{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:25:39Z","timestamp":1769502339885,"version":"3.49.0"},"reference-count":43,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T00:00:00Z","timestamp":1613260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003629","name":"Korea Meteorological Administration","doi-asserted-by":"publisher","award":["KMI2020-00910"],"award-info":[{"award-number":["KMI2020-00910"]}],"id":[{"id":"10.13039\/501100003629","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Traditional radar-based rainfall estimation is typically done by known functional relationships between the rainfall intensity (R) and radar measurables, such as R\u2013Zh, R\u2013(Zh, ZDR), etc. One of the biggest advantages of machine learning algorithms is the applicability to a non-linear relationship between a dependent variable and independent variables without any predefined relationships. We explored the potential use of two supervised machine learning methods (regression tree and random forest) in rainfall estimation using dual-polarization radar variables. The regression tree does not require normalization and scaling of data; however, this method is quite unstable since each split depends on the parent split. Since the random forest is an ensemble method of regression trees, it has less variability in prediction compared with regression trees, but consumes more computer resources. We considered several different configurations for machine learning algorithms with different sets of dependent and independent variables. The random forest model was appropriately tuned. In the test of variable importance, the specific differential phase (differential reflectivity) was the most important variable to predict the rainfall rate (residual that is the difference between the true rainfall rate and the one estimated from the R\u2013Z relationship). The models were evaluated by 10-fold cross-validation. The best model was the random forest model using a residual with the non-classified training set. The results indicated that the machine learning algorithms outperformed the traditional R\u2013Z relationship. Then, we applied the best machine learning model to an S-band dual-polarization radar (Mt. Myeonbong) and validated the result with ground rain gauges. The results of the application to radar data showed that the estimates of the residuals had spatial variability. The stratiform and weak rain areas had positive residuals while convective areas had negative residuals, indicating that the spatial error structure driven by the R\u2013Z relationship was well captured by the model. The rainfall rates of all pixels over the study area were adjusted with the estimated residuals. The rainfall rates adjusted by residual showed excellent agreement with the rain gauge, especially at high rainfall rates.<\/jats:p>","DOI":"10.3390\/rs13040694","type":"journal-article","created":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T08:53:56Z","timestamp":1613292836000},"page":"694","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Quantitative Precipitation Estimates Using Machine Learning Approaches with Operational Dual-Polarization Radar Data"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1182-6751","authenticated-orcid":false,"given":"Kyuhee","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Astronomy and Atmospheric Sciences, Center for Atmospheric REmote sensing (CARE), Kyungpook National University, Daegu 41566, Korea"}]},{"given":"Joon Jin","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Statistical Science, Baylor University, Waco, TX 76798-7140, USA"}]},{"given":"Wonbae","family":"Bang","sequence":"additional","affiliation":[{"name":"Department of Astronomy and Atmospheric Sciences, Center for Atmospheric REmote sensing (CARE), Kyungpook National University, Daegu 41566, Korea"}]},{"given":"GyuWon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Astronomy and Atmospheric Sciences, Center for Atmospheric REmote sensing (CARE), Kyungpook National University, Daegu 41566, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1175\/1520-0426(1995)012<0249:CODPRE>2.0.CO;2","article-title":"Comparison of Dual-Polarization Radar Estimators of Rain","volume":"12","author":"Ryzhkov","year":"1995","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1175\/1520-0450(2002)041<0674:EIREWA>2.0.CO;2","article-title":"Experiments in Rainfall Estimation with a Polarimetric Radar in a Subtropical Environment","volume":"41","author":"Brandes","year":"2002","journal-title":"J. Appl. Meteorol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1175\/JTECH1887.1","article-title":"A comparative study of rainfall retrievals based on specific differential phase shifts at X- and S-band radar frequencies","volume":"23","author":"Matrosov","year":"2006","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1175\/JHM-D-10-05013.1","article-title":"Rainfall Estimation with an Operational Polarimetric C-Band Radar in the United Kingdom: Comparison with a Gauge Network and Error