{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T05:43:37Z","timestamp":1790660617853,"version":"4.1.0"},"reference-count":28,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T00:00:00Z","timestamp":1768694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Mongkut\u2019s Institute of Technology Ladkrabang","award":["2565-02-01-028"],"award-info":[{"award-number":["2565-02-01-028"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Satellite communication systems experience significant signal degradation during rain events, a phenomenon that can be leveraged for meteorological applications. This study introduces a novel hybrid machine learning framework combining unsupervised clustering with cluster-specific supervised deep learning models to transform satellite signal attenuation into a predictive tool for rainfall prediction. Unlike conventional single-model approaches treating all atmospheric conditions uniformly, our methodology employs K-Means Clustering with the Elbow Method to identify four distinct atmospheric regimes based on Signal-to-Noise Ratio (SNR) patterns from a 12-m Ku-band satellite ground station at King Mongkut\u2019s Institute of Technology Ladkrabang (KMITL), Bangkok, Thailand, combined with absolute pressure and hourly rainfall measurements. The dataset comprises 98,483 observations collected with 30-s temporal resolutions, providing comprehensive coverage of diverse tropical atmospheric conditions. The experimental platform integrates three subsystems: a receiver chain featuring a Low-Noise Block (LNB) converter and Software-Defined Radio (SDR) platform for real-time data acquisition; a control system with two-axis motorized pointing incorporating dual-encoder feedback; and a preprocessing workflow implementing data cleaning, K-Means Clustering (k = 4), Synthetic Minority Over-Sampling Technique (SMOTE) for balanced representation, and standardization. Specialized Long Short-Term Memory (LSTM) networks trained for each identified cluster enable capture of regime-specific temporal dynamics. Experimental validation demonstrates substantial performance improvements, with cluster-specific LSTM models achieving R2 values exceeding 0.92 across all atmospheric regimes. Comparative analysis confirms LSTM superiority over RNN and GRU. Classification performance evaluation reveals exceptional detection capabilities with Probability of Detection ranging from 0.75 to 0.99 and False Alarm Ratios below 0.23. This work presents a scalable approach to weather radar systems for tropical regions with limited ground-based infrastructure, particularly during rapid meteorological transitions characteristic of tropical climates.<\/jats:p>","DOI":"10.3390\/s26020648","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:58:54Z","timestamp":1768834734000},"page":"648","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hybrid Unsupervised\u2013Supervised Learning Framework for Rainfall Prediction Using Satellite Signal Strength Attenuation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6870-0885","authenticated-orcid":false,"given":"Popphon","family":"Laon","sequence":"first","affiliation":[{"name":"School of Engineering, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanawit","family":"Sahavisit","sequence":"additional","affiliation":[{"name":"School of Engineering, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Supavee","family":"Pourbunthidkul","sequence":"additional","affiliation":[{"name":"School of Engineering, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarut","family":"Puangragsa","sequence":"additional","affiliation":[{"name":"School of Engineering, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pattharin","family":"Wichittrakarn","sequence":"additional","affiliation":[{"name":"International Academy of Aviation Industry, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2387-6059","authenticated-orcid":false,"given":"Pattarapong","family":"Phasukkit","sequence":"additional","affiliation":[{"name":"School of Engineering, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3838-6098","authenticated-orcid":false,"given":"Nongluck","family":"Houngkamhang","sequence":"additional","affiliation":[{"name":"Department of Nanoscience and Nanotechnology, School of Integrated Innovative Technology, King Mongkut\u2019s Institute of Technology Ladkrabang, Bangkok 10520, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gyasi-Agyei, Y. (2020). Identification of the Optimum Rain Gauge Network Density for Hydrological Modelling Based on Radar Rainfall Analysis. Water, 12.","DOI":"10.3390\/w12071906"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5411","DOI":"10.5194\/essd-14-5411-2022","article-title":"OpenMRG: Open data from Microwave links, Radar, and Gauges for rainfall quantification in Gothenburg, Sweden","volume":"14","author":"Andersson","year":"2022","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Isabona, J., Imoize, A.L., Ojo, S., Lee, C.-C., and Li, C.-T. (2022). Atmospheric Propagation Modelling for Terrestrial Radio Frequency Communication Links in a Tropical Wet and Dry Savanna Climate. Information, 13.","DOI":"10.3390\/info13030141"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Toriola, W., Ojo, J., and Ashidi, A. (2021). Characterization of rain specific attenuation and frequency scaling technique for satellite communication systems in a tropical location. Journal of Physics: Conference Series, IOP Publishing.","DOI":"10.1088\/1742-6596\/2034\/1\/012019"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.3390\/rs13112156","article-title":"Characteristics of Rain-Induced Attenuation over Signal Links at Frequency Ranges of 25 and 38 GHz Observed in Beijing","volume":"13","author":"Han","year":"2021","journal-title":"Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Samad, M.A., and Choi, D.