This study examines the effectiveness of ARIMA and LSTM models in forecasting bean production in Mozambique, using data from 2002 to 2022. The analysis reveals that the limited sample size, comprising only 21 years of data, significantly impacts the accuracy of both models, as reflected in high MAPE values. The ARIMA(1,1,1) model demonstrates robustness with the lowest RMSE among the ARIMA models, but the LSTM model, despite its challenges, shows superior capability in capturing nonlinear patterns, resulting in a lower average MAPE. Forecasts for the period from 2023 to 2030 suggest stable bean production with slight annual variations, although the wide confidence intervals highlight the inherent uncertainty in these predictions. This study underscores the importance of improving forecasting models to better guide agricultural planning and policy-making, particularly in the context of Mozambique's food insecurity challenges and the global objectives of SDG 2. The results emphasize the need for more extensive data collection and the inclusion of additional variables to enhance the accuracy of future forecasts, contributing to the reduction of food insecurity and the achievement of sustainable development goals in Mozambique.
| Published in | International Journal of Agricultural Economics (Volume 10, Issue 2) |
| DOI | 10.11648/j.ijae.20251002.13 |
| Page(s) | 67-85 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Agricultural Forecasting, ARIMA Models, LSTM Neural Networks, Beans, Food Security
| [1] | FAO, IFAD, UNICEF, WFP, and WHO, ‘The State of Food Security and Nutrition in the World 2023’, 2023. [Online]. Available: |
| [2] | FAO, IFAD, UNICEF, WFP, and WHO, ‘The Stat of Food Security and Nutrition in the World’, 2024. [Online]. Available: |
| [3] | M. Rezaey, ‘Popping Efficiencies of Popping Beans, and Physicochemical Characteristics and Functional Properties of Their Flour, Protein, and Starch Fractionates’, Washington State University, 2023. |
| [4] | N. Gogoi, K. K. Baruah, and R. S. Meena, ‘Grain legumes: impact on soil health and agroecosystem’, in Legumes for Soil Health and Sustainable Management, Springer, 2018, pp. 511-539. |
| [5] | E. Kebede, ‘Contribution, Utilization, and Improvement of Legumes-Driven Biological Nitrogen Fixation in Agricultural Systems’, Front. Sustain. Food Syst., vol. 5, no. November, pp. 1-18, 2021, |
| [6] |
World Bank, ‘Climate-Smart Agriculture in Mozambique’, 2017. [Online]. Available:
https://climateknowledgeportal.worldbank.org/sites/default/files/2019-06/CSA-in-Mozambique.pdf |
| [7] | Ambika et al., ‘Unraveling Origin, History, Genetics, and Strategies for Accelerated Domestication and Diversification of Food Legumes’, Front. Genet., vol. 13, no. July, pp. 1-21, 2022, |
| [8] | A. E. Yanni, S. Iakovidi, E. Vasilikopoulou, and V. T. Karathanos, ‘Legumes: A Vehicle for Transition to Sustainability’, Nutrients, vol. 16, no. 1, p. 98, 2023, |
| [9] | B. Vanlauwe, M. Hungria, F. Kanampiu, and K. E. Giller, ‘The role of legumes in the sustainable intensification of African smallholder agriculture: Lessons learnt and challenges for the future’, Agric. Ecosyst. Environ., vol. 284, no. March, p. 106583, 2019, |
| [10] | S. M. T. Gharibzahedi and B. Smith, ‘The functional modification of legume proteins by ultrasonication: A review’, Trends Food Sci. Technol., vol. 98, no. 10, pp. 107-116, 2020, |
| [11] | R. Elahi and T. Mu, ‘High Hydrostatic Pressure (HHP)-Induced Structural Modification of Patatin and Its Antioxidant Activities’, Molecules, vol. 22, no. 438, pp. 1-20, 2017, |
| [12] | FAO, ‘Mozambique Country Brief’, 2023. [Online]. Available: |
| [13] | F. Sparvoli et al., ‘Sensory characteristics and nutritional quality of food products made with a biofortified and lectin free common bean (Phaseolus vulgaris l.) flour’, Nutrients, vol. 13, no. 12, pp. 1-28, 2021, |
| [14] | M. Philipo, P. A. Ndakidemi, and E. R. Mbega, ‘Importance of common bean genetic zinc biofortification in alleviating human zinc deficiency in sub-Saharan Africa’, Cogent Food Agric., vol. 7, no. 1, 2021, |
| [15] | A. Pathania, S. K. Sharma, and P. N. Sharma, Cammon Bean. 2014. |
| [16] | P. Smýkal et al., ‘Legume Crops Phylogeny and Genetic Diversity for Science and Breeding’, CRC. Crit. Rev. Plant Sci., vol. 34, pp. 43-104, 2015, |
| [17] | C. Chávez-Mendoza and E. Sánchez, ‘Bioactive compounds from mexican varieties of the common bean (Phaseolus vulgaris): Implications for health’, Molecules, vol. 22, no. 8, pp. 1-32, 2017, |
| [18] | K. Rani et al., Legumes for Sustainable Soil and Crop Management. 2019. |
| [19] |
FAOSTAT, ‘Crops and livestock products (Production)’, 27.12.2023, 2023.
