arXiv subjects

Simon Pfreundschuh

Publications and source records attributed to Simon Pfreundschuh.

6 recordsLinked to original sources

arXiv2026

GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products

The Integrated Multi-Satellite Retrievals for the Global Precipitation Measurement (IMERG) product combines precipitation estimates from passive microwave (PMW) and infrared (IR) sensors to provide quasi-global precipitation estimates at half-hourly resolution. Because IR observations are primarily sensitive to cloud-top properties, however, IR-based precipitation estimates are generally less accurate than PMW estimates and can introduce artifacts into the merged precipitation fields. We introduce GPROF-IR, a neural-network-based precipitation retrieval designed to provide precipitation estimates from single-channel geostationary IR observations for the upcoming IMERG V08. GPROF-IR uses a convolutional neural network to exploit spatiotemporal information from sequences of half-hourly IR observations. We validate GPROF-IR against independent surface-based precipitation measurements over land and ocean. GPROF-IR substantially improves upon existing single-channel IR retrievals, including the IR retrieval used in IMERG V07 and more recent neural-network-based approaches. During overpasses of flagship PMW sensors, GPROF-IR is more accurate than the corresponding IMERG PMW estimates over CONUS and Austria, but not Korea. Over CONUS, GPROF-IR outperforms the merged IMERG V07 product for hourly and daily precipitation accumulations. Against shipborne disdrometer observations, GPROF-IR is more accurate than IMERG V07 in the tropics but slightly less accurate in the extratropics. Since geostationary IR observations are continuously available across much of the globe since 1983, GPROF-IR provides a promising basis for improving merged precipitation products and developing long-term, temporally consistent precipitation records.

physics.ao-ph↗

arXiv2026

Prithvi-Precip: Integrating Satellite Observations into an Atmospheric AI Foundation Model for Precipitation Forecasting

Accurate precipitation forecasting remains one of the most challenging problems in weather prediction. While recent AI weather prediction (AIWP) systems have achieved substantial improvements in medium-range forecasting skill, precipitation often remains a secondary target and is commonly learned from reanalysis datasets that contain considerable uncertainty. In this work, we investigate two complementary strategies for improving AI-based precipitation forecasts. Building on the Prithvi-WxC foundation model, we develop Prithvi-Precip, a global precipitation forecasting system, and examine (1) the impact of training targets derived from satellite-based precipitation estimates rather than reanalysis fields and (2) the direct assimilation of satellite observations into the forecasting model. We systematically evaluate key design choices for finetuning the Prithvi-WxC AI foundation model for precipitation forecasting. We find that autoregressive rollout training produces substantially more accurate forecasts than direct conditioning on forecast lead time. Using independent radar-based precipitation estimates for evaluation, we show that training on satellite-derived precipitation targets yields improved forecast accuracy relative to training on MERRA-2 precipitation fields. Furthermore, direct ingestion of satellite observations provides additional improvements at short lead times, with the largest gains occurring in tropical and subtropical regions. Together, these advances enable Prithvi-Precip to substantially improve upon directly comparable precipitation forecasts from the Goddard Earth Observing System. Our results highlight the potential of improved precipitation targets and the direct integration of satellite observations as promising pathways for advancing medium-range AI precipitation forecasting.

physics.ao-ph↗

arXiv2026

Bridging the Sensitivity Gap in Precipitation Estimates from Spaceborne Radars using Passive Microwave Observations

Current global precipitation estimates from spaceborne precipitation radars are limited by their sensitivity to light and frozen precipitation, leading to systematic underestimation of precipitation at high latitudes. Because passive microwave retrievals (PMW) are commonly trained using these radar observations as reference data, this limitation is propagated into PMW This study introduces a novel PMW oceanic precipitation retrieval, GPROF-NN eXtended Precipitation Regime (XPR), that combines reference estimates from a cloud radar and a precipitation radar to overcome the sensitivity limitations of current spaceborne precipitation radars. The retrieval is trained to estimate light precipitation from CloudSat observations and moderate-to-heavy precipitation using observations from the GPM Dual-Frequency Precipitation Radar. The two estimates are combined using a fusion scheme to obtain a consistent precipitation estimate across precipitation regimes. Validation against in situ measurements from shipborne disdrometers shows a 26% improvement in the detection skill for high-latitude precipitation in terms of the critical success index and a reduction in the underestimation of high-latitude and frozen precipitation by more than 50% compared to retrievals constrained only by precipitation radar data. However, the fused retrieval does not improve the precision of instantaneous precipitation estimates, which is likely due to significant random errors in the CloudSat-based reference estimates of liquid precipitation. These results demonstrate that PMW retrievals can leverage the complementary sensitivities of cloud and precipitation radars to provide more consistent precipitation estimates across precipitation regimes than either reference instrument alone. The proposed retrieval provides a pathway to improve the representation of oceanic precipitation in future GPM precipitation products.

