# The 3D Neural Network for Improving Radar-Rainfall Estimation in Monsoon Climate

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Study Area and Data

#### 2.2. Data Preparation

#### 2.3. Geometric Transformation and Pixel Matching

#### 2.4. Rainfall Intensity Classification

#### 2.5. Non-Linear Least Square Optimization in Z-R Modeling

#### 2.6. Artificial Neural Network (ANN) Regression Model

_{c}larger than 0.7).

#### 2.7. Accuracy Assessment

^{2}), root mean square error (RMSE), bias, and Nash- Sutcliffe efficiency index (NSE) [21,58] as follows.

## 3. Results and Discussion

#### 3.1. Pixel Matching

^{2}resolution by minimizing the artefact (void pixels) at the boarder of filled reflectivity in this study. Ref. [60] also found NN effective for large spatial resolution.

#### 3.2. Optimized Parametric Z-R Model

#### 3.3. Rainfall Estimation from Z-R Model

^{2}and G/R were used to measure the variation and performance of radar derived rainfall during monsoon (Figure 8). The G/R provided an insight of how much the radar rainfall deviates from the gauge measurements, where G/R < 1 indicates overestimation and G/R > 1 is underestimation. The regression analysis showed that LM had better ability (R

^{2}< 0.5 for 6 months) than that of MP and ROS to estimate the NEM rainfall. LM provided reliable estimates as depicted from the rain estimates (G/R = 1) for most of the months. The trend for the estimated rainfall indicates that MP and ROS underestimated rainfall in October (G/R > 1). All the radar derived model showed low R

^{2}for February 2013 and October 2014. This could be due to the transitional monsoon event while LM had almost the same estimate at the ground (G/R = 1).

#### 3.4. ANN Training Network Evaluation

#### 3.5. Validation of ANN Model

^{2}> 0.5 for 10 months, but it has overestimated the rainfall (G/R < 1). Like LM (Figure 8a), the ANN underestimated the rainfall in October 2014 and the R

^{2}= 0.3. This is because on that month the transition monsoon occurred where the rainfall had high variation of DSD.

