مقایسه عملکرد مدل­های نرو فازی، برنامه­ریزی بیان ژن و جنگل تصادفی در برآورد مقاومت فروروی خاک

نوع مقاله : مقالات پژوهشی

نویسندگان

حسین علی عبد الرضا ¹

شکراله اصغری ¹

مهسا حسنپور کاشانی ²

حسین شهاب آرخازلو ¹

¹ گروه علوم و مهندسی خاک، دانشکده کشاورزی و منابع طبیعی، دانشگاه محقق اردبیلی، اردبیل، ایران

² گروه مهندسی آب، دانشکده کشاورزی و منابع طبیعی، دانشگاه محقق اردبیلی، اردبیل، ایران

https://doi.org/10.22067/jsw.2026.99264.1555

چکیده

مقاومت فروروی (PR) خاک یکی از ویژگی­های کلیدی و مهم در ارزیابی میزان فشردگی خاک در برابر تردد ادوات کشاورزی در اراضی زراعی به شمار می­رود. اندازه­گیری مستقیم PR در خاک وقت­گیر و پرهزینه بوده و به­دلیل خطای ابزاری ممکن است چندان قابل اعتماد نباشد. هدف اصلی این پژوهش، ارزیابی و مقایسه عملکرد سه مدل هوشمند نروفازی (NF)، برنامه­ریزی بیان ژن (GEP) و جنگل تصادفی (RF) در برآورد PR از روی ویژگی­های زودیافت خاک می­باشد. برای این منظور، داده­های مربوط به 105 نمونه خاک زراعی دشت اردبیل شامل رطوبت خاک مزرعه، رطوبت اشباع، شن، سیلت، رس، میانگین و انحراف معیار هندسی قطر ذرات، جرم مخصوص ظاهری و حقیقی، تخلخل کل، کربن آلی، آهک و PR به­کار گرفته شد. برای آموزش مدل­ها از 78 داده و برای آزمون مدل­ها از 27 داده استفاده گردید. پانزده ترکیب متفاوت از متغیرهای زودیافت خاک به­عنوان ورودی مدل­های NF، GEP و RF برای برآورد PR انتخاب شد. رطوبت خاک مزرعه به­عنوان یک متغیر سهل الوصول و زودیافت در بهترین مدل NF، GEP و RF برای برآورد PR خاک مورد استفاده قرار گرفت. مقادیر آماره­های ضریب تبیین (R²)، ریشه میانگین مربعات خطای نرمال شده (NRMSE)، میانگین خطا (ME) و ضریب نش-ساتکلیف (NS) براساس داده­های آزمونی برابر 50/0، 19/0، MPa 03/0 و 51/0 و 51/0، 20/0، MPa 13/0 و 48/0 و 58/0، 20/0، MPa 31/0 و 50/0 به­ترتیب برای بهترین مدل NF، GEP و RF در برآورد PR تعیین گردید. نتایج نشان داد که مدل NF با سه متغیر ورودی شامل جرم مخصوص ظاهری، شن و رطوبت خاک مزرعه در مقایسه با دو مدل هوشمند دیگر (GEP و RF) به‌دلیل داشتن NRMSE پایین و NS بالا توانست مقاومت فروروی خاک را با دقت نسبتاً بالایی در اراضی زراعی دشت اردبیل برآورد نماید.

کلیدواژه‌ها

اراضی زراعی

مقاومت خاک

مدل­های هوشمند

ویژگی­های زودیافت

موضوعات

• علوم خاک

---

عنوان مقاله English

Comparison of the Performance of Neuro-fuzzy, Gene Expression Programming and Random Forest Models in Estimating Soil Penetration Resistance

نویسندگان English

H. Ali Abdoraza ¹

Sh. Asghari ¹

M. Hasanpour Kashani ²

H. Shahab Arkhazloo ¹

¹ Department of Soil Sciences and Engineering, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran

² Water Engineering Department, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran

چکیده English

Introduction
Soil compaction is a significant component that has a detrimental impact on soil structure, inhibits plant development, lowers water penetration rate, diminishes crop production, and raises machine (e.g., tractors, cultivators, etc.) usage costs. In general, compaction is the result of applied pressure that results in a rise in bulk density or decrease in soil porosity. One of the most used indices for the investigation and evaluation of soil compaction is based on penetration resistance (PR) of the soil. However, identifying soil compaction by the records of soil penetrometer equipment in the field is time-consuming, expensive, and may produce unreliable results due to instrumental errors; thus, it is useful to apply different intelligent models to predict PR through easily accessible and low-cost soil parameters. The aim of this study was to compare the performance of three intelligent models, namely neuro-fuzzy (NF), gene expression programming (GEP), and random forest (RF), in estimating PR from readily available soil variables.

