Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model

Weather radar data can capture large-scale bird migration information, helping solve a series of migratory ecological problems. However, extracting and identifying bird information from weather radar data remains one of the challenges of radar aeroecology. In recent years, deep learning was applied to the field of radar data processing and proved to be an effective strategy. This paper describes a deep learning method for extracting biological target echoes from weather radar images. This model uses a two-stream CNN (Atrous-Gated CNN) architecture to generate fine-scale predictions by combining the key modules such as squeeze-and-excitation (SE), and atrous spatial pyramid pooling (ASPP). The SE block can enhance the attention on the feature map, while ASPP block can expand the receptive field, helping the network understand the global shape information. The experiments show that in the typical historical data of China next generation weather radar (CINRAD), the precision of the network in identifying biological targets reaches up to 99.6%. Our network can cope with complex weather conditions, realizing long-term and automated monitoring of weather radar data to extract biological target information and provide feasible technical support for bird migration research.

Download Full-text

Wasserstein Generative Adversarial Networks Based Data Augmentation for Radar Data Analysis

Applied Sciences ◽

10.3390/app10041449 ◽

2020 ◽

Vol 10 (4) ◽

pp. 1449

Author(s):

Hansoo Lee ◽

Jonggeun Kim ◽

Eun Kyeong Kim ◽

Sungshin Kim

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Weather Radar ◽

Image Synthesis ◽

Radar Data ◽

Generative Adversarial Networks ◽

Necessary Condition ◽

Radar Images ◽

Adversarial Networks ◽

Wide Range

Ground-based weather radar can observe a wide range with a high spatial and temporal resolution. They are beneficial to meteorological research and services by providing valuable information. Recent weather radar data related research has focused on applying machine learning and deep learning to solve complicated problems. It is a well-known fact that an adequate amount of data is a positively necessary condition in machine learning and deep learning. Generative adversarial networks (GANs) have received extensive attention for their remarkable data generation capacity, with a fascinating competitive structure having been proposed since. Consequently, a massive number of variants have been proposed; which model is adequate to solve the given problem is an inevitable concern. In this paper, we propose exploring the problem of radar image synthesis and evaluating different GANs with authentic radar observation results. The experimental results showed that the improved Wasserstein GAN is more capable of generating similar radar images while achieving higher structural similarity results.

Download Full-text

Using the c-band Doppler weather radar data to reconstruct extreme rainfall event on 11th march 2018 in Bangka island, Indonesia

MATEC Web of Conferences ◽

10.1051/matecconf/201822904013 ◽

2018 ◽

Vol 229 ◽

pp. 04013 ◽

Cited By ~ 1

Author(s):

Jaka Anugrah Ivanda Paski ◽

Donaldi Sukma Permana

Keyword(s):

Extreme Rainfall ◽

Weather Radar ◽

Weather Conditions ◽

Temporal Analysis ◽

Radar Data ◽

Doppler Weather Radar ◽

Extreme Rainfall Event ◽

Radar Images ◽

Precipitation Estimation ◽

Constant Altitude

Extreme weather in the form of heavy rainfall hit Bangka Island, Indonesia on 10 - 11 March 2018 caused flooding in some areas such as in Pangkal Pinang and Muntok in Bangka Barat District, Air Asam Belinyu in Bangka Induk District, and Koba in Bangka Tengah District. Observation of weather conditions at Pangkal Pinang Meteorological Station on 10 March 2018 recorded temperature ranged from 23 to 25°C; relative humidity (RH) ranged from 91 to 100% and measured rainfall reached 84.4 mm/day. In Muntok, the measured rainfall reached 257.5 mm/day which exceeds the March average rainfall 250 mm/month. This study aims to reconstruct this extreme rainfall using C-Band Doppler weather radar centered in Palembang, South Sumatera Province with Python-wradlib library. Weather radar images were displayed in Constant Altitude Plan Position Indicator (CAPPI) and Quantitative Precipitation Estimation (QPE) temporal analysis was performed in areas of extreme rainfall by applying the Marshall-Palmer reflectivity-rain rate (Z-R) relationship. The analysis was conducted by observing the movement and growth of convective clouds through the Palembang radar over Bangka Island and identifying the regional extreme rainfall using Indonesia In-House Radar Integration System (IIRIS) over Sumatra Island. The results suggest that the reconstructed rainfall reached 236.7 mm/day for Muntok, 92.1 mm/day for Pangkal Pinang, 106.0 mm/day for Koba and 80.8 mm/day for Air Asam Belinyu. Although most of the location sites are more than 200 km from the radar center, both of the reconstructed and measured rainfall is well comparable.

