مدل سازی ردپای آب گندم با استفاده از مدل‌های یادگیری ماشین در استان فارس

نوع مقاله : پژوهشی

نویسندگان

1 دانش ‏آموختۀ کارشناسی ارشد آبخیزداری، گروه مهندسی منابع طبیعی، دانشگاه هرمزگان، بندرعباس ایران

2 هیئت علمی گروه مهندسی منابع طبیعی، دانشیار، دانشکدۀ کشاورزی و منابع طبیعی، دانشگاه هرمزگان، بندرعباس ایران

10.22059/ije.2022.346879.1670

چکیده

این مطالعه با هدف تخمین، پیش‏بینی و مدل‏سازی ردپای آب سبز و آبی محصول زراعی گندم با استفاده از مدل‏های یادگیری ماشین در اراضی فاریاب در دورۀ آماری (1384 تا 1396) انجام شد. بر این اساس، با استفاده از داده‏های اقلیمی و گیاهی و روش فازی کلاستر، مناطق کشت گندم فاریاب در استان فارس به چهار منطقه همگن تقسیم شد. در هر منطقه براساس چارچوب اوکسترا، ردپای آب آبی، سبز و خاکستری برآورد شد. سپس، ردپای آب در هم اقلیم همگن به دو دسته آموزش (70 درصد) و آزمون (30 درصد) تقسیم شد و با استفاده از مدل شبکۀ عصبی و دو کرنل لوگ لوجستیک و تانژانت هایپربولیک (50 ترکیب ورودی)، مدل جنگل تصادفی و رگرسیون بردار پشتیبان (تابع کرنل سیگموئید) با متغیرهای اقلیمی و گیاهی، پیش‏بینی صورت گرفت و نتایج مدل‏ها با شاخص‏های ارزیابی خطا و دیاگرام تیلور مورد مقایسه قرار گرفت. نتایج نشان داد بهترین مدل برای برآورد ردپای آب گندم فاریاب در استان فارس مدل شبکۀ عصبی مصنوعی با تابع لوگ لوجستیک با ضریب همبستگی بیش از 72/0 و میانگین خطای مطلق کمتر از 48/0 (مترمکعب بر تن) است و می‏تواند به ارتقای فرایند تصمیم‏گیری به مدیران آب و برنامه‏ریزان کمک کنند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Wheat water footprint modeling using machine learning models in Fars province

نویسندگان [English]

  • Fateme Badrooj 1
  • Ommolbanin Bazrafshan 2
1 Department of Natural resources Engineering, Faculty of Agricultural Science and Natural Resources, University of Hormozgan, Bandar Abbas, Iran
2 Department of Natural resources Engineering, Faculty of Agricultural Science and Natural Resources, University of Hormozgan, Bandar Abbas, Iran
چکیده [English]

This study was conducted with the aim of estimating and modeling the green and blue water footprint of wheat crop using machine learning models in irrigated lands during (2004-2016). Therefore, using climatic and crop data and the fuzzy cluster method, the irrigated wheat cultivation areas in Fars province were divided into four homogeneous regions. Blue, green and gray water footprints were estimated in each region based on the Hoekstra framework. Then, the water footprint in the homogeneous climate was divided into two categories: training (70%) and testing (30%) and using the neural network model and two kernel such as log logistic and hyperbolic tangent (50 input combinations), random forest model and support vector regression (Sigmoid kernel function) was predicted with climatic and plant variables and the results of the models were compared with error evaluation indices and Taylor diagram. The results showed that the best model for estimating the water footprint of wheat in Fars province is the artificial neural network model with logistic log function with a correlation coefficient of more than 0.72 and an average absolute error of less than 0.48. This model can help improve the decision-making process for water managers and planners in the agricultural sector.

