{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:56:53Z","timestamp":1772301413030,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Citizen Science Earth Observation Lab (CSEOL) pilot projects","award":["776691 (TWIGA)"],"award-info":[{"award-number":["776691 (TWIGA)"]}]},{"name":"the European Community\u2019s Horizon 2020 Programme (2014\u20132020)","award":["776691 (TWIGA)"],"award-info":[{"award-number":["776691 (TWIGA)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Food and economic security in West Africa rely heavily on rainfed agriculture and are threatened by climate change and demographic growth. Accurate rainfall information is therefore crucial to tackling these challenges. Particularly, information about the occurrence and length of droughts as well as the onset date of the rainy season is essential for agricultural planning. However, existing rainfall models fail to accurately represent the highly variable and sparsely monitored West African rainfall patterns. In this paper, we show the potential of deep learning (DL) to model rainfall in the region and propose a methodology to develop DL models in data-scarce areas. We built two DL models for satellite rainfall (rain\/no-rain) detection over northern Ghana from Meteosat TIR data based on standard DL architectures: Convolutional neural networks (CNNs) and convolutional long short-term memory neural networks (ConvLSTM). The Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) and Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System (PERSIANN-CCS) products are used as benchmarks. We use rain gauge data from the Trans-African Hydro-Meteorological Observatory (TAHMO) for model development and performance evaluation. We show that our models compare well against existing products despite being considerably simpler, developed with a small training dataset\u2014i.e., 8 stations covering 2.5 years with 20.4% of the data missing\u2014and using TIR data alone. Concretely, our models consistently outperform PERSIANN-CCS for rain\/no-rain detection at a sub-daily timescale. While IMERG is the overall best performer, the DL models perform better in the second half of the rainy season despite their simplicity (i.e., up to 120 k parameters). Our results suggest that DL-based regional models are a promising alternative to state-of-the-art global products for providing regional rainfall information, especially in meteorologically complex regions such as the (sub)tropics, which are poorly covered by ground-based rainfall observations.<\/jats:p>","DOI":"10.3390\/rs15071922","type":"journal-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T01:35:59Z","timestamp":1680572159000},"page":"1922","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["The Potential of Deep Learning for Satellite Rainfall Detection over Data-Scarce Regions, the West African Savanna"],"prefix":"10.3390","volume":"15","author":[{"given":"M\u00f3nica","family":"Est\u00e9banez-Camarena","sequence":"first","affiliation":[{"name":"Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands"}]},{"given":"Riccardo","family":"Taormina","sequence":"additional","affiliation":[{"name":"Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7200-3353","authenticated-orcid":false,"given":"Nick","family":"van de Giesen","sequence":"additional","affiliation":[{"name":"Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9572-2193","authenticated-orcid":false,"given":"Marie-Claire","family":"ten Veldhuis","sequence":"additional","affiliation":[{"name":"Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mortimore, M. (1989). Adapting to Drought. Farmers, Famine and Desertification in West Africa, Cambridge University Press.","DOI":"10.1017\/CBO9780511720772"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/S0140-1963(18)30838-3","article-title":"Spatial aspects of drought in the Sahel","volume":"18","author":"Agnew","year":"1990","journal-title":"Arid. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fpls.2016.01262","article-title":"Agriculture in West Africa in the Twenty-First Century: Climate Change and Impacts Scenarios, and Potential for Adaptation","volume":"7","author":"Sultan","year":"2016","journal-title":"Front. Plant Sci."},{"key":"ref_4","unstructured":"United Nations Department of Economic and Social Affairs, Population Division (2022). World Population Prospects 2022: Summary of Results, United Nations. UN DESA\/POP\/2022\/TR\/NO. 3."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1038\/s41558-021-01066-x","article-title":"Emergence of seasonal delay of tropical rainfall during 1979\u20132019","volume":"11","author":"Song","year":"2021","journal-title":"Nat. Clim. Chang."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shukla, S., Husak, G., Turner, W., Davenport, F., Funk, C., Harrison, L., and Krell, N. (2021). A slow rainy season onset is a reliable harbinger of drought in most food insecure regions in Sub-Saharan Africa. