A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV
Short-term rainfall forecast using GNSS-derived tropospheric parameters has gradually become a research hotspot in GNSS meteorology. Nevertheless, the occurrence of rainfall can be attributed to the impact of various weather factors. With only using tropospheric parameters retrieved from GNSS (such...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/13/9/1381 |
| _version_ | 1797491342385872896 |
|---|---|
| author | Zengqi Ma Guohe Guo Min Cai Xuewen Chen Wenjie Li Liang Zhang |
| author_facet | Zengqi Ma Guohe Guo Min Cai Xuewen Chen Wenjie Li Liang Zhang |
| author_sort | Zengqi Ma |
| collection | DOAJ |
| description | Short-term rainfall forecast using GNSS-derived tropospheric parameters has gradually become a research hotspot in GNSS meteorology. Nevertheless, the occurrence of rainfall can be attributed to the impact of various weather factors. With only using tropospheric parameters retrieved from GNSS (such as ZTD or PWV) for linear forecast, it could be challenging to describe the process of rainfall occurrence accurately. Unlike traditional linear algorithms, machine learning can construct better the relationship between various meteorological parameters and rainfall. Therefore, a combined linear–nonlinear short-term rainfall forecast method is proposed in this paper. In this method, the PWV time series is first linearly fitted using least squares, and rainfall events are determined based on the PWV value, PWV variation, and PWV variation rate. Then, a support vector machine (SVM) is used to establish a nonlinear rainfall forecasting model using the PWV value, air temperature, air pressure, and rainfall. Finally, the previous two rainfall forecast methods are combined to obtain the final rainfall event. To evaluate the accuracy of the proposed method, experiments were conducted utilizing the temperature, pressure, and rainfall data from ERA5. The experimental results show that, compared to existing short-term rainfall forecast models, the proposed method could significantly lower the false alarm rate (FAR) of rainfall forecasts without compromising the true detection rate (TDR), which were 26.33% and 98.66%, respectively. In addition, the proposed method was verified using measured GNSS and meteorological data from Yunmao City, Guangdong, and the TDR and FAR of the verified results were 100% and 20.2%, respectively, which were proven to apply to actual rainfall forecasts. |
| first_indexed | 2024-03-10T00:46:08Z |
| format | Article |
| id | doaj.art-6c1358208ecd4ad48e770ae1969ce478 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T00:46:08Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-6c1358208ecd4ad48e770ae1969ce4782023-11-23T14:58:42ZengMDPI AGAtmosphere2073-44332022-08-01139138110.3390/atmos13091381A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWVZengqi Ma0Guohe Guo1Min Cai2Xuewen Chen3Wenjie Li4Liang Zhang5Guangdong Provincial Highway Construction Co., Ltd., Guangzhou 510623, ChinaGuangdong Yunmao Expressway Co., Ltd., Guangzhou 525346, ChinaGuangdong Provincial Highway Construction Co., Ltd., Guangzhou 510623, ChinaGuangdong Yunmao Expressway Co., Ltd., Guangzhou 525346, ChinaGuangdong Yunmao Expressway Co., Ltd., Guangzhou 525346, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaShort-term rainfall forecast using GNSS-derived tropospheric parameters has gradually become a research hotspot in GNSS meteorology. Nevertheless, the occurrence of rainfall can be attributed to the impact of various weather factors. With only using tropospheric parameters retrieved from GNSS (such as ZTD or PWV) for linear forecast, it could be challenging to describe the process of rainfall occurrence accurately. Unlike traditional linear algorithms, machine learning can construct better the relationship between various meteorological parameters and rainfall. Therefore, a combined linear–nonlinear short-term rainfall forecast method is proposed in this paper. In this method, the PWV time series is first linearly fitted using least squares, and rainfall events are determined based on the PWV value, PWV variation, and PWV variation rate. Then, a support vector machine (SVM) is used to establish a nonlinear rainfall forecasting model using the PWV value, air temperature, air pressure, and rainfall. Finally, the previous two rainfall forecast methods are combined to obtain the final rainfall event. To evaluate the accuracy of the proposed method, experiments were conducted utilizing the temperature, pressure, and rainfall data from ERA5. The experimental results show that, compared to existing short-term rainfall forecast models, the proposed method could significantly lower the false alarm rate (FAR) of rainfall forecasts without compromising the true detection rate (TDR), which were 26.33% and 98.66%, respectively. In addition, the proposed method was verified using measured GNSS and meteorological data from Yunmao City, Guangdong, and the TDR and FAR of the verified results were 100% and 20.2%, respectively, which were proven to apply to actual rainfall forecasts.https://www.mdpi.com/2073-4433/13/9/1381GNSSPWVSVMrainfall forecast model |
| spellingShingle | Zengqi Ma Guohe Guo Min Cai Xuewen Chen Wenjie Li Liang Zhang A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV Atmosphere GNSS PWV SVM rainfall forecast model |
| title | A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV |
| title_full | A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV |
| title_fullStr | A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV |
| title_full_unstemmed | A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV |
| title_short | A Combined Linear–Nonlinear Short-Term Rainfall Forecast Method Using GNSS-Derived PWV |
| title_sort | combined linear nonlinear short term rainfall forecast method using gnss derived pwv |
| topic | GNSS PWV SVM rainfall forecast model |
| url | https://www.mdpi.com/2073-4433/13/9/1381 |
| work_keys_str_mv | AT zengqima acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT guoheguo acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT mincai acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT xuewenchen acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT wenjieli acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT liangzhang acombinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT zengqima combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT guoheguo combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT mincai combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT xuewenchen combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT wenjieli combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv AT liangzhang combinedlinearnonlinearshorttermrainfallforecastmethodusinggnssderivedpwv |