#### 3.6. Case Study Analysis of Radar Rainfall Spatial Pattern

## 4. Conclusions

## Author Contributions

## Funding

## Informed Consent Statement

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Ochoa Rodriguez, S. Rainfall Estimates for Urban Drainage Modelling: An Investigation into Resolution Requirements and Radar-Rain Gauge Data Merging at the Required Resolutions. Ph.D. Thesis, Imperial College, London, UK, 2016. [Google Scholar]
- Yoon, S.-S.; Phuong, A.T.; Bae, D.-H. Quantitative comparison of the spatial distribution of radar and gauge rainfall data. J. Hydrometeorol.
**2012**, 13, 1939–1953. [Google Scholar] [CrossRef] - Folino, G.; Guarascio, M.; Chiaravalloti, F.; Gabriele, S. A Deep Learning based architecture for rainfall estimation integrating heterogeneous data sources. In Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14–19 July 2019; pp. 1–8. [Google Scholar]
- Davies, R. Malaysia Floods–Kelantan Flooding Worst Recorded as Costs Rise to RM1 Billion. FloodList-Asia
**2015**, 2019. Available online: http://floodlist.com/asia/malaysia-floods-kelantan-worst-recorded-costs (accessed on 28 March 2021). - Maggioni, V.; Massari, C. On the performance of satellite precipitation products in riverine flood modeling: A review. J. Hydrol.
**2018**, 558, 214–224. [Google Scholar] [CrossRef] - Ochoa-Rodriguez, S.; Wang, L.P.; Willems, P.; Onof, C. A review of radar-rain gauge data merging methods and their potential for urban hydrological applications. Water Resour. Res.
**2019**, 55, 6360–6391. [Google Scholar] [CrossRef] - Luo, Y.; Li, L.; Johnson, R.H.; Chang, C.-P.; Chen, L.; Wong, W.-K.; Chen, J.; Furtado, K.; McBride, J.L.; Tyagi, A. Science and prediction of monsoon heavy rainfall. Sci. Bull.
**2019**, 64, 1557–1561. [Google Scholar] [CrossRef] [Green Version] - Battan, L.J. Radar Observation of the Atmosphere; University of Chicago Press: Chicago, IL, USA, 1973; p. 323. [Google Scholar]
- Fraile, R.; Fernandez-Raga, M. On a more consistent definition of radar reflectivity. Atmósfera
**2009**, 22, 375–385. [Google Scholar] - Marshall, J.S.; Palmer, W.M.K. The distribution of raindrops with size. J. Meteorol.
**1948**, 5, 165–166. [Google Scholar] [CrossRef] - Wu, W.; Zou, H.; Shan, J.; Wu, S. A dynamical ZR relationship for precipitation estimation based on radar echo-top height classification. Adv. Meteorol.
**2018**, 2018, 8202031. [Google Scholar] [CrossRef] [Green Version] - Fabry, F. Radar Meteorology: Principles and Practice; Cambridge University Press: Cambridge, UK, 2015. [Google Scholar]
- Hashiguchi, H.; Vonnisa, M.; Nugroho, S.; Yoseva, M. ZR Relationships for Weather Radar in Indonesia from the Particle Size and Velocity (Parsivel) Optical Disdrometer. In Proceedings of the 2018 Progress in Electromagnetics Research Symposium (PIERS-Toyama), Toyama, Japan, 1–4 August 2018; pp. 37–41. [Google Scholar]
- Ayat, H.; Kavianpour, M.R.; Moazami, S.; Hong, Y.; Ghaemi, E. Calibration of weather radar using region probability matching method (RPMM). Theor. Appl. Climatol.