Materials and methods
Disturbed and undisturbed soil samples (n=105) were collected from 0-10 cm depth of agricultural lands in Ardabil plain, Iran. The values of sand, silt, clay, CaCO₃, bulk (BD) and particle (PD) density, organic carbon (OC), field water content (FWC) and saturated water content were measured in the soil samples in the laboratory according to the standard methods. Mean geometric diameter (d_g) and geometric standard deviation (σ_g) of soil particles were calculated from sand, silt and clay percentages. Total porosity (n) was computed using BD and PD data. The penetration resistance (PR) of the soil was obtained in the field using cone penetrometer (analog model) with 5 replicates. Data were randomly divided in to two sets: 78 data points for training and 27 for testing the models. Fifteen different combinations of readily available soil variables were selected as inputs for the neuro-fuzzy (NF), gene expression programming (GEP), and random forest (RF) models to estimate PR. The triangular, sigmoid, trapezoid, gaussian and bell shape membership functions in the input layer and constant membership function in the output layer, were applied in the neuro-fuzzy (NF) modeling using MATLAB software through a trial-and-error method. A set of optimal parameters was chosen before developing a best GEP model in the Gene Xpro Tools 4.0 software. The number of chromosomes and genes, head size and linking function were selected by the trial and error method, and they are 30, 3, 8, and +, respectively. The rates of genetic operators were chosen according to the literature studies. Weka software was used for planning random forest (RF) models. The accuracy of NF, GEP and RF models in estimating PR was evaluated by coefficient of determination (R²), normalized root mean square error (NRMSE), mean error (ME) and Nash-Sutcliffe coefficient (NS) statistics.

Results and discussion
The values of sand (26.26 to 87.43%), silt (5.99 to 67.18%), clay (3.99 to 17.34%), OC (0.30 to 2.41%), FWC (4.56 to 33.18%), BD (1.02 to 1.63 g cm^-3) and PR (1.10 to 6.60 MPa) indicated good variations in the soils of the studied area. Significant correlations were found between PR and FWC (r = - 0.57^**), sand (r = - 0.21^*), OC (r = - 0.47^**) and BD (r = 0.66^**). Previous researchers also reported a negative and significant correlation between PR and FWC and a positive and significant correlation between PR and BD. The results of NF, GEP and RF models showed that the most suitable variables to predict PR were field water content (FWC), sand, bulk density (BD), total porosity and mean geometric diameter (d_g) of soil particles. Values of coefficient of determination (R²), normalized root mean square error (NRMSE), mean error (ME), and Nash-Sutcliffe coefficient (NS) were calculated for the best models based on the test data as follows: 0.50, 0.19, 0.03 MPa, 0.51 for NF; 0.51, 0.20, 0.13 MPa, 0.48 for GEP; and 0.58, 0.20, 0.31 MPa, 0.50 for RF.

Conclusion
The results showed that according to the lowest values of normalized root mean square error (NRMSE) and the highest values of Nash-Sutcliffe coefficient (NS), the accuracy of the neuro-fuzzy (NF) model to estimate soil PR was higher than that of the gene expression programming (GEP) and random forest (RF) models in this study; The input variables of the best NF model in estimating soil penetration resistance (PR) were field water content (FWC), sand and bulk density (BD).

کلیدواژه‌ها English

Agricultural lands

Intelligent models

Readily available parameters

Soil penetration resistance

Authors retain the copyright. This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

 

مراجع

1-         Asghari, Sh., Hasanpour Kashani, M., & Shahab Arkhazloo, H. (2024). Modeling soil penetration resistance using regression, artificial neural network and gene expression programming. Journal of Soil and Wather, 38(2), 269-283. (In Persian). https://doi.org/10.22067/JSW.2024.86792.1385

2-         Bayat, H., Neyshabouri, M.R., & Hajabbasi, M. (2008). Comparing neural networks, linear and nonlinear regression techniques to model penetration resistance. Turkish Journal of Agriculture and Forestry, 32, 425-433.

