{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:09:27Z","timestamp":1792789767706,"version":"4.5.0"},"reference-count":26,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Council for Scientific and Technological Development","award":["310186\/2023-4"],"award-info":[{"award-number":["310186\/2023-4"]}],"id":[{"id":"https:\/\/ror.org\/03swz6y49","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Council for Scientific and Technological Development","award":["404462\/2025-1"],"award-info":[{"award-number":["404462\/2025-1"]}],"id":[{"id":"https:\/\/ror.org\/03swz6y49","id-type":"ROR","asserted-by":"crossref"}]},{"award":["310186\/2023-4"],"award-info":[{"award-number":["310186\/2023-4"]}],"id":[{"id":"https:\/\/ror.org\/03swz6y49","id-type":"ROR","asserted-by":"publisher"}]},{"award":["404462\/2025-1"],"award-info":[{"award-number":["404462\/2025-1"]}],"id":[{"id":"https:\/\/ror.org\/03swz6y49","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Minas Gerais Research Foundation","award":["APQ-00661-22"],"award-info":[{"award-number":["APQ-00661-22"]}]},{"name":"Minas Gerais Research Foundation","award":["APQ-00613-26"],"award-info":[{"award-number":["APQ-00613-26"]}]},{"name":"Brazilian Coffee Research and Development Consortium","award":["20.24.22.005.00.00"],"award-info":[{"award-number":["20.24.22.005.00.00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Plants"],"abstract":"<jats:p>Early yield estimation is important for improving decision-making and management practices in coffee production systems. However, approaches that use aerial imagery to characterize flowering and relate it to subsequent yield remain limited. This study evaluated the potential of RGB imagery acquired by remotely piloted aircraft (RPA) combined with Deep Learning techniques to classify coffee plants according to three levels of a flowering proxy and to investigate its relationship with yield. A dataset comprising 1593 segmented RGB images was classified into Low, Medium, and High flowering levels using a custom convolutional neural network and three transfer learning architectures: VGG16, ResNet50V2, and MobileNetV2. ResNet50V2 was selected for final evaluation based on its validation performance and achieved 92.12% accuracy, 92.40% macro-precision, 91.81% macro-recall, and 92.06% macro-F1 on the test dataset. The flowering proxy showed a positive association with field-observed yield, with Spearman\u2019s \u03c1 = 0.701 (p &lt; 0.001) and R2 = 0.528 for the combined dataset of Arara and Mundo Novo. In consolidated out-of-sample predictions, the model achieved R2 = 0.489, MAE = 1.03 kg plant\u22121, and RMSE = 1.18 kg plant\u22121. Performance differed between cultivars, with consolidated R2 values of 0.567 for Arara and 0.329 for Mundo Novo. Spatial analysis also showed correspondence between the distribution of flowering levels derived from RGB imagery and the subsequent spatial distribution of yield. These findings indicate that RPA-based RGB imagery and Deep Learning can provide spatialized information related to coffee flowering and its productive performance, with potential applications in precision agriculture. Further evaluation across production cycles, cultivars, and environmental conditions is needed to assess the robustness and generalization of the approach.<\/jats:p>","DOI":"10.3390\/plants15193019","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T08:15:18Z","timestamp":1790928918000},"page":"3019","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aerial Phenotyping of Coffee Flowering Using Deep Learning for Early Yield Prediction"],"prefix":"10.3390","volume":"15","author":[{"given":"Elias Hor\u00e1cio","family":"Zavala","sequence":"first","affiliation":[{"name":"Department of Agricultural Engineering (DEA), School of Engineering (EENG), Federal University of Lavras (UFLA), Lavras 37203-202, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-2210","authenticated-orcid":false,"given":"Gabriel Ara\u00fajo e Silva","family":"Ferraz","sequence":"additional","affiliation":[{"name":"Department of Agricultural Engineering (DEA), School of Engineering (EENG), Federal University of Lavras (UFLA), Lavras 37203-202, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"given":"Felipe Andr\u00e9s","family":"Obando