MACHINE LEARNING APPROACHES TO PREDICTIVE MODELING OF LIVESTOCK DEVELOPMENT
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
The subject of this research is the forecasting of the population dynamics of sheep and goats in Ukraine under wartime, economic, and climatic challenges that directly affect livestock farming and national food security. The present study is of particular pertinence, given the pivotal role that small ruminants play in ensuring the supply of meat, dairy products and wool. A decline in animal numbers may result in shortages of livestock products, deterioration of the socio-economic situation in rural areas, and a reduction in Ukraine's export capacity. The purpose of the paper is twofold: firstly, to develop short- and medium-term forecasting models for sheep and goat populations by combining classical statistical techniques with modern machine learning approaches; and secondly, to identify the strengths and weaknesses of these models across different forecasting horizons. The methodological framework utilised is founded upon statistical data of an official nature, as recorded by the Main Department of Statistics in the Odesa region for the period 2007–2025. Four approaches were employed: the SARIMAX statistical model; the additive Prophet model; and LSTM neural networks, which were implemented using PyTorch and Keras. Forecast performance was evaluated using the RMSE, MAE, MAPE and MASE metrics, enabling a comprehensive comparison of the models. The results confirm that the sheep and goat population in Ukraine has been in persistent decline, with sharper falls observed since the start of the full-scale war. The Keras-based LSTM model proved to be the most accurate for short-term forecasts (12 months), while the PyTorch-based LSTM model demonstrated the greatest stability for medium-term predictions (24 months). The SARIMAX and Prophet models achieved moderate accuracy but struggled to reproduce peaks and troughs in the time series. The study's scientific novelty lies in its integration of statistical and neural network forecasting approaches, while explicitly accounting for wartime disruptions and crisis-related factors. This makes the research one of the first attempts to adapt hybrid forecasting models to the Ukrainian livestock sector in wartime. The practical value lies in the ability to use the developed models at both the micro and macro levels. Individual farms can use them to optimise production and resource planning, while policymakers can use the forecasts to design effective state support programmes, strengthen food security strategies and ensure the sustainable recovery of the agricultural sector.
How to Cite
##plugins.themes.bootstrap3.article.details##
food security, time series, machine learning, forecasting, SARIMAX, PyTorch, Keras, Prophet
Abdullaieva, A., Andrusenko, N., Hromová, O., Martynova, L., Prutska, O., & Yurchyk, I. (2022). The impact of the Russian-Ukrainian war on EU food security. Economic Affairs, 67(4s), 859–867. DOI: https://doi.org/10.46852/0424-2513.4s.2022.19
Akram, M. N., Amin, M., Yasin, A., & Aslam, M. Z. (2022). Future trends of red meat production in Pakistan: time series analysis. JAPS: Journal of Animal & Plant Sciences, 32(2). DOI: https://doi.org/10.36899/JAPS.2022.2.0446
Al Khatib, AMG., Yonar, H., Abotaleb, M., Mishra, P., Yonar, A., Karakaya, K., Badr, A., Dhaka, V. (2021). Modeling and forecasting of egg production in India using time series models. Eurasian J Vet Sci., 37, 4, 265–273. DOI: https://doi.org/10.15312/EurasianJVetSci.2021.352
Aljohani, E. S., Al Duwais, A. A., & Alderiny, M. M. M. (2024). Estimating and forecasting red meat consumption and production in Saudi Arabia during 2022-2030. DOI: https://doi.org/10.5897/AJAR2024.16642
Anuththara, G. L. I., & Weerathilake, W. A. D. V. (2021). Trend Analysis and Short-Term Forecasting of Goat and Sheep Populations and their Meat Production in Sri Lanka using Single and Double Exponential Smoothing Models. Wayamba Journal of Animal Science, 13, 1898–1903. Available at: https://account.wjas.sljol.info/index.php/sljo-j-wjas/article/view/29/28