Download Full-text

Fusion of rain radar images and wind forecasts in adeep learning model applied to rain nowcasting

10.5194/egusphere-egu21-11990 ◽

2021 ◽

Author(s):

Anastase Charantonis ◽

Vincent Bouget ◽

Dominique Béréziat ◽

Julien Brajard ◽

Arthur Filoche

Keyword(s):

Deep Learning ◽

Optical Flow ◽

Weather Forecast ◽

Forecast Model ◽

Radar Data ◽

Learning Model ◽

Rainfall Forecasting ◽

Radar Images ◽

Deep Learning Model ◽

Rain Radar

<p>Short or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risks monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model and to an approach based on optical flow. Our network outperforms by 8% the F1-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 minutes. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls. These results can also be found in Bouget, V., B&#233;r&#233;ziat, D., Brajard, J., Charantonis, A., & Filoche, A. (2020). Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting. arXiv preprint arXiv:2012.05015</p>

Download Full-text

Combining citizen science and weather radar data to study large‐scale bird movements

Ibis ◽

10.1111/ibi.12906 ◽

2020 ◽

Author(s):

Nadja Weisshaupt ◽

Teemu Lehtiniemi ◽

Jarmo Koistinen

Keyword(s):

Citizen Science ◽

Large Scale ◽

Weather Radar ◽

Radar Data

Download Full-text

Detecting and Tracking Communal Bird Roosts in Weather Radar Data

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i01.5373 ◽

2020 ◽

Vol 34 (01) ◽

pp. 378-385

Author(s):

Zezhou Cheng ◽

Saadia Gabriel ◽

Pankaj Bhambhani ◽

Daniel Sheldon ◽

Subhransu Maji ◽

...

Keyword(s):

Latent Variable ◽

Weather Radar ◽

Radar Data ◽

Learning System ◽

Variable Model ◽

Detection Model ◽

Radar Images ◽

Biological Phenomena ◽

The Us ◽

Spatio Temporal

The US weather radar archive holds detailed information about biological phenomena in the atmosphere over the last 20 years. Communally roosting birds congregate in large numbers at nighttime roosting locations, and their morning exodus from the roost is often visible as a distinctive pattern in radar images. This paper describes a machine learning system to detect and track roost signatures in weather radar data. A significant challenge is that labels were collected opportunistically from previous research studies and there are systematic differences in labeling style. We contribute a latent-variable model and EM algorithm to learn a detection model together with models of labeling styles for individual annotators. By properly accounting for these variations we learn a significantly more accurate detector. The resulting system detects previously unknown roosting locations and provides comprehensive spatio-temporal data about roosts across the US. This data will provide biologists important information about the poorly understood phenomena of broad-scale habitat use and movements of communally roosting birds during the non-breeding season.

Download Full-text

The large-scale spatio-temporal variability of precipitation over Sweden observed from the weather radar network

Atmospheric Measurement Techniques Discussions ◽

10.5194/amtd-6-10699-2013 ◽

2013 ◽

Vol 6 (6) ◽

pp. 10699-10730

Author(s):

A. Devasthale ◽

L. Norin

Keyword(s):

