همکاری با انجمن علمی مدیریت و کنترل مناطق بیابانی ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار پژوهشی ، بخش تحقیقات مرتع، موسسه تحقیقات جنگلها و مراتع کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران،

2 دانش آموخته کارشناسی ارشد مرتع‌داری، دانشکده منابع طبیعی، دانشگاه ارومیه، ایران.

3 دانشیار، گروه مرتع و آبخیزداری،دانشکده منابع طبیعی، دانشگاه ارومیه، ایران

4 دانشیار پژوهشی ، بخش تحقیقات مرتع، موسسه تحقیقات جنگلها و مراتع کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران،

5 استادیار، گروه مرتع و آبخیزداری، دانشکده منابع طبیعی و محیط زیست، دانشگاه ملایر، ملایر، همدان، ایران

چکیده

در صورت بهره‌برداری مداوم از علوفه مرتع در صورتی که عناصر مهمی همانند NPC به خاک برنگردد، موجب می‌شود اراضی مرتعی حاصلخیزی خود را از دست بدهند. بنابراین، امروزه در حوزه مدیریت مراتع، اصلاح و احیاء مراتع اهمیت بالایی پیدا کرده است. یکی از روشهای اصلاح مراتع، کودپاشی می‌باشد. اگر عملیات کودپاشی متناسب با شرایط اقلیمی، وضعیت پوشش و خصوصیات خاک انجام شود، باعث بهبود مرتع می‌گردد. در غیر این صورت سبب افزایش غلظت املاح و سمی شدن خاک، آلودگی آب‌ها و خشک شدن گیاهان می‌شود. هدف از این پژوهش ارائه مدلی مبتنی بر استفاده از شبکه عصبی مصنوعی است که روابط بین کربن آلی، نیتروژن و فسفر خاک مرتع و عوامل گیاهی و ادافیکی مؤثر بر آن را بیان کند که بر مبنای نتایج آن، بتوان در زیست‌بوم‌های مرتعی فاقد آمار، عناصر مذکور را به‌منظور مدیریت کودپاشی برآورد نمود. در این پژوهش متغیرهای وابسته شامل کربن آلی، نیتروژن و فسفر خاک مراتع نازلوچای ارومیه بودند. هشت عامل هدایت الکتریکی، اسیدیته، درصد رس، درصد سیلت، درصد شن، میزان آهک، تولید و درصد تاج پوشش گیاهان مرتعی نیز به‌منظور انجام تحلیل عاملی انتخاب گردیدند. سپس با استفاده از شبکه عصبی پرسپترون چند لایه با توابع انتقالی سیگموئید و تانژانت هیپربولیک و آکسون خطی در لایه پنهان و تابع انتقال خطی در لایه خروجی، میزان کربن آلی، نیتروژن و فسفر خاک مراتع تخمین زده شد. نتایج نشان داد که تابع انتقال سیگموئید برای نیتروژن، فسفر و کربن آلی خاک مرتع با ضریب تبیین به‌ترتیب 70/0، 66/0 و 79/0 و میانگین مربعات خطای به‌ترتیب 008/0، 21/0 و 08/0 نسبت به تابع انتقال تانژانت هیپربولیک و آکسون توانسته است بخوبی کربن آلی، نیتروژن و فسفر خاک مرتع را مدل‌سازی کند. بنابراین با توجه به نتایج مذکور، شبکه عصبی توانست با دقت بالایی میزان کربن آلی، نیتروژن و فسفر خاک مرتع را در تیپ‌های مرتعی که فاقد نمونه‌برداری مقادیر NPC بودند، پیش‌بینی کند. در مورد کودپاشی در تیپ‌های مرتعی فاقد آمار، بر اساس میزان نیتروژن، فسفر و کربن آلی تخمین زده شده خاک تصمیم‌گیری شد. بدین صورت کهبر اساس نتایج، تیپ گیاهی Astragalus gummifera- prangos uloptera-Bromus tomentellus نیاز به کود فسفره و نیتروژنه دارد. تیپ گیاهی Onobrychis cornuta- Festuca ovina-Thymus kotschyanus نیازمند کود فسفره و تیپ گیاهی Astragalus macrostachys- Noeae mucronata-Stipa barbata به مواد آلی و کود نیتروژنه و فسفره نیاز دارد.