Anwar, A., Na-Lampang, K., Preyavichyapugdee, N., & Punyapornwithaya, V. (2022). Lumpy Skin Disease Outbreaks in Africa, Europe, and Asia (2005–2022): Multiple Change Point Analysis and Time Series Forecast. Viruses, 14(10), 2203. DOI: https://doi.org/10.3390/v14102203
Delaney, E., Greene, D., Shalloo, L., Lynch, M., & Keane, M. T. (2022, August). Forecasting for sustainable dairy produce: enhanced long-term, milk-supply forecasting using k-NN for data augmentation, with prefactual explanations for XAI. In International Conference on Case-Based Reasoning (pp. 365-379). Cham: Springer International Publishing. DOI: https://doi.org/10.1007/978-3-031-14923-8_24
Etxegarai, G., López, A., Aginako, N., & Rodríguez, F. (2022). An analysis of different deep learning neural networks for intra-hour solar irradiation forecasting to compute solar photovoltaic generators' energy production. Energy for Sustainable Development, 68, 1–17. DOI: https://doi.org/10.1016/j.esd.2022.02.002
Ferraz, F., Ribeiro, D., Lopes, M. B., Pedro, S., Vinga, S., & Carvalho, A. M. (2023, September). Comparative Analysis of Machine Learning Models for Time-Series Forecasting of Escherichia Coli Contamination in Portuguese Shellfish Production Areas. In International Conference on Machine Learning, Optimization, and Data Science (pp. 174-188). Cham: Springer Nature Switzerland. DOI: https://doi.org/10.1007/978-3-031-53969-5_14
Gokulakrishnan, S., Kumar, G. S., Pandian, A., Ramesh, J., Thilakar, P., Radhakrishnan, L., & Nanthini, A. R. (2024). Forecasting feed prices for small ruminants in Tamil Nadu. Indian Journal of Small Ruminants (The), 30(1), 174–181. DOI: http://dx.doi.org/10.5958/0973-9718.2024.00014.X
Hasnain, A., Sheng, Y., Hashmi, M. Z., Bhatti, U. A., Hussain, A., Hameed, M., ... & Zha, Y. (2022). Time series analysis and forecasting of air pollutants based on prophet forecasting model in Jiangsu province, China. Frontiers in Environmental Science, 10, 945628. DOI: https://doi.org/10.3389/fenvs.2022.945628
Ishchuk, S. O., & Lyakhovska, O. V. (2024). Trends in the development of the agricultural economy of Ukraine in war conditions: the regional dimension. Regional Economy, 113 (3), 96–105. DOI: https://doi.org/10.36818/1562-0905-2024-3-8
Jaiswal, P., & Bhattacharjee, M. (2022). Understanding the potential of livestock market with special reference to the export of swine meat from India: A study of time-series analysis using arima-based forecasting method. Asian Journal of Dairy and Food Research, 41(3), 293–297. DOI: http://dx.doi.org/10.18805/ajdfr.DR-1797
Jha, B. K., & Pande, S. (2021, April). Time series forecasting model for supermarket sales using FB-prophet. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 547-554). IEEE. DOI: https://doi.org/10.1109/ICCMC51019.2021.9418033
Klaharn, K., Ngampak, R., Chudam, Y., Salvador, R., Jainonthee, C., & Punyapornwithaya, V. (2024). Analyzing and forecasting poultry meat production and export volumes in Thailand: a time series approach. Cogent Food & Agriculture, 10(1). DOI: https://doi.org/10.1080/23311932.2024.2378173
Kolluru, V. K., Challagundla, Y., Chintakunta, A. N., Roy, B., Bermak, A., & SM, R. D. (2024, December). AI-Driven Energy Optimization: Household Power Consumption Prediction With LSTM Networks and PyTorch-Ray Tune in Smart IoT Systems. In 2024 International Conference on Microelectronics (ICM) (pp. 1-6). IEEE. DOI: https://doi.org/10.1109/ICM63406.2024.10815802
Liudvenko, D., Tomilova-Yaremchuk, N., Khomovyi, S., Krupa, N., & Kaminetska, O. (2024). The negative impact of military operations on the economic indicators of the livestock industry in Ukraine: accounting, analytical and audit aspect. Achievements of the Economy: Prospects and Innovations, (8). DOI: https://doi.org/10.5281/zenodo.12794991
