ایجاد توابع انتقالی شبه‌پیوسته برای برآورد منحنی نگه‌داشت آب خاک با استفاده از روش درخت M5

نوع مقاله : مقاله کامل علمی پژوهشی

نویسندگان

1 دانشجوی دکتری ، گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه بوعلی‌سینا، همدان، ایران.

2 دانشیار، گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه بوعلی‌سینا، همدان، ایران.

چکیده

سابقه و هدف: اخیرا توابع انتقالی شبه‌پیوسته (PC-PTF) برای برآورد منحنی نگه‌داشت آب خاک (SWRC) معرفی شده‌است. این توابع به‌شدت به قدرت الگوریتم‌های یادگیری ماشین حساس هستند. روش درخت M5 مشابه درخت‌های رگرسیون است، که توابع خطی در برگ‌های آن قرار دارند و دارای قدرت بالایی در ایجاد توابع انتقالی است. با این وجود تاکنون از این روش برای ایجاد PC-PTF برای طیف وسیعی از بافت‌های خاک استفاده نشده است. همچنین، کارایی برخی متغیرهای ساختمان خاک در بهبود PC-PTFها بررسی نشده است. علاوه‌بر‌این، وابستگی توزیع خطای PC-PTFها به عوامل مختلف مورد بررسی عمیق قرار نگرفته است. بنابراین اهداف این مطالعه ایجاد توابع انتقالی شبه پیوسته با استفاده از روش M5، بررسی تأثیر متغیرهای ساختمان خاک بر عملکرد این توابع و بررسی وابستگی خطای این توابع به عوامل مختلف بود.
مواد و روش‌ها: تعداد 120 نمونه خاک از استان‌های تهران و همدان از عمق 15 تا 60 سانتی‌متری با کاربری زراعی، باغی و مرتع برداشت شد. بافت خاک، جرم مخصوص ظاهری (BD) ، SWRC، هدایت هیدرولیکی اشباع (Ks) ، مواد آلی (OM) ، میانگین وزنی قطر خاکدانه‌ها (MWD) و مقاومت فروروی در مکش 300 هکتوپاسکال (PR300) اندازه‌گیری شد. 13 تابع انتقالی شبه‌پیوسته، با هر کدام از روش‌های درخت M5 و رگرسیون غیر خطی، در قالب 3 گروه متغیر ورودی، برای برآورد SWRC ایجاد شد. توزیع‌خطای تمام توابع‌انتقالی شبه‌پیوسته براساس آماره‌ مجذور میانگین مربعات خطا بر روی مثلث بافت خاک ترسیم شد.
یافته‌ها: در تابع اول، مکش خاک به‌عنوان تنها تخمین‌گر مورد استفاده قرار گرفت. رگرسیون غیرخطی مدل قابل قبولی برای تابع اول با ضریب تعیین 718/0 ایجاد کرد. در توابع شبه‌پیوسته 3 تا 6 اجزای بافت، BD و رطوبت FC (مکش 300 هکتوپاسکال) و PWP (مکش 15000 هکتوپاسکال) برای برآورد SWRC مورد استفاده قرار گرفتند. ضریب تعیین این توابع 719/0 تا 990/0 به‌دست آمد که بهبود عملکرد برآورد SWRC را نشان داد. در روش M5، استفاده از رطوبت FC موجب بهبود قابل توجه عملکرد مدل گردید و با مجذور میانگین مربعات 015/0 و cm3cm-3 020/0، و ضرب تعیین 987/0 و 973/0 به‌ترتیب در مراحل آموزش و اعتبارسنجی، یک مدل بهینه‌ را ایجاد کرد. در روش M5، هر تابعی که از Ks و MWD به‌عنوان تخمین‌گر استفاده کرد، بهبود معنی‌داری نسبت به تابع 4 که از اجزای بافت خاک و BD به‌عنوان تخمین‌گر استفاده کرده بود، نشان داد. مقادیر آماره آکائیک در هر دو مرحله آموزش و اعتبارسنجی در روش M5 نسبت به رگرسیون غیرخطی، به‌ترتیب به‌میزان 37 تا 283 درصد و 111 تا 157 درصد کمتر به دست آمد. توزیع خطا بر روی مثلث بافت خاک، هیچ وابستگی به بافت خاک نشان نداد، ولی به روش ایجاد توابع شبه‌پیوسته و متغیرهای ورودی مرتبط بود.
نتیجه‌گیری: می‌توان با روش‌های هوش مصنوعی قدرتمند یک مدل جامع برای SWRC ایجاد کرد، که باعث عدم نیاز کاربران به مدل‌های مختلف SWRC مانند ون‌گنوختن برای خاک‌های مختلف خواهد بود. استفاده از مجموعه‌ای از متغیرهای بافت و ساختمان خاک باعث افزایش دقت برآورد SWRC می‌گردد. ولی آن‌دسته از متغیرهای ساختمانی، که شاخصی از توزیع اندازه منافذ هستند، برای برآورد SWRC مناسب‌تر بودند. تاثیر بیشتر FC، در بهبود برآورد SWRC نسبت به PWP، کارایی بیشتر رطوبت در مکش‌های میانی در برآورد SWRC را نشان داد. الگوریتم قوی روش درخت M5 برخی الگوهای روابط میان متغیرهای ورودی و خروجی که توسط روش رگرسیون غیرخطی قابل تشخیص نبود، را تشخیص داد. با توجه به وابستگی توزیع خطا بر روی مثلث بافت خاک، به روش ایجاد توابع شبه‌پیوسته و متغیرهای ورودی، باید نقشه‌های توزیع خطا را بر اساس فاکتورهای مذکور دسته‌بندی نمود