کلیدواژه‌ها

عنوان مقاله [English]

Management of rangelands by using artificial neural network in Nazlouchai rangelands in West Azarbayjan province

نویسندگان [English]

  • Mahshid Souri 1
  • mirfarhad blurfrush 2
  • Hirad Aghbari 3
  • javad motamedi 4
  • Behnaz Attaeian 5

1 1. Assistant Professor, Rangeland Research Division, Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran,

2 M.Sc. Graduate of Range Management, Faculty of Natural Resources, University of Urmia, Iran.

3 Associated Professor, Faculty of Natural Resources, University of Urmia, Iran

4 Associated Professor, Rangeland Research Division, Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran.

5 Assistant Professor, Natural Resources and EnvironmentFaculty ,Malayer,Hamedan,Iran

چکیده [English]

     If the rangeland forage is used continuously, the important elements such as NPC do not return to the soil, which will cause the rangeland lands to lose their fertility. Therefore, nowadays, in the field of rangeland management, rangeland improvement and rehabilitation has become very important. The use of fertilizers is one of the methods to rehabilitation the rangelands. If the proper fertilizer application is carried out in accordance with the climatic conditions, cover condition, and soil characteristics, it will improve the rangeland. Otherwise, it will increase the concentration of salts, soil toxicity, and surface and groundwater contamination and leads to drying of the plants. The aim of this study is to present a model based on the use of an artificial neural network that expresses the relationships between organic carbon, nitrogen and phosphorus of rangeland soil and plant factors, based on which, it is possible to estimate the mentioned elements in the rangeland ecosystems without statistics to manage fertilization. Based on the results, organic carbon, nitrogen and phosphorus of the soil were estimated in the Nazlocha rangeland of Urmia. Eight factors of electrical conductivity, acidity, clay percentage, silt percentage, sand percentage, lime content, production and canopy cover percentage of rangeland plants were also selected for factor analysis. Therefore, according to the mentioned results, the neural network was able to accurately predict the amount of organic carbon, nitrogen and phosphorus in rangeland soils. According to the results, the vegetation type Astragalus gummifera-prangos uloptera-Bromus tomentellus requires phosphorus and nitrogen fertilizers. Onobrychis cornuta- Festuca ovina-Thymus kotschyanus requires phosphorus fertilizer, and Astragalus macrostachys-Noeae mucronata-Stipa barbata requires organic matter and nitrogen and phosphorus fertilizers.

کلیدواژه‌ها [English]

  • rangeland improvement
  • artificial neural network
  • fertilizer
  • NPC soil
  • Nazloochaei rangeland
 