Nehrey, M., & Finger, R. (2024). Assessing the initial impact of the Russian invasion on Ukrainian agriculture: Challenges, policy responses, and future prospects. Heliyon, 10(21). DOI: https://doi.org/10.1016/j.heliyon.2024.e39208
Novykova, I. (2024). Anti-crisis transformation of the formation of livestock product competitiveness in Ukraine. Achievements of the Economy: Prospects and Innovations, (12). DOI: https://doi.org/10.5281/zenodo.14502998
Novikova, I., Zabarna, E., Volkova, O., Fedotova, I., & Korolkov, V. (2023). Economic prospects of post-war recovery: challenges and opportunities for sustainable development in Ukraine. Financial and Credit Activity Problems of Theory and Practice, 3(50), 298–307. DOI: https://doi.org/10.55643/fcaptp.3.50.2023.4091
Omar, M. A., Hassan, F. A., Shahin, S. E., & El-Shahat, M. (2024). The usage of the autoregressive integrated moving average model for forecasting milk production in Egypt (2022–2025). Open Veterinary Journal, 14(1), 256. DOI: https://doi.org/10.5455/OVJ.2024.v14.i1.22
Pavelko, O., Lazaryshyna, I., Los, Z., Vasylieva, V., & Kvasnii, L. (2024). The activities and development prospects analysis of the agricultural sector of Ukraine. In BIO Web of Conferences (Vol. 114, p. 01031). EDP Sciences. DOI: https://doi.org/10.1051/bioconf/202411401031
Perez-Guerra UH, Macedo R, Manrique YP, Condori EA, Gonza´les HI, Ferna´ndez E, et al. (2023) Seasonal autoregressive integrated moving average (SARIMA) time-series model for milk production forecasting in pasture-based dairy cows in the Andean highlands. PLoS ONE, 18(11): e0288849. DOI: https://doi.org/10.1371/journal.pone.0288849
The State Statistics Service of Ukraine. Main Department of Statistics in Odesa Region. Available at: https://www.od.ukrstat.gov.ua/
Sharma, K., Bhalla, R., Ganesan, G. (2022). Time series forecasting using FB-Prophet. Algorithms Computing and Mathematics Conference (ACM-2022). Chennai, India, 59–65. Available at: https://ceur-ws.org/Vol-3445/PAPER_07.pdf
Shcherbak, D. (2024). Innovation factors of increasing the competitiveness of Ukrainian. City development, (1 (01), 133–139. DOI: https://doi.org/10.32782/city-development.2024.1-18
Shebanina, O., Burkovska, A., Petrenko, V., & Burkovska, A. (2023). Economic planning at agricultural enterprises: Ukrainian experience of increasing the availability of data in the context of food security. Agricultural and Resource Economics, 9(4), 168–191. DOI: https://doi.org/10.51599/are.2023.09.04.08
Tomchuk V., Kapula I. (2023) Problems of development of the agricultural sector of Ukraine’s economy on the way to European integration. Ekonomichnyy analiz, 33(3), 171–177. DOI: https://doi.org/10.35774/econa2023.03.171
Venkatesan, S., & Cho, Y. (2024). Multi-Timeframe Forecasting Using Deep Learning Models for Solar Energy Efficiency in Smart Agriculture. Energies, 17(17), 4322. DOI: https://doi.org/10.3390/en17174322
Warnasekara J, Agampodi S, Abeynayake R (2021) Time series models for prediction of leptospirosis in different climate zones in Sri Lanka. PLoS ONE 16(5): e0248032. DOI: https://doi.org/10.1371/journal.pone.0248032
Wei, Z., Wei, K., Liu, J., & Zhou, Y. (2023). The relationship between agricultural and animal husbandry economic development and carbon emissions in Henan Province, the analysis of factors affecting carbon emissions, and carbon emissions prediction. Marine Pollution Bulletin, 193, 115134. DOI: https://doi.org/10.1016/j.marpolbul.2023.115134
Wibawa, A. P., Utama, A. B. P., Elmunsyah, H., Pujianto, U., Dwiyanto, F. A., & Hernandez, L. (2022). Time-series analysis with smoothed Convolutional Neural Network. Journal of big Data, 9(1), 44. DOI: https://doi.org/10.1186/s40537-022-00599-y
Xu, W. (2022, December). Stock Price Prediction based on CNN-LSTM Model in the PyTorch Environment. In 2022 2nd International Conference on Economic Development and Business Culture (ICEDBC 2022) (pp. 1272–1276). Atlantis Press. DOI: https://doi.org/10.2991/978-94-6463-036-7_188
This work is licensed under a Creative Commons Attribution 4.0 International License.