https://www.fao.org/faostat/en/#data/QCL (accessed Jan. 03, 2024). |
| [20] | M. K. Pandey et al., ‘Emerging genomic tools for legume breeding: Current status and future prospects’, Front. Plant Sci., vol. 7, no. MAY2016, pp. 1-18, 2016, |
| [21] | N. S. Affrifah, M. A. Uebersax, and S. Amin, ‘Nutritional significance, value-added applications, and consumer perceptions of food legumes: A review’, Legum. Sci., vol. 5, no. 4, pp. 1-16, 2023, |
| [22] | C. Mukankusi et al., ‘Genomics, genetics and breeding of common bean in Africa: A review of tropical legume project’, Plant Breed., vol. 138, no. 4, pp. 401-414, 2019, |
| [23] | C. Ojiewo et al., ‘The Role of Vegetables and Legumes in Assuring Food, Nutrition, and Income Security for Vulnerable Groups in Sub-Saharan Africa’, World Med. Heal. Policy, vol. 7, no. 3, pp. 187-210, 2015, |
| [24] | M. A. Uebersax et al., ‘Dry beans (Phaseolus vulgaris L.) as a vital component of sustainable agriculture and food security—A review’, Legum. Sci., vol. 5, no. 1, p. e155, 2023, |
| [25] | S. S. Snapp, C. M. Cox, and B. G. Peter, ‘Multipurpose legumes for smallholders in sub-Saharan Africa: Identification of promising 'scale out’ options’, Glob. Food Sec., vol. 23, no. February, pp. 22-32, 2019, |
| [26] | A. Mookerjee and T. Tanaka, ‘Influence of enzymatic treatments on legume proteins for improved functional and nutritional properties: expansion of legume protein utilization as food ingredients’, Curr. Opin. Food Sci., vol. 49, p. 100974, 2023, |
| [27] | S. Debebe, ‘Post ‑ harvest losses of crops and its determinants in Ethiopia : tobit model analysis’, Agric. Food Secur., vol. 11, no. 13, pp. 1-8, 2022, |
| [28] | E. Ellis, E. M. Kwo, and M. Ngadi, ‘Economic and nutritional implications of losses and contributing factors along the bean value chain’, J. Stored Prod. Res., vol. 87, pp. 1-13, 2020, |
| [29] | FAOSTAT, ‘Value of food imports in total merchandise exports (percent) (3-year average)’, Food and Agriculture Organization of the United Nations, 2023. Value of food imports in total merchandise exports percent 3-year average (accessed Jul. 31, 2023). |
| [30] | A. R. M. Al-Tawaha et al., ‘Legume Production and Climate Change’, in Improvement of Plant Production in the Era of Climate Change, CRC Press, 2022, pp. 221-248. |
| [31] | E. B. Nchanji and C. K. Lutomia, ‘Regional impact of COVID-19 on the production and food security of common bean smallholder farmers in Sub-Saharan Africa: Implication for SDG’s’, Glob. Food Sec., vol. 29, no. January, p. 100524, 2021, |
| [32] | K. C. Kaizzi et al., ‘Bean yield and economic response to fertilizer in eastern and southern Africa’, Nutr. Cycl. Agroecosystems, vol. 111, no. 1, pp. 47-60, 2018, |
| [33] | D. S. MacCarthy, J. Kihara, P. Masikati, and S. G. K. Adiku, ‘Decision support tools for site-specific fertilizer recommendations and agricultural planning in selected countries in sub-Sahara Africa’, Nutr. Cycl. Agroecosystems, vol. 110, no. 3, pp. 343-359, 2018, |
| [34] | A. Reuzé et al., ‘Stages of Change toward Meat Reduction: Associations with Motives and Longitudinal Dietary Data on Animal-Based and Plant-Based Food Intakes in French Adults’, Nutr. Epidemiol., vol. 153, no. 11, pp. 3295-3307, 2023, |
| [35] | R. F. Nanelo and A. E. José, ‘Modelos de produção agroecológica familiar: o caso dos distritos de Metuge e Gondola, Moçambique’, Rev. Verde Agroecol. e Desenvolv. Sustentável, vol. 17, no. 2, pp. 118-126, 2022, |
| [36] | T. F. Khumalo, Social issues related to climate change and food production (crops). Elsevier Inc., 2021. |
| [37] | G. Munkombwe, C. Nthewa, and J. A. Mutaliano, ‘Strengthening seed delivery system for enhanced adoption of improved sorghum varieties among smallholder farmers in Malawi, Mozambique and Zambia’, in IOP Conference Series: Earth and Environmental Science, 2020, vol. 482, no. 012008, pp. 1-6, |