-  Ansari, V., 2009. Principles of technical implementation of rangeland improvement and rehabilitation projects, Puneh publication, 176 pages.
-  Arzani, H., 1997. Instructions on evaluation of the rangelands of different climate zones of Iran, Institute of Forestry and Rangelands, 67 pages.
-  Bahrami, B. and Ghorbani, A., 2013. Evaluation of neural network and regression models to predict species diversity using some soil and physiographic factors (Case Study: Kharabeh Sanji watershed of Urmia). Journal of Natural Ecosystems of Iran, 5 (2): 65-80.
-  Bilgili, M., 2010. Prediction of soil temperature using regression and artificial neural network models. Journal of Meteor Atmospheric Physics, 110:59–70.
-  Bodaghabadi, J., Bagheri, M., Esfandiari, I. and Toomanian, N., 2015. Digital soil mapping using artificial neural networks and terrain-related attributes. Journal of Pedosphere, 25 (4): 580-591.
-  Bly, A.G. And Woodard, H. J., 2003. Foliar nitrogen application timing influence on grain yield and protein concentration of hard red winter and spring wheat. Journal of Agronomy, 95: 335-338.
-  Bremner, M., Sparks, L., Page, L., Helmke, A., Loeppert, H., Soltanpour, N. and Sumner, M., 1996. Nitrogen-total methods of soil analysis. Part 3-Chemical Methods: 1085-1121.
-  Corcini, A., cervi, F. and Ronchetti, F., 2009. Weight of evidence and artificial neural networks for potential groundwater spring mapping: an application to the Mt. Modino area (Northern Apennines, Italy), Journal of Geomorphology, 3: 79–87.
-  Corrado, M., Fanelli, A.M. and Chieco, M., 2008. A Neural Network for Water Level Predictionin Artesian Wells, International Conferences on Computational Intelligence for Modelling, Control and Automation; Intelligent Agents, Web Technologies and Internet Commerce; and Innovation in Software Engineering, USA, Pp: 686-69.
-  Coulibaly, P., Anctil, F. and Bobee, B., 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach, Journal of Hydrology, 23(3): 244-257.
-  Dianti Tilki, A., Turan, M., Hosseini, A. and Msadaghi, M., 2010. Investigation on the effect of nitrogenous and phosphorus fertilizers on quality of forage eruca sativa in Golestan Ghorbani rangelands of Maraveh Tapeh. Iranian Journal of Rangeland and Desert Research, 17 (2): 180-190.
-  Elliott, D. E. and Abbott, R.J., 2003. Nitrogen fertilizer use on rainfed pasture in the Mt. Lofty Ranges, Pasture mass, composition and nutritive characteristics. Journal of Experimental Agricultural, 43: 553-577.
-  Frame, J., 1992. Improved grassland management farming press books, Ipswich, 200p.
-  Jangju, M., 2009. Improvement and Range Development, Mashhad University Press, 240 pages.
-  Ghaderi, B., 2008. Investigating the effect of Alfalfa seedling on some properties of vegetation of natural ranges. Iranian Journal of Research and Development in Natural Resources, (15): 166 - 177.
-  Griffe, P., Metha, S. and Shankar, D., 2003. Organic production of medicinal, aromatic and dye yielding plants (MADPs): forward, preface and introduction. Journal of Food and Agriculture Organization, 2: 52-63.
-  Guevara, J.C., Carlos, R.S., Oscar, R.E. and Le Houerou, H.N., 2000. N and P fertilization on rangeland production in Midwest Argentina. Journal of Range Manage, 53: 410-414.
-  Gupta, M.L., Prasad, A., Ram, M. and Kumar, S., 2002. Effect of the vesicular-arbuscular mycorrhiza (VAM) fungus Glomus fasiculatum on the essential oil yield related characters and nutrient acquisitioning the crops of different cultivars of menthol mint (Mentha arvensis) under field conditions. Journal of Bio resource Technology, 81: 77-79.
-  Hazelton, P. and Murphy, B., 2007. Interpreting soil test results, National Library of Australia Cataloguing-in-Publication entry, Pp: 67-89.
-  Holmberg, M., Forsius M., Starr, M. and Huttunen, M., 2006. An application of artificial neural networks to carbon, nitrogen and phosphorus concentration in three boreal streams and impacts of climate change. International Society for Ecological Information 3rd Conference. Grottaferrata, Roma, 195:51-60.
-  Huang, P. and Tsai, W., 2010. Using multiple-criteria decision-making techniques for eco environmental vulnerability assessment: a case study on the Chi-Jia-Wan Stream watershed, Taiwan. Journal of Environment Monitoring Assess, 168: 141–158.
-  Isik, s., klin, L. and Schoonover, J.E., 2012. Modeling effects of changing land use/cover on daily stream flow: artificial neural network and curve number based hybrid approach. Journal of Hydrology, 50(3):1984-2001.