**2018**, 134, 165–176. [Google Scholar] [CrossRef] - Sahlaoui, Z.; Mordane, S. Radar rainfall estimation in Morocco: Quality control and gauge adjustment. Hydrology
**2019**, 6, 41. [Google Scholar] [CrossRef] [Green Version] - Kim, T.-J.; Kwon, H.-H.; Lima, C. A Bayesian partial pooling approach to mean field bias correction of weather radar rainfall estimates: Application to Osungsan weather radar in South Korea. J. Hydrol.
**2018**, 565, 14–26. [Google Scholar] [CrossRef] - Nuurul Hudaa, S.; Ahmad Fadzil, I.; Ani Liza, A.; Wahida, S. Evaluation of radar reflectivity-rainfall rate, Z-R relationships during a stratiform event in the tropics. In In Proceedings of the 2nd Asia-Pacific Conference on Antennas and Propagation, Chiang Mai, Thailand, 5–7 August 2013; pp. 185–186. [Google Scholar]
- Suzana, R.; Wardah, T.; Hamid, A.S. Radar hydrology: New Z/R relationships for Klang River Basin Malaysia based on rainfall classification. World Acad. Sci. Eng. Technol.
**2011**, 5, 141–145. [Google Scholar] - Goudenhoofdt, E.; Delobbe, L.; Willems, P. Regional frequency analysis of extreme rainfall in Belgium based on radar estimates. Hydrol. Earth Syst. Sci.
**2017**, 21, 5385. [Google Scholar] [CrossRef] [Green Version] - Seo, B.-C.; Dolan, B.; Krajewski, W.F.; Rutledge, S.A.; Petersen, W. Comparison of single-and dual-polarization–based rainfall estimates using NEXRAD Data for the NASA Iowa flood studies project. J. Hydrometeorol.
**2015**, 16, 1658–1675. [Google Scholar] [CrossRef] - Thorndahl, S.; Nielsen, J.E.; Rasmussen, M.R. Bias adjustment and advection interpolation of long-term high resolution radar rainfall series. J. Hydrol.
**2014**, 508, 214–226. [Google Scholar] [CrossRef] - Gjertsen, U.; Salek, M.; Michelson, D. Gauge-adjustment of radar-based precipitation estimates. In Proceedings of the ERAD Copernicus GmbH, Visby, Sweden; 2004; pp. 7–11. [Google Scholar]
- De Hart, J.C.; Bell, M.M. A comparison of the polarimetric radar characteristics of heavy rainfall from Hurricanes Harvey (2017) and Florence (2018). J. Geophys. Res. Atmos.
**2020**, 125. [Google Scholar] [CrossRef] - Meena, K.; Sujatha, J. Reduced Time Compression in Big Data Using MapReduce Approach and Hadoop. J. Med. Syst.
**2019**, 43, 239. [Google Scholar] [CrossRef] - Borga, M.; Tonelli, F.; Moore, R.J.; Andrieu, H. Long-term assessment of bias adjustment in radar rainfall estimation. Water Resour. Res.
**2002**, 38. [Google Scholar] [CrossRef] [Green Version] - Rosenfeld, D.; Wolff, D.B.; Atlas, D. General probability-matched relations between radar reflectivity and rain rate. J. Appl. Meteorol.
**1993**, 32, 50–72. [Google Scholar] [CrossRef] [Green Version] - Rosenfeld, D.; Wolff, D.B.; Amitai, E. The Window Probability Matching Method for Rainfall Measurements with Radar. J. Appl. Meteorol.
**1994**, 33, 682–693. [Google Scholar] [CrossRef] [Green Version] - Piman, T.; Babel, M.; Gupta, A.D.; Weesakul, S. Development of a window correlation matching method for improved radar rainfall estimation. Hydrol. Earth Syst. Sci. Discuss.
**2007**, 11, 1361–1372. [Google Scholar] [CrossRef] [Green Version] - Alqudah, A.; Chandrasekar, V.; Le, M. Investigating rainfall estimation from radar measurements using neural networks. Nat. Hazards Earth Syst. Sci.
**2013**, 13, 535–544. [Google Scholar] [CrossRef] [Green Version] - Chiang, Y.-M.; Chang, F.-J.; Jou, B.J.-D.; Lin, P.-F. Dynamic ANN for precipitation estimation and forecasting from radar observations. J. Hydrol.
**2007**, 334, 250–261. [Google Scholar] [CrossRef] - Chaipimonplin, T. Investigation internal parameters of neural network model for Flood Forecasting at Upper River Ping, Chiang Mai. KSCE J. Civ. Eng.