physics.ao-ph↗

arXiv2025

A Benchmark Dataset for Satellite-Based Estimation and Detection of Rain

Accurately tracking the global distribution and evolution of precipitation is essential for both research and operational meteorology. Satellite observations remain the only means of achieving consistent, global-scale precipitation monitoring. While machine learning has long been applied to satellite-based precipitation retrieval, the absence of a standardized benchmark dataset has hindered fair comparisons between methods and limited progress in algorithm development. To address this gap, the International Precipitation Working Group has developed SatRain, the first AI-ready benchmark dataset for satellite-based detection and estimation of rain, snow, graupel, and hail. SatRain includes multi-sensor satellite observations representative of the major platforms currently used in precipitation remote sensing, paired with high-quality reference estimates from ground-based radars corrected using rain gauge measurements. It offers a standardized evaluation protocol to enable robust and reproducible comparisons across machine learning approaches. In addition to supporting algorithm evaluation, the diversity of sensors and inclusion of time-resolved geostationary observations make SatRain a valuable foundation for developing next-generation AI models to deliver more accurate, detailed, and globally consistent precipitation estimates.

physics.ao-ph↗

arXiv2024

WxC-Bench: A Novel Dataset for Weather and Climate Downstream Tasks

High-quality machine learning (ML)-ready datasets play a foundational role in developing new artificial intelligence (AI) models or fine-tuning existing models for scientific applications such as weather and climate analysis. Unfortunately, despite the growing development of new deep learning models for weather and climate, there is a scarcity of curated, pre-processed machine learning (ML)-ready datasets. Curating such high-quality datasets for developing new models is challenging particularly because the modality of the input data varies significantly for different downstream tasks addressing different atmospheric scales (spatial and temporal). Here we introduce WxC-Bench (Weather and Climate Bench), a multi-modal dataset designed to support the development of generalizable AI models for downstream use-cases in weather and climate research. WxC-Bench is designed as a dataset of datasets for developing ML-models for a complex weather and climate system, addressing selected downstream tasks as machine learning phenomenon. WxC-Bench encompasses several atmospheric processes from meso-$β$ (20 - 200 km) scale to synoptic scales (2500 km), such as aviation turbulence, hurricane intensity and track monitoring, weather analog search, gravity wave parameterization, and natural language report generation. We provide a comprehensive description of the dataset and also present a technical validation for baseline analysis. The dataset and code to prepare the ML-ready data have been made publicly available on Hugging Face -- https://huggingface.co/datasets/nasa-impact/WxC-Bench

cs.LG↗

arXiv2024

Prithvi WxC: Foundation Model for Weather and Climate

Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downscaling, or nowcasting. While the parallel developments in the AI literature focus on foundation models -- models that can be effectively tuned to address multiple, different use cases -- the developments on the weather and climate side largely focus on single-use cases with particular emphasis on mid-range forecasting. We close this gap by introducing Prithvi WxC, a 2.3 billion parameter foundation model developed using 160 variables from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Prithvi WxC employs an encoder-decoder-based architecture, incorporating concepts from various recent transformer models to effectively capture both regional and global dependencies in the input data. The model has been designed to accommodate large token counts to model weather phenomena in different topologies at fine resolutions. Furthermore, it is trained with a mixed objective that combines the paradigms of masked reconstruction with forecasting. We test the model on a set of challenging downstream tasks namely: Autoregressive rollout forecasting, Downscaling, Gravity wave flux parameterization, and Extreme events estimation. The pretrained model with 2.3 billion parameters, along with the associated fine-tuning workflows, has been publicly released as an open-source contribution via Hugging Face.

cs.LG↗