Modeling of peach production energy using machine learning in Nazarabad township, Alborz province

Document Type : Research Paper

Authors

Department of Mechanical Engineering of Agricultural Machinery, Faculty of Agricultural Engineering and Technology, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

Abstract

Today, providing food security for the world's growing population by preserving the earth's resources & minimal environmental effects has become one of the basic & important challenges in sustainable agriculture, & the optimal use of resources is one of the main requirements of sustainable agriculture. In this study, the pattern of energy consumption during peach production, analysis & modeling of energy & performance of peach production in Nazarabad city was investigated. Data were collected through interviews & filling specialized questionnaires. The results showed that the total energy consumption & production were equal to 72716.83 & 5234.89 megajoules per hectare, respectively. Electricity was the most consumed input with a share of 59% of the total input energy. The indices of energy efficiency, energy efficiency, energy intensity and net energy were obtained as 0.07, (kg/MJ) 0.03, (MJ/Kg) 26.39 and (MJ) -67481 respectively. Modeling was done with three methods: enhanced gradient regression, decision tree regression, and random forest regression, and RRMSE was -0.003, -0.0090, and -0.0091, and R2 was 0.98, 0.95, and 90, respectively was calculated. The results showed that the enhanced gradient method is able to accurately predict the values of the energy efficiency indices of peach production. The results showed that the energy efficiency and production can be predicted with high accuracy through the inputs of irrigation water, electricity, chemical and animal fertilizers, labor force, chemical poisons, diesel fuel and machines and machine learning method. Sensitivity analysis was performed with SHAP and the results showed that the most influential input in energy prediction was nitrogen fertilizer.

Keywords

Main Subjects


Modeling of peach production energy using machine learning in Nazarabad township, Alborz province

 

EXTENDED ABSTRACT

 

Background:

it is predicted that by 2050, the world's population will reach 9.2 million people, and Iran will be one of the 20 most populous countries in the world this year. Also, according to the report of the Food and Agriculture Organization of the United Nations (FAO), in order to provide food for the people of the world in 2050, the production of products must increase by 70% during this time. Agriculture is also the most important food producer, not only energy consumer, but also the most important energy supplier. Securing the food security of the world's growing population with conservation of earth's resourcesand environmental is one of the basic and important challenges of sustainable agriculture Therefore, It has gone towards the use of artificial intelligence and machine technologies to produce healthier and more products with the least use of resources

Research Method:

In this research, modeling the energy and performance of peach production in Nazarabad city was done using machine learning And the pattern of energy consumption in peach production was investigated. Data were collected through interviews and specialized questionnaires, and simple random sampling was used to determine the sample size. Cochran's formula was used to determine the sample size, and three algorithms of Gradient boostingregression (GBR), decision tree (DTR) and random forest (RFR) were used for prediction and modeling.

Findings:

The results showed that the total consumed and produced energy is equal to 72716.83 and 5234.89 megajoules respectively on the hectares and renewable energyis 8.6%, Non-renewable energy is 91.39%, indirect energy is 86.21% and direct energy is 13 percent. of the total energy consumption, Electricity was the most consumed input with a share of 59% of the total input energy. The indices of energy efficiency, energy efficiency, energy intensity and net energy were obtained as 0.07, (kg/MJ) 0.03, (MJ/kg) 26.39 and (MJ) 67481 respectively. Modeling was done with three methods: Gradient boostingRegression (GBR), Decision Tree Algorithm (DTR) and Random Forest Algorithm (RFR) and RRMSE was -0.003, -0.0090 and -0.0091 and R2 was 0.98, 0.95 and 0.90 respectively. The calculation of the results showed that the GBR method can predict energy consumption of peaches with higher accuracy than the energy indices and for RRMSE performance 0.04, 0.039 and 0.033 respectively and R 0.67, 0.47 respectively and 0.74 was calculated. The results showed that the RFR method is able to predict Peach production more accurately.

Conclusions:

The results showed that the amounts of energy consumption and production of peaches can be more accurately predicted with the inputs of irrigation water, electricity, chemical and animal fertilizers, labor, chemical poisons, diesel fuel and machinery and machine learning methods. Sensitivity analysis was done with SHAP analysis and the results showed that nitrogen fertilizer and machinery are two important features of input parameters for energy prediction and the most effective fertilizers in peach production are phosphate, nitrogen and potassium respectively and insecticides have the least effect on yield.