**2016**, 20, 478–484. [Google Scholar] [CrossRef] - Yen, M.-H.; Liu, D.-W.; Hsin, Y.-C.; Lin, C.-E.; Chen, C.-C. Application of the deep learning for the prediction of rainfall in Southern Taiwan. Sci. Rep.
**2019**, 9, 1–9. [Google Scholar] [CrossRef] [Green Version] - Liu, H.; Chandrasekar, V.; Xu, G. An adaptive neural network scheme for radar rainfall estimation from WSR-88D observations. J. Appl. Meteorol.
**2001**, 40, 2038–2050. [Google Scholar] [CrossRef] [Green Version] - Xiao, R.; Chandrasekar, V. Development of a neural network based algorithm for rainfall estimation from radar observations. IEEE Trans. Geosci. Remote Sens.
**1997**, 35, 160–171. [Google Scholar] [CrossRef] [Green Version] - Teschl, R.; Randeu, W.L.; Teschl, F. Improving weather radar estimates of rainfall using feed-forward neural networks. Neural Netw.
**2007**, 20, 519–527. [Google Scholar] [CrossRef] - Reba, M.; Roslan, N.; Syafiuddin, A.; Hashim, M. Evaluation of Empirical Radar Rainfall Model during the massive Flood in Malaysia. In Proceedings of the Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, Beijing, China, 10–15 July 2016; pp. 4406–4409. [Google Scholar]
- Hadi, M.; Suprayogi, S.; Murti, S. Daily Quantitative Precipitation Estimates Use Weather Radar Reflectivity in South Sulawesi. In Proceedings of the IOP Conference Series: Earth and Environmental Science, Yogyakarta, Indonesia, 22–23 October 2018; p. 012042. [Google Scholar]
- VAISALA. User Guide IRIS/SIGMET. Available online: https://www.vaisala.com/en/products/instruments-sensors-and-other-measurement-devices/weather-radar-products/iris-focus (accessed on 1 January 2016).
- Mapiam, P.P.; Sriwongsitanon, N. Climatological ZR relationship for radar rainfall estimation in the upper Ping river basin. ScienceAsia
**2008**, 34, 215. [Google Scholar] [CrossRef] [Green Version] - Tan, M.L.; Ibrahim, A.L.; Cracknell, A.P.; Yusop, Z. Changes in precipitation extremes over the Kelantan River Basin, Malaysia. Int. J. Climatol.
**2017**, 37, 3780–3797. [Google Scholar] [CrossRef] - Che Ros, F.; Tosaka, H.; Sidek, L.M.; Basri, H. Homogeneity and trends in long-term rainfall data, Kelantan River Basin, Malaysia. Int. J. River Basin Manag.
**2016**, 14, 151–163. [Google Scholar] [CrossRef] - Tan, M.L.; Ramli, H.P.; Tam, T.H. Effect of DEM Resolution, Source, Resampling Technique and Area Threshold on SWAT Outputs. Water Resour. Manag.
**2018**, 32, 4591–4606. [Google Scholar] [CrossRef] - Helmus, J.; Collis, S. The Python ARM Radar Toolkit (Py-ART), a library for working with weather radar data in the Python programming language. J. Open Res. Softw.
**2016**, 4. [Google Scholar] [CrossRef] [Green Version] - Yoo, C.; Ha, E. Effect of zero measurements on the spatial correlation structure of rainfall. Stoch. Environ. Res. Risk Assess.
**2007**, 21, 287–297. [Google Scholar] [CrossRef] - Daliakopoulos, I.N.; Tsanis, I.K. A weather radar data processing module for storm analysis. J. Hydroinform.
**2012**, 14, 332–344. [Google Scholar] [CrossRef] [Green Version] - Yang, L.; Jang, B.-J.; Lim, S.; Kwon, K.-C.; Lee, S.-H.; Kwon, K.-R. Weather radar image gener ation method using inter polation based on CUDA. J. Korea Multimed. Soc.
