FORECASTING THE MARKETED QUANTITY OF ‘TAHITI’ ACID LIME USING RANDOM FOREST AND TEMPORAL VALIDATION
DOI:
https://doi.org/10.66104/x4hqfw39Keywords:
machine learning, citrus production, time-series forecastingAbstract
Forecasting the marketed quantity of agricultural products can contribute to the planning of production and commercial operations. This study aimed to develop and evaluate a Random Forest model to predict the marketed quantity of ‘Tahiti’ acid lime with a one-month forecast horizon. Monthly data from 2018 to 2023 were obtained from a production unit located in Capitão Poço, Pará, Brazil. The model incorporated historical information on marketed quantity and seasonal components, while climatic variables were additionally evaluated through sensitivity analysis. Predictive performance was assessed using expanding-window temporal validation, with 2021, 2022, and 2023 as test periods. Across the 36 out-of-sample predictions, the Random Forest achieved an MAE of 279,100.1 kg, an RMSE of 387,771.5 kg, and a predictive R² of 0.530, outperforming reference models based on persistence, historical monthly mean, and the same month of the previous year. However, linear regression showed better overall performance (MAE = 239,165.4 kg; RMSE = 343,104.6 kg; R² = 0.632), indicating that greater algorithmic complexity did not result in higher predictive performance for this dataset. Climatic variables did not provide incremental predictive gains over the evaluated forecast horizon. The results highlight the importance of temporal and seasonal structure in forecasting marketed quantity and reinforce the need to compare machine learning algorithms with more parsimonious models.Downloads
References
Akinbile, Christopher O., et al. "Trends and spatial analysis of temperature and rainfall patterns on rice yields in Nigeria." Atmospheric Science Letters 21.3 (2020): e944. DOI: https://doi.org/10.1002/asl.944
Andrade, Adalberto, et al. "Uso de ciência de dados para predição do consumo de fertilizantes no Brasil." Brazilian e-Science Workshop (BreSci). SBC, 2020. DOI: https://doi.org/10.5753/bresci.2020.11176
Arantes, Leticia Tondato. "Drone aplicado na agricultura digital." Ipê Agronomic Journal (2019). DOI: https://doi.org/10.37951/2595-6906.2019v3i1.4323
Bassan, Meire Menezes, et al. "Beneficiamento pós-colheita de lima ácida'Tahiti'afeta sua qualidade e conservação." Ciência Rural 46.1 (2015): 184-190. DOI: https://doi.org/10.1590/0103-8478cr20141492
da Silva Carvalho, Roberto Luís, and Angel Ramon Sanchez Delgado. "ESTIMATIVAS DAS MODELAGENS POR REDES NEURAIS TIPO GMDH E BOX-JENKINS PARA AS SÉRIES DE TEMPERATURAS MÁXIMAS E MÍNIMAS DO MUNICÍPIO DE ARIQUEMES (RO)." Revista Brasileira de Climatologia 26 (2020) DOI: https://doi.org/10.5380/abclima.v26i0.59145
Cavalcante, WS da S., et al. "Tecnologias e inovações no uso de drones na agricultura." Brazilian Journal of Development 8.1 (2022): 7108-7117. DOI: https://doi.org/10.34117/bjdv8n1-481
Coutinho, Eluã Ramos, Robson Mariano Silva, and Angel Ramon Sanchez Delgado. "Utilização de técnicas de inteligência computacional na predição de dados meteorológicos." Revista Brasileira de Meteorologia 31.1 (2016): 24-36. DOI: https://doi.org/10.1590/0102-778620140115