 

 

 

 

Aghighi, H., Azadbakht, M., Ashourloo, D., Shahrabi, H. S., & Radiom, S. (2018). Machine learning regression techniques for the silage maize yield prediction using time-series images of Landsat 8 OLI. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(12), 4563-4577.‏
Amirahmadi, E., Moudrý, J., Konvalina, P., Hörtenhuber, S. J., Ghorbani, M., Neugschwandtner, R. W. & Kopecký, M. (2022). Environmental Life Cycle Assessment in Organic and Conventional Rice Farming Systems: Using a Cradle to Farm Gate Approach. Sustainability14(23), 15870.‏
Amiri, Suleiman, Sharifi, Goljanian, Motsharai, &  Zainab Al-Sadat. (2017). Investigating the pathogenicity of the fungus Metarhizium anisopliae on the green peach tree Myzus persicae. Applied research in herbal medicine, 6(1), 77-86.(In Persian)
Department of Jihad-e-Agriculture ofIran   .(2022). Annual agricultural statistics. (in persian) ,  From http://www.maj.ir/.  
Statistical Center of Iran. (2022). Provincial geographic and weather data, (in persian) ,  From http://www.amar.org.ir.
Asgharipour M.R., Mousavinik S.M., Enayat F.F. (2016) Evaluation of energy input & greenhouse gases emissions from alfalfa production in the Sistan region, Iran. EnergyReports 2:135-140.
Canakci, M., Topakci, M., Akinci, I. & Ozmerzi, A. (2005). Energy use pattern of some field crops & vegetable production: Case study for Antalya Region, Turkey. Energy Conversion & Management, 46(4), 655-666.
Dewi, C., & Chen, R. C. (2020). Decision making based on IoT data collection for precision agriculture. Intelligent Information & Database Systems: Recent Developments 11, 31-42.‏
Elhami, B., Raini, M. G. N., Taki, M., Marzban, A., & Heidarisoltanabadi, M. (2021). Analysis & comparison of energy-economic-environmental cycle in two cultivation methods (seeding & transplanting) for onion production (case study: central parts of Iran). Renewable Energy, 178, 875-890.‏
Erdal, G., Esengün, K., Erdal, H. & Gündüz, O. (2007). Energy use & economical analysis of sugar beet production in Tokat province of Turkey. Energy, 32(1), 35-41.
Ghaderpour O. & Rafiee SH. (2016). Analysis, modeling of energy & yield of dryl& chickpea in the Bukan township. Iran Biosystem Engeering(In Persian).
Ghasemi Varnamkhasadi, Mehdi, Hashemi Garam Dareh, Seyed Mahmoud, and Hashemi Garam Dareh, Seyed Ali. (2014). Investigating energy indicators and optimizing its use in peach production, a case study: Saman region in Chaharmahal and Bakhtiari province. Agricultural Machinery, 5(1), 206-216. SID https://sid.ir/paper/201455/fa (In Persian).
Ghatrehsamani, S., Ebrahimi, R., Kazi, S. N., Badry, A. B., & Sadeghinezhad, E. (2016). Optimization model of peach production relevant to input energies–Yield function in Chaharmahal va Bakhtiari Province, Iran. Energy, 99, 315-321.‏
Goldstein, A., Fink, L., Meitin, A., Bohadana, S., Lutenberg, O., & Ravid, G. (2018). Applying machine learning on sensor data for irrigation recommendations: revealing the agronomist’s tacit knowledge. Precision agriculture, 19, 421-444.‏
Haji Faraji, Mahdekht and Aghajani, Abdolreza, 2017, An introduction to the recognition of peach fruit, the third national conference of knowledge and technology of agricultural sciences, natural resources and environment of Iran, Tehran.
Hemalatha, N., Brendon, V. F., Shihab, M. M., & Rajesh, M. K. (2015). Machine Learning Algorithm for Predicting Ethylene Responsive Transcription Factor in Rice Using an Ensemble Classifier. Procedia Computer Science, 49, 128-135.‏
Kaab, A., Sharifi, M., Mobli, H., Nabavi-Pelesaraei, A., & Chau, K. W. (2019). Combined life cycle assessment & artificial intelligence for prediction of output energy & environmental impacts of sugarcane production. Science of the Total Environment, 664, 1005-1019.‏
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers & electronics in agriculture, 147, 70-90.‏