-Y. (2020). Learning-Assisted Rain Attenuation Prediction Models. Appl. Sci., 10.","DOI":"10.3390\/app10176017"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Shen, X., and Huang, D.D. (2021). Retrieval of Raindrop Size Distribution Using Dual-Polarized Microwave Signals from LEO Satellites: A Feasibility Study through Simulations. Sensors, 21.","DOI":"10.3390\/s21196389"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Samad, M.A., Diba, F.D., and Choi, D.-Y. (2021). A Survey of Rain Fade Models for Earth\u2013Space Telecommunication Links\u2014Taxonomy, Methods, and Comparative Study. Remote Sens., 13.","DOI":"10.3390\/rs13101965"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.jastp.2019.03.005","article-title":"Evaluation of some rain attenuation prediction models for satellite communication at Ku and Ka bands","volume":"188","author":"Igwe","year":"2019","journal-title":"J. Atmos. Sol. Terr. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Olurotimi, E. (2021). Estimation of cloud attenuation over some coastal cities for satellite space links in South Africa. Journal of Physics: Conference Series, IOP Publishing.","DOI":"10.1088\/1742-6596\/1874\/1\/012011"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104895","DOI":"10.1016\/j.atmosres.2020.104895","article-title":"Raindrop size distribution and microphysical characteristics of a great rainstorm in 2016 in Beijing, China","volume":"239","author":"Luo","year":"2020","journal-title":"Atmos. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1109\/LGRS.2016.2543299","article-title":"Fade-Slope Model for Rain Attenuation Prediction in Tropical Region","volume":"13","author":"Das","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Domb Alon, M.M., and Leshem, G. (2022). Satellite to Ground Station, Attenuation Prediction for 2.4\u201372 GHz Using LTSM, an Artificial Recurrent Neural Network Technology. Electronics, 11.","DOI":"10.3390\/electronics11040541"},{"key":"ref_14","unstructured":"Kaneko, R., Nakayoshi, M., and Onomura, S. (2019). Rainfall Prediction by a Recurrent Neural Network Algorithm LSTM Learning Surface Observation Data. AGU Fall Meeting Abstracts, AGU."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.5194\/nhess-20-1233-2020","article-title":"Extreme wave analysis based on atmospheric pattern classification: An application along the Italian coast","volume":"20","author":"Solari","year":"2020","journal-title":"Nat. Hazards Earth Syst. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"124","DOI":"10.3390\/galaxies13060124","article-title":"Reinforcement Learning-Driven Framework for High-Precision Target Tracking in Radio Astronomy","volume":"13","author":"Sahavisit","year":"2025","journal-title":"Galaxies"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"472","DOI":"10.4314\/njt.v42i4.7","article-title":"Evaluation of rainfall rates and rain-induced signal attenuation for satellite communication in the South-South Region of Nigeria","volume":"42","author":"Ukommi","year":"2024","journal-title":"Niger. J. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liao, X., Fan, L., Wang, Y., Yu, Z., Wang, G., Li, X., and Zhang, J. (2023). Attenuation Characterization of Terahertz Waves in Foggy and Rainy Conditions at 0.1\u20131 THz Frequencies. Electronics, 12.","DOI":"10.3390\/electronics12071684"},{"key":"ref_19","unstructured":"International Telecommunication Union (2005). Recommendation ITU-R P.838-3: Specific Attenuation Model for Rain for Use in Prediction Methods, ITU."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Giannetti, F., and Reggiannini, R. (2021). Opportunistic Rain Rate Estimation from Measurements of Satellite Downlink Attenuation: A Survey. Sensors, 21.","DOI":"10.3390\/s21175872"},{"key":"ref_21","first-page":"226","article-title":"Research on K-Value Selection Method of K-Means Clustering Algorithm","volume":"2","author":"Yuan","year":"2019","journal-title":"J. Multidiscip. Sci. J."},{"key":"ref_22","unstructured":"Humaira, H., and Rasyidah, R. (2018, January 24\u201325). Determining the Appropiate Cluster Number Using Elbow Method for K-Means Algorithm. Proceedings of the 2nd Workshop on Multidisciplinary and Applications (WMA) 2018, Padang, Indonesia."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1007\/s00477-024-02745-9","article-title":"The effectiveness of data pre-processing methods on the performance of machine learning techniques using RF, SVR, Cubist and SGB: A study on undrained shear strength prediction","volume":"38","author":"Demir","year":"2024","journal-title":"Stoch. Environ. Res. Risk Assess."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.54097\/xgeyhr93","article-title":"The Investigation of LSTM-Random Search with Various Standardization and Normalization Technologies","volume":"85","author":"Ma","year":"2024","journal-title":"Highlights Sci. Eng. Technol."},{"key":"ref_25","first-page":"321","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Artif. Intell. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4903","DOI":"10.1007\/s10994-022-06296-4","article-title":"A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning","volume":"113","author":"Elreedy","year":"2023","journal-title":"Mach. Learn."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jing, J., Li, Q., and Peng, X. (2019). MLC-LSTM: Exploiting the Spatiotemporal Correlation between Multi-Level Weather Radar Echoes for Echo Sequence Extrapolation. Sensors, 19.","DOI":"10.3390\/s19183988"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Gao, Y., Guan, J., Zhang, F., Wang, X., and Long, Z. (2022). Attention-Unet-Based Near-Real-Time Precipitation Estimation from Fengyun-4A Satellite Imageries. Remote Sens., 14.","DOI":"10.3390\/rs14122925"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/648\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T05:10:39Z","timestamp":1769058639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,18]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020648"],"URL":"https:\/\/doi.org\/10.3390\/s26020648","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,18]]}}}