Random Forest Analysis of Exogenous Variables Impacting Rice Production in the Philippines
1Vicente E. Montano, 2Maria Teresa S. Bulao
1,2Faculty of Business Administration Education, University of Mindanao, Davao City, Philippines
https://doi.org/10.47191/jefms/v7-i1-13ABSTRACT:
This research examines the relationship of rice production as the endogenous variable in a production function theory that considers key exogenous factors such as fertilizer consumption, irrigation water use, agricultural machinery, poverty rate, and agricultural land area. The study reveals the interdependencies shaping rice production in the Philippines. Applying the Cobb- Douglas function enhanced through the random forest regression algorithm establishes fertilizer consumption's focal role, focusing its essential impact on rice yields. Proper allocation of irrigation, access to agriculture machinery, poverty alleviation, and effective land use appear as significant contributors to overall production, defining 98% of the variability in rice production in random forests in both the in-sample and out-of-sample results. The findings emphasize the necessity for holistic strategies in agricultural planning, aiming for targeted interventions in fertilizer management, irrigation infrastructure, mechanized farming, poverty alleviation, and land-use.
KEYWORDS:
Production function theory, Rice production, Cobb-Douglas Model, Random Forest, Philippines
REFERENCES:
1) Alam, M. K., Bell, R. W., Hasanuzzaman, M., Salahin, N., Rashid, M. H., Akter, N., ... & Khatun, M. F. (2020). Rice (Oryza sativa L.) establishment techniques and their implications for soil properties, global warming potential mitigation and crop yields. Agronomy, 10(6), 888.
2) Bairagi, S., Zereyesus, Y., Baruah, S., & Mohanty, S. (2022). Structural shifts in food basket composition of rural and urban Philippines: Implications for the food supply system. Plos one, 17(3), e0264079.
3) Balié, J., Minot, N., & Valera, H. G. A. (2021). Distributional impacts of the rice tariffication policy in the Philippines. Economic Analysis and Policy, 69, 289-306.
4) Bravo-Ureta, B. E., Higgins, D., & Arslan, A. (2020). Irrigation infrastructure and farm productivity in the Philippines: A stochastic Meta-Frontier analysis. World development, 135, 105073.
5) Buresh, R. J., Castillo, R. L., Torre, J. C. D., Laureles, E. V., Samson, M. I., Sinohin, P. J., & Guerra, M. (2019). Site-specific nutrient management for rice in the Philippines: Calculation of field-specific fertilizer requirements by Rice Crop Manager. Field Crops Research, 239, 56-70.
6) Chau, Nguyen Thi, and Tofael Ahamed. (2022). Analyzing Factors That Affect Rice Production Efficiency and Organic Fertilizer Choices in Vietnam. Sustainability 14, no. 14: 8842. https://doi.org/10.3390/su14148842
7) Chen, Z., Li, X., Liu, T., Fu, H., Yuan, X., Cheng, Q., ... & Li, X. (2023). Strategies for fertilizer management to achieve higher yields and environmental and fertilizer benefits of rice production in China. Science of The Total Environment, 904, 166325.
8) Coulston, J. W., Blinn, C. E., Thomas, V. A., & Wynne, R. H. (2016). Approximating prediction uncertainty for random forest regression models. Photogrammetric Engineering & Remote Sensing, 82(3), 189-197.
9) Cuevas, A. C. (2019). The Effect of NFA Buffer Stocks on the Retail Price of Rice in the Philippines. Journal of Economics, Management & Agricultural Development, 5(1), 55-76.
10) Dait, J. M. G. (2023). A Panel Data Study on Factors Affecting Rice Production in the Philippines.
11) Dikitanan, R., Grosjean, G., Nowak, A. C., & Leyte, J. (2017). Climate-resilient agriculture in Philippines. CSA Country Profiles for Asia.
12) Does rice tariffication in the Philippines worsen income poverty and inequality. (2021, February 19).
13) PIDS - Philippine Institute for Development Studies. https://pids.gov.ph/publication/policy-notes/does-rice-tariffication-in-the-philippines-worsen-income-poverty-and-inequality.
14) Donkor, E., Matthews, N., & Ogundeji, A. A. (2018). Efficiency of rice farming in Ghana: policy implications for rice sector development. African Development Review, 30(2), 149-161.
