Abstract. Pysteps is an open-source and community-driven Python library for probabilistic precipitation nowcasting, that is, very-short-range forecasting (0–6 h). The aim of pysteps is to serve two different needs. The first is to provide a modular and well-documented framework for researchers interested in developing new methods for nowcasting and stochastic space–time simulation of precipitation. The second aim is to offer a highly configurable and easily accessible platform for practitioners ranging from weather forecasters to hydrologists. In this sense, pysteps has the potential to become an important component for integrated early warning systems for severe weather. The pysteps library supports various input/output file formats and implements several optical flow methods as well as advanced stochastic generators to produce ensemble nowcasts. In addition, it includes tools for visualizing and post-processing the nowcasts and methods for deterministic, probabilistic and neighborhood forecast verification. The pysteps library is described and its potential is demonstrated using radar composite images from Finland, Switzerland, the United States and Australia. Finally, scientific experiments are carried out to help the reader to understand the pysteps framework and sensitivity to model parameters.
Generative adversarial networks (GANs) have been recently adopted for super-resolution, an application closely related to what is referred to as "downscaling" in the atmospheric sciences: improving the spatial resolution of low-resolution images. The ability of conditional GANs to generate an ensemble of solutions for a given input lends itself naturally to stochastic downscaling, but the stochastic nature of GANs is not usually considered in super-resolution applications. Here, we introduce a recurrent, stochastic super-resolution GAN that can generate ensembles of time-evolving high-resolution atmospheric fields for an input consisting of a low-resolution sequence of images of the same field. We test the GAN using two data sets: one consisting of radar-measured precipitation from Switzerland; the other of cloud optical thickness derived from the Geostationary Earth Observing Satellite 16 (GOES-16). We find that the GAN can generate realistic, temporally consistent super-resolution sequences for both data sets. The statistical properties of the generated ensemble are analyzed using rank statistics, a method adapted from ensemble weather forecasting; these analyses indicate that the GAN produces close to the correct amount of variability in its outputs. As the GAN generator is fully convolutional, it can be applied after training to input images larger than the images used to train it. It is also able to generate time series much longer than the training sequences, as demonstrated by applying the generator to a three-month data set of the precipitation radar data. The source code to our GAN is available at https://github.com/jleinonen/downscaling-rnn-gan.
Machine learning algorithms are trained on a 10-yr archive of composite weather radar images in the Swiss Alps to nowcast precipitation growth and decay in the next few hours in moving coordinates (Lagrangian frame). The hypothesis of this study is that growth and decay is more predictable in mountainous regions, which represent a potential source of practical predictability by machine learning methods. In this paper, artificial neural networks (ANN) are employed to learn the complex nonlinear dependence relating the growth and decay to the input predictors, which are geographical location, mesoscale motion vectors, freezing level height, and time of the day. The average long-term growth and decay patterns are effectively reproduced by the ANN, which allows exploring their climatology for any combination of predictors. Due to the low intrinsic predictability of growth and decay, its prediction in real time is more challenging, but is substantially improved when adding persistence information to the predictors, more precisely the growth and decay and precipitation intensity in the immediate past. The improvement is considerable in mountainous regions, where, depending on flow direction, the root-mean-square error of ANN predictions can be 20%–30% lower compared with persistence. Because large uncertainty is associated with precipitation forecasting, deterministic machine learning predictions should be coupled with a model for the predictive uncertainty. Therefore, we consider a probabilistic perspective by estimating prediction intervals based on a combination of quantile decision trees and ANNs. The probabilistic framework is an attempt to address the problem of conditional bias, which often characterizes deterministic machine learning predictions obtained by error minimization.
