Predicting the Gray Water Footprint and Water Use Efficiency in Farms Using ML Models (Case Study: Lorestan Province)

Document Type : Research Paper

Authors

1 MSc Student, Department of Water Engineering, Lorestan University, Khorramabad, Iran.

2 Assistant Professor, Department of Water Engineering, Lorestan University, Khorramabad, Iran.

Abstract

This study aims to (1) evaluate the Crop Water Productivity (CWP) and gray Water Footprint (WFGray) for key agricultural systems in Lorestan province, Iran, to identify hotspots of inefficiency and pollution, and (2) develop and compare Machine Learning (ML) models for predicting these metrics to aid in management and forecasting. We calculated CWP and WFGray for major crops (including forage corn, wheat, beans, potatoes and vegetables) across multiple meteorological stations in Lorestan province. Furthermore, we employed two ML algorithms including Random Forest (RF) and Support Vector Machine (SVM) to model and predict these indices. Model performance was evaluated using the Mean Absolute Error (MAE). The assessment revealed significant regional and crop-specific disparities. Forage corn was the most efficient and sustainable system (CWP: 2.173 kg/m³, WFGray: 0.05 m³/kg), whereas bean production was the least efficient (CWP: 0.064 kg/m³). Spatially, stations like Azna (potato) demonstrated best practices, while Kuhdasht was identified as a critical area of concern due to low efficiency and high fertilizer pollution. In modeling, the optimal algorithm was target-dependent: RF was superior for predicting CWP (MAE: 0.236), while SVM performed relatively better for the more complex WFGray. This study concludes that addressing water security and agricultural pollution in the region requires tailored, crop-specific interventions and improved farm management practices. Furthermore, while ML model (particularly RF) proves to be a powerful tool for forecasting water productivity, accurately modeling the environmental impact (WFGray) remains a challenge, highlighting the need for more robust data and further research in this domain.

Keywords

Main Subjects


Aligholinia, T., Rezaei, H., Behmanesh, J., & Montaseri, M. (2017). Water Footprint Index Study for dominant crops in Urmia Lake basin and its relationship with irrigation management. Water and Soil Science27(4), 37-48.
Bageri, F., Khalili, K., & Nazeri Tahrudi, M. (2023). Evaluation of Entropy Theory Based on Random Forest in Quality Monitoring of Ground Water Network. Water and Irrigation Management13(1), 123-139.
Behmanesh, J. (2016). Determination and evaluation of blue and green water footprint of dominant tillage crops in Urmia lake watershed. Journal of Water and Soil Conservation23(3), 337-344. doi: 10.22069/jwfst.2016.3203
Dehghanpir, S., Bazrafshan, O., Ramezani Etedali, H., Holisaz, A., & Ababaei, B. (2023). Application of the water footprint concept in the assessment of water scarcity and water stress in the agricultural sector in Hormozgan Province. Water and Soil Management and Modelling3(1), 233-248. doi: 10.22098/mmws.2022.11731.1163.
Ding, S., Zhu, Z., & Zhang, X. (2017). An overview on semi-supervised support vector machine. Neural Computing and Applications28(5), 969-978.
Gerkani Nezhad Moshizi, Z., Bazrafshan, O., Ramezani Etedali, H., Esmaeilpour, Y., & Collins, B. (2022). The Effect of Past Climate Change on the Water Footprint Trend in Saffron at Homogeneous Agroclimatic Regions of Khorasan. Journal of Saffron Research10(2), 295-311. doi: 10.22077/jsr.2022.5742.1199
Goodarzi, M., Abbasi, F., & Hedayatipour, A. (2023). Evaluation of Irrigation Water Application and Water Footprint of Major Agricultural and Horticultural Crops in the Markazi Province. Water and Soil37(4), 503-517. doi: 10.22067/jsw.2023.81144.1253
Hoekstra, A. Y. (2008). Water neutral: reducing and offsetting the impacts of water footprints, Value of Water Research Report Series No. 28. Delft, Netherlands: UNESCO-IHE. Recuperado em10.
Hoekstra, A. Y., & Chapagain, A. K. (2011). Globalization of water: Sharing the planet's freshwater resources. John Wiley & Sons.
Li, Z., Wang, W., Ji, X., Wu, P., & Zhuo, L. (2023). Machine learning modeling of water footprint in crop production distinguishing water supply and irrigation method scenarios. Journal of Hydrology625, 130171.
Lotfy, A. A., Abuarab, M. E., Farag, E., Derardja, B., Khadra, R., Abdelmoneim, A. A., & Mokhtar, A. (2024). Forecasting Blue and Green Water Footprint of Wheat Based on Single, Hybrid, and Stacking Ensemble Machine Learning Algorithms Under Diverse Agro-Climatic Conditions in Nile Delta, Egypt. Remote Sensing16(22), 4224.
Ma, W., Opp, C., & Yang, D. (2020). Past, present, and future of virtual water and water footprint. Water12(11), 3068.
Madani, K. (2014). Water management in Iran: what is causing the looming crisis?. Journal of environmental studies and sciences4(4), 315-328.
Mekonnen, M. M., & Hoekstra, A. Y. (2011). The green, blue and grey water footprint of crops and derived crop products. Hydrology and earth system sciences15(5), 1577-1600.
Mekonnen, M. M., & Hoekstra, A. Y. (2016). Four billion people facing severe water scarcity. Science advances2(2), e1500323.
Nazeri Tahroudi, M., Ahmadi, F., & Mirabbasi, R. (2023). Performance comparison of IHACRES, random forest and copula-based models in rainfall-runoff simulation. Applied Water Science13(6), 134.
Ostad-Ali-Askari, Kaveh., Kharazi, H. G.., Shayannejad, M.., & Zareian, M. J. (2019). Effect of management strategies on reducing negative impacts of climate change on water resources of the Isfahan–Borkhar aquifer using MODFLOW. River Research and Applications, 35, 611-631. http://doi.org/10.1002/rra.3463
Oveisi, F., Fattahi Ardakani, A., & Fehresti Sani, M. (2019). Investigation of Virtual Water and Ecological Footprints of Water in Wheat Fields of Isfahan Province. Journal of Water and Soil Science, 23(1), 87-99, http://jstnar.iut.ac.ir/article-1-3636-fa.html.
Piri, H., & Sarani, R. (2020). Investigation of Economic Productivity of Crop Products in Sistan and Baluchestan Province by Water Footprint Approach. Iranian Journal of Soil and Water Research51(5), 1093-1104. doi: 10.22059/ijswr.2020.289567.668325
Pisner, D. A., & Schnyer, D. M. (2020). Support vector machine. In Machine learning (pp. 101-121). Academic Press.
Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random forest algorithm overview. Babylonian Journal of Machine Learning2024, 69-79.
Serrano, A., Guan, D., Duarte, R., & Paavola, J. (2016). Virtual water flows in the EU27: a consumption‐based approach. Journal of Industrial Ecology20(3), 547-558.
Su, H., Kang, W., Xu, Y., & Wang, J. (2018). Assessing groundwater quality and health risks of nitrogen pollution in the Shenfu mining area of Shaanxi Province, northwest China. Exposure and health10(2), 77-97.
Vörösmarty, C. J., McIntyre, P. B., Gessner, M. O., Dudgeon, D., Prusevich, A., Green, P., ... & Davies, P. (2010). Global threats to human water security and river biodiversity. nature467(7315), 555-561.
Zwart, S. J., & Bastiaanssen, W. G. (2004). Review of measured crop water productivity values for irrigated wheat, rice, cotton and maize. Agricultural water management69(2), 115-133.