Kaul, M., Hill, R. L., & Walthall, C. (2005). Artificial neural networks for corn & soybean yield prediction. Agricultural Systems, 85(1), 1-18
Khanali, M., Akram, A., Behzadi, J., Mostashari-Rad, F., Saber, Z., Chau, K. W., & Nabavi-Pelesaraei, A. (2021). Multi-objective optimization of energy use & environmental emissions for walnut production using imperialist competitive algorithm. Applied Energy, 284, 116342.‏
Khoobbakht, G., & Akram, A. (2020). Investigating the Pattern of Energy Consumption, Sensitivity Analysis and Economic Performance of Plum Production in Khansar Township, Isfahan, Iran. Iranian Journal of Biosystems Engineering, 51(2), 263-272.‏
Khoshnevisan, B., Rafiee, S., Omid, M., & Mousazadeh, H. (2013). Reduction of CO2 emission by improving energy use efficiency of greenhouse cucumber production using DEA approach. Energy, 55, 676-682.‏
Mohammadi, A. & Omid, M. (2010). Economical analysis & relation between energy inputs & yield of greenhouse cucumber production in Iran. Applied Energy, 87(1), 191-196.
Mohammadzadeh, A., Damghani, A.M., Vafabakhsh, J., & Deihimfard, R. 2017. Assessing energy efficiencies, economy, & global warming potential (GWP) effects of major crop production systems in Iran: a case study in East Azerbaijan province. Environmental Science & Pollution Research 24: 16971-16
Morellos, A., Pantazi, X. E., Moshou, D., Alex&ridis, T., Whetton, R., Tziotzios, G., ... & Mouazen, A. M. (2016). Machine learning based prediction of soil total nitrogen, organic carbon & moisture content by using VIS-NIR spectroscopy. Biosystems Engineering, 152, 104-116.‏
Mostafaeipour, A., Fakhrzad, M. B., Gharaat, S., Jahangiri, M., Dhanraj, J. A., B&, S.& Mosavi, A. (2020). Machine learning for prediction of energy in wheat production. Agriculture, 10(11), 517
Nabavi-Pelesaraei, A., Abdi, R., Rafiee, S., & Mobtaker, H. G. (2014). Optimization of energy required & greenhouse gas emissions analysis for orange producers using data envelopment analysis approach. Journal of Cleaner Production, 65, 311-317.‏
Najafabadi, M. M., Sabouni, M., Azadi, H., & Taki, M. (2022). Rice production energy efficiency evaluation in north of Iran; application of Robust Data Envelopment Analysis. Cleaner Engineering and Technology, 6, 100356.‏
Nikkhah, A., Royan, M., Khojastehpour, M., & Bacenetti, J. (2017). Environmental impacts modeling of Iranian peach production. Renewable & Sustainable Energy Reviews, 75, 677-682.‏
Nie, P., Roccotelli, M., Fanti, M. P., Ming, Z., & Li, Z. (2021). Prediction of home energy consumption based on gradient boosting regression tree. Energy Reports, 7, 1246-1255.‏
Pahlavan, R., Omid, M. & Akram, A. (2012). Energy input–output analysis & application of artificial neural networks for predicting greenhouse basil production. Energy, 37(1), 171-176.
Papageorgiou, E. I., Aggelopoulou, K. D., Gemtos, T. A., & Nanos, G. D. (2013). Yield prediction in apples using Fuzzy Cognitive Map learning approach. Computers & electronics in agriculture, 91, 19-29.‏
Pourhasan, Shah Hosseini, Sidi. (2021). Presenting a classification method based on deep learning in differentiating types of agricultural products using time series satellite images. Scientific Journal of Mapping Sciences & Techniques, 11(1), 129-142. (In Persian)
Rafiee, S., Avval, S. H. M., & Mohammadi, A. (2010). Modeling & sensitivity analysis of energy inputs for apple production in Iran. Energy, 35(8), 3301-3306.‏
Rezapour, S., Jooy&eh, E., Ramezanzade, M., Mostafaeipour, A., Jahangiri, M., Issakhov, A., ... & Techato, K. (2021). Forecasting rainfed agricultural production in arid & semi-arid l&s using learning machine methods: A case study. Sustainability, 13(9), 4607.‏
