• Home
  • Search
  • Nowcasting Meso-γ-Scale Convective Storms Using Convolutional LSTM Models and High-Resolution Radar Observations
  • Cite Icon3
  • https://doi.org/10.16993/tellusa.37Copy DOI Icon

Nowcasting Meso-γ-Scale Convective Storms Using Convolutional LSTM Models and High-Resolution Radar Observations

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

As a deep learning approach to improving precipitation nowcasting, this study proposes convolutional Long Short-Term Memory (LSTM) models which specifically target meso-γ-scale, localized convective storms although there are numerous types of thunderstorms across scales. A Convolutional LSTM Model (CLM) and an Encoder-Decoder Model (EDM) were built by employing LSTM networks that perform better with sequential data. For training, radar reflectivity (<em>Z</em>) datasets of the Multi-Parameter Phased Array Weather Radar (MP-PAWR) for a convective storm event that occurred over the Tokyo metropolitan area were used as input to the models. An Advection Forecast Model (AFM) that utilizes an optical flow method to generate <em>u</em> and <em>v</em> motion vectors and the Lagrangian advection scheme was also developed to compare with nowcasts from the LSTM models. Model performances were assessed using statistics and skill score measures such as Critical Success Index (CSI) and Probability of Detection (POD) with lead time up to 10 min. It was found that for a total rain area with <em>Z</em> &gt; 10 dB<em>Z</em>, the CLM had the best skill, showing higher CSI scores and correlation coefficients than other models for all lead times. For a convective rain area with <em>Z</em> &gt; 35 dB<em>Z</em>, the CLM showed equal to or slightly higher CSI scores than the AFM until the lead time of 7.5 min but underpredicted the strength of convective cells with a lower CSI at 10 min. Both the CLM and EDM showed more negative <em>Z</em> biases at longer lead times, resulting in lower CSI and POD scores than the AFM in this convective rain category. The higher skill of the AFM at longer lead times is most likely because the convective cells were advected without changing their shapes and intensities largely in this short period.

Loading PDF

Similar Papers
  • PDF
  • Research Article
  • Citations8

Forecasting Orange Juice Futures: LSTM, ConvLSTM, and Traditional Models Across Trading Horizons

  • Oct 22, 2024
  • Journal of Risk and Financial Management
  • Apostolos Ampountolas
  • Conference Article
  • Citations38

Short-term Traffic Flow Prediction Based on ConvLSTM Model

  • Jun 01, 2020
  • Xiaoyu Chen +2
  • Research Article
  • Citations1

Enhancing Seizure Detection Accuracy in Wearable EEG Devices Using Deep Learning Algorithms

  • Jan 01, 2025
  • Journal of Disability Research
  • Mohammed Alarfaj +4
  • Research Article
  • Citations5

Vascular wall motion detection models based on long short-term memory in plane-wave-based ultrasound imaging

  • Mar 21, 2023
  • Physics in Medicine & Biology
  • Jeongwung Seo +2
  • PDF
  • Research Article
  • Citations24

Next frame prediction using ConvLSTM

  • Jan 01, 2022
  • Journal of Physics: Conference Series
  • Padmashree Desai +5
  • Research Article
  • Citations6

Learning Syllables Using Conv-LSTM Model for Swahili Word Representation and Part-of-speech Tagging

  • May 26, 2021
  • ACM Transactions on Asian and Low-Resource Language Information Processing
  • Casper Shikali Shivachi +3
  • Research Article
  • Citations1

Missing Well-Log Data Prediction Using a Hybrid U-Net and LSTM Network Model

  • Oct 01, 2025
  • Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description
  • Benard Sasu Oppong +3
  • Research Article
  • Citations83

Short- and mid-term forecasts of actual evapotranspiration with deep learning

  • Sep 01, 2022
  • Journal of Hydrology
  • Ebrahim Babaeian +4
  • Conference Article
  • Citations8

A Deep Learning-Based Real-time Seizure Detection System

  • Dec 05, 2020
  • N Shawki +5
  • Research Article
  • Citations12

Deep learning models for enhanced forest-fire prediction at Mount Kilimanjaro, Tanzania: Integrating satellite images, weather data and human activities data

  • Jun 01, 2025
  • Natural Hazards Research
  • Cesilia Mambile +2
  • Research Article
  • Citations47

Forecasting Hourly Solar Radiation Using Artificial Intelligence Techniques

  • Jan 01, 2021
  • IEEE Canadian Journal of Electrical and Computer Engineering
  • Chibuzor N Obiora +3
  • PDF
  • Research Article
  • Citations39

Comparative study of singing voice detection based on deep neural networks and ensemble learning

  • Nov 26, 2018
  • Human-centric Computing and Information Sciences
  • Shingchern D You +2
  • Preprint Article

Utilizing Physics-Based Predictions as Inputs to LSTM Models for Robust Data-Driven Discharge Simulations of Gauged Catchments Across Denmark

  • Mar 18, 2025
  • Lucas Dalgaard Jensen +4
  • Conference Article

Comparative Evaluation of Temporal Fusion Transformer (TFT) and Long Short-Term Memory (LSTM) Models for Optimizing Water-Alternating-Gas (WAG) Processes in CCUS Projects

  • Jan 13, 2026
  • Ahmed Wagia-Alla +2
  • Research Article
  • Citations23

Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach

  • Jan 01, 2024
  • Space Weather
  • Se‐Heon Jeong +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.