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Creating semi-continuous pedotransfer functions for estimating soil water retention curve using the M5 tree method

نویسندگان [English]

  • Reza Kiani 1
  • Hossein Bayat 2
1 PhD student, Department of Soil Science and Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran.
2 Associate Professor, Department of Soil Science and Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran.
چکیده [English]

Background and Objectives: Recently, pseudo-continuous transfer functions (PC-PTFs) have been introduced for estimating soil water retention curve (SWRC). The M5 tree method is similar to regression trees, where linear functions are located in its leaves, and it has a high capability in creating transfer functions. These functions are highly sensitive to the power of machine learning algorithms. However, so far, the powerful M5 tree method has not been used to develop PC-PTFs for a wide range of soil textures. Additionally, the effectiveness of some soil structural variables in improving PC-PTFs has not been investigated, so far. Furthermore, the dependency of the error distribution of PC-PTFs on soil textural triangles to various factors has not been deeply examined. Therefore, the objectives of this study were to develop PC-PTFs using the M5 method, investigate the effect of soil structural variables on the performance of these functions, and examine the error dependence of these functions on different factors.
Materials and Methods: A total of 120 soil samples were collected from depths of 10 to 60 centimeters, with agricultural, orchard, and pastureland uses of Tehran and Hamedan provinces, and soil texture, bulk density (BD), SWRC, saturated hydraulic conductivity (Ks), organic matter (OM), mean weight diameter (MWD) of soil aggregates, and penetration resistance at 300 hectopascals (PR300) were measured. Thirteen PC-PTFs, in three groups of inputs, were developed to estimate SWRC, using M5 tree and non-linear regression methods. The error distribution of all PC-PTFs was plotted on the soil texture triangle, according to root mean square error (RMSE).
Results:
In the first function, soil suction was used as the only estimator. A non-linear regression model produced an acceptable model for the first function with a R2 of 0.718. In PC-PTFs 3 to 6, components of soil texture, BD, and FC (at 300 hPa matric suction) and PWP (at 15000 hPa matric suction) moisture contents were used to estimate SWRC. The R2for these functions ranged from 0.719 to 0.990, indicating an improvement in the performance of SWRC estimation. In the M5 method, the use of FC significantly improved the model performance and created an optimal model, resulting in RMSE of 0.015 and 0.020 cm³cm⁻³, and R² of 0.987 and 0.973 in the training and validation stages, respectively. In the M5 method, any function using Ks and MWD as estimators showed significant improvement compared to PC-PTF4, which used soil texture components and BD as estimators. The AIC values in both training and validation stages in the M5 method were 37% to 283% and 111% to 157% lower compared to non-linear regression, respectively. The error distribution on the soil texture triangle showed no dependence on soil texture but was related to the method of creating PC-PTFs and relevant input variables.
Conclusions: A powerful artificial intelligence methods can be employed to create a comprehensive model for SWRC. This would eliminate the need for users to rely on various SWRC models such as van Genuchten for different soils. Incorporating a set of soil texture and structure variables increases the accuracy of SWRC estimation. However, among structural variables, those indicating pore size distribution were more suitable for SWRC estimation. The greater impact of FC compared to PWP demonstrated the higher efficiency of moisture in intermediate matric suctions for SWRC estimation. The robust algorithm of the M5 tree method identified some patterns of relationships between input and output variables that were not detectable by non-linear regression. Considering the dependence of error distribution on the soil texture triangle to the method of creating PC-PTFs and input variables, categorizing error distribution maps should be done based on the mentioned factors.