**2015**, 18, 473–482. [Google Scholar] [CrossRef] [Green Version] - Brandes, E.A. Optimizing rainfall estimates with the aid of radar. J. Appl. Meteorol.
**1975**, 14, 1339–1345. [Google Scholar] [CrossRef] - Mcroberts, D.B. Minimizing Biases in Radar Precipitation Estimates. Ph.D. Thesis, Texas A&M University, College Station, TX, USA, 2014. [Google Scholar]
- Goudenhoofdt, E. Precipitation Estimation from Weather Radar Measurements: Statistical Analysis of Convective Storms and Extreme Rainfall. Ph.D. Thesis, Arenberg Doctoral School, Leuven, Belgium, 2018. [Google Scholar]
- Cressman, G.P. An operational objective analysis system. Mon. Weather Rev.
**1959**, 87, 367–374. [Google Scholar] [CrossRef] - Xavier, A.C.; King, C.W.; Scanlon, B.R. Daily gridded meteorological variables in Brazil (1980–2013). Int. J. Climatol.
**2016**, 36, 2644–2659. [Google Scholar] [CrossRef] [Green Version] - Prat, O.P.; Barros, A.P. Combining a Rain Microphysical Model and Observations: Implications for Radar Rainfall Estimation. In Proceedings of the Radar Conference, 2009 IEEE, Pasadena, CA, USA, 4–8 May 2009; pp. 1–4. [Google Scholar]
- Varikoden, H.; Preethi, B.; Samah, A.; Babu, C. Seasonal variation of rainfall characteristics in different intensity classes over Peninsular Malaysia. J. Hydrol.
**2011**, 404, 99–108. [Google Scholar] [CrossRef] - Van de Beek, C.; Leijnse, H.; Hazenberg, P.; Uijlenhoet, R. Close-range radar rainfall estimation and error analysis. Atmos. Meas. Tech.
**2016**, 9, 3837. [Google Scholar] [CrossRef] [Green Version] - Orellana-Alvear, J.; Célleri, R.; Rollenbeck, R.; Bendix, J. Analysis of Rain Types and Their Z-R Relationships at Different Locations in the High Andes of Southern Ecuador. J. Appl. Meteorol. Climatol.
**2017**, 56, 3065–3080. [Google Scholar] [CrossRef] - Roweis, S. Levenberg-Marquardt Optimization; University of Toronto: Toronto, ON, Canada, 1996. [Google Scholar]
- Steiner, M.; Smith, J.A.; Burges, S.J.; Alonso, C.V.; Darden, R.W. Effect of bias adjustment and rain gauge data quality control on radar rainfall estimation. Water Resour. Res.
**1999**, 35, 2487–2503. [Google Scholar] [CrossRef] - Yang, T.-H.; Feng, L.; Chang, L.-Y. Improving radar estimates of rainfall using an input subset of artificial neural networks. J. Appl. Remote Sens.
**2016**, 10, 026013. [Google Scholar] [CrossRef] - Taylor, K.E. Summarizing multiple aspects of model performance in a single diagram. J. Geophys. Res. Atmos.
**2001**, 106, 7183–7192. [Google Scholar] [CrossRef] - Konik, M.; Kowalewski, M.; Bradtke, K.; Darecki, M. The operational method of filling information gaps in satellite imagery using numerical models. Int. J. Appl. Earth Obs. Geoinf.
**2019**, 75, 68–82. [Google Scholar] [CrossRef] - Song, L.; Chen, M.; Gao, F.; Cheng, C.; Chen, M.; Yang, L.; Wang, Y. Elevation influence on rainfall and a parameterization algorithm in the Beijing area. J. Meteorol. Res.
**2019**, 33, 1143–1156. [Google Scholar] [CrossRef] - Haberlandt, U. Geostatistical interpolation of hourly precipitation from rain gauges and radar for a large-scale extreme rainfall event. J. Hydrol.
**2007**, 332, 144–157. [Google Scholar] [CrossRef] - Zhang, J.; Howard, K.; Gourley, J. Constructing three-dimensional multiple-radar reflectivity mosaics: Examples of convective storms and stratiform rain echoes. J. Atmos. Ocean. Technol.
