CEMA-LSTM: Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

Abstract

Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain. Recent relevant research activities have shown their concerns on various deep learning models for radar echo extrapolation, where radar echo maps were used to predict their consequent moment, so as to recognize potential severe convective weather events. However, these approaches suffer from an inaccurate prediction of echo dynamics and unreliable depiction of echo aggregation or dissipation, due to the size limitation of convolution filter, lack of global feature, and less attention to features from previous states. To address the problems, this paper proposes a CEMA-LSTM recurrent unit, which is embedded with a Contextual Feature Correlation Enhancement Block (CEB) and a Multi-Attention Mechanism Block (MAB). The CEB enhances contextual feature correlation and supports its model to memorize significant features for near-future prediction; the MAB uses a position and channel attention mechanism to capture global features of radar echoes. Two practical radar echo datasets were used involving the FREM and CIKM 2017 datasets. Both quantification and visualization of comparative experimental results have demonstrated outperformance of the proposed CEMA-LSTM over recent models, e.g., PhyDNet, MIM and PredRNN++, etc. In particular, compared with the second-ranked model, its average POD, FAR and CSI have been improved by 3.87%, 1.65% and 1.79%, respectively on the FREM, and by 1.42%, 5.60% and 3.16%, respectively on the CIKM 2017.

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

“…Which can forecast the real-time data effectively. 50 Hossain applied LSTM to RT forecasting of photovoltaic power generation, and combined the K-means algorithm to convert historical data into dynamic phenolic characteristics, so as to improve the measurement accuracy. 51 Compared with RT forecasting methods based on machine learning.…”

“…This network improves the advantages of the reserved RNN network, and also optimizes the disadvantages of RNN for long time series processing. Which can forecast the real‐time data effectively 50 . Hossain applied LSTM to RT forecasting of photovoltaic power generation, and combined the K‐means algorithm to convert historical data into dynamic phenolic characteristics, so as to improve the measurement accuracy 51 …”

CFNet: An Eigenvalue Preserved Approach to Multiscale Building Segmentation in High-Resolution Remote Sensing Images

“…Then the input feature F is generated as a V ∈ R C×H×W by convolutional layer operation, which is turned into R C×HW by reshape operation, and we then matrix multiply this V and G and perform an element-by-element summation with X to obtain F ∈ R C×H×W . The process for the overall global relational attention module can then be written as Equation (3).…”

“…S EMANTIC segmentation is a fundamental research problem in today's computer vision research community, which aims to segment images into several predefined and semantically labeled coherent parts [1], [2]. This is a specific application of artificial intelligence in a realistic sense, and is used in radar [3], [4], remote sensing [5], and electricity [6]. However, driven by the current development of Earth observation technology, satellite remote sensing images and aerial images with high spatial resolution have been used by various technologies [7], such as terrain image classification, feature target detection and marker image recognition.…”

DenMerD: A Feature Enhanced Approach to Radar Beam Blockage Correction with Edge-Cloud Computing

“…Weather radar, as an active remote sensing instrument, employs electromagnetic waves to ascertain precipitation location and intensity. Contemporary weather radar offers high spatial and temporal resolution data, proving valuable for meteorological services [1][2][3]. Due to atmospheric refraction, equipment failure and other factors, radar echoes can suffer from beam blockage [4,5].…”