کلیدواژه‌ها [English]

  • Estimation error map
  • Field capacity moisture content
  • Non-linear regression
  • Organic matter
  • Saturated hydraulic conductivity

مراجع

 1.Yuan, S., Liu, X., & Buzzi, O. (2021). A microstructural perspective on soil collapse. Geotechnique, 71(2), 132-140. doi: 10.1680/jgeot.18.P.256.
2.Rawls, W. J., Brakensiek, C. L., & Saxton, K. E. (1982). Estimation of soil water properties. Transactions - American Society of Agricultural Engineers, 25(5), 1316-1320. doi: 10.13031/2013. 33720.
3.Rawls, W. J., Nemes, A., & Pachepsky, Y. (2004). Effect of soil organic carbon on soil hydraulic properties. p. 95-114, In:
Y. Pachepsky & W.J. Rawls, Editors. Developments in Soil Science, Elsevier. doi: https://doi.org/10.1016/S0166-2481 (04)30006-1.
4.Kuzmanovski, V., Trajanov, A., Leprince, F., Džeroski, S., & Debeljak, M. (2015). Modeling water outflow from tile-drained agricultural fields. Science of The Total Environment, 505, 390-401. doi: https:// doi.org/10.1016/j.scitotenv.2014.10.009.
5.Vereecken, H., Amelung, W., Bauke,
S. L., Bogena, H., Brüggemann, N., Montzka, C., Vanderborght, J., Bechtold, M., Blöschl, G., Carminati, A., Javaux, M., Konings, A. G., Kusche, J., Neuweiler, I., Or, D., Steele-Dunne, S., Verhoef, A., Young, M., & Zhang, Y. (2022). Soil hydrology in the Earth system. Nature Reviews Earth & Environment, 3(9), 573-587. doi: 10. 1038/s43017-022-00324-6.
6.Gupta, S., & Larson, W. (1979). Estimating soil water retention characteristics from particle size distribution, organic matter percent, and bulk density. Water Resources Research, 15(6), 1633-1635. doi: https://doi.org/ 10.1029/WR015i006p01633.
7.Vereecken, H., Weynants, M., Javaux, M., Pachepsky, Y., Schaap, M., & Genuchten, M. T. (2010). Using pedotransfer functions to estimate the van Genuchten–Mualem soil hydraulic properties: A review. Vadose Zone Journal, 9(4), 795-820. doi: https:// doi.org/10.2136/vzj2010.0045.
8.Zhang, Y., & Schaap, M. G. (2017). Weighted recalibration of the Rosetta pedotransfer model with improved estimates of hydraulic parameter distributions and summary statistics (Rosetta3). Journal of Hydrology,
547, 39-53. doi: https://doi.org/10.1016/ j.jhydrol.2017.01.004.
9.Weihermüller, L., Lehmann, P., Herbst, M., Rahmati, M., Verhoef, A., Or, D., Jacques, D., & Vereecken, H. (2021). Choice of Pedotransfer Functions Matters when Simulating Soil Water Balance Fluxes. Journal of Advances in Modeling Earth Systems, 13(3), e2020MS002404. doi:https://doi.org/10.1029/2020MS002404.
10.Van Genuchten, M. T. (1980). A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil Science Society of America Journal, 44(5), 892-898. doi: https:// doi.org/10.2136/sssaj1980.03615995004400050002x.
11.Wösten, J., Pachepsky, Y. A., & Rawls, W. (2001). Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology, 251(3), 123-150. doi: https://doi.org/ 10.1016/S0022-1694(01)00464-4.
12.Minasny, B., & McBratney, A. B. (2002). The neuro-m method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal, 66(2), 352-361. doi: https://doi.org/10.2136/sssaj2002.3520.
13.Haghverdi, A., Cornelis, W. M., & Ghahraman, B. (2012). A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data. Journal of Hydrology, 442-443, 46-54. doi: https:// doi.org/10.1016/j.jhydrol.2012.03.036.
14.Haghverdi, A., Öztürk, H. S., & Cornelis, W. M. (2014). Revisiting the pseudo continuous pedotransfer function concept: Impact of data quality and