**2005**, 22, 30–42. [Google Scholar] [CrossRef] - Sun, M.; Wang, H.; Li, Z.; Gao, M.; Xu, Z.; Li, J. Study on reflectivity data interpolation and mosaics for multiple Doppler weather radars. Eurasip J. Wirel. Commun. Netw.
**2019**, 2019, 145. [Google Scholar] [CrossRef] - Tahir, W.; Azad, W.H.; Husaif, N.; Osman, S.; Ibrahim, Z.; Ramli, S. Climatological Calibration of Z-R Relationship for Pahang River Basin. J. Teknol.
**2019**, 81. [Google Scholar] [CrossRef] [Green Version] - Yoon, J.; Joo, J.; Yoo, C.; Hwang, S.; Lim, S. On quality of radar rainfall with respect to temporal and spatial resolution for application to urban areas. Meteorol. Appl.
**2017**, 24, 19–30. [Google Scholar] [CrossRef] [Green Version] - Seela, B.K.; Janapati, J.; Lin, P.L.; Wang, P.K.; Lee, M.T. Raindrop size distribution characteristics of summer and winter season rainfall over north Taiwan. J. Geophys. Res. Atmos.
**2018**, 123. [Google Scholar] [CrossRef] [Green Version] - Marzuki, M.; Hashiguchi, H.; Yamamoto, M.; Mori, S.; Yamanaka, M. Regional variability of raindrop size distribution over Indonesia. Ann. Geophys.
**2013**, 31, 1941–1948. [Google Scholar] [CrossRef] [Green Version] - Ramli, S.; Tahir, W. Radar hydrology: New Z/R relationships for quantitative precipitation estimation in Klang River Basin, Malaysia. Int. J. Environ. Sci. Dev.
**2011**, 2, 223–227. [Google Scholar] [CrossRef] - Auipong, N.; Trivej, P. Study of Z-R relationship among different topographies in Northern Thailand. J. Phys. Conf. Ser.
**2018**, 1144, 012098. [Google Scholar] [CrossRef] - Stull, R.B. Meteorology Today for Scientists and Engineers: A Technical Companion Book to Meteorology Today; Donald Ahrens, C., Ed.; West Publishing Company: Egan, MN, USA, 1995. [Google Scholar]
- Kumar, L.S.; Lee, Y.H.; Yeo, J.X.; Ong, J.T. Tropical rain classification and estimation of rain from Z-R (reflectivity-rain rate) relationships. Prog. Electromagn. Res.
**2011**, 32, 107–127. [Google Scholar] [CrossRef] [Green Version] - Steiner, M.; Smith, J.A.; Uijlenhoet, R. A microphysical interpretation of radar reflectivity–Rain rate relationships. J. Atmos. Sci.
**2004**, 61, 1114–1131. [Google Scholar] [CrossRef] - Yakubu, M.L.; Yusop, Z.; Fulazzaky, M.A. The influence of rain intensity on raindrop diameter and the kinetics of tropical rainfall: Case study of Skudai, Malaysia. Hydrol. Sci. J.
**2016**, 61, 944–951. [Google Scholar] [CrossRef] - Aumjira, P.; Trivej, P. Rainfall Estimation from Radar in Different Seasons over Northern Thailand. J. Phys. Conf. Ser.
**2018**, 1144, 012122. [Google Scholar] [CrossRef] - Abon, C.C.; Kneis, D.; Crisologo, I.; Bronstert, A.; David, C.P.C.; Heistermann, M. Evaluating the potential of radar-based rainfall estimates for streamflow and flood simulations in the Philippines. Geomat. Nat. Hazards Risk
**2015**, 7, 1390–1405. [Google Scholar] [CrossRef] - Yeo, J.; Lee, Y.; Ong, J. Radar measured rain attenuation with proposed Z-R relationship at a tropical location. Aeu-Int. J. Electron. Commun.
**2015**, 69, 458–461. [Google Scholar] [CrossRef] - Park, S.; Berenguer, M.; Sempere-Torres, D. Long-term analysis of gauge-adjusted radar rainfall accumulations at European scale. J. Hydrol.