-  Ingleby, H.R. and Crowe, T.G., 2001. Neural network models for predicting organic matter content in Saskatchewan soils. Journal of Canadian Biosystems Engineering, 43:71-75.
-  Jia, B. R., Zhou, G.S., Wang, Y. H., Yang, W. P. and Zhou, L., 2005. Partitioning root and microbial contributions to soil respiration in Leymus chinensis population. Journal of Soil Biology & Biochemistry, 38:653-660.
-  Keshavarzi, A., Sarmadian, F., Ewisomran., And Munawar, I., 2015. A neural network model for estimating soil phosphorus using terrain analysis. The Egyptian Journal of Remote Sensing and Space Science, (18): 127-135.
-  Kumar, B., Trivedi, P. and Pandey, A., 2009. Pseudomonas corrugates: A suitable bacterial inoculants for maize grown under rain fed conditions of Himalayan region. Journal of Soil Biology and Biochemistry, 39: 3093-3100.
-  Melesse, A. M., Ahmad, S., McClain, M.E., Wang, X. and Lim, Y. H., 2011. Suspended sediment load prediction of river systems: An artificial neural network approach. Agricultural Water Management Journal, 98(5): 855-866.
-  Mesdaghi, M., 2002. Rangeland in Iran, Astan Quds Razavi Publishing, Fifth Edition, 333 pages.
-  Minasny, B. and Mcbratney, A. B., 2002. The neuro-m method for fitting neural network parametric pedo transfer functions. Journal of Soil Science Society, 66:352-361.
-  Mohanty, S., Madnk, J.A. and Ashwani, D. K., 2013. Comparative evaluation of numerical model and artificial neural network for simulating groundwater flow in Kathajodi–Surua Inter-basin of Odisha, India. Journal of Hydrology, 495: 38-51.
-  Motamedi, J. and Bahrami, B., 2012. Soil organic carbon analysis using artificial neural network to determine the contribution of management factors to climate change in the management of rangeland ecosystems, Second National Conference on Climate Change and Its Impact on Agriculture and the Environment, July, Urmia.
-  Ojaghlu, P., 2007. Effect of inoculum with biofertilizer (Azotobacter and phosphate fertilizer) on growth, yield and yield components of safflower, Master's degree in Agriculture, Faculty of Agriculture, Islamic Azad University, Tabriz, 96 p.
-  Olsen, S. R. and Sommers, L. E., 1982. Phosphorus, methods of soil analysis part 2, America Society Agronomy, Soil Science Society of America Journal, Madison Wisconsin: 403-430.
-  Pilevar Shahri, A.R., Ayoubi Sh., and Khademi H., 2011. Comparison of Artificial Neural Network (ANN) and Multivariate Linear Regression (MLR) Models to Predict Soil Organic Carbon Using Digital Terrain Analysis. Journal of Water and Soil, 24(6): 1151-1163.
-  Rezvantalab, N., Pirdashti, H., Bahmanyar, M. A. and Abbasian, A., 2008. Study some of yield andyield component of corn (Zea mays L.) response to different types and rates of organic and chemicalfertilizers. Journal of Agricultural Science and Natural Resource, 15(5): 139-147.
-  Sarmadian, F. and Keshavarzia, F., 2010. Comparison of artificial neural network and multivariate regression methods in prediction of soil cation exchange capacity (Case study: Ziaran region). Journal of Desert, 15:167-174.
-  Shalmani, A., Asadi, H., Bagheri, F. and Shabanpour Shahrestani, M, 2010. Comparison of regression pedotransfer functions and artificial neural networks for soil aggregate stability simulation. World Applied Sciences Journal, 8 (9): 1065-1072.
-  Shiria, J., Keshavarzi, A., Bagherzadehe, A., Mousavi, R. and Karimi, M., 2017. Modeling soil cation exchange capacity using soil parameters: Assessing the heuristic models. Journal of Computers and Electronics in Agriculture, 135: 242-251.
-  Sreekanth, P. D., Geethanjali, N., Sreedevi, P. D., Shakeel, A., Kumar, N.R. and Jayanthi, P.D.K., 2009. Forecasting groundwater level using artificial neural networks. Journal of Current Science, 96 (7): 933-939.
-  Tabari, H., Sabziparvar, A. A., and Ahmadi, M., 2011. Comparison of artificial neural network and multivariate linear regression methods for estimation of daily soil temperature in an arid region. Journal of Meteor Atmospheric Physics, 110:135–142.
-  Wosten, J.H.M., Pachepsky, Y.A. and Rawls, W. J., 2001. Pedo transfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology, 251:123-150.
-  Wu, S. C., Caob, Z. H., Lib, Z. G., Cheunga, K. C., and Wong, M. H., 2005. Effects of bio fertilizers containing N-fixer, P and K Solubilizes and AM fungi on maize growth: a greenhouse trial. Journal of Geoderma, 125: 155-166.