A comparative analysis of TRMM-rain gauge data merging techniques at the daily time scale for distributed rainfall-runoff modelling applications. J. Hydrometeor. ABSTRACT 2 This study compares 2 non-parameteric rainfall data merging methodsthe Mean Bias Correction and Double kernel Smoothing -with 2 geostatistical methods -Kriging with External Drift and Bayesian Combination -for optimizing the hydrometeorological performance of a satellite-based precipitation product over a mesoscale tropical Andean watershed in Peru. The analysis is conducted using 11 years of daily time series from the Tropical Rainfall Measuring Mission Multi-satellite Precipitation Analysis research product (TMPA, also TRMM 3B42) and 173 rain gauges from the national weather station network. The results are assessed using (1) a cross-validation procedure, and (2) a catchment water balance analysis and hydrological modelling. We found that the Double kernel Smoothing method delivered the most consistent improvement over the original satellite product in both the crossvalidation and hydrological evaluation. The Mean Bias Correction also improved hydrological performance scores, particularly at sub-basin scale wherethe rain gauge density is higher. Given the spatial heterogeneity of the climate, the size of the modelled catchment, and the sparsity of data, we conclude that non-parametric merging methods can perform as well as or better than more complex geostatistical methods, whose assumptions may not hold under the studied conditions. Based on these results, we propose a systematic approach to the selection of satellite-rain gauge data merging technique based on data characteristics. Finally, the underperformance of an Ordinary Kriging interpolation of the rain gauge data, compared to TMPA and other merged products, supports the use of satellite-based products over gridded rain-gauge products that utilize sparse data for hydrological modelling at large scale.Hydrological studies rely on the quality of rainfall estimates to produce meaningful modelling 41 output. Rain gauges can deliver accurate point measurements but their poor ability to describe 42 the spatial structure of rainfall can be a major limitation when precipitation fields are required, 43 for example, in distributed hydrological modelling applications. This problem is more severe in 44 tropical regions due to high rainfall variability and scarce data conditions. 45
Abstract. In this paper we present a non-stationary stochastic generator for radar rainfall fields based on the short-space Fourier transform (SSFT). The statistical properties of rainfall fields often exhibit significant spatial heterogeneity due to variability in the involved physical processes and influence of orographic forcing. The traditional approach to simulate stochastic rainfall fields based on the Fourier filtering of white noise is only able to reproduce the global power spectrum and spatial autocorrelation of the precipitation fields. Conceptually similar to wavelet analysis, the SSFT is a simple and effective extension of the Fourier transform developed for space-frequency localisation, which allows for using windows to better capture the local statistical structure of rainfall. The SSFT is used to generate stochastic noise and precipitation fields that replicate the local spatial correlation structure, i.e. anisotropy and correlation range, of the observed radar rainfall fields. The potential of the stochastic generator is demonstrated using four precipitation cases observed by the fourth generation of Swiss weather radars that display significant non-stationarity due to the coexistence of stratiform and convective precipitation, differential rotation of the weather system and locally varying anisotropy. The generator is verified in its ability to reproduce both the global and the local Fourier power spectra of the precipitation field. The SSFT-based stochastic generator can be applied and extended to improve the probabilistic nowcasting of precipitation, design storm simulation, stochastic numerical weather prediction (NWP) downscaling, and also for other geophysical applications involving the simulation of complex nonstationary fields.