| [38] |
MADER, ‘Inquérito Integrado Agrário’, 2020. [Online]. Available:
https://www.agricultura.gov.mz/wp-content/uploads/2021/06/MADER_Inquerito_Agrario_2020.pdf |
| [39] |
E. Maereka et al., ‘Estimation and Characterization of Bean Seed Demand in Angonia District of Mozambique’, 2015. [Online]. Available:
https://cgspace.cgiar.org/server/api/core/bitstreams/1295ee00-901f-4eeb-8c46-2921997fcaff/content |
| [40] | M. Farid, ‘Symbiotic Nitrogen Fixation in Common Bean’, University of Guelph, 2015. |
| [41] | I. Karavidas et al., ‘Agronomic Practices to Increase the Yield and Quality of Common Bean (Phaseolus vulgaris L.): A Systematic Review’, Agronomy, vol. 12, no. 2, pp. 1-39, 2022, |
| [42] |
Diário Económico, ‘Tribunal Moçambicano Volta a Suspender Exportação de Feijão Bóer Para a Índia’, 19/12/2023, 2023.
https://www.diarioeconomico.co.mz/2023/12/19/negocios/comercio/tribunal-mocambicano-volta-a-suspender-exportacao-de-feijao-boer-para-a-india/ (accessed Apr. 04, 2024). |
| [43] | O. A. Outlook, ‘Chapter 3. Cereals’, pp. 125-141, 2019. |
| [44] | M. Y. Chidege, P. B. Venkataramana, and P. A. Ndakidemi, ‘Enhancing Food Grains Storage Systems through Insect Pest Detection and Control Measures for Maize and Beans: Ensuring Food Security Post-COVID-19 Tanzania’, Sustainability, vol. 16, no. 1767, pp. 1-22, 2024, |
| [45] | E. Santos, G. Marques, and T. Lino-Neto, Phaseolus vulgaris L. as a functional food for aging protection, 2nd ed. Elsevier Inc., 2020. |
| [46] | E. R. Abraham et al., ‘Time series prediction with artificial neural networks: An analysis using Brazilian soybean production’, Agric., vol. 10, no. 10, pp. 1-18, 2020, |
| [47] | P. Hara, M. Piekutowska, and G. Niedbała, ‘Selection of Independent Variables for Crop Yield Prediction Sensing Data’, Land, vol. 10, no. 609, pp. 1-21, 2021, |
| [48] | F. Mahaluça et al., ‘Mozambique Consumer Price Index Estimation through Time Series Models’, J. Econ. Res. Rev., vol. 2, no. 2, 2022, |
| [49] | A. S. Ahmar, P. K. Singh, R. Ruliana, and A. K. Pandey, ‘NNAR Models to Predict Food Grain in India’, Forecasting, vol. 5, no. 138-152, pp. 138-152, 2023, |
| [50] | Y. Guo et al., ‘Agricultural Price Prediction Based on Combined Forecasting Model under Spatial-Temporal Influencing Factors’, Sustain., vol. 14, no. 17, pp. 1-18, 2022, |
| [51] | F. B. Tchimeutcheu, J. Marie, and A. Ngono, ‘Keys Determinants of Food Insecurity in Sub-Saharan Africa’, J. Humanit. Soc. Sci., vol. 7, no. 3, pp. 01-10, 2024, |
| [52] | S. Devra, P. DV, S. MS, and R. SR, ‘Time series forecasting of price for oilseed crops by combining ARIMA and ANN’, Int. J. Stat. Appl. Math., vol. 8, no. 4, pp. 40-54, 2023, |
| [53] | W. T. Loo, K. Chua, P. Mazumdar, A. Cheng, and N. Osman, ‘Arbuscular Mycorrhizal Symbiosis : A Strategy for Mitigating the Impacts of Climate Change on Tropical Legume Crops’, Plants, vol. 11, no. 2875, pp. 1-33, 2022, |
| [54] | V. V. Kumari et al., ‘Drought and Heat Stress in Cool-Season Food Legumes in Sub-Tropical Regions: Consequences, Adaptation, and Mitigation Strategies’, Plants, vol. 10, no. 1038, pp. 1-21, 2021, |
| [55] | O. A. Odeku, Q. A. Ogunniyi, O. O. Ogbole, and J. Fettke, ‘Forgotten Gems : Exploring the Untapped Benefits of Underutilized Legumes in Agriculture, Nutrition, and Environmental Sustainability’, Plants, vol. 13, no. 1208, pp. 1-27, 2024, |
| [56] | G. W. Sileshi, J. C. Dagar, A. J. Nath, and E. Kuntashula, Agroforestry as a Climate-Smart Agriculture: Strategic Interventions, Current Practices and Policies. Springer, 2023. |
| [57] | O. O. Oyebanji et al., ‘Impact of climate change on the spatial distribution of endemic legume species of the Guineo-Congolian forest, Africa’, Ecol. Indic., vol. 122, pp. 1-8, 2021, |