Royan, M., Khojastehpour, M., Emadi, B., & Mobtaker, H. G. (2012). Investigation of energy inputs for peach production using sensitivity analysis in Iran. Energy Conversion & Management, 64, 441-446.
‏ Sadr, S., & Eslami, M. (2021). Determination of effective weather variables on pistachio yield using C&R decision tree algorithm. Journal of Agricultural Meteorology, 9(1), 53-62.‏
Singh, S., & Mittal, J. P. (1992). Energy in production agriculture. Mittal Publications.‏
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020,). Fooling lime & shap: Adversarial attacks on post hoc explanation methods. In Proceedings of the AAAI/ACM Conference on AI, Ethics, & Society (pp. 180-186).‏
Su, Y. X., Xu, H., & Yan, L. J. (2017). Support vector machine-based open crop model (SBOCM): Case of rice production in China. Saudi journal of biological sciences, 24(3), 537-547.‏
Sun, S., Bao, Y., Lu, M., Liu, W., Xie, X., Wang, C., & Liu, W. (2016). A comparison of models for the short-term prediction of rice stripe virus disease & its association with biological & meteorological factors. Acta Ecologica Sinica, 36(3), 166-171.‏
Shahbeik, H., Rafiee, S., Shafizadeh, A., Jeddi, D., Jafary, T., Lam, S. S., ... & Aghbashlo, M. (2022). Characterizing sludge pyrolysis by machine learning: towards sustainable bioenergy production from wastes. Renewable Energy, 199, 1078-1092.‏
Tabatabaie, S.M.H., Rafiee, S. & Keyhani, A. (2012). Energy consumption flow & econometric models of two plum cultivars productions in Tehran province of Iran. Energy, 44(1), 211-216.
Vafabakhsh, J., & Mohammadzadeh, A. (2019). Energy flow & GHG emissions in major field & horticultural crop production systems (case study: Sharif Abad plain). Journal of Agroecology, 11(2), 365
Wei, Yixuan, Xingxing Zhang, Yong Shi, Liang Xia, Song Pan, Jinshun Wu, Mengjie Han, & Xiaoyun Zhao. 2018. “A Review of Data-Driven Approaches for Prediction & Classification of Building Energy Consumption.” Renewable & Sustainable Energy Reviews 82 (September): 1027–47
Yang, Y., Shahbeik, H., Shafizadeh, A., Masoudnia, N., Rafiee, S., Zhang, Y., ... & Aghbashlo, M. (2022). Biomass microwave pyrolysis characterization by machine learning for sustainable rural biorefineries. Renewable Energy, 201, 70-86.
Yildizhan, H., Taki, M., Özilgen, M., & Gorjian, S. (2021). Renewable energy utilization in apple production process: A thermodynamic approach. Sustainable EnergyTechnologies& Assessments, 43, 100956.
Zhang, L., Traore, S., Ge, J., Li, Y., Wang, S., Zhu, G., ... & Fipps, G. (2019). Using boosted tree regression & artificial neural networks to forecast upl& rice yield under climate change in Sahel. Computers & Electronics in Agriculture, 166, 105031.‏
Payandeh, Zahra, Khairalipour, Kamran, and Karimi, Mahmoud. (2015). Investigating the efficiency of broiler breeding units using the data envelopment analysis method, case study: Isfahan province. Biosystem Engineering of Iran (Agricultural Sciences of Iran), 47(3), 577-585(In Persian).
Molai, Komil, Kihani, Alireza, Karimi, Mahmoud, Khairalipour, Kamran, and Ghasemi Varnamkhashadi, Mehdi. (2009). Energy ratio of dry wheat - case study: Euclid city (Persia). Biosystem Engineering of Iran (Agricultural Sciences of Iran), 39(1), 13-19.
Dekamin, M., Kheiralipour, K., & Afshar, R. K. (2022). Energy, economic, and environmental assessment of coriander seed production using material flow cost accounting and life cycle assessment. Environmental Science and Pollution Research, 29(55), 83469-83482.‏
Kheiralipour, K., & Sheikhi, N. (2021). Material and energy flow in different bread baking types. Environment, development and sustainability, 23, 10512-10527.
‏Ramedani, Z., Alimohammadian, L., Kheialipour, K., Delpisheh, P., & Abbasi, Z. (2019). Comparing energy state and environmental impacts in ostrich and chicken production systems. Environmental science and pollution research, 26, 28284-28293.‏