کلیدواژه‌ها [English]

  • Water Footprint
  • Homogeneous Regions
  • Irrigated Wheat
  • Artificial Neural Network Model
  • Log Logistic Function

مراجع

  • Oveisi F, Fattahi Ardakani A, Fehresti Sani M. Investigation of Virtual Water and Ecological Footprints of Water in Wheat Fields of Isfahan Province. JWSS, 2019; 23 (1) :87-99. [Persian]
  • Bazrafshan, O., Zamani, H., Etedali, H. R., & Dehghanpir, S. Assessment of citrus water footprint components and impact of climatic and non-climatic factors on them. Scientia Horticulturae, 2019; 250, 344-351.
  • Elbeltagi, A., Aslam, M. R., Malik, A., Mehdinejadiani, B., Srivastava, A., Bhatia, A. S., & Deng, J. The impact of climate changes on the water footprint of wheat and maize production in the Nile Delta, Egypt. Science of the Total Environment, 2020a; 743, 140770.
  • Elbeltagi, A., Deng, J., Wang, K., & Hong, Y. Crop Water footprint estimation and modeling using an artificial neural network approach in the Nile Delta, Egypt. Agricultural Water Management, 2020b; 235, 106080.
  • Moni, S., Aziz, E., Majeed, A. P. A., & Malek, M. The prediction of blue water footprint at Semambu water treatment plant by means of Artificial Neural Networks (ANN) and Support Vector Machine (SVM) models. Physics and Chemistry of the Earth, Parts A/B/C, 2021; 123, 103052.
  • Mokhtar, A., Jalali, M., He, H., Al-Ansari, N., Elbeltagi, A., Alsafadi, K.,... & Rodrigo-Comino, J. Estimation of SPEI Meteorological Drought Using Machine Learning Algorithms. IEEE Access, 2021a; 9, 65503-65523.
  • dehghan pir, S., bazrafshan, O., hlizadeh, A. Virtual Water Trade and Use in Watershed: (Case study: Baraftab-E Hajiabad and Payab- E Rudan watersheds, Hormozgan Province). Journal of Range and Watershed Management, 2017; 70(3), 647-660. [Persian]
  • Shiff, S., Lensky, I. M., & Bonfil, D. J. Using satellite data to optimize wheat yield and quality under climate change. Remote Sensing, 2021; 13(11), 2049.
  • Green, H. Wheat importance, history and adaptation. Theoretical and practical new approach in cereal science and technology, 2021; 3.
  • Tavanpour, N., & Ghaemi, A. A. Zoning of Fars Province in terms of rain-fed winter wheat cultivation based on precipitation and morphological factors. Iranian Journal of Irrigation & Drainage, 2016; 10(4), 544-555.
  • Srnivas, V., , Hariprasad, D. , Bhaskar Rao, D. V. , Anjaneyulu, Y. , Baskaran, R. , Venkatraman B. Simulation of the Indian summer monsoon regional climate using advanced research WRF model.International Journal of Climatology, 2013; 33(5), 1057-1320.
  • Bhatia, V S and Singh, P and Wani, S P and Rao, A V R K and Srinivas, K. Yield Gap Analysis of Soybean, Groundnut, Pigeonpea and Chickpea in India Using Simulation Modeling:Global Theme on Agroecosystems Report no. 31. Monograph. International Crops Research Institute for the Semi-Arid Tropics,
  • Žalik, K. R., Žalik, B. Validit index for clusters of different sizes and densitiesPattern Recognition Letters, 2011; 32(2), 221-234,ISSN 0167-8655,
  • Bezdek, J. C., Coray, C., Gunderson, R. and Watson J. Detection and Characterization of Cluster Substructure I. Linear Structure: Fuzzy c-Lines. SIAM Journal on Applied Mathematics, 1981; 40(2) 10.1137/0140029.

 

