3DAEFA-Based Thunderstorm Prediction System With Higher Performance

Yang, Xu; Xing, Hongyan; Xu, Wanyue; Ji, Xinyuan; Su, Xin

doi:10.1109/jsen.2022.3213077

Cited by 6 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is no practical operation in AEF data processing and thunderstorm localization. AEF resolutions in References 16,19,24,37 and this paper are higher, all reaching 0.1 V/m, compared to that in Reference 36. This advantage mainly comes from AEFA design (i.e., single‐axis rotary vane).…”

Section: Results and Analysesmentioning

confidence: 59%

“…Those components labeled as thunderstorm attributes are implemented for thunderstorm localization, imaging and prediction, which fully guarantees the reliability of thunderstorm detection. The CNN‐BiLSTM model established in this paper achieves a higher

{R}^2

of 97%, which is in the same order of magnitude as those achieved in References 24,37 (95.58% and 99.62%). An additional elevation correction session in this paper effectively reduces the negative impact of elevation on the final prediction in the IoT scenario.…”

Section: Results and Analysesmentioning

confidence: 59%

“…Both of them promote thunderstorm detection developments from the time domain to the spatial domain, and enhance thunderstorm visualizations. Paper 24 develops a thunderstorm prediction system. Multiple AEF features are fused to form a switchable pattern with multiple switching conditions.…”

Section: Results and Analysesmentioning

confidence: 99%

“…In Table 1, the processing time is between 18 and 20 s. The proposed method shows stable processing performance and high computational efficiency in different rounds. Paper 24 adopts a 1‐min interval AEF data read way. The proposed method is sufficient to accomplish the task of thunderstorm prediction in this read way with excellent relative real‐time performance.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Considering the strong spatio‐temporal correlation of AEF signals, a thunderstorm prediction framework is built by combining LSTM with bi‐directional LSTM (BiLSTM) in Reference 8. A switchable‐pattern thunderstorm prediction method is proposed in Reference 24 to ensure the prediction performance under different weather, based on Reference 8. Using remote sensing weather data, paper 25 quantitatively assesses the accuracy of LSTM network model variants for thunderstorm severity prediction.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BiLSTM‐based thunderstorm prediction for IoT applications

Zhuang,

Zhu

2024

Computational Intelligence

View full text Add to dashboard Cite

Although the market demand for smart devices (SDs) in the Internet of Things (IoT) era is surging, the corresponding thunderstorm protection measures have rarely attracted attention. This paper presents a thunderstorm prediction method with elevation correction, to reduce the thunderstorm damage to SDs by visually tracking thunderstorm activities. First, a self‐made three‐dimensional atmospheric electric field apparatus (3DAEFA) deployed in IoT is developed to collect real‐time AEF data. A 3DAEFA‐based localization model is established, and the localization formula after correction is derived. AEF data predicted by the bi‐directional long short‐term memory (BiLSTM) model are input to this formula to obtain thunderstorm point charge localization results. Then, the localization skill is evaluated. Finally, the proposed method is assessed in experiments, under single and multiple point charge conditions. There are significant reductions of at least 33.1% and 8.8% in ranging and elevation angle errors, respectively. Particularly, this post‐prediction correction reduces the deviation of fitted point charge moving paths by at most 0.189 km, demonstrating excellent application effects. Comparisons with radar charts and existing methods testify that this method can effectively predict thunderstorms.

show abstract

Section: Results and Analysesmentioning

confidence: 59%