Frimpong, Samuel Akwasi, et al. "Machine and deep learning in agricultural engineering: A comprehensive survey and meta-analysis of techniques, applications, and challenges." Computers 14.10 (2025): 438. DOI: https://doi.org/10.3390/computers14100438
Furtado, Kenedy Daniel Calegari, et al. "O papel dos drones na agricultura 4.0 e 5.0: Auxílio tecnológico para uma agricultura eficiente, produtiva e sustentável." Tecnologia e Inovação Em Ciências Agrárias e Biológicas Avanços para a Sociedade Atual (2023). DOI: https://doi.org/10.56238/tecnolocienagrariabiosoci-013
Gatera, Antoine, et al. "Comparison of random forest and support vector machine regression models for forecasting road accidents." Scientific African 21 (2023): e01739. DOI: https://doi.org/10.1016/j.sciaf.2023.e01739
Gurgel, Fábio de Lima, et al. "Early rootstock selection under ‘tahiti’acid lime crown in Capitão Poço, Pará State, Brazil." Acta Scientiarum. Agronomy 46 (2024): e63302. DOI: https://doi.org/10.4025/actasciagron.v46i1.63302
Gurgel, Fábio de Lima, et al. "Rootstocks for citrus orchards in the state of Pará." Pesquisa Agropecuária Brasileira 60 (2025): e04134. DOI: https://doi.org/10.1590/s1678-3921.pab2025.v60.04134
Jiménez, Fernando, et al. “Feature Selection Based Multivariate Time Series Forecasting: An Application to Antibiotic Resistance Outbreaks Prediction.” Artificial Intelligence in Medicine, vol. 104, 2020, article 101818. DOI: https://doi.org/10.1016/j.artmed.2020.101818
Kamilaris, Andreas, and Francesc X. Prenafeta-Boldú. "A review of the use of convolutional neural networks in agriculture." The Journal of Agricultural Science 156.3 (2018): 312-322. DOI: https://doi.org/10.1017/S0021859618000436
Karbassi Yazdi, Amir, et al. “Forecasting Crop Yields in Rainfed India: A Comparative Assessment of Machine Learning Baselines and Implications for Precision Agribusiness.” Agriculture, vol. 16, no. 1, 2026, article 65. DOI: https://doi.org/10.3390/agriculture16010065
Martorano, L. G., et al. "Estudos climáticos do estado do Pará, classificação climática (Köppen) e deficiência hídrica (Thornthwaite, Mather)." (1993).
Mattos Jr., Dirceu de, et al. "Lima ácida Tahiti no Centro de Citricultura: pesquisas e difusão de tecnologia." Informativo Centro de Citricultura Sylvio Moreira 308.309 (2021): 1-12.
Marzak, Zahira, et al. “Forecasting Multivariate Time Series with Trend and Seasonality: A Random Forest Approach.” Innovative Intelligent Industrial Production and Logistics, Springer Nature, 2025, pp. 128–144. DOI: https://doi.org/10.1007/978-3-031-80775-6_9
Meher, Bharat Kumar, et al. "Forecasting stock prices of fintech companies of India using random forest with high-frequency data." Journal of Open Innovation: Technology, Market, and Complexity 10.1 (2024): 100180. DOI: https://doi.org/10.1016/j.joitmc.2023.100180
Nieto, Paulino José García, et al. "Predicting the critical superconducting temperature using the random forest, MLP neural network, M5 model tree and multivariate linear regression." Alexandria Engineering Journal 86 (2024): 144-156. DOI: https://doi.org/10.1016/j.aej.2023.11.034
Pabitha, C., S. Benila, and A. Suresh. "A digital footprint in enhancing agricultural practices with improved production using machine learning." (2023).
Parisi, M. C. M., C. M. Henrique, and P. Prati. "Perdas pós-colheita: um gargalo na produção de alimentos." Pesquisa & Tecnologia 9.2 (2012): 1-5.
