A Novel Fusion Forecast Model for Hail Weather in Plateau Areas Based on Machine Learning

Zhang, Yan; Ji, Zhong; Xue, Bing; Wang, Ping

doi:10.1007/s13351-021-1021-2

Cited by 3 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the use of the 10-dimensional PCA comprehensive feature scheme is more effective than directly building models in the 490-dimensional feature space. This aligns with our expectations and previous research findings [19,20,42]; (2) The Fisher feature comprehensive scheme, overall, outperforms the PCA feature comprehensive scheme. This is because PCA's "maximum variance criterion" may not necessarily align with the classification objective, while Fisher's "intra-class cohesion, inter-class separation [52]" criterion aligns with the goals of a classification function.…”

Section: Hail Identification Model Based On Mechanism Features From C...supporting

confidence: 92%

“…Relying solely on a single feature parameter for hail identification can easily introduce biases. Therefore, the adoption of multiple indicators concurrently in the identification process is an inevitable trend in its development [18][19][20]. Lopez et al [21] combined VIL, maximum reflectivity, and height of the maximum reflectivity to construct a logistic model, which yielded promising test results in probability form.…”

Section: Introductionmentioning

confidence: 99%

“…With the advancement of artificial intelligence technologies, the utilization of machine learning nonlinear modeling methods has presented new opportunities in hail identification. Researchers have leveraged multiple meteorological parameters to employ support vector machines for hail classification recognition [1,24], devised integrated hail forecasting models using random forests and Bayesian minimum error decision approaches [19], and designed deep neural networks for precipitation forecasting [25].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Research on Hail Mechanism Features Based on Dual-Polarization Radar Data

Li,

Zhang,

Wang

et al. 2023

Atmosphere

Self Cite

View full text Add to dashboard Cite

Hail is a type of severe convective weather disaster characterized by abundant water vapor and strong updrafts, resulting in intense and high reflectivity echoes in hail clouds, often accompanied by an overhanging form. Although hail research has made great progress, it is still challenging to achieve accurate identification of hail. Compared with traditional radar, dual-polarization radar can output a variety of polarization parameters and provide information about the shape and phase of precipitation particles, which is conducive to the identification of hail particles. In this study, dual-polarization radar data are used to explore more hail features from various perspectives, starting with the morphological characteristics of hail clouds and using common feature extraction methods in the field of image processing. A comprehensive approach to high-dimensional features is developed. Using machine learning methods, hail identification models are constructed in both the traditional mechanism feature space and the new feature space constructed in this study. Experimental results strongly confirm the significant effectiveness of the five-dimensional new mechanism features developed in this paper for hail identification.

show abstract

Section: Hail Identification Model Based On Mechanism Features From C...supporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Hail Mechanism Features Based on Dual-Polarization Radar Data

Li,

Zhang,

Wang

et al. 2023

Atmosphere

Self Cite

View full text Add to dashboard Cite

show abstract

“…At present, machine learning has a great application prospect in the field of meteorology [10,11]. This paper introduces an extreme learning machine in the field of machine learning into the spectral moment estimation of weather signals and studies a spectral moment estimation algorithm based on ELM.…”

Section: Introductionmentioning

confidence: 99%

Weather Radar High-resolution Spectral Moment Estimation Using Bidirectional Extreme Learning Machine

Wang,

Qiao,

Jiang

et al. 2024

PIER C

View full text Add to dashboard Cite

Since the performance of the spectral moment estimation algorithm commonly used in engineering degrades under the conditions of low SNR, this paper introduces the Extreme Learning Machine (ELM) to the spectral moment estimation of weather signals based on the correlation of the signals of adjacent range cells. To solve the problem that the hidden layer nodes of ELM algorithm are difficult to be determined, the Bidirectional Extreme Learning Machine (B-ELM) algorithm is applied to achieve the high resolution of spectral moments. Firstly, to improve the SNR of the training samples, time-domain pulse signals are converted into weather power spectrum by Welch method. Then, the parameters of the B-ELM hidden layer nodes are directly calculated by backpropagation of network residuals. The model parameters are optimized according to the least-squares solution, where the optimal number of hidden layer nodes is determined adaptively. Finally, the optimized B-ELM model is employed for the spectral moment estimation of weather signals. The algorithm is validated to be fast and accurate for spectral moment estimation using the measured IDRA weather radar data and is easy to implement in engineering.

show abstract

“…Hail refers to hard, spherical, cone-shaped, or irregularly shaped solid precipitation with a diameter of more than 2 mm [1]. Hail is a serious agro-meteorological disaster that can cause serious damage to crop during the growing season, resulting in crop yield reduction or crop extinction, resulting in heavy economic losses [2][3]. Oases in Xinjiang are surrounded by mountains and water, mostly adjacent to deserts or surrounded by Gobi.…”

Section: Introductionmentioning

confidence: 99%

Interannual variation trend of hail days in hail prone areas in Xinjiang

Fan

Wang

Zhang³

2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Hail causes significant agricultural losses in Xinjiang every year, and the study of interannual variation of hail days and its causes can provide a climatic background for hail warning and defense. This study analyzes the trends and abrupt changes in the interannual variability of hail days in the areas with frequent hail using linear trend analysis and abrupt climate change detection methods, and explains the climatic causes of these trends using atmospheric stability. The results show that areas with frequent hails in Xinjiang are located on both sides of the Tianshan Mountains and their adjacent areas, and area with the most to the fewest hail days are in the following order: Zhaosu and Bayinbruck on the Alpine Platform, Aksu region on the south side of the Tianshan Mountains, and Bortala and Kuy-Ma Basin on the north side of the Tianshan Mountains. The interannual variation of hail days in Aksu region, Bortala and Kuy-Ma Basin from 1961 - 2016 shows a linear increasing trend, but the increase is small, only 0.2 - 0.4 d per 10 a, which is contrary to the conclusion of previous studies where the number of hail days in the Chinese region showed a decreasing trend; whereas the Alpine Platforms shows a linear decreasing trend with a larger decrease of 2.5 d per 10 a. The annual number of hail days on the Alpine Platform changed abruptly in 1993 and in the Aksu region in 1978. The linear increase (decrease) in the interannual variation of the warm season modified total index leads to a linear increase (decrease) in the number of hail days on both sides of the Tianshan Mountains and on the Alpine Platform. The trend of interannual variation in the number of hail days in the hail-prone areas in Xinjiang depends on the altitude of the elevation, with a decreasing trend at higher elevations and an increasing trend at lower elevations.

show abstract

A Novel Fusion Forecast Model for Hail Weather in Plateau Areas Based on Machine Learning

Cited by 3 publications

References 39 publications

Research on Hail Mechanism Features Based on Dual-Polarization Radar Data

Research on Hail Mechanism Features Based on Dual-Polarization Radar Data

Weather Radar High-resolution Spectral Moment Estimation Using Bidirectional Extreme Learning Machine

Interannual variation trend of hail days in hail prone areas in Xinjiang

Contact Info

Product

Resources

About