FORECASTING THE MARKETED QUANTITY OF ‘TAHITI’ ACID LIME USING RANDOM FOREST AND TEMPORAL VALIDATION

Authors

  • Letícia Moura da Silva Universidade Federal Rural da Amazônia (UFRA), Brasil
  • Antonia Benedita da Silva Bronze Universidade Federal Rural da Amazônia (UFRA), Brasil
  • Glenda Rafaele da Silva Universidade Federal Rural da Amazônia (UFRA), Brasil
  • Larissa Pacheco Nogueira Universidade Federal Rural da Amazônia (UFRA), Brasil
  • Marcos Paulo Souza de Almeida Universidade Federal Rural da Amazônia (UFRA), Brasil
  • Camila Galvão Viana Universidade Federal Rural da Amazônia (UFRA), Brasil

DOI:

https://doi.org/10.66104/x4hqfw39

Keywords:

machine learning, citrus production, time-series forecasting

Abstract

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.
Views: 514Downloads: 131

Downloads

Download data is not yet available.

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

2026-09-22

How to Cite

Silva, L. M. da, Bronze, A. B. da S., Silva, G. R. da, Nogueira, L. P., Almeida, M. P. S. de, & Viana, C. G. (2026). FORECASTING THE MARKETED QUANTITY OF ‘TAHITI’ ACID LIME USING RANDOM FOREST AND TEMPORAL VALIDATION. REMUNOM, 13(20), 1-22. https://doi.org/10.66104/x4hqfw39

Similar Articles

1-10 of 50

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)