One of the most crucial applications of radar-based precipitation nowcasting systems is the short-term forecast of extreme rainfall events such as flash floods and severe thunderstorms. While deep learning nowcasting models have recently shown to provide better overall skill than traditional echo extrapolation models, they suffer from conditional bias, sometimes reporting lower skill on extreme rain rates compared to Lagrangian persistence, due to excessive prediction smoothing. This work presents a novel method to improve deep learning prediction skills in particular for extreme rainfall regimes. The solution is based on model stacking, where a convolutional neural network is trained to combine an ensemble of deep learning models with orographic features, doubling the prediction skills with respect to the ensemble members and their average on extreme rain rates, and outperforming them on all rain regimes. The proposed architecture was applied on the recently released TAASRAD19 radar dataset: the initial ensemble was built by training four models with the same TrajGRU architecture over different rainfall thresholds on the first six years of the dataset, while the following three years of data were used for the stacked model. The stacked model can reach the same skill of Lagrangian persistence on extreme rain rates while retaining superior performance on lower rain regimes.Plain Positions Indicators (PPI) or Constant Altitude Plain Position Indicator (CAPPI), or the Maximum vertical reflectivity (CMAX or MAX(Z)). Sequences of reflectivity maps are used as input for prediction models. More formally, given a reflectivity field at time T 0 , radar-based nowcasting methods aim to extrapolate m future time steps T 1 , T 2 , ..., T m in the sequence, using as input the current and n previous observations T −n , ..., T −1 , T 0 .Traditional nowcasting models are manly based on Lagrangian echo extrapolation [7,8], with recent modification that try to infer precipitation growth and decay [9,10] or integrate with Numerical Weather Predictions to extend the time horizon of the prediction [11,12]. In the last few years, Deep Learning (DL) models based on combination of Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) have shown substantial improvement over nowcasting methods based on Lagrangian extrapolations for quantitative precipitation forecasting (QPF) [13]. Shi et al. [14] introduced the application of the Convolutional Long Short-Term Memory (Conv-LSTM) network architecture with the specific goal of improving precipitation nowcasting over extrapolation models, where LSTM is modified using a convolution operator in the state-to-state and input-to-state transitions. Subsequent work introduced dynamic recurrent connections [15] (TrajGRU) that allowed the improvement of prediction skills, spatial resolution, and temporal length of the forecast, with comparable number of parameters and memory requirements. Subsequent works introduced more complex memory blocks and architectures [16] and increased num...
A Bayesian precipitation nowcasting system based on the ensemble Kalman filter is formulated. Starting from the last available radar observations, the prediction step of the filter consists of a stochastic radar extrapolation technique, while the correction step updates the radar extrapolation nowcast using information from the most recent forecast by the numerical weather prediction model (NWP). The result is a flow-dependent and seamless blending scheme that is based on the spread of the nowcast and NWP ensembles, used as the definition of the forecast error. To simplify the matrix operations, the Bayesian update is performed in the subspace spanned by the principal components, hence the term reduced space. Synthetic data experiments demonstrated that the Bayesian nowcast correctly captures the flow dependency in both the NWP forecast and the radar extrapolation skills. Four experiments with real precipitation data and a relatively small ensemble size (21 members) represented a first test under realistic conditions, such as stratiform wintertime precipitation and localized summertime convection. The skill was quantified in terms of fractions skill score at 32-km scale and 2.0 mm h−1 intensity. The results indicate that the system is able to produce blended forecasts that are at least as skillful as the nowcast-only or the NWP-only forecasts at any lead time.
The dependence of precipitation growth and decay on the orientation of orographic features, mesoscale flow and freezing‐level height is quantified using a 10‐year archive of composite weather radar images over the Swiss Alpine region. The mesoscale flow is described by the motion of radar precipitation echoes, computed through variational echo tracking, while the freezing‐level height is extracted from the analyses of the numerical weather prediction model COSMO. On the northern side of the Alps, the areas of growth are generally observed on the upwind slopes of the Alpine chain, while on the southern side their location also depends on factors other than the motion of precipitation, such as the convergence of low‐level flows. On the other hand, the decay of precipitation is generally found in the inner Alpine valleys and on the downwind slopes of the Alpine chain. Compared to situations characterized by low freezing level, the areas of precipitation growth penetrate more into the mountain range with high‐freezing‐level conditions. When considering a time lag of 1 h and specific flow conditions, the systematic growth and decay of precipitation can explain up to 30–40% of its total variability over the orography. The relative contribution to the total variability is lower with high freezing level because the non‐systematic variability is larger. The statistical analysis of precipitation growth and decay using large archives of composite radar images highlights the mesoscale flow conditions and geographical locations most prone to orographic precipitation enhancement, but also has potential to improve existing precipitation nowcasting systems in mountainous regions and to provide a basis for the verification of systematic biases of numerical weather prediction models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.