**2019**, 573, 768–777. [Google Scholar] [CrossRef] [Green Version] - Neuper, M.; Ehret, U. Quantitative precipitation estimation with weather radar using a data-and information-based approach. Hydrol. Earth Syst. Sci.
**2019**, 23, 3711–3733. [Google Scholar] [CrossRef] [Green Version] - Roslan, N.; Md, N.; Syafiuddin, A.; Hashim, M. Range and Intensity Dependent Quantitative Precipitation Estimation from High Resolution Weather Radar for The Tropical Rainfall. In Proceedings of the 39th Asian Conference on Remote Sensing:Remote Sensing Enabling Prosperity (ACRS 2018), Kuala Lumpur, Malaysia, 15–19 October 2018; pp. 1492–1501. [Google Scholar]
- Syafrina, A.; Zalina, M.; Juneng, L. Historical trend of hourly extreme rainfall in Peninsular Malaysia. Theor. Appl. Climatol.
**2015**, 120, 259–285. [Google Scholar] [CrossRef] [Green Version] - Dutta, D.; Sharma, S.; Kannan, B.; Venketswarlu, S.; Gairola, R.; Rao, T.; Viswanathan, G. Sensitivity of ZR relations and spatial variability of error in a Doppler Weather Radar measured rain intensity. Indian J. Radio Space Phys.
**2012**, 41, 448–460. [Google Scholar] - Kirsch, B.; Clemens, M.; Ament, F. Stratiform and convective radar reflectivity–rain rate relationships and their potential to improve radar rainfall estimates. J. Appl. Meteorol. Climatol.
**2019**, 58, 2259–2271. [Google Scholar] [CrossRef] - Schleiss, M.; Olsson, J.; Berg, P.; Niemi, T.; Kokkonen, T.; Thorndahl, S.; Nielsen, R.; Nielsen, J.E.; Bozhinova, D.; Pulkkinen, S. The accuracy of weather radar in heavy rain: A comparative study for Denmark, the Netherlands, Finland and Sweden. Hydrol. Earth Syst. Sci.
**2020**, 24, 3157–3188. [Google Scholar] [CrossRef] - Bronstert, A.; Agarwal, A.; Boessenkool, B.; Crisologo, I.; Fischer, M.; Heistermann, M.; Köhn-Reich, L.; López-Tarazón, J.A.; Moran, T.; Ozturk, U.; et al. Forensic hydro-meteorological analysis of an extreme flash flood: The 2016-05-29 event in Braunsbach, SW Germany. Sci. Total Environ.
**2018**, 630, 977–991. [Google Scholar] [CrossRef] - Montero-Martínez, G.; García-García, F. On the behaviour of raindrop fall speed due to wind. Q. J. R. Meteorol. Soc.
**2016**, 142, 2013–2020. [Google Scholar] [CrossRef] - Xavier, P.; Lim, S.Y.; Ammar Bin Abdullah, M.F.; Bala, M.; Chenoli, S.N.; Handayani, A.S.; Marzin, C.; Permana, D.; Tangang, F.; Williams, K.D. Seasonal Dependence of Cold Surges and their Interaction with the Madden–Julian Oscillation over Southeast Asia. J. Clim.
**2020**, 33, 2467–2482. [Google Scholar] [CrossRef] - Li, P.-C.; Yu, T.-T. Landslide Early Warning with Rainfall Data from Correcting Weather Radar Reflectivity Using Machine Learning. In Proceedings of the EGU General Assembly Conference Abstracts, 4–8 May 2020; p. 19265. [Google Scholar]
- Tan, H.; Chandrasekar, V.; Chen, H. A Machine Learning Model for Radar Rainfall Estimation Based on Gauge Observations. In Proceedings of the 2017 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 4–7 January 2017; pp. 1–2. [Google Scholar]
- Yang, Z.; Liu, P.; Yang, Y. Convective/Stratiform Precipitation Classification Using Ground-Based Doppler Radar Data Based on the K-Nearest Neighbor Algorithm. Remote Sens.
**2019**, 11, 2277. [Google Scholar] [CrossRef] [Green Version] - Alias, N.E.; Mohamad, H.; Chin, W.Y.; Yusop, Z. Rainfall analysis of the Kelantan big yellow flood 2014. J. Teknol.
**2016**, 78. [Google Scholar] [CrossRef] [Green Version]