| [58] | P. K. Jha, S. Beebe, P. Alvarez-Toro, C. Mukankusi, and J. Ramirez-Villegas, ‘Characterizing patterns of seasonal drought stress for use in common bean breeding in East Africa under present and future climates’, Agric. For. Meteorol., vol. 342, no. 10, p. 109735, 2023, |
| [59] | U. Amato, A. Antoniadis, I. De Feis, Y. Goude, and A. Lagache, ‘Forecasting high resolution electricity demand data with additive models including smooth and jagged components’, Int. J. Forecast., vol. 37, no. 1, pp. 171-185, 2021, |
| [60] | J. Lu, G. J. Carbone, X. Huang, K. Lackstrom, and P. Gao, ‘Mapping the sensitivity of agriculture to drought and estimating the effect of irrigation in the United States, 1950-2016’, Agric. For. Meteorol., vol. 292-293, no. 7, p. 108124, 2020, |
| [61] | T. Dimri, S. Ahmad, and M. Sharif, ‘Time series analysis of climate variables using seasonal ARIMA approach’, J. Earth Syst. Sci., vol. 129, no. 1, pp. 1-16, 2020, |
| [62] | H. Teichgraeber et al., ‘Extreme events in time series aggregation: A case study for optimal residential energy supply systems’, Appl. Energy, vol. 275, pp. 1-6, 2020, |
| [63] | H. Dong, X. Guo, H. Reichgelt, and R. Hu, ‘Predictive power of ARIMA models in forecasting equity returns: a sliding window method’, J. Asset Manag., vol. 21, no. 6, pp. 549-566, 2020, |
| [64] | E. B. Sinu, M. A. Kleden, and A. Atti, ‘Application of Arima Model for Forecasting National Economic Growth: a Focus on Gross Domestic Product Data’, J. Math. Its Appl., vol. 18, no. 2, pp. 1261-1272, 2024, |
| [65] | L. Komara and D. Sirodj, ‘Metode Autoregressive Integrated Moving Average (ARIMA) untuk Meramalkan Produksi Padi di Provinsi Jawa Tengah’, Bandung Conf. Ser. Stat., vol. 3, no. 2, pp. 496-504, 2023, |
| [66] | Z. Liu, Z. Zhu, J. Gao, and C. Xu, ‘Forecast Methods for Time Series Data: A Survey’, IEEE Access, vol. 9, pp. 91896-91912, 2021, |
| [67] | S. A. Alzakari, A. A. Alhussan, A. T. Qenawy, A. M. Elshewey, and M. Eed, ‘An Enhanced Long Short ‑ Term Memory Recurrent Neural Network Deep Learning Model for Potato Price Prediction’, Potato Res., pp. 1-19, 2024, |
| [68] | T. Tang, D. Jiao, T. Chen, G. Gui, and S. Member, ‘Medium- and Long-Term Precipitation Forecasting Method Based on Data Augmentation and Machine Learning Algorithms’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, no. Ml, pp. 1000-1011, 2022, |
| [69] | M. Bouri, K. S. Arslan, and F. Sahin, ‘Climate-Smart Pest Management in Sustainable Agriculture: Promises and Challenges’, Sustainability, vol. 15, no. 4592, pp. 1-17, 2023, |
| [70] | S. Gvozdenac, B. Dedić, S. Mikić, J. Ovuka, and D. Miladinović, ‘Impact of Climate Change on Integrated Pest Management Strategies’, in Climate Change and Agriculture: Perspectives, Sustainability and Resilience, 2022, pp. 311-372. |
| [71] | L. Manuel, O. Chiziane, G. Mandhlate, F. Hartley, and E. Tostão, ‘Impact of climate change on the agriculture sector and household welfare in Mozambique : an analysis based on a dynamic computable general equilibrium model’, Clim. Change, vol. 167, no. 6, pp. 1-18, 2021, |
APA Style
Mahaluca, F., Carsane, F., Vilanculos, A. (2025). Modeling and Forecasting Bean Production in Mozambique: Challenges and Implications for Food Security and SDG 2. International Journal of Agricultural Economics, 10(2), 67-85. https://doi.org/10.11648/j.ijae.20251002.13
ACS Style
Mahaluca, F.; Carsane, F.; Vilanculos, A. Modeling and Forecasting Bean Production in Mozambique: Challenges and Implications for Food Security and SDG 2. Int. J. Agric. Econ. 2025, 10(2), 67-85. doi: 10.11648/j.ijae.20251002.13
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijae.20251002.13,
author = {Filipe Mahaluca and Faizal Carsane and Alfeu Vilanculos},
title = {Modeling and Forecasting Bean Production in Mozambique: Challenges and Implications for Food Security and SDG 2