data mining method. Geoderma,
226-227, 31-38. doi: https://doi.org/ 10.1016/j.geoderma.2014.02.026.
15.Li, Y., & Vanapalli, S. K. (2022). Prediction of soil-water characteristic curves using two artificial intelligence (AI) models and AI aid design method for sands. Canadian Geotechnical Journal, 59(1), 129-143. doi: 10.1139/ cgj-2020-0562.
16.Rastgou, M., Bayat, H., Mansoorizadeh, M., & Gregory, A. S. (2022). Estimating Soil Water Retention Curve by Extreme Learning Machine, Radial Basis Function, M5 Tree and Modified Group Method
of Data Handling Approaches. Water Resources Research, 58(4), e2021WR 031059. doi: https://doi.org/10.1029/ 2021WR031059.
17.Haghverdi, A., Öztürk, H. S., & Durner, W. (2018). Measurement and estimation of the soil water retention curve using the evaporation method and the pseudo continuous pedotransfer function. Journal of Hydrology, 563, 251-259. doi: https://doi.org/10.1016/ j.jhydrol. 2018.06.007.
18.Nguyen, P. M., Haghverdi, A., de Pue, J., Botula, Y. D., Le, K. V., Waegeman, W., & Cornelis, W. M. (2017). Comparison of statistical regression and data-mining techniques in estimating soil water retention of tropical delta soils. Biosystems Engineering, 153, 12-27. doi: https:// doi.org/10.1016/j.biosystemseng. 2016.10.013.
19.Pachepsky, Y. A., & Rawls, W. (2003). Soil structure and pedotransfer functions. European Journal of Soil Science,
54(3), 443-452. doi: https://doi.org/ 10.1046/j.1365-2389.2003. 00485.x.
20.Zakerinia, M., & Ghorbani, K. (2013). Feasibility of decision tree application (M5 model) for determining soil moisture characteristic curve from easily available soil parameters. Journal of Water and Soil Conservation,
20(5), 221-230. doi: 20.1001.1.23222 069.1392.20.5.14.0. [In Persian]
21.Pachepsky, Y., & Rawls, W. J. 2004. Development of pedotransfer functions in soil hydrology. Vol. 30. p, 512, Elsevier.
22.Rastgou, M. (2020). Comprehensive comparison of the methods of developing pedotransfer functions (PTFs) and development of new algorithms to predict soil water retention curve (SWRC) and soil hydraulic conductivity curve (SHCC). in Soil Science and Enguneering. 2020, Bu-Ali Sina University: Hamedan, Iran. p. 363. [In Persian]
23.Gee, G. W., & Or, D. (2002). Particle- Size Analysis. p, 225-295. In: Warren, A.D. (ed) Methods of Soil Analysis. Part 4. Physical Methods. Soil Science Society of America Inc, Madison.
24.Grossman, R., & Reinsch, T. (2002). Bulk Density and Linear Extensibility. p. 201-228, In: J.H. Dane, Topp, G.C., Editor. Methods of Soil Analysis: Part 4 Physical Methods, Soil Science Society of America Inc, Madison.
25.Grossman, R. B., & Reinsch, T. G. (2002). Water Retention and Storage.
p. 201–228., In: J.H. Dane, Topp, G.C., Editor. Methods of Soil Analysis. Part 4. Physical Methods, Soil Science Society of America, Madison.
26.Reynolds, W. D., & Elrick, D. E. (2002). Falling Head Soil Core (tank) Method. p. 809-812., In: A.D. Warren, Editor. Methods of Soil Analysis. Part 4. Physical Methods, Soil Science Society of America Inc, Madison.
27.Walkley, A., & Black, I. A. (1934). An examination of the Degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil Science, 37(1), 29-38. doi: http://dx.doi.org/ 10.1097/00010694-193401000-00003.
28.Kemper, W., & Rosenau, R. (1986). Aggregate stability and size distribution. p. 425-442, In: A. Klute, Editor. Methods of Soil Analysis: Part 1 Physical and Mineralogical Methods, Soil Science Society of America, Inc. Madison. doi: 10.2136/sssabookser5.1. 2ed.