Analysis","volume":"12","author":"Bringi","year":"2011","journal-title":"J. Hydrometeorol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1175\/JAMC-D-17-0160.1","article-title":"Dual-polarization radar rainfall estimation over tropical oceans","volume":"57","author":"Thompson","year":"2018","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Bringi, V.N., and Chandrasekar, V. (2001). Polarimetric Doppler Weather Radar: Principles and Applications, Cambridge University Press.","DOI":"10.1017\/CBO9780511541094"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1175\/1520-0426(1996)013<0454:AORMUS>2.0.CO;2","article-title":"Advantages of Rain Measurements Using Specific Differential Phase","volume":"13","author":"Ryzhkov","year":"1996","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1175\/JTECH2085.1","article-title":"Effects or radar beam shielding on rainfall estimation for the polarimetric C-band radar","volume":"24","author":"Friedrich","year":"2007","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"243","DOI":"10.15191\/nwajom.2013.0120","article-title":"Principles and applications of dual-polarization weather radar. Part II: Warm and cold season applications","volume":"1","author":"Kumjian","year":"2013","journal-title":"J. Oper. Meteorol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1175\/1520-0469(1948)005<0165:TDORWS>2.0.CO;2","article-title":"The distribution of raindrops with size","volume":"5","author":"Marshall","year":"1948","journal-title":"J. Meteorol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"871","DOI":"10.2151\/jmsj.83.871","article-title":"Effect of natural variations in rain drop size distributions on rain rate estimators of 3 cm wavelength polarimetric radar","volume":"83","author":"Maki","year":"2005","journal-title":"J. Meteorol. Soc. Jpn."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1175\/JTECH1899.1","article-title":"Sources of errors in rainfall measurements by polarimetric radar: Variability of drop size distributions, observational noise, and variation of relationships between R and polarimetric parameters","volume":"23","author":"Lee","year":"2006","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1175\/1520-0426(1987)004<0588:RREFDP>2.0.CO;2","article-title":"Rain rate estimates from differential polarization measurements","volume":"4","author":"Sachidananda","year":"1987","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1175\/JAM2213.1","article-title":"Rainfall Estimation with a Polarimetric Prototype of WSR-88D","volume":"44","author":"Ryzhkov","year":"2005","journal-title":"J. Appl. Meteorol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1175\/2010JTECHA1488.1","article-title":"A new dual-polarization radar rainfall algorithm: Application in Colorado precipitation events","volume":"28","author":"Cifelli","year":"2011","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1175\/1520-0450(1981)020<1362:APSOCM>2.0.CO;2","article-title":"A Preliminary Study of Comparative Measurements of Rainfall Rate Using the Differential Reflectivity Radar Technique and a Raingage Network","volume":"20","author":"Seliga","year":"1981","journal-title":"J. Appl. Meteorol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ryzhkov, A.V., and Zrnic, D.S. (2019). Radar Polarimetry for Weather Observations, Springer International Publishing. Springer Atmospheric Sciences.","DOI":"10.1007\/978-3-030-05093-1"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.neunet.2007.04.005","article-title":"Improving weather radar estimates of rainfall using feed-forward neural networks","volume":"20","author":"Teschl","year":"2007","journal-title":"Neural Netw."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.rse.2013.10.026","article-title":"Improving the accuracy of rainfall rates from optical satellite sensors with machine learning\u2014A random forests-based approach applied to MSG SEVIRI","volume":"141","author":"Appelhans","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.atmosres.2018.05.001","article-title":"Improvement of rainfall estimation from MSG data using Random Forests classification and regression","volume":"211","author":"Ouallouche","year":"2018","journal-title":"Atmos. Res."},{"key":"ref_21","unstructured":"Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A. (1984). Classification and Regression Trees, Routledge."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1109\/TGRS.2012.2210429","article-title":"Modeling and prediction of rainfall using radar reflectivity data: A data-mining approach","volume":"51","author":"Kusiak","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"111716","DOI":"10.1016\/j.rse.2020.111716","article-title":"Deep learning in environmental remote sensing: Achievements and challenges","volume":"241","author":"Yuan","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.jhydrol.2006.10.021","article-title":"Dynamic ANN for precipitation estimation and forecasting from radar observations","volume":"334","author":"Chiang","year":"2007","journal-title":"J. Hydrol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, H., Chandrasekar, V., and Cifelli, R. (2019, January 9\u201315). A Deep Learning Approach to Dual-Polarization Radar Rainfall Estimation. Proceedings of the 2019 URSI Asia-Pacific Radio Science Conference (AP-RASC), New Delhi, India.","DOI":"10.23919\/URSIAP-RASC.2019.8738337"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1175\/1520-0426(2002)019<0602:TDVDAD>2.0.CO;2","article-title":"Two-Dimensional Video Disdrometer: A Description","volume":"19","author":"Kruger","year":"2002","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/RG011i001p00001","article-title":"Doppler radar characteristics of precipitation at vertical incidence","volume":"11","author":"Atlas","year":"1973","journal-title":"Rev. Geophys."