Pinto, João V. de N., et al. "Fruit yield and gas exchange of Tahiti lime at different irrigation depths in the Amazon." Revista Brasileira de Engenharia Agrícola e Ambiental 27.6 (2023): 463-471. DOI: https://doi.org/10.1590/1807-1929/agriambi.v27n6p463-471
Prasad, N. R., N. R. Patel, and Abhishek Danodia. "Crop yield prediction in cotton for regional level using random forest approach: NR Prasad et al." spatial information research 29.2 (2021): 195-206. DOI: https://doi.org/10.1007/s41324-020-00346-6
Rivera-Hernández, Benigno, et al. "Seasonal changes in physiological responses and yield of Citrus latifolia under high-density planting and different soil moisture tensions." Horticulturae 11.12 (2025): 1472. DOI: https://doi.org/10.3390/horticulturae11121472
Roberts, Michael J., et al. "Comparing and combining process-based crop models and statistical models with some implications for climate change." Environmental Research Letters 12.9 (2017): 095010. DOI: https://doi.org/10.1088/1748-9326/aa7f33
Rustick, Andressa, José Airton Azevedo dos Santos, and Cidmar Ortiz dos Santos. "Aplicação de modelos de redes neurais artificiais na previsão da produção, importação e consumo de fertilizantes no Brasil." Peer Review 5.16 (2023): 1-14. DOI: https://doi.org/10.53660/610.prw2201
Shawon, Sarowar Morshed, et al. "Crop yield prediction using machine learning: An extensive and systematic literature review." Smart Agricultural Technology 10 (2025): 100718. DOI: https://doi.org/10.1016/j.atech.2024.100718
Sim, Ha Seon, et al. "Prediction of strawberry growth and fruit yield based on environmental and growth data in a greenhouse for soil cultivation with applied autonomous facilities." Horticultural Science and Technology 38.6 (2020): 840-849. DOI: https://doi.org/10.7235/HORT.20200076
Sousa, Denis de Pinho, et al. "Estimation of evapotranspiration and single and dual crop coefficients of acai palm in the Eastern Amazon (Brazil) using the Bowen ratio system." Irrigation Science 39.1 (2021): 5-22. DOI: https://doi.org/10.1007/s00271-020-00710-2
Srivastava, Anoop Kumar, et al. "Climate change and citrus nutrition: mechanisms, nutrient imbalances, and inclusive management." Frontiers in Plant Science 17 (2026): 1798826. DOI: https://doi.org/10.3389/fpls.2026.1798826
Tajudeen, Tawakalitu Titilayo, et al. "The effect of climate change on food crop production in Lagos State." Foods 11.24 (2022): 3987. DOI: https://doi.org/10.3390/foods11243987
Wolfart, Simone Beatriz, et al. "ESTUDO DE MÉTODOS PARA PREVISÃO DA PRODUÇÃO DE GRÃOS NO BRASIL VIA SÉRIES TEMPORAIS." Cadernos do IME-Série Estatística 49 (2020): 17-17. DOI: https://doi.org/10.12957/cadest.2020.57913
Yao, Zhaoyuan, et al. "Improving high-resolution soil moisture mapping in China via dense ground-based observations and multi-source data fusion." Agricultural Water Management 333 (2026): 110570. DOI: https://doi.org/10.1016/j.agwat.2026.110570
Published
Issue
Section
License
Copyright (c) 2026 Letícia Moura da Silva, Antonia Benedita da Silva Bronze, Glenda Rafaele da Silva, Larissa Pacheco Nogueira, Marcos Paulo Souza de Almeida, Camila Galvão Viana

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License, which permits the sharing of the work with proper acknowledgment of authorship and initial publication in this journal;
Authors are authorized to enter into separate, additional agreements for the non-exclusive distribution of the version of the work published in this journal (e.g., posting in an institutional repository or publishing it as a book chapter), provided that authorship and initial publication in this journal are properly acknowledged, and that the work is adapted to the template of the respective repository;
Authors are permitted and encouraged to post and distribute their work online (e.g., in institutional repositories or on their personal websites) at any point before or during the editorial process, as this may lead to productive exchanges and increase the impact and citation of the published work (see The Effect of Open Access);
Authors are responsible for correctly providing their personal information, including name, keywords, abstracts, and other relevant data, thereby defining how they wish to be cited. The journal’s editorial board is not responsible for any errors or inconsistencies in these records.
PRIVACY POLICY
The names and email addresses provided to this journal will be used exclusively for the purposes of this publication and will not be made available for any other purpose or to third parties.
Note: All content of the work is the sole responsibility of the author and the advisor.