Vega","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Agricultural Sciences, Digital University Institution of Antioquia (IU Digital), Medell\u00edn 050015, Antioquia, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Mirian de Lourdes","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Department of Agricultural Engineering (DEA), School of Engineering (EENG), Federal University of Lavras (UFLA), Lavras 37203-202, MG, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6138-8182","authenticated-orcid":false,"given":"Milene Alves de Figueiredo","family":"Carvalho","sequence":"additional","affiliation":[{"name":"Embrapa Caf\u00e9, Empresa Brasileira de Pesquisa Agropecu\u00e1ria (Embrapa), Bras\u00edlia 70770-901, DF, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8783-0378","authenticated-orcid":false,"given":"Samuel Henrique Braga","family":"da Cunha","sequence":"additional","affiliation":[{"name":"Department of Agriculture, Food, Environment and Forestry (DAGRI), University of Florence, 50145 Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0455-7426","authenticated-orcid":false,"given":"Andrea","family":"Pagliai","sequence":"additional","affiliation":[{"name":"Department of Agriculture, Food, Environment and Forestry (DAGRI), University of Florence, 50145 Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6990-7573","authenticated-orcid":false,"given":"Daniele","family":"Sarri","sequence":"additional","affiliation":[{"name":"Department of Agriculture, Food, Environment and Forestry (DAGRI), University of Florence, 50145 Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"ref_1","unstructured":"Companhia Nacional de Abastecimento (CONAB) (2025). Acompanhamento Da Safra Brasileira, Companhia Nacional de Abastecimento (CONAB)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1590\/s1678-3921.pab2023.v58.02967","article-title":"Maturation and detachment force for mechanized harvesting of irrigated Conilon coffee in the Brazilian Cerrado","volume":"58","author":"Santin","year":"2023","journal-title":"Pesqui. Agropecu. Bras."},{"key":"ref_3","unstructured":"Morais, H., Marur, J., Caramori, P.H., Koguishi, M.S., Gomes, C., and De Arruda Ribeiro, A.M. (2018). Desenvolvimento de Gemas Florais, Florada, Fotoss\u00edntese e Produtividade de Cafeeiros em Condi\u00e7\u00f5es de Sombreamento, Embrapa."},{"key":"ref_4","first-page":"1","article-title":"Interaction between climate, flowering and production of dry coffee (Coffea arabica L.) in Minas Gerais","volume":"16","author":"Rezende","year":"2021","journal-title":"Coffee Sci."},{"key":"ref_5","first-page":"e161978","article-title":"Supervised classification and NDVI calculation from remote piloted aircraft images for coffee plantations applications","volume":"16","author":"Ferraz","year":"2021","journal-title":"Coffee Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.25186\/.v17i.2007","article-title":"Precision coffee growing: A review","volume":"17","author":"Santana","year":"2022","journal-title":"Coffee Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2458","DOI":"10.3390\/agriengineering5040151","article-title":"Coffee Growing with Remotely Piloted Aircraft System: Bibliometric Review","volume":"5","author":"Bento","year":"2023","journal-title":"AgriEngineering"},{"key":"ref_8","unstructured":"Chandra, A.L., Desai, S.V., Guo, W., and Balasubramanian, V.N. (2020). Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Su, R., Wang, Y., Chen, G., Wang, Z., Yin, P., and Wang, J. (2022). Automatic Estimation of Apple Orchard Blooming Levels Using the Improved YOLOv5. Agronomy, 12.","DOI":"10.3390\/agronomy12102483"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Santana, L.S., Ferraz, G.A.E.S., dos Santos, G.H.R., Bento, N.L., and Faria, R.d.O. (2023). Identification and Counting of Coffee Trees Based on Convolutional Neural Network Applied to RGB Images Obtained by RPA. Sustainability, 15.","DOI":"10.3390\/su15010820"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Abraham, E.R., dos Reis, J.G.M., Vendrametto, O., Neto, P.L.d.O.C., Toloi, R.C., de Souza, A.E., and Morais, M.d.O. (2020). Time series prediction with artificial neural networks: An analysis using Brazilian soybean production. Agriculture, 