  • Hoekstra, A. Y. Water Neutral: Reducing and of Setting the Impacts of Water Footprints. Value of Water Research Report Series, NO. 28, Delft, the Netherlands: Unesco-IHE Institute for Water Education,
  • Chapagain, A., & Orr, S. UK Water Footprint: the impact of the UK’s food and fibre consumption on global water resources Volume two: appendices. WWF-UK, Godalming, 2008; 31-33.
  • Allen, R. G., Pereira, L. S., Raes, D., & Smith, M. Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage, 1998; 300(9), 56.D05109.
  • Bazrafshan, o., ramezani etedali, h., garkani nezhad moshizi, z., shamili, m.Virtual water trade and water footprint accounting of Saffron production in Iran. Agricultural Water Management, 2019; 213 368–374.
  • Bazrafshan, o., Zamani, h., Ramezani etedali, h., garkani nezhad moshizi, z., shamili, m., ismaelpour, y., gholami, h. Improving water management in date palms using economic value of water footprint and virtual water trade concepts in Iran. Agricultural Water Management, 2020; 229, 10594.
  • Ravi, V., Pradeepkumar, D., Deb, K. Financial time series prediction using hybrids of chaos theory, multi-layer perceptron and multi-objective evolutionary algorithms. Swarm and Evolutionary Computation, 2017; 36, 136-149
  • Khashei M., Hajirahimi Z. A comparative study of series arima/mlp hybrid models for stock price forecasting, 2019; 2625-2640.
  • Friedman, J. H. Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics, 2001; 29(5), 1189–1232.
  • Jahanbakhshi F, Ekhtesasi M R. Performance Evaluation of Three Image Classification Methods (Random Forest, Support Vector Machine and the Maximum Likelihood) in Land Use Mapping. JWSS, 2019; 22 (4) :235-247.
  • Ahmadpour, H., Bazrafshan, O., Rafiei-Sardooi, E., Zamani, H., & Panagopoulos, T. Gully Erosion Susceptibility Assessment in the Kondoran Watershed Using Machine Learning Algorithms and the Boruta Feature Selection. Sustainability, 2021; 13(18), 10110.
  • Ababaei, B., Ramezani Etedali, H. Estimation of Water Footprint Compartments in National Wheat Production. Water and Soil. 2016; 29(6), 1458-1468.. [Persian]
  • Elbeltagi, A., Azad, N., Arshad, A., Mohammed, S., Mokhtar, A., Pande, C., R.Etedali, H., A.Bhat, S., Abu Reza, Md., Islam, T., Deng, J. Applications of Gaussian process regression for predicting blue water footprint: Case study in Ad Daqahliyah, Egypt. Science Direct, 2021; 107052.
  • Fathizad, H., Hakimzadeh Ardakani, M. Evaluation of the Efficiency of Artificial Neural Network and Random Forest Models in Predicting Groundwater Quality Parameters of Yazd-Ardakan Plain. Integrated Watershed Management, 2022; 1(2), 1-19. [Persian]
  • Norouzi, H., Nadiri, A., Asghari Moghaddam, A., Norouzi, M. Comparing Performans of Fuzzy Logic, Artificial Neural Network and Random Forest Models in Transmissivity Estimation of Malekan Plain Aquifer. Iranian journal of Ecohydrology, 2018; 5(3), 739-751. [Persian]
  • Mokhtar, A., Elbeltagi, A., Maroufpoor, S., Azad, N., He, H., Alsafadi, K.,... & He, W. Estimation of the rice water footprint based on machine learning algorithms. Computers and Electronics in Agriculture, 2021b; 191, 106501.
  • Mohammadi, M., Vagharfard, H., Mahdavi Najafabadi, R., Daneshkar Arasteh, P., Nazemosadat, M. Rainfall-runoff Modelling of Coastal Watersheds near Hormuz Strait Using Data Mining. Iranian Journal of Soil and Water Research, 2021; 52(2), 313-327. [Persian]
  • siasar, H., honar, T. Application of Support vector machine, CHAID and Random forest models, in estimated daily Reference evapotranspiration in northern Sistan and Baluchestan province. Iranian Journal of Irrigation & Drainage, 2019; 13(2), 378-388.
  • Ghasemi, A., Fallah, A., Shataee Joibari, S. Evaluation of four algorithms for estimation of canopy cover of mangrove forests by using aerial imagery. Journal of RS and GIS for Natural Resources, 2016; 7(2), 1-16. [Persian]
  • Ridoutt, B. G. and Pfister S. Reducing humanity’s water footprint. Environmental Science & Technology, 2010; 44 (16), 6019-6021.
  • Zhao, , Lu, D., Wang, G., Liu, L., Li, D., Zhu, J., Yu, S. (2016). Forest aboveground biomass estimation in Zhejiang Province using the integration of Landsat TM and ALOS PALSAR data. International Journal of Applied Earth Observation and Geoinformation, 2016; 53(10), 1-15.
اکوهیدرولوژی
دوره 9، شماره 3
مهر 1401
صفحه 675-689

فایل ها

سابقه مقاله

  • تاریخ دریافت: 11 فروردین 1401
  • تاریخ بازنگری: 10 اردیبهشت 1401
  • تاریخ پذیرش: 30 خرداد 1401

هم رسانی

ارجاع به این مقاله

آمار