29.Jones, C. A. (1983). Effect of soil texture on critical bulk densities for root growth. Soil Science Society of America Journal, 47(6), 1208-1211. doi: https:// doi.org/10.2136/sssaj1983.03615995004700060029x.
30.Tietje, O., & Tapkenhinrichs, M. (1993). Evaluation of pedo-transfer functions. Soil Science Society of America Journal, 57(4), 1088-1095. doil: https://doi.org/ 10.2136/sssaj1993.03615995005700040035x.
31.Pal, M., Singh, N. K., & Tiwari, N. K. (2012). M5 Model Tree for Pier Scour Prediction Using Field Dataset, Kimberley Structural Consulting Engineers. Journal of Civil Engineering, 16(6), 1079-1084. doi: 10.1007/s12205-012-1472-1.
32.Wösten, J. H. M., Pachepsky, Y. A., & Rawls, W. J. (2001). Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology, 251(3), 123-150. doi: https:// doi.org/10.1016/S0022-1694(01)00464-4.
33.Akaike, H. (1974). A new look at the statistical model identification. Automatic Control, IEEE Transactions on,
19(6), 716-723. doi: 10.1109/tac.1974. 1100705.
34.Hwang, S. I., Lee, K. P., Lee, D. S., & Powers, S. E. (2002). Models for estimating soil particle-size distributions. Soil Science Society of America Journal, 66(4), 1143–1150. doi: https://doi.org/ 10.2136/sssaj2002.1143.
35.Ghavami, M. S., Ayoubi, S., Mosaddeghi, M. R., & Naimi, S. (2023). Digital mapping of soil physical and mechanical properties using machine learning at the watershed scale. Journal of Mountain Science, 20(10), 2975-2992. doi: 10.1007/s11629-023-8056-z.
36.Wilding, L. P., & Drees, L. R. (1983). Spatial variability and pedology. p. 83–116, In: L.P. Wilding, N.E. Smeck & G.F. Hall, Editors. Pedogenesis and soil taxonomy: Concepts and interactions, Elsevier, New York.
37.Brady, N. C., & Weil, R. R. 2010. Elements of the Nature and Properties of Soils. Pearson Educational International Upper Saddle River, NJ. doi: http:// lccn.loc.gov/2016008568.
38.Hillel, D. 1998. Environmental soil physics: Fundamentals, applications, and environmental considerations. Academic press. Waltham.
39.Nemes, A., Rawls, W. J., & Pachepsky, Y. A. (2005). Influence of organic matter on the estimation of saturated hydraulic conductivity. Soil Science Society of America Journal, 69(4), 1330-1337. doi: https://doi.org/ 10.2136/sssaj2004.0055.
40.Pachepsky, Y., Rawls, W., Gimenéz, D., & Watt, J. P. C. (1998). Use of soil penetration resistance and group method of data handling to improve soil water retention estimates. Soil and Tillage Research, 49(1-2), 117-126. doi: https:// doi.org/10.1016/S0167-1987(98)00168-8.
41.Brooks, R. H., & Corey, A. J. (1964). Hydraulic properties of porous media. Hydrol. Pap. 3. Colorado State Univ., Fort Collins.
42.Jain, S. K., Singh, V. P., & Van Genuchten, M. T. (2004). Analysis of soil water retention data using artificial neural networks. Journal of Hydrologic Engineering, 9(5), 415-420. doi: 10.1061/ ~ASCE!1084-0699~2004!9:5~415!.
43.Saxton, K., & Rawls, W. (2006). Soil water characteristic estimates by texture and organic matter for hydrologic solutions. Soil Science Society of America Journal, 70(5), 1569-1578. doi: https://doi.org/10.2136/sssaj2005.0117.
44.Rastgou, M., Bayat, H., Mansoorizadeh, M., & Gregory, A. S. (2020). Estimating the soil water retention curve: Comparison of multiple nonlinear regression approach and random forest data mining technique. Computers and Electronics in Agriculture, 174, 105502. doi:https://doi.org/10.1016/j.compag.
