Author Contributions
Conceptualization, Y.H. (Yang Huang) and Y.B.; methodology, Y.H. (Yang Huang) and Y.B.; software, Y.H. (Yang Huang); validation, Y.H. (Yang Huang); formal analysis, Y.H. (Yang Huang) and G.P.P.; data curation, Y.H. (Yang Huang); writing—original draft preparation, Y.H. (Yang Huang); writing—review and editing, Y.B., Q.L., G.P.P., Y.H. (Yanfeng Huo) and F.W.; visualization, Y.H. (Yang Huang); supervision, Y.B.; funding acquisition, Q.L. All authors have read and agreed to the published version of the manuscript.
Figure 1.
Technical flow of precipitation retrieval algorithm.
Figure 1.
Technical flow of precipitation retrieval algorithm.
Figure 2.
ROC-AUC curve (The dash line represents the classification ability equal to 0, also known as the pure opportunity line, and the green line represents the ROC curve).
Figure 2.
ROC-AUC curve (The dash line represents the classification ability equal to 0, also known as the pure opportunity line, and the green line represents the ROC curve).
Figure 3.
Sample number of different ratios (a) during the day and (b) at night.
Figure 3.
Sample number of different ratios (a) during the day and (b) at night.
Figure 4.
ROC-AUC score for different numbers of (a) trees and (b) features.
Figure 4.
ROC-AUC score for different numbers of (a) trees and (b) features.
Figure 5.
Importance ranking of feature variables in precipitation identification model (a) during the day and (b) at night.
Figure 5.
Importance ranking of feature variables in precipitation identification model (a) during the day and (b) at night.
Figure 6.
Hour-by-hour results of precipitation identification model on testing dataset (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 6.
Hour-by-hour results of precipitation identification model on testing dataset (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 7.
Precipitation identification results from 0200 UTC to 0230 UTC on 18 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 7.
Precipitation identification results from 0200 UTC to 0230 UTC on 18 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 8.
Precipitation identification results of 1500 UTC~1530 UTC on 9 August 2022: (a) GPM IMERG precipitation product, (b) FY-4B/AGRI operational precipitation product and (c) RF model inversion results.
Figure 8.
Precipitation identification results of 1500 UTC~1530 UTC on 9 August 2022: (a) GPM IMERG precipitation product, (b) FY-4B/AGRI operational precipitation product and (c) RF model inversion results.
Figure 9.
Evaluation indicators of ocean and land, (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 9.
Evaluation indicators of ocean and land, (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 10.
Evaluation indicators of different underlying surfaces of land, (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 10.
Evaluation indicators of different underlying surfaces of land, (a) FAR, (b) POD, (c) CSI and (d) ETS.
Figure 11.
Sample numbers for different ratios during (a) day and (b) night.
Figure 11.
Sample numbers for different ratios during (a) day and (b) night.
Figure 12.
MSE for different numbers of (a) trees and (b) features.
Figure 12.
MSE for different numbers of (a) trees and (b) features.
Figure 13.
Importance ranking of feature variables in precipitation estimation model (a) during day and (b) at night.
Figure 13.
Importance ranking of feature variables in precipitation estimation model (a) during day and (b) at night.
Figure 14.
Density scatterplot of precipitation intensity with GPM IMERG and RF predictions (a) during day and (b) at night.
Figure 14.
Density scatterplot of precipitation intensity with GPM IMERG and RF predictions (a) during day and (b) at night.
Figure 15.
(a) BIAS and (b) RMSE between retrieval model and operational product at different precipitation levels.
Figure 15.
(a) BIAS and (b) RMSE between retrieval model and operational product at different precipitation levels.
Figure 16.
Hour-by-hour results of the precipitation estimation model for the testing dataset (a) R, (b) BIAS and (c) RMSE.
Figure 16.
Hour-by-hour results of the precipitation estimation model for the testing dataset (a) R, (b) BIAS and (c) RMSE.
Figure 17.
Precipitation estimation results from 0200 UTC to 0230 UTC on 18 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 17.