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0242883"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3285","DOI":"10.1002\/2017GL076521","article-title":"Global changes in drought conditions under different levels of warming","volume":"45","author":"Naumann","year":"2018","journal-title":"Geophys. Res. Lett."},{"key":"ref_8","unstructured":"Clapp, F. (1970). Estimating Monthly Precipitation from Satellite Data, NMC Office Note 46."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1175\/1520-0450(1989)028<0252:RPTAAR>2.0.CO;2","article-title":"Relating Point to Area Average Rainfall in Semiarid West Africa and the Implications for Rainfall Estimates Derived from Satellite Data","volume":"28","author":"Flitcroft","year":"1989","journal-title":"J. Appl. Meteor. Climatol."},{"key":"ref_10","unstructured":"Arnaud, Y., Desbois, M., and Gioda, A. (August, January 30). Towards a Rainfall Estimation Using Meteosat over Africa; Reprinted from Hydraulics Hydrology of Arid Lands; In Proceedings of the Int\u2019l. Symposium HY & IR Div.IASCE, San Diego, CA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1175\/1520-0450(1995)034<0411:SDIVOW>2.0.CO;2","article-title":"Satellite-Derived Interannual Variability of West African Rainfall during 1983\u20131988","volume":"34","author":"Ba","year":"1995","journal-title":"J. Appl. Meteor. Climatol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2015.66","article-title":"The Climate Hazards Infrared Precipitation with Stations\u2014A New Environmental Record for Monitoring Extremes","volume":"2","author":"Funk","year":"2015","journal-title":"Sci. Data"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2805","DOI":"10.1175\/JAMC-D-14-0016.1","article-title":"Extension of the TAMSAT Satellite-Based Rainfall Monitoring over Africa and from 1983 to Present","volume":"53","author":"Tarnavsky","year":"2014","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"124412","DOI":"10.1016\/j.jhydrol.2019.124412","article-title":"Evaluation of 23 Gridded Precipitation Datasets across West Africa To Cite This Version: HAL Id: Hal-02626156","volume":"581","author":"Defrance","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Atiah, W.A., Amekudzi, L.K., Aryee, J.N.A., Preko, K., and Danuor, S.K. (2020). Validation of Satellite and Merged Rainfall Data over Ghana, West Africa. Atmosphere, 11.","DOI":"10.3390\/atmos11080859"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1175\/JAM2173.1","article-title":"Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System","volume":"43","author":"Hong","year":"2004","journal-title":"J. Appl. Meteorol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1175\/JHM-D-18-0256.1","article-title":"Comparison of Rainfall Products over Sub-Saharan Africa","volume":"21","year":"2020","journal-title":"J. Hydrometeorol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5801","DOI":"10.5194\/hess-22-5801-2018","article-title":"The PERSIANN Family of Global Satellite Precipitation Data: A Review and Evaluation of Products","volume":"22","author":"Nguyen","year":"2018","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_19","unstructured":"Huffman, G., Bolvin, D., Braithwaite, D., Hsu, K., and Joyce, R. (2013). Algorithm Theoretical Basis Document (ATBD) NASA Global Precipitation Measurement (GPM) Integrated Multi-SatellitE Retrievals for GPM (IMERG). Nasa, 29."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"112754","DOI":"10.1016\/j.rse.2021.112754","article-title":"Review of GPM IMERG Performance: A Global Perspective","volume":"268","author":"Pradhan","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2817","DOI":"10.1175\/JHM-D-17-0139.1","article-title":"Validation of IMERG Precipitation in Africa","volume":"18","author":"Dezfuli","year":"2017","journal-title":"J. Hydrometeorol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1175\/1520-0450-39.5.666","article-title":"Discrepancy between Gauges and Satellite Estimates of Rainfall in Equatorial Africa","volume":"39","author":"McCollum","year":"2000","journal-title":"J. Appl. Meteorol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1038\/s41586-021-03854-z","article-title":"Skillful Precipitation Nowcasting Using Deep Generative Models of Radar","volume":"597","author":"Ravuri","year":"2021","journal-title":"Nature"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Miao, Q., Pan, B., Wang, H., Hsu, K., and Sorooshian, S. (2019). Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network. Water, 11.","DOI":"10.3390\/w11050977"},{"key":"ref_25","unstructured":"Tao, Y., Gao, X., Ihler, A., Hsu, K., and Sorooshian, S. (2016). 2016 IEEE Congress on Evolutionary Computation (CEC), IEEE Press."