15) Felipe, J., & McCombie, J. (2011). On Herbert Simon's criticisms of the Cobb—Douglas and the CES production functions. Journal of Post Keynesian Economics, 275-293.
https://psa.gov.ph/system/files/phdsd/Press%20Release_5%20%281%29.pdf
17) Gao, J., Zeng, W., Ren, Z., Ao, C., Lei, G., Gaiser, T., & Srivastava, A. K. (2023). A Fertilization Decision Model for Maize, Rice, and Soybean Based on Machine Learning and Swarm Intelligent Search Algorithms. Agronomy, 13(5), 1400.
18) Global Yield Atlas (n.d.). Philippines. https://www.yieldgap.org/philippines
19) Hediger, S., Michel, L., & Näf, J. (2022). On the use of random forest for two-sample testing. Computational Statistics & Data Analysis, 170, 107435.
20) Inthavong, H. (2006). Factors influencing rice production efficiency in Ban Home, Laos.
21) Jaiswal, J. K., & Samikannu, R. (2017, February). Application of random forest algorithm on feature subset selection and classification and regression. In 2017 world congress on computing and communication technologies (WCCCT) (pp. 6568). Ieee.
22) Jiménez, M. I., Abbott, P., & Foster, K. (2018). Measurement and analysis of agricultural productivity in Colombia. Ecos de Economía, 22(47), 4-37.
23) Kajisa, K., Moya, P., & Gascon, F. (2022). The Central Luzon Loop Survey: Rice Farming in the Philippines from 1966 to 2021. Agricultural Development in Asia and Africa: Essays in Honor of Keijiro Otsuka, 33-47.
24) Koirala, K. H., Mishra, A., & Mohanty, S. (2016). Impact of land ownership on productivity and efficiency of rice farmers: The case of the Philippines. Land use policy, 50, 371-378.
25) Kürschner, E., Baumert, D., Plastrotmann, C., Poppe, A. K., Riesinger, K., & Ziesemer, S. (2016). Improving market access for smallholder rice producers in the Philippines. Albrecht Daniel Thaer-Institut für Agrar-und Gartenbauwissenschaften.
26) Lagare, J. (2023, June 19). PH rice farm mechanization remains slow. Inquirer.Net. https://business.inquirer.net/406205/ph-rice-farm-mechanization-remains-slow
27) Launio, C. C., & Abyado, M. O. (2022). Farmer-led Small-scale Irrigation Systems Management in Highland Vegetable Farming in the Cordillera Region, Philippines. Journal of Economics, Management & Agricultural Development, 8(1), 1-22.
28) Li, L., Wang, Y., Nie, L., Ashraf, U., Wang, Z., Zhang, Z., ... & Pan, S. (2022). Deep placement of nitrogen fertilizer increases rice yield and energy production efficiency under different mechanical rice production systems. Field Crops Research, 276, 108359.
29) Liu, Q., Gan, M., & Jiang, R. (2017). A sequence-based method to predict the impact of regulatory variants using random forest. BMC Systems Biology, 11(2), 1-9.
30) Liu, Q., Wu, T. Y., Pu, L., & Sun, J. (2022). Comparison of fertilizer use efficiency in grain production between developing countries and developed countries. Journal of the Science of Food and Agriculture, 102(6), 2404-2412.
31) Mapa, C. (2022, August 15). Proportion of Poor Filipinos was Recorded at 18.1 Percent in 2021. Home Poverty Statistics. Philippines Statistics Authority. https://psa.gov.ph/statistics/poverty/node/167972.
32) Mariano, M. J., Villano, R., & Fleming, E. (2010). Are irrigated farming ecosystems more productive than rainfed farming systems in rice production in the Philippines?. Agriculture, ecosystems & environment, 139(4), 603-610.
33) Mariyono, J. (2020). Policy And Productivity Analyses Of Indonesian Rice Agriculture. Deepublish.
34) Murthy, K. V. (2002). Arguing a case for Cobb-Douglas production function. Review of Commerce Studies, 20, 21.
35) Naher, U. A., Shah, A. L., Sarkar, M. I. U., Islam, S. M., Ahmed, M. N., Panhwa, Q. A., & Othman, R. (2015). Fertilizer consumption scenario and rice production in Bangladesh. Advances in tropical soil science, 3, 81-98.
36) Palash, M. S., Rahman, M. W., Amin, M. R., Mainuddin, M., & Jalilov, S. M. (2019). Water stress effect on the factors of production of irrigated rice in Northwest regions of Bangladesh. The Bangladesh Journal of Agricultural Economics, 40(1&2), 43-56.