10.","DOI":"10.3390\/agriculture10100475"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"14488","DOI":"10.1038\/s41598-022-18635-5","article-title":"Prediction of annual coffee production yield using artificial neural network and multiple linear regression techniques","volume":"12","author":"Kittichotsatsawat","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6323965","DOI":"10.34133\/2020\/6323965","article-title":"Coffee Flower Identification Using Binarization Algorithm Based on Convolutional Neural Network for Digital Images","volume":"2020","author":"Wei","year":"2020","journal-title":"Plant Phenomics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"111649","DOI":"10.1016\/j.scienta.2022.111649","article-title":"Quantification of flowering in coffee growing with low-cost RGB sensor UAV-mounted","volume":"309","author":"Cano","year":"2023","journal-title":"Sci. Hortic."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bola\u00f1os, J., Corrales, J.C., and Campo, L.V. (2023). Feasibility of Early Yield Prediction per Coffee Tree Based on Multispectral Aerial Imagery: Case of Arabica Coffee Crops in Cauca-Colombia. Remote Sens., 15.","DOI":"10.3390\/rs15010282"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Silva, S.A.d.S., Ferraz, G.A.e.S., Figueiredo, V.C., Volpato, M.M.L., Ferreira, D.D., Machado, M.L., Borges, F.E.d.M., and Conti, L. (2025). Integration of Field Data and UAV Imagery for Coffee Yield Modeling Using Machine Learning. Drones, 9.","DOI":"10.3390\/drones9100717"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2019). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.isprsjprs.2023.02.003","article-title":"Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard","volume":"197","author":"Zhang","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"62","DOI":"10.38141\/10778\/68106","article-title":"RELACI\u00d3N ENTRE PRODUCCI\u00d3N Y CARACTER\u00cdSTICAS FENOT\u00cdPICAS EN Coffea arabica L.","volume":"68","author":"Unigarro","year":"2017","journal-title":"Rev. Cenicaf\u00e9"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Unigarro, C.A., Cay\u00f3n Salinas, D.G., Le\u00f3n-Burgos, A.F., and Fl\u00f3rez-Ramos, C.P. (2025). Flowering and Fruiting of Coffea arabica L.: A Comprehensive Perspective from Phenology. Plants, 14.","DOI":"10.3390\/plants14213396"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1590\/S0006-87052010000400029","article-title":"Modelos Agrometeorol\u00f3gicos De Estimativa Da Du-Ra\u00e7\u00e3o Do Est\u00e1dio Flora\u00e7\u00e3o-Matura\u00e7\u00e3o Para Tr\u00eas Cultivares De Caf\u00e9 Ar\u00e1bica","volume":"69","author":"Nunes","year":"2010","journal-title":"Bragantia"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"6683","DOI":"10.1093\/jxb\/erae395","article-title":"Machine learning-enabled computer vision for plant phenotyping: A primer on AI\/ML and a case study on stomatal patterning","volume":"75","author":"Tan","year":"2024","journal-title":"J. Exp. Bot."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"42971","DOI":"10.1109\/ACCESS.2022.3166515","article-title":"Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning","volume":"10","year":"2022","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Barbosa, B.D.S., Ferraz, G.A.E.S., Santos, L.M., Santana, L.S., Marin, D.B., Rossi, G., and Conti, L. (2021). Application of rgb images obtained by uav in coffee farming. Remote Sens., 13.","DOI":"10.3390\/rs13122397"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e20240156","DOI":"10.1590\/1678-992x-2024-0156","article-title":"Deep learning to classify the ripeness of coffee fruit in the mechanized harvesting process","volume":"82","author":"Zanella","year":"2025","journal-title":"Sci. Agric."}],"container-title":["Plants"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2223-7747\/15\/19\/3019\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T04:14:56Z","timestamp":1791087296000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2223-7747\/15\/19\/3019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":26,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["plants15193019"],"URL":"https:\/\/doi.org\/10.3390\/plants15193019","relation":{},"ISSN":["2223-7747"],"issn-type":[{"value":"2223-7747","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]}}}