},{"key":"ref_26","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":"Qiangqiang","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_27","unstructured":"Schmid, J. (2000). The SEVIRI Instrument. Assembly, 1\u201310."},{"key":"ref_28","unstructured":"(2017). EUMETSAT MSG Level 1.5 Image Data Format Description. Image, 127."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1002\/wat2.1034","article-title":"The Trans-African Hydro-Meteorological Observatory (TAHMO)","volume":"1","author":"Hut","year":"2014","journal-title":"WIREs Water"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1175\/1520-0450(1997)036<1176:PEFRSI>2.0.CO;2","article-title":"Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks","volume":"36","author":"Hsu","year":"1997","journal-title":"J. Appl. Meteorol."},{"key":"ref_31","unstructured":"World Bank Group (2018). Third Ghana Economic Update: Agriculture as an Engine of Growth and Jobs Creation. Africa Region. Report, 1\u201363."},{"key":"ref_32","unstructured":"McSweeney, C., New, M., and Lizcano, G. (2008). UNDP General Climate Change Country Profiles: Ghana, UNDP."},{"key":"ref_33","unstructured":"GMet Climatology (2021, October 19). Ghana Meteorological Agency, Available online: https:\/\/www.meteo.gov.gh\/gmet\/climatology\/."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1628","DOI":"10.1002\/qj.3345","article-title":"Rainfall Types over Southern West Africa: Objective Identification, Climatology and Synoptic Environment","volume":"144","author":"Maranan","year":"2018","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1175\/JCLI-3316.1","article-title":"Regional and Diurnal Variability of the Vertical Structure of Precipitation Systems in Africa Based on Spaceborne Radar Data","volume":"18","author":"Geerts","year":"2005","journal-title":"J. Clim."},{"key":"ref_36","unstructured":"Callo-concha, D., Gaiser, T., and Ewert, F. (2012). Farming and Cropping Systems in the West African Sudanian Savanna. WASCAL research area: Northern Ghana, Southwest Burkina Faso and Northern Benin. ZEF Work. Pap. Ser. 100., 1\u201349."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Moraux, A., Dewitte, S., Cornelis, B., and Munteanu, A. (2021). A Deep Learning Multimodal Method for Precipitation Estimation. Remote Sens., 13.","DOI":"10.3390\/rs13163278"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"124664","DOI":"10.1016\/j.jhydrol.2020.124664","article-title":"A spatiotemporal deep fusion model for merging satellite and gauge precipitation in China","volume":"584","author":"Wu","year":"2020","journal-title":"J. Hydrol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on Deep Learning with Class Imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"8558","DOI":"10.1029\/2018WR022643","article-title":"A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists","volume":"54","author":"Shen","year":"2018","journal-title":"Water Resour. Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1029\/2018WR024090","article-title":"Improving Precipitation Estimation Using Convolutional Neural Network","volume":"55","author":"Pan","year":"2019","journal-title":"Water Resour. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_43","first-page":"802","article-title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","volume":"2015","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., and Wu, Y. (2022). Coca: Contrastive captioners are image-text foundation models. arXiv."},{"key":"ref_45","first-page":"1","article-title":"Transformers in vision: A survey","volume":"54","author":"Salman","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1175\/2008WAF2222159.1","article-title":"Visualizing Multiple Measures of Forecast Quality","volume":"24","author":"Roebber","year":"2009","journal-title":"Weather Forecast."},{"key":"ref_48","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA."},{"key":"ref_49","unstructured":"Raschka, S. (2018). Model evaluation, model selection, and algorithm selection in machine learning. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.1029\/2018GL077891","article-title":"Global Virga Precipitation Distribution Derived from Three Spaceborne Radars and Its Contribution to the False Radiometer Precipitation Detection","volume":"45","author":"Wang","year":"2018","journal-title":"Geophys. Res. Lett."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A ConvNet for the 2020s. arXiv.","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/7\/1922\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:09:09Z","timestamp":1760123349000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/7\/1922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":51,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["rs15071922"],"URL":"https:\/\/doi.org\/10.3390\/rs15071922","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,3]]}}}