37) Primartha, R., & Tama, B. A. (2017, November). Anomaly detection using random forest: A performance revisited. In 2017 International conference on data and software engineering (ICoDSE) (pp. 1-6). IEEE.
38) Probst, P., Wright, M. N., & Boulesteix, A. L. (2019). Hyperparameters and tuning strategies for random forest. Wiley Interdisciplinary Reviews: data mining and knowledge discovery, 9(3), e1301.
39) Qin, J. (2021, January). Econometrics Research on Factors Affecting the Output Value of China's Agricultural Output Level: Empirical Analysis Based on the Cobb-Douglas Production Function Model. In Proceedings of the 2021 12th International Conference on E-Education, E-Business, E-Management, and E-Learning (pp. 287-295).
40) Rejesus, R. M., Palis, F. G., Rodriguez, D. G. P., Lampayan, R. M., & Bouman, B. A. (2011). Impact of the alternate wetting and drying (AWD) water-saving irrigation technique: Evidence from rice producers in the Philippines. Food Policy, 36(2), 280-288.
41) (The) Rice data analytics dashboard. Philippine Rice Research Institute (PhilRice). https://www.philrice.gov.ph/ricelytics/
42) Rodriguez, D. J. F., & Piadozo, E. S. (2016). Characterization of farm mechanization among lowland rice farmers in Laguna, Philippines. Journal of Economics, Management & Agricultural Development, 2(2), 97-108.
43) Rois, R., Ray, M., Rahman, A., & Roy, S. K. (2021). Prevalence and predicting factors of perceived stress among Bangladeshi university students using machine learning algorithms. Journal of Health, Population and Nutrition, 40, 1-12.
44) Saepudin, T., & Amalia, A. (2022). Analysis of Rice Production Approach to Cobb Douglas Production Function in Tambakdahan Sub-District Subang District. Agricultural Socio-Economics Journal, 22(2), 121-127.
45) Sebastian, L. S., Alviola, P. A., & Francisco, S. R. (2000). Bridging the rice yield gap in the Philippines. Bridging the rice yield gap in the Asia-Pacific region, 13.
46) Selva, E. (2023, August 1). Rise meeting towards rice self-sufficiency. Department of Agriculture, National Irrigation Administration. EDSA, Diliman, Quezon City. https://www.nia.gov.ph/content/rise-meeting-towards-rice-self-sufficiency
47) Silva, J. V., Reidsma, P., Velasco, M. L., Laborte, A. G., & van Ittersum, M. K. (2018). Intensification of rice-based farming systems in Central Luzon, Philippines: Constraints at field, farm and regional levels. Agricultural systems, 165, 55-70.
48) Stuecker, M. F., Tigchelaar, M., & Kantar, M. B. (2018). Climate variability impacts on rice production in the Philippines. PloS one, 13(8), e0201426.
49) Tan, K., Ma, W., Wu, F., & Du, Q. (2019). Random forest–based estimation of heavy metal concentration in agricultural soils with hyperspectral sensor data. Environmental monitoring and assessment, 191, 1-14.
50) Teves, C. (2018, June 2). Agri czar pushes for solar irrigation to boost rice production. Philippines News Agency. https://www.pna.gov.ph/articles/1037267
51) Tina, D., Ouaret, R., & Pascal, F. (2022, November). Interpretability in machine learning predictions: case of Random Forest regression using Partial Dependence Plots. In 18ème congrès de la Société Française de Génie des Procédés.
52) Tolentino, V. B. J., & de la Peña, B. M. (2022). 7 The Political Economy of Rice Policy in the Philippines. Pro-poor Development Policies: Lessons from the Philippines and East Asia, 157.
53) Turmel, M. S., Turner, B. L., & Whalen, J. K. (2011). Soil fertility and the yield response to the System of Rice Intensification. Renewable Agriculture and Food Systems, 26(3), 185-192.
54) Yousaf, M., Li, J., Lu, J., Ren, T., Cong, R., Fahad, S., & Li, X. (2017). Effects of fertilization on crop production and nutrient-supplying capacity under rice-oilseed rape rotation system. Scientific reports, 7(1), 1270.
55) Yuan, Z. (2011). Analysis of agricultural input-output based on Cobb–Douglas production function in Hebei Province, North China. African Journal of Microbiology Research, 5(32), 5916-5922.
56) Zeytoon-Nejad, A., Goodwin, B. K., & Ghosh, S. (2023). Generalizing the General: Generalizing the CES production function to allow for the viability
