A convolutional recurrent neural network for strong convective rainfall nowcasting using weather radar data in Southeastern Brazil

Caseri, Angelica; Santos, Leonardo Bacelar Lima; Stephany, Stephan

doi:10.1016/j.aiig.2022.06.001

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By handling vast amounts of historical weather data, machine learning algorithms can identify complex relationships and can effectively capture the nonlinear dynamics of weather patterns that contribute to convective rainfall events. This enables more accurate predictions and improved understanding of the complex dynamic physical processes involved in convective rainfall (Caseri et al, 2022; Gibson et al, 2021; Huntingford et al, 2019).…”

Section: How Can We Improve Bathing Water Forecasting Using Advances ...mentioning

confidence: 99%

Forecasting bathing water quality in the UK: A critical review

Krupska,

Speight,

Robinson

et al. 2024

WIREs Water

View full text Add to dashboard Cite

Climate change is altering rainfall patterns resulting in increasing variability and intensity of rainfall events worldwide. Increases to short duration, intense rainfall (i.e., convective rainfall), will lead to increases in sewage overflow and run‐off from agricultural land. Such events generate spikes in micro‐organisms from feces and manure, especially Escherichia coli and intestinal enterococci, that temporarily end up in bathing waters posing serious health risks to bathers. Forecasting of bathing water quality associated with convective rainfall presents a distinctive forecasting challenge due to high uncertainties associated with predicting the timing, location, and impact of such events. In this article, we review examples of bathing water quality forecasting practices, with a focus on the United Kingdom where convective rainfall in the summer bathing water season is a particular concern, and question whether the current approach is robust in a changing climate. We discuss potential upgrades in bathing water forecasting and identify the main challenges that must be addressed before an improved framework for bathing water forecasting can be achieved. Although developments in meteorological and hydrological short‐range forecasting capabilities are promising, convective rainfall forecasting has significant predictability limits. We suggest taking full advantage of short‐range forecasts to provide sub‐daily bathing water forecasts, focusing on targeted bathing water monitoring regimes to improve model accuracy with the ultimate goal of providing improved information and guidance for beach users.This article is categorized under: Science of Water > Water and Environmental Change Human Water > Water Governance Science of Water > Water Quality

show abstract

Section: How Can We Improve Bathing Water Forecasting Using Advances ...mentioning

confidence: 99%

Forecasting bathing water quality in the UK: A critical review

Krupska,

Speight,

Robinson

et al. 2024

WIREs Water

View full text Add to dashboard Cite

show abstract

“…Nowcasting precipitation demands a higher temporal and geographical precision than traditional weather prediction techniques such as numerical weather prediction (NWP) [34]. Precipitation forecasting is therefore quite difficult [35,36]. The dynamics suggested in the space-time domain can be taught to predict the path of clouds in the near future based on past observations of weather radar echoes.…”

Section: Experiments On Radar Echomentioning

confidence: 99%

MSSTNet: A Multi-Scale Spatiotemporal Prediction Neural Network for Precipitation Nowcasting

Gao

Cheng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Convolution-based recurrent neural networks and convolutional neural networks have been used extensively in spatiotemporal prediction. However, these methods tend to concentrate on fixed-scale spatiotemporal state transitions and disregard the complexity of spatiotemporal motion. Through statistical analysis, we found that the distribution of the spatiotemporal sequence and the variety of spatiotemporal motion state transitions exhibit some regularity. In light of these statistics and observations, we propose the Multi-scale Spatiotemporal Neural Network (MSSTNet), an end-to-end neural network based on 3D convolution. It can be separated into three major child modules: a distribution feature extraction module, a multi-scale motion state capture module, and a feature decoding module. Furthermore, the MSST unit is designed to model multi-scale spatial and temporal information in the multi-scale motion state capture module. We first conduct the experiments on the MovingMNIST dataset, which is the most commonly used dataset in the field of spatiotemporal prediction, MSSTNet can achieve state-of-the-art results for this dataset, and ablation experiments demonstrate that the MSST unit has positive significance for spatiotemporal prediction. In addition, this paper applies the model to valuable precipitation nowcasting, due to efficiently capturing the multi-scale information of distribution and motion, the new MSSTNet model can predict the real-world radar echo more accurately.

show abstract

“…It is worth mentioning that intense rainfall in smaller watersheds located in mountainous regions may cause flash flood (FF) events in plainer downstream areas [7]. FF develop quickly, and significantly impact human lives and infrastructures [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

A Neural Network-Based Hydrological Model for Very High-Resolution Forecasting Using Weather Radar Data

Santos

Freitas

Bacelar

et al. 2023

Eng

View full text Add to dashboard Cite

Many hydro-meteorological disasters in small and steep watersheds develop quickly and significantly impact human lives and infrastructures. High-resolution rainfall data and machine learning methods have been used as modeling frameworks to predict those events, such as flash floods. However, a critical question remains: How long must the rainfall input data be for an empirical-based hydrological forecast? The present article employed an artificial neural network (ANN)hydrological model to address this issue to predict river levels and investigate its dependency on antecedent rainfall conditions. The tests were performed using observed water level data and high-resolution weather radar rainfall estimation over a small watershed in the mountainous region of Rio de Janeiro, Brazil. As a result, the forecast water level time series only archived a successful performance (i.e., Nash–Sutcliffe model efficiency coefficient (NSE) > 0.6) when data inputs considered at least 2 h of accumulated rainfall, suggesting a strong physical association to the watershed time of concentration. Under extended periods of accumulated rainfall (>12 h), the framework reached considerably higher performance levels (i.e., NSE > 0.85), which may be related to the ability of the ANN to capture the subsurface response as well as past soil moisture states in the watershed. Additionally, we investigated the model’s robustness, considering different seeds for random number generating, and spacial applicability, looking at maps of weights.

show abstract

A convolutional recurrent neural network for strong convective rainfall nowcasting using weather radar data in Southeastern Brazil

Cited by 9 publications

References 9 publications

Forecasting bathing water quality in the UK: A critical review

Forecasting bathing water quality in the UK: A critical review

MSSTNet: A Multi-Scale Spatiotemporal Prediction Neural Network for Precipitation Nowcasting

A Neural Network-Based Hydrological Model for Very High-Resolution Forecasting Using Weather Radar Data

Contact Info

Product

Resources

About