2020.105502.
45.Rawls, W., Pachepsky, Y. A., Ritchie, J., Sobecki, T., & Bloodworth, H. (2003). Effect of soil organic carbon on soil water retention. Geoderma, 116(1), 61-76.
doi: https://doi.org/10.1016/S0016-7061 (03)00094-6.
46.Pachepsky, Y. A., & Rawls, W. J. (2003). Soil structure and pedotransfer functions. European Journal of Soil Science, 54(3), 443-451. doi:10.1046/j. 1365-2389.2003.00485.x.
47.Schaap, M. G., Leij, F. J., & Van Genuchten, M. T. (2001). Rosetta: A computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. Journal of Hydrology, 251(3-4), 163-176. doi: https://doi.org/10.1016/S0022-1694 (01) 00466-8.
48.Wagner, B., Tarnawski, V., Wessolek, G., & Plagge, R. (1998). Suitability of models for the estimation of soil hydraulic parameters. Geoderma,
86(3), 229-239. doi: https://doi.org/ 10.1016/S0016-7061(98)00040-8.
49.Tajik, S., Ayoubi, S., & Zeraatpisheh, M. (2020). Digital mapping of soil organic carbon using ensemble learning model in Mollisols of Hyrcanian forests, northern Iran. Geoderma Regional,
20, e00256. doi:https://doi.org/10. 1016/j.geodrs.2020.e00256.
50.Kay, B. D., & VandenBygaart, A. J. (2002). Conservation tillage and depth stratification of porosity and soil organic matter. Soil and Tillage Research,
66(2), 107-118. doi:https://doi.org/ 10. 1016/S0167-1987(02)00019-3.
51.Minasny, B., Hopmans, J. W., Harter, T., Eching, S., Tuli, A., & Denton, M. (2004). Neural networks prediction of soil hydraulic functions for alluvial soils using multistep outflow data. Soil Science Society of America Journal, 68(2), 417-429. doi: https://doi.org/10. 2136/sssaj2004.4170.
52.Stock, O., & Downes, N. K. (2008). Effects of additions of organic matter on the penetration resistance of glacial till for the entire water tension range. Soil and Tillage Research, 99(2), 191-201. doi:https://doi.org/10.1016/j.still.2008.02.002.
53.Beare, M., Hendrix, P., & Coleman, D. (1994). Water-stable aggregates and organic matter fractions in conventional-and no-tillage soils. Soil Science Society of America Journal, 58(3), 777-786. doi: https://doi.org/10.2136/ sssaj1994. 03615995005800030020x.
54.Tomasella, J., Pachepsky, Y., Crestana, S., & Rawls, W. (2003). Comparison of two techniques to develop pedotransfer functions for water retention. Soil Science Society of America Journal, 67(4), 1085-1092. doi: https://doi.org/ 10.2136/sssaj2003.1085
55.Samadianfard, S., Nazemi, A. H., & Sadraddini, A. A. (2014). M5 model tree and gene expression programming based modeling of sandy soil water movement under surface drip irrigation. Agriculture Science Developments, 3, 178-190.
56.Huynh, H. (2015). Improving M5 Model Tree by Evolutionary Algorithm. Østfold University College, Halden, Norway. Master Thesis. uri:http://hdl.handle. net/11250/293858.
57.Kisi, O., Shiri, J., & Demir, V. (2017). Chapter 3 - Hydrological Time Series Forecasting Using Three Different Heuristic Regression Techniques. p. 45-65, In: P. Samui, S. Sekhar & V. E. Balas, Editors. Handbook of Neural Computation, Academic Press. doi: https://doi.org/ 10.1016/B978-0-12-811318-9.00003-X.
58.Melucci, M., & Pretto, L. (2007). PageRank: When order changes. In European Conference on Information Retrieval. Springer.
مجله مدیریت خاک و تولید پایدار
دوره 14، شماره 3
مهر 1403
صفحه 53-76

فایل ها

هم رسانی

ارجاع به این مقاله

آمار