In this study, we present RainNet, a deep convolutional neural network
for radar-based precipitation nowcasting. Its design was inspired by
the U-Net and SegNet families of deep learning models, ...which were
originally designed for binary segmentation tasks. RainNet was trained
to predict continuous precipitation intensities at a lead time of 5 min, using several years of quality-controlled weather radar
composites provided by the German Weather Service (DWD). That data set
covers Germany with a spatial domain of 900 km×900 km
and has a resolution of 1 km in space and 5 min in
time. Independent verification experiments were carried out on 11
summer precipitation events from 2016 to 2017. In order to achieve
a lead time of 1 h, a recursive approach was implemented by using
RainNet predictions at 5 min lead times as model inputs for
longer lead times. In the verification experiments, trivial Eulerian
persistence and a conventional model based on optical flow served as
benchmarks. The latter is available in the rainymotion
library and had previously been shown to outperform DWD's operational
nowcasting model for the same set of verification events. RainNet significantly outperforms the benchmark models at all lead
times up to 60 min for the routine verification metrics mean
absolute error (MAE) and the critical success index (CSI) at intensity
thresholds of 0.125, 1, and 5 mm h−1. However, rainymotion turned out to be superior in predicting the exceedance of higher
intensity thresholds (here 10 and 15 mm h−1). The limited
ability of RainNet to predict heavy rainfall intensities is an
undesirable property which we attribute to a high level of spatial
smoothing introduced by the model. At a lead time of 5 min, an
analysis of power spectral density confirmed a significant loss of
spectral power at length scales of 16 km and below. Obviously,
RainNet had learned an optimal level of smoothing to produce a nowcast
at 5 min lead time. In that sense, the loss of spectral power
at small scales is informative, too, as it reflects the limits of
predictability as a function of spatial scale. Beyond the lead time of
5 min, however, the increasing level of smoothing is a mere
artifact – an analogue to numerical diffusion – that is not
a property of RainNet itself but of its recursive application. In the
context of early warning, the smoothing is particularly unfavorable
since pronounced features of intense precipitation tend to get lost
over longer lead times. Hence, we propose several options to address
this issue in prospective research, including an adjustment of the
loss function for model training, model training for longer lead
times, and the prediction of threshold exceedance in terms of a binary
segmentation task. Furthermore, we suggest additional input data that
could help to better identify situations with imminent precipitation
dynamics. The model code, pretrained weights, and training data are
provided in open repositories as an input for such future studies.
Decline of the North American avifauna Rosenberg, Kenneth V; Dokter, Adriaan M; Blancher, Peter J ...
Science (American Association for the Advancement of Science),
10/2019, Letnik:
366, Številka:
6461
Journal Article
Recenzirano
Odprti dostop
Species extinctions have defined the global biodiversity crisis, but extinction begins with loss in abundance of individuals that can result in compositional and functional changes of ecosystems. ...Using multiple and independent monitoring networks, we report population losses across much of the North American avifauna over 48 years, including once-common species and from most biomes. Integration of range-wide population trajectories and size estimates indicates a net loss approaching 3 billion birds, or 29% of 1970 abundance. A continent-wide weather radar network also reveals a similarly steep decline in biomass passage of migrating birds over a recent 10-year period. This loss of bird abundance signals an urgent need to address threats to avert future avifaunal collapse and associated loss of ecosystem integrity, function, and services.
Weather radars have been widely used to detect and quantify precipitation and nowcast severe weather for more than 50 years. Operational weather radars generate huge three-dimensional datasets that ...can accumulate to terabytes per day. So it is essential to review what can be done with existing vast amounts of data, and how we should manage the present datasets for the future climatologists. All weather radars provide the ref lectivity factor, and this is the main parameter to be archived. Saving reflectivity as volumetric data in the original spherical coordinates allows for studies of the three-dimensional structure of precipitation, which can be applied to understand a number of processes, for example, analyzing hail or thunderstorm modes. Doppler velocity and polarimetric moments also have numerous applications for climate studies, for example, quality improvement of reflectivity and rain rate retrievals, and for interrogating microphysical and dynamical processes. However, observational data alone are not useful if they are not accompanied by sufficient metadata. Since the lifetime of a radar ranges between 10 and 20 years, instruments are typically replaced or upgraded during climatologically relevant time periods. As a result, present metadata often do not apply to past data. This paper outlines the work of the Radar Task Team set by the Atmospheric Observation Panel for Climate (AOPC) and summarizes results from a recent survey on the existence and availability of long time series. We also provide recommendations for archiving current and future data and examples of climatological studies in which radar data have already been used.