**Figure 2.**Illustration of single radar beam observing one target (A) at the atmosphere is a function of the range (r), elevation angles (θ) and azimuth angles (ϕ) to be converted into Cartesian position in a function of the latitude (x), longitude (y), and height (z).

**Figure 3.**The error-bar plots illustrating reflectivity measured in different gauge locations interpolated by the nearest distance (

**a**) and the 3D interpolation (

**b**), and the performance of (

**c**) measured in terms of residual mean square error (RMSE). Horizontal bars indicate the standard error of the means.

**Figure 4.**Time series plot for the corresponding (

**a**) reflectivity (dBZ) and (

**b**) rainfall intensity (mm/h) from 2013 to 2015. Higher reflectivity found up to 60 dBZ and high rainfall intensity was recorded at 150 mm/h. Yellow line represents the time average of each parameter.

**Figure 5.**Trend plot of α (solid line with circle mark) and β (dash line with cross mark) at each month from January 2013 to March 2015.

**Figure 6.**The Taylor diagram illustrating a statistical comparison of four different hourly radar rainfall estimates with rain gauge (RG) observation under different rainfall intensities: (

**a**) low, (

**b**) moderate, (

**c**) high, and (

**d**) all intensity. The azimuthal angle denotes correlation; the radial distance is standard deviation; and the semicircles centered at the RG represent residual mean square error (RMSE).

**Figure 8.**Plot of R

^{2}and G/R of radar rainfall estimates on a monthly basis for all rainfall intensity for (

**a**) LM, (

**b**) MP, (

**c**) ROS, and (

**d**) ANN models.

**Figure 9.**Plot of RMSE for monthly radar rainfall at (

**a**) all, (

**b**) low, (

**c**) medium, and (

**d**) high rain intensities.

**Figure 10.**Scatter plots of radar rainfall estimates based on ANN versus rainfall measurements from the gauges. (

**a**) training, (

**b**) testing and (

**c**) all regressions of the reflectivity for all rainfall intensity. The color lines are fitted line and the dashed lines are 95% confidence bounds of the fitted line.

**Figure 11.**Scatter plots of radar rainfall estimates based on ANN versus rainfall measurements from the gauges at (

**a**) low, (

**b**) medium, and (

**c**) high intensity rainfall. The straight line is the regression line.

**Figure 12.**Plot of the rain gauge measurement and estimated rainfall from the radar rainfall on hourly basis for (

**a**) 16 to 19 December 2014 (96 h) and (

**b**) 20 to 24 December 2014 (102 h).

**Figure 13.**CAPPI map on daily basis generated from the LM model for (

**a**) 16 December 2014, (

**b**) 17 December 2014, (

**c**) 18 December 2014, and (

**d**) 19 December 2014 for KB weather radar station.

**Figure 14.**CAPPI map on daily basis generated from the ANN model from the KB weather radar for similar date as Figure 13. (

**a**) 16 December 2014, (

**b**) 17 December 2014, (

**c**) 18 December 2014, and (

**d**) 19 December 2014.

Specification | Description |
---|---|

Model | EEC WSR 745/1996 |

Peak power | 500 kW |

Pulse width | 2.0 µs |

Gain | Minimum 39 dB |

Pulse response frequency | 250 Hz |

Beamwidth | 1.9 degree maximum on axes |

Elevation range | 0.0, 0.7, 1.5 and 2.5 degree |

Threshold LOG | 0.75 dB |

Threshold CSR | 18 dB |

Intensity Type | Optimized Z-R |
---|---|

All intensity | Z = 216.3 R^{1.6} |

Low | Z = 214.3 R^{1.6} |

Medium | Z = 215.9 R^{1.6} |

High | Z = 218.2 R^{1.6} |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Roslan, N.; Md Reba, M.N.; Sharoni, S.M.H.; Hossain, M.S.
The 3D Neural Network for Improving Radar-Rainfall Estimation in Monsoon Climate. *Atmosphere* **2021**, *12*, 634.
https://doi.org/10.3390/atmos12050634

**AMA Style**

Roslan N, Md Reba MN, Sharoni SMH, Hossain MS.
The 3D Neural Network for Improving Radar-Rainfall Estimation in Monsoon Climate. *Atmosphere*. 2021; 12(5):634.
https://doi.org/10.3390/atmos12050634

**Chicago/Turabian Style**

Roslan, Nurulhani, Mohd Nadzri Md Reba, Syarawi M. H. Sharoni, and Mohammad Shawkat Hossain.
2021. "The 3D Neural Network for Improving Radar-Rainfall Estimation in Monsoon Climate" *Atmosphere* 12, no. 5: 634.
https://doi.org/10.3390/atmos12050634