},
journal = {International Journal of Agricultural Economics},
volume = {10},
number = {2},
pages = {67-85},
doi = {10.11648/j.ijae.20251002.13},
url = {https://doi.org/10.11648/j.ijae.20251002.13},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijae.20251002.13},
abstract = {This study examines the effectiveness of ARIMA and LSTM models in forecasting bean production in Mozambique, using data from 2002 to 2022. The analysis reveals that the limited sample size, comprising only 21 years of data, significantly impacts the accuracy of both models, as reflected in high MAPE values. The ARIMA(1,1,1) model demonstrates robustness with the lowest RMSE among the ARIMA models, but the LSTM model, despite its challenges, shows superior capability in capturing nonlinear patterns, resulting in a lower average MAPE. Forecasts for the period from 2023 to 2030 suggest stable bean production with slight annual variations, although the wide confidence intervals highlight the inherent uncertainty in these predictions. This study underscores the importance of improving forecasting models to better guide agricultural planning and policy-making, particularly in the context of Mozambique's food insecurity challenges and the global objectives of SDG 2. The results emphasize the need for more extensive data collection and the inclusion of additional variables to enhance the accuracy of future forecasts, contributing to the reduction of food insecurity and the achievement of sustainable development goals in Mozambique.
},
year = {2025}
}
TY - JOUR T1 - Modeling and Forecasting Bean Production in Mozambique: Challenges and Implications for Food Security and SDG 2 AU - Filipe Mahaluca AU - Faizal Carsane AU - Alfeu Vilanculos Y1 - 2025/04/29 PY - 2025 N1 - https://doi.org/10.11648/j.ijae.20251002.13 DO - 10.11648/j.ijae.20251002.13 T2 - International Journal of Agricultural Economics JF - International Journal of Agricultural Economics JO - International Journal of Agricultural Economics SP - 67 EP - 85 PB - Science Publishing Group SN - 2575-3843 UR - https://doi.org/10.11648/j.ijae.20251002.13 AB - This study examines the effectiveness of ARIMA and LSTM models in forecasting bean production in Mozambique, using data from 2002 to 2022. The analysis reveals that the limited sample size, comprising only 21 years of data, significantly impacts the accuracy of both models, as reflected in high MAPE values. The ARIMA(1,1,1) model demonstrates robustness with the lowest RMSE among the ARIMA models, but the LSTM model, despite its challenges, shows superior capability in capturing nonlinear patterns, resulting in a lower average MAPE. Forecasts for the period from 2023 to 2030 suggest stable bean production with slight annual variations, although the wide confidence intervals highlight the inherent uncertainty in these predictions. This study underscores the importance of improving forecasting models to better guide agricultural planning and policy-making, particularly in the context of Mozambique's food insecurity challenges and the global objectives of SDG 2. The results emphasize the need for more extensive data collection and the inclusion of additional variables to enhance the accuracy of future forecasts, contributing to the reduction of food insecurity and the achievement of sustainable development goals in Mozambique. VL - 10 IS - 2 ER -
Higher Institute of Accounting and Auditing of Mozambique (ISCAM), Maputo, Mozambique; Department of Economics, University Saint Thomas of Mozambique (USTM), Maputo, Mozambique
Department of Economics, University Saint Thomas of Mozambique (USTM), Maputo, Mozambique
Higher Institute of Accounting and Auditing of Mozambique (ISCAM), Maputo, Mozambique; Faculty of Economics, Eduardo Mondlane University (UEM), Maputo, Mozambique
