters, such as landslides, floods, and droughts, may constitute a significant majority of natural disasters. The past five decades have witnessed over 11,000 reported weather-related disasters globally, tragically claiming over two million lives and inflicting $3.64 trillion in economic losses. Developing countries disproportionately bear this burden, accounting for over 91% of these fatalities. However, advancements in early warning systems and disaster management have yielded a nearly threefold reduction in fatalities between 1970 and