Precipitation estimation results from 0200 UTC to 0230 UTC on 18 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 18.
Precipitation estimation results of 1500 UTC~1530 UTC on 9 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 18.
Precipitation estimation results of 1500 UTC~1530 UTC on 9 August 2022: (a) GPM IMERG product, (b) FY-4B/AGRI operational precipitation product and (c) RF model.
Figure 19.
RMSE comparison of different underlying surfaces: (a) land and sea classification, (b) land classification.
Figure 19.
RMSE comparison of different underlying surfaces: (a) land and sea classification, (b) land classification.
Figure 20.
Evaluation indicators of precipitation identification model and FY-4B/AGRI operational precipitation product based on the ground rain gauge data and GPM IMERG product (a) during the day and (b) at night.
Figure 20.
Evaluation indicators of precipitation identification model and FY-4B/AGRI operational precipitation product based on the ground rain gauge data and GPM IMERG product (a) during the day and (b) at night.
Figure 21.
Evaluation indicators of precipitation estimation model and FY-4B/AGRI operational precipitation product based on the ground rain gauge data and GPM IMERG product (a) during the day and (b) at night.
Figure 21.
Evaluation indicators of precipitation estimation model and FY-4B/AGRI operational precipitation product based on the ground rain gauge data and GPM IMERG product (a) during the day and (b) at night.
Table 1.
FY-4B/AGRI specifications.
Table 1.
FY-4B/AGRI specifications.
Band | Central Wavelength (μm) | Spectral Bandwidth (μm) | Spatial Resolution (km) | Main Applications |
---|
1 | 0.47 | 0.45~0.49 | 1 | Visibility, Aerosol |
2 | 0.65 | 0.55~0.75 | 0.5 | Visibility, Vegetation |
3 | 0.825 | 0.75~0.90 | 1 | Vegetation, Aerosol |
4 | 1.379 | 1.371~1.386 | 2 | Cirrus cloud |
5 | 1.61 | 1.58~1.64 | 2 | Cloud/Snow, Water cloud/Ice cloud |
6 | 2.225 | 2.10~2.35 | 2 | Cirrus cloud, Aerosol |
7 | 3.75 | 3.50~4.00 (high) | 2 | Cloud, Fire point |
8 | 3.75 | 3.50~4.00 (low) | 4 | Earth’s surface |
9 | 6.25 | 5.80~6.70 | 4 | Upper-level water vapour |
10 | 6.95 | 6.75~7.15 | 4 | Mid-level water vapour |
11 | 7.42 | 7.24~7.60 | 4 | Lower-level water vapour |
12 | 8.55 | 8.3~8.8 | 4 | Cloud |
13 | 10.80 | 10.30~11.30 | 4 | Cloud, Surface temperature |
14 | 12.00 | 11.50~12.50 | 4 | Cloud, Total water vapor |
15 | 13.3 | 13.00~13.60 | 4 | Cloud |
Table 2.
Land cover types and corresponding labels.
Table 2.
Land cover types and corresponding labels.
Land Cover Types | Labels |
---|
Farmland | 10, 20 |
Woodland | 12, 51, 52, 61, 62, 71, 72, 81, 82, 91, 92, 120, 121, 122 |
Grassland | 11, 130, 140, 150, 152, 153 |
Bare land | 200, 201, 202 |
Artificial surfaces | 190 |
Water bodies | 210 |
Table 3.
Physical-related features used by the model during the day and at night and their specific expressions.
Table 3.
Physical-related features used by the model during the day and at night and their specific expressions.
Feature Variables | Day | Night |
---|
CTH |
|
|
CTT |
|
|
CWP |
|
|
CP |
|
|
WV |
|
|
Topography | DEM OV | DEM OV |
Satellite zenith angle | SAZ | SAZ |
Table 4.
Classification table of precipitation.
Table 4.
Classification table of precipitation.
| GPM IMERG: Precipitation | GPM IMERG: Non-Precipitation |
---|
RF Prediction: Precipitation | NA | NB |
RF Prediction: Non-precipitation | NC | ND |
Table 5.
Validation results for different ratios during day in the precipitation identification model.