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bang, W., Lee, G., Ryzhkov, A., Schuur, T., and Lim, K.-S.S. (2020). Comparison of microphysical characteristics between southern Korea and Oklahoma using two-dimensional video disdrometer data. J. Hydrometeorol., 1\u201361.","DOI":"10.1175\/JHM-D-20-0087.1"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1175\/JAMC-D-16-0304.1","article-title":"Toward completing the raindrop size spectrum: Case studies involving 2D-video disdrometer, droplet spectrometer, and polarimetric radar measurements","volume":"56","author":"Thurai","year":"2017","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/0022-4073(96)00002-7","article-title":"T-matrix computations of light scattering by nonspherical particles: A review","volume":"55","author":"Mishchenko","year":"1996","journal-title":"J. Quant. Spectrosc. Radiat. Transf."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1175\/JTECH2051.1","article-title":"Drop shapes, model comparisons, and calculations of polarimetric radar parameters in rain","volume":"24","author":"Thurai","year":"2007","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.jhydrol.2005.11.046","article-title":"Radar calibration by gage, disdrometer, and polarimetry: Theoretical limit caused by the variability of drop size distribution and application to fast scanning operational radar data","volume":"328","author":"Lee","year":"2006","journal-title":"J. Hydrol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"65","DOI":"10.2151\/jmsj.2015-005","article-title":"Rainfall Estimation from an Operational S-Band Dual-Polarization Radar: Effect of Radar Calibration","volume":"93","author":"Kwon","year":"2015","journal-title":"J. Meteorol. Soc. Jpn. Ser. II"},{"key":"ref_35","first-page":"18","article-title":"Classification and regression by random forest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"ref_36","unstructured":"Van Huffel, S. (1997). Generalization of the TLS approach in the errors-in-variables problem. Recent Advances in Total Least Squares Techniques and Errors-in-Variables Modeling, SIAM."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1175\/1520-0426(1988)005<0783:ESOMRA>2.0.CO;2","article-title":"Error Structure of Multiparameter Radar and Surface Measurements of Rainfall Part I: Differential Reflectivity","volume":"5","author":"Chandrasekar","year":"1988","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1175\/1520-0426(1990)007<0621:ESOMRA>2.0.CO;2","article-title":"Error Structure of Multiparameter Radar and Surface Measurements of Rainfall. Part III: Specific Differential Phase","volume":"7","author":"Chandrasekar","year":"1990","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1175\/1520-0450(1993)032<1288:OOMREO>2.0.CO;2","article-title":"Optimization of Multiparameter Radar Estimates of Rainfall","volume":"32","author":"Chandrasekar","year":"1993","journal-title":"J. Appl. Meteorol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1175\/2008JHM1015.1","article-title":"An algorithm for real-time rainfall rate estimation by using polarimetric radar: RIME","volume":"10","author":"Silvestro","year":"2009","journal-title":"J. Hydrometeorol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/0022-1694(70)90255-6","article-title":"River flow forecasting through conceptual models part I\u2014A discussion of principles","volume":"10","author":"Nash","year":"1970","journal-title":"J. Hydrol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.jhydrol.2015.08.063","article-title":"Inter-comparison of radar rainfall rate using Constant Altitude Plan Position Indicator and hybrid surface rainfall maps","volume":"531","author":"Kwon","year":"2015","journal-title":"J. Hydrol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1007\/s00376-015-4092-0","article-title":"Identification and removal of non-meteorological echoes in dual-polarization radar data based on a fuzzy logic algorithm","volume":"32","author":"Ye","year":"2015","journal-title":"Adv. Atmos. Sci."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/4\/694\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:24:01Z","timestamp":1760160241000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/4\/694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,14]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["rs13040694"],"URL":"https:\/\/doi.org\/10.3390\/rs13040694","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,14]]}}}