Temporal Variability ◽

High Intensity ◽

Large Scale ◽

Weather Radar ◽

Radar Data ◽

The Arctic ◽

Northern Sweden ◽

Late Night ◽

Spatio Temporal ◽

Precipitation Events

Abstract. Using measurements from the national network of 12 weather radar stations for the last decade (2000–2010), we investigate the large-scale spatio-temporal variability of precipitation over Sweden. These statistics provide useful information to evaluate regional climate models as well as for hydrology and energy applications. A strict quality control is applied to filter out noise and artifacts from the radar data. We focus on investigating four distinct aspects namely, the diurnal cycle of precipitation and its seasonality, the dominant time scale (diurnal vs. seasonal) of variability, precipitation response to different wind directions, and the correlation of precipitation events with the North Atlantic Oscillation (NAO) and the Arctic Oscillation (AO). When classified based on their intensity, moderate to high intensity events (precipitation > 0.34 mm (3 h)−1) peak distinctly during late afternoon over the majority of radar stations in summer and during late night or early morning in winter. Precipitation variability is highest over the southwestern parts of Sweden. It is shown that the high intensity events (precipitation > 1.7mm (3 h)−1) are positively correlated with NAO and AO (esp. over northern Sweden), while the low intensity events are negatively correlated (esp. over southeastern parts). It is further observed that southeasterly winds often lead to intense precipitation events over central and northern Sweden, while southwesterly winds contribute most to the total accumulated precipitation for all radar stations. Apart from its operational applications, the present study demonstrates the potential of the weather radar data set for studying climatic features of precipitation over Sweden.

Download Full-text

AutoNowP: An Approach Using Deep Autoencoders for Precipitation Nowcasting Based on Weather Radar Reflectivity Prediction

Mathematics ◽

10.3390/math9141653 ◽

2021 ◽

Vol 9 (14) ◽

pp. 1653

Author(s):

Gabriela Czibula ◽

Andrei Mihai ◽

Alexandra-Ioana Albu ◽

Istvan-Gergely Czibula ◽

Sorin Burcea ◽

...

Keyword(s):

Binary Classification ◽

Weather Radar ◽

Predictive Performance ◽

Weather Conditions ◽

Radar Data ◽

Probability Of Detection ◽

Radar Reflectivity ◽

Classification Model ◽

Precipitation Forecast ◽

Short Term

Short-term quantitative precipitation forecast is a challenging topic in meteorology, as the number of severe meteorological phenomena is increasing in most regions of the world. Weather radar data is of utmost importance to meteorologists for issuing short-term weather forecast and warnings of severe weather phenomena. We are proposing AutoNowP, a binary classification model intended for precipitation nowcasting based on weather radar reflectivity prediction. Specifically, AutoNowP uses two convolutional autoencoders, being trained on radar data collected on both stratiform and convective weather conditions for learning to predict whether the radar reflectivity values will be above or below a certain threshold. AutoNowP is intended to be a proof of concept that autoencoders are useful in distinguishing between convective and stratiform precipitation. Real radar data provided by the Romanian National Meteorological Administration and the Norwegian Meteorological Institute is used for evaluating the effectiveness of AutoNowP. Results showed that AutoNowP surpassed other binary classifiers used in the supervised learning literature in terms of probability of detection and negative predictive value, highlighting its predictive performance.

Download Full-text

Precipitation Nowcasting with Weather Radar Images and Deep Learning in São Paulo, Brasil

Atmosphere ◽

10.3390/atmos11111157 ◽

2020 ◽

Vol 11 (11) ◽

pp. 1157

Author(s):

Suzanna Maria Bonnet ◽

Alexandre Evsukoff ◽

Carlos Augusto Morales Rodriguez

Keyword(s):

Deep Learning ◽

Weather Radar ◽

Sao Paulo ◽

São Paulo ◽

Additional Tool ◽

Radar Images ◽

Radar Echoes ◽

Meteorological Systems ◽

Weather Changes ◽

Time Required

Precipitation nowcasting can predict and alert for any possibility of abrupt weather changes which may cause both human and material risks. Most of the conventional nowcasting methods extrapolate weather radar echoes, but precipitation nowcasting is still a challenge, mainly due to rapid changes in meteorological systems and time required for numerical simulations. Recently video prediction deep learning (VPDL) algorithms have been applied in precipitation nowcasting. In this study, we use the VPDL PredRNN++ and sequences of radar reflectivity images to predict the future sequence of reflectivity images for up to 1-h lead time for São Paulo, Brazil. We also verify the feasibility for the continuous use of the VPDL model, providing the meteorologist with trends and forecasts in precipitation edges regardless of the weather event occurring. The results obtained confirm the potential of the VPDL model as an additional tool to assist nowcasting. Even though meteorological systems that trigger natural disasters vary by location, a general solution can contribute as a tool to assist decision-makers and consequently issue efficient alerts.

Download Full-text