Table 5.
Validation results for different ratios during day in the precipitation identification model.
Non-Precipitation: Precipitation | FAR | POD | CSI | ETS |
---|
4:1 | 0.226 | 0.610 | 0.518 | 0.439 |
3:1 | 0.300 | 0.658 | 0.535 | 0.452 |
2:1 | 0.326 | 0.744 | 0.547 | 0.454 |
1:1 | 0.436 | 0.856 | 0.515 | 0.400 |
Table 6.
Validation results for different ratios at night in the precipitation identification model.
Table 6.
Validation results for different ratios at night in the precipitation identification model.
Non-Precipitation: Precipitation | FAR | POD | CSI | ETS |
---|
4:1 | 0.248 | 0.593 | 0.496 | 0.413 |
3:1 | 0.277 | 0.639 | 0.513 | 0.425 |
2:1 | 0.346 | 0.740 | 0.530 | 0.430 |
1:1 | 0.453 | 0.859 | 0.502 | 0.379 |
Table 7.
Evaluation indicators of the identification model.
Table 7.
Evaluation indicators of the identification model.
| FAR | POD | CSI | ETS |
---|
Day | 0.326 | 0.744 | 0.547 | 0.454 |
Night | 0.346 | 0.740 | 0.530 | 0.430 |
Table 8.
Evaluation indicators of precipitation identification model and FY-4B/AGRI operational precipitation product.
Table 8.
Evaluation indicators of precipitation identification model and FY-4B/AGRI operational precipitation product.
Evaluation Indicators | Retrieval Model | Operational Product |
---|
Day | Night | Day | Night |
---|
FAR | 0.385 | 0.448 | 0.319 | 0.393 |
POD | 0.680 | 0.639 | 0.328 | 0.337 |
CSI | 0.477 | 0.421 | 0.284 | 0.277 |
ETS | 0.432 | 0.369 | 0.252 | 0.239 |
Table 9.
Validation results for different ratios during day in the precipitation estimation model.
Table 9.
Validation results for different ratios during day in the precipitation estimation model.
Sample Ratio | Light Rain | Moderate Rain | Heavy Rain | Torrential Rain |
---|
BIAS | RMSE | BIAS | RMSE | BIAS | RMSE | BIAS | RMSE |
---|
75:20:3:1 | 0.698 | 1.122 | −0.488 | 2.101 | −4.639 | 5.909 | −14.852 | 17.987 |
1:1:1:1 | 0.878 | 1.292 | −0.234 | 2.025 | −4.457 | 5.713 | −14.306 | 17.367 |
Table 10.
Validation results for different ratios at night in the precipitation estimation model.
Table 10.
Validation results for different ratios at night in the precipitation estimation model.
Sample Ratio | Light Rain | Moderate Rain | Heavy Rain | Torrential Rain |
---|
BIAS | RMSE | BIAS | RMSE | BIAS | RMSE | BIAS | RMSE |
---|
75:20:3:1 | 0.722 | 1.179 | −0.541 | 2.175 | −4.985 | 6.212 | −15.003 | 17.871 |
1:1:1:1 | 0.910 | 1.374 | −0.237 | 2.131 | −4.767 | 5.986 | −14.481 | 17.334 |
Table 11.
Evaluation indicators of the precipitation estimation model.
Table 11.
Evaluation indicators of the precipitation estimation model.
| R | BIAS | RMSE |
---|
Day | 0.631 | 0.308 | 2.495 |
Night | 0.604 | 0.332 | 2.558 |
Table 12.
Evaluation indicators of precipitation estimation model and FY-4B/AGRI operational precipitation product.
Table 12.
Evaluation indicators of precipitation estimation model and FY-4B/AGRI operational precipitation product.
Evaluation Indicators | Retrieval Model | Operational Product |
---|
Day | Night | Day | Night |
---|
R | 0.441 | 0.421 | 0.254 | 0.311 |
BIAS | 0.744 | 1.029 | 0.598 | 1.517 |
RMSE | 2.832 | 3.127 | 4.641 | 5.291 |