Quantitative precipitation nowcasting (QPN) has become an
essential technique in various application contexts, such as early warning or
urban sewage control. A common heuristic prediction approach is ...to track the
motion of precipitation features from a sequence of weather radar images and
then to displace the precipitation field to the imminent future (minutes to
hours) based on that motion, assuming that the intensity of the features
remains constant (“Lagrangian persistence”). In that context, “optical
flow” has become one of the most popular tracking techniques. Yet the
present landscape of computational QPN models still struggles with producing
open software implementations. Focusing on this gap, we have developed and
extensively benchmarked a stack of models based on different optical flow
algorithms for the tracking step and a set of parsimonious extrapolation
procedures based on image warping and advection. We demonstrate that these
models provide skillful predictions comparable with or even superior to
state-of-the-art operational software. Our software library (“rainymotion”)
for precipitation nowcasting is written in the Python programming language
and openly available at GitHub (https://github.com/hydrogo/rainymotion,
Ayzel et al., 2019). That way,
the library may serve as a tool for providing fast, free, and transparent
solutions that could serve as a benchmark for further model development and
hypothesis testing – a benchmark that is far more advanced than the
conventional benchmark of Eulerian persistence commonly used in QPN
verification experiments.
Abstract
Over the years, research has been directed to investigate radar as potential tools for estimating rain. The radar reflectivity is measured by comparing the location of the rain gauge and the ...associated vertical path at certain altitude. The latitude and longitude of the rain gauge is identified to pinpoint the exact associated location by using Rainbow®5 meteorological software. In this work, radar reflectivity was estimated by using S-band Terminal Doppler Weather Radar (TWDR) data at Malaysian KLIA radar station. The rain gauge is owned by Malaysian Department of Irrigation and Drainage (DID) at several locations within the vicinity of the radar. A technique to estimate the
Z-R
relationship by using radar reflectivity information and rainfall rate from rain gauge values is demonstrated in this article. Comparisons between radar reflectivity and actual rain gauge measurement is presented. Preliminary findings using available
Z-R
relation shows similar values with the actual measurement and suitable to be used in tropical climate country such as Malaysia.
Quantitative precipitation estimation with commercial microwave links (CMLs) is a technique developed to supplement weather radar and rain gauge observations. It is exploiting the relation between ...the attenuation of CML signal levels and the integrated rain rate along a CML path. The opportunistic nature of this method requires a sophisticated data processing using robust methods. In this study we focus on the processing step of rain event detection in the signal level time series of the CMLs, which we treat as a binary classification problem. This processing step is particularly challenging, because even when there is no rain, the signal level can show large fluctuations similar to that during rainy periods. False classifications can have a high impact on falsely estimated rainfall amounts. We analyze the performance of a convolutional neural network (CNN), which is trained to detect rainfall-specific attenuation patterns in CML signal levels, using data from 3904 CMLs in Germany. The CNN consists of a feature extraction and a classification part with, in total, 20 layers of neurons and 1.4×105 trainable parameters. With a structure inspired by the visual cortex of mammals, CNNs use local connections of neurons to recognize patterns independent of their location in the time series. We test the CNN's ability to recognize attenuation patterns from CMLs and time periods outside the training data. Our CNN is trained on 4 months of data from 800 randomly selected CMLs and validated on 2 different months of data, once for all CMLs and once for the 3104 CMLs not included in the training. No CMLs are excluded from the analysis. As a reference data set, we use the gauge-adjusted radar product RADOLAN-RW provided by the German meteorological service (DWD). The model predictions and the reference data are compared on an hourly basis. Model performance is compared to a state-of-the-art reference method, which uses the rolling standard deviation of the CML signal level time series as a detection criteria. Our results show that within the analyzed period of April to September 2018, the CNN generalizes well to the validation CMLs and time periods. A receiver operating characteristic (ROC) analysis shows that the CNN is outperforming the reference method, detecting on average 76 % of all rainy and 97 % of all nonrainy periods. From all periods with a reference rain rate larger than 0.6 mm h−1, more than 90 % was detected. We also show that the improved event detection leads to a significant reduction of falsely estimated rainfall by up to 51 %. At the same time, the quality of the correctly estimated rainfall is kept at the same level in regards to the Pearson correlation with the radar rainfall. In conclusion, we find that CNNs are a robust and promising tool to detect rainfall-induced attenuation patterns in CML signal levels from a large CML data set covering all of Germany.
Convective precipitation nowcasting remains challenging due to the fast change in convective weather. Radar images are the most important data source in nowcasting research area. This study proposes ...a radar data-based U-Net model for precipitation nowcasting. The nowcasting problem is first transformed into an image-to-image translation problem in deep learning under the U-Net architecture, which is based on convolutional neural networks (CNNs). The input of the model is five consecutive radar images; the output is the predicted radar reflectivity image. The model consists of three operations: upsampling, downsampling, and skip connection. Three methods, U-Net, TREC, and TrajGRU, are used for comparison in the experiments. The experimental results show that both deep learning methods outperform the TREC method, and the CNN-based U-Net can achieve almost the same performance as TrajGRU which is a recurrent neural network (RNN)-based model. With the advantages that U-Net is simple, efficient, easy to understand, and customize, this result shows the great potential of CNN-based models in addressing time-series applications.