EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatiotemporal Dual-Polarization Radar Quantitative Precipitation Estimation Using Convolutional Neural Networks

Chenhao Xie, Yonghua Zhang, Yi Zhang, Haonan Chen, Li Li, Yuxin Chen, Jian Sun

Remote Sensing · 17.11.2026 · 18 (22) · 3941

DOI: 10.3390/rs18223941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.11.2026. Verfasst von Chenhao Xie und 6 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: GBA Academy of Meteorological Research, China Meteorological Administration, uangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hourly quantitative precipitation estimation (QPE) from weather radar remains difficult during intense rainfall because fixed empirical relations and temporal averaging may not represent rapid scan-to-scan changes and localized echo structure. We evaluated five convolutional neural network configurations using S-band dual-polarization radar and rain-gauge observations in Guangzhou, China. A locally calibrated composite dual-polarization estimator (Composite-DP) provided a conventional reference. Each sample contains ZH, ZDR, and KDP from ten consecutive 0.5° scans over the preceding hour in a 3 × 10 × 21 × 21 tensor. Three-dimensional convolution spans time and two horizontal dimensions, without vertical-volume input. The dataset from 2018 to 2021 comprised 3,008,738 matched samples with rainfall ≥ 0.1 mm h−1, including 2,611,457 for training, 149,221 from six 2020 events for validation, and 141,428 from six 2021 events for testing. The models included a temporally averaged 2D baseline (2DPoly-QPENet), a time-resolved 3D baseline (3DPoly-QPENet), separate temporal (3DTime-QPENet) and multiscale (3DEcho-QPENet) extensions, and their fusion (3DHybrid-QPENet). The temporal extension represented the encoded ten-step sequence with a convolutional long short-term memory (ConvLSTM) layer, whereas the multiscale extension used an encoder–decoder pathway. On the independent test set, Composite-DP yielded an RMSE of 4.139 mm h−1. Compared with 2DPoly-QPENet, 3DPoly-QPENet had a lower mean absolute error (MAE; 1.321 versus 1.524 mm h−1) and root-mean-square error (RMSE; 3.088 versus 3.307 mm h−1), while its correlation coefficient (CC) was higher (0.860 versus 0.832). Among the individual extensions, 3DEcho-QPENet had lower overall errors than 3DTime-QPENet. Their fusion, 3DHybrid-QPENet, achieved the lowest overall MAE (1.270 mm h−1) and RMSE (2.971 mm h−1), with a Bias of −0.537 mm h−1 and the highest CC (0.866). Across the baseline and extension comparisons, the time-resolved 3D representation and the joint temporal and multiscale configuration were associated with lower hourly QPE errors. 3DHybrid-QPENet also had the lowest relative error (RE), MAE, and RMSE in all five rainfall-intensity classes. Above 50 mm h−1, however, its Bias remained −20.031 mm h−1, indicating persistent underestimation. Generalization beyond the study region remains to be evaluated.

Förderung

  • GBA Academy of Meteorological Research
  • China Meteorological Administration
  • uangdong Basic and Applied Basic Research Foundation
  • Liaoning Province Science and Technology Plan Joint Program
  • Shanghai Typhoon Research Foundation
  • Guangzhou Municipal Science and Technology Project

Zitieren

APA

Xie, C., Zhang, Y., Zhang, Y., Chen, H., Li, L., Chen, Y., & Sun, J. (2026). Spatiotemporal Dual-Polarization Radar Quantitative Precipitation Estimation Using Convolutional Neural Networks. Remote Sensing, 18(22), 3941. https://doi.org/10.3390/rs18223941

Vancouver

Xie C, Zhang Y, Zhang Y, Chen H, Li L, Chen Y, et al. Spatiotemporal Dual-Polarization Radar Quantitative Precipitation Estimation Using Convolutional Neural Networks. Remote Sensing. 2026;18(22):3941. doi:10.3390/rs18223941

BibTeX
@article{Xie2026,
  author = {Xie, Chenhao and Zhang, Yonghua and Zhang, Yi and Chen, Haonan and Li, Li and Chen, Yuxin and Sun, Jian},
  title = {Spatiotemporal Dual-Polarization Radar Quantitative Precipitation Estimation Using Convolutional Neural Networks},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {3941},
  doi = {10.3390/rs18223941}
}
Kostenlos starten →