3-         Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32.

4-         Elaoud, A., Hassen, H.B., Jalel, R., Salah, N.B., Masmoudi, A., & Masmoudi, A. (2023). Machine learning approach for predicting soil penetration resistance under different moisture conditions. Journal of Terramechanics, 110, 39-45. https://doi.org/10.1016/j.jterra.2023.08.002

5-         Ferreira, C. (2006). Gene Expression Programming: Mathematical modeling by an artificial intelligence. Springer, Berlin, Heidelberg, New York, p. 478.

6-         Ghorbani, M.A., Deo, R.C., Kashani, M.H., Shahabi, M., & Ghorbani, S. (2019). Artificial intelligence-based fast and efficient hybrid approach for spatial modeling of soil electrical conductivity. Soil and Tillage Research, 186, 152–164. https://doi.org/10.1016/j.still.2018.09.012

7-         Hosseini, M., Movahedi Naeini, S.A.R., Dehghani, A.A., & Zeraatpisheh, M. (2018). Modeling of soil mechanical resistance using intelligent methods. Journal of Soil Science and Plant Nutrition, 18(4), 939-951. https://doi.org/10.4067/s0718-95162018005002702

8-         Kozak, E., Pachepsky, Y.A., Sokolowski, S., Sokolowska, Z., & Stepniewski, W. (1996). A modified number-based method for estimating fragmentation fractal dimensions of soils. Soil Science Society of America Journal, 60, 1291-1297. https://doi.org/10.2136/sssaj1996.03615995006000050002x

9-         Lowery, B., & Morrison, JE. (2002). Soil penetrometer and penetrability. In: Dane J.H., & Topp GC (eds.). Methods of soil analysis, part 4. Physical methods. Madison (WI): Soil Science Society of America, 363–388. https://doi.org/10.2136/sssabookser5.4.c16

10-     Parsaie, F., Farrokhian Firouzi., A., Davari, M., & Taghizadeh-Mehrjardi, R. (2025). Digital mapping of soil penetration resistance and shear strength using machine learning algorithms in the Kilane watershed, Kurdistan province. Journal of Range & Watershed Management, 78(1), 124-143. https://doi.org/10.22059/jrwm.2024. 381733.1783

11-     Santos, F.L., De Jesus, V.A.M., & Valente, D.S.M. (2012). Modeling of soil penetration resistance using statistical analyses and artificial neural networks. Acta Scientiarum. Agronomy, 34, 219-224. https://doi.org/10.4025/ actasciagron.v34i2.11627

12-     Sheykhzadeh, G.R., Asghari, Sh., & Mesri Gundoshmian, T. (2016). Estimating penetration resistance in agricultural soils of Ardabil plain using artificial neural network and regression methods. Water and Soil, 30(3), 941-954. (In Persian). https://doi.org/10.22067/JSW.V30I3.42235

13-     Shiri, J., Keshavarzi, A., Kisi, O., & Karimi, S. (2017). Using soil easily measured parameters for estimating soil water capacity: Soft computing approaches. Computers and Electronics in Agriculture, 141, 327-339. https://doi.org/10.1016/j.compag.2017.08.012

14-     Singh, V.K., Kumar, D., Kashyap, P.S., Singh, P.K., Kumar, A., & Singh, S.K. (2020). Modelling of soil permeability using different data driven algorithms based on physical properties of soil. Journal of Hydrology, 580(124223). https://doi.org/10.1016/j.jhydrol.2019.124223

15-     Unal, I., Kabaş, O., & Sozer, S. (2024). Comparison of two different artificial neural network models for prediction of soil penetration resistance. Journal of Agricultural Engineering, 55(1), 79-86. https://doi.org/10.4081/jae. 2023.1550

16-     Warrick, A.W. (2002). Soil Physics Companion. CRC Press. 247p.

17-     Wan, H., Qi, H., & Shang, S. (2023). Estimating soil water and salt contents from field measurements with time domain reflectometry using machine learning algorithms. Agricultural Water Management, 285, 108364. https://doi.org/10.1016/j.agwat.2023.108364

18-     Waseem, M., Mani, N., Andiego, G., & Usman, M. (2017). A review of criteria of fit for hydrological models. International Research Journal of Engineering and Technology, 4(11), 1765-1772.