مدل‌سازی آب قابل استفاده خاک با استفاده از روش‌های نروفازی، برنامه‌ریزی بیان ژن و جنگل تصادفی

مقالات آماده انتشار

نوع مقاله : مقالات پژوهشی

نویسندگان

• مهسا حسنپور کاشانی ¹
• شکراله اصغری ²

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

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

10.22067/jsw.2025.92342.1470

چکیده

آب قابل استفاده خاک (SAW) از تفاضل دو نقطه مهم و کاربردی منحنی رطوبتی خاک (رطوبت‌های ظرفیت مزرعه‌ای و پژمردگی دائم) به‌دست می‌آید؛ روش مستقیم اندازه‌گیری این نقاط رطوبتی خاک مستلزم صرف وقت و هزینه زیادی می‌باشد. بنابراین اخیراً از روش‌های غیر مستقیم مانند توابع انتقالی رگرسیونی و مدل‌های هوشمند برای تخمین این متغیرهای دیریافت خاک استفاده گردیده است. هدف از این پژوهش، مقایسه عملکرد سه مدل‌ هوشمند نروفازی (NF)، برنامه‌ریزی بیان ژن (GEP) و جنگل تصادفی (RF) در برآورد SAW از روی ویژگی‌های زودیافت خاک بود. در این تحقیق، داده‌های اندازه‌گیری شده مربوط به تعداد 102 نمونه خاک سطحی دشت اردبیل شامل مقادیر ذرات شن، سیلت، رس، میانگین و انحراف معیار هندسی قطر ذرات، جرم مخصوص ظاهری، کربن آلی و SAW مورد استفاده قرار گرفت. داده‌ها به‌طور تصادفی به دو گروه آموزشی (82 نمونه) و آزمونی (20 نمونه) تقسیم شدند. شش تابع SAW با ترکیب متفاوت از متغیرهای زودیافت خاک به‌عنوان ورودی مدل انتخاب و مدل‌های NF، GEP و RF برای هر کدام اجرا گردید. نتایج مدل‌ها بیانگر آن بود که کربن آلی و جرم مخصوص ظاهری خاک، دو متغیر ورودی مهم و اثرگذار در برآورد SAW بودند. مقادیر آماره‌های ضریب تبیین (R2)، مجذور میانگین مربعات خطا (RMSE)، میانگین خطا (ME) و ضریب نش-ساتکلیف (NS) براساس داده‌های آزمونی برابر 73/0، % g g-1 51/2، % g g-1 09/0 و 71/0، 76/0، % g g-1 10/3 ، % g g-1 41/1 - و 56/0، 68/0، % g g-1 30/3 ، % g g-1 45/1 - و 50/0 به‌ترتیب برای بهترین مدل‌‌ NF، GEP و RF تعیین شد. مقایسه نتایج آماره‌های ارزیابی مدل‌ها نشان داد که مدل NF به علت داشتن مقدار کم RMSE، مقدار نزدیک به صفر ME و مقدار زیاد NS نسبت به دو مدل دیگر از خطای پایین و دقت بالا در برآورد SAW برخوردار بود.

کلیدواژه‌ها

• آب خاک
• برآورد
• متغیر زودیافت
• مدل های هوشمند

موضوعات

• علوم خاک

عنوان مقاله [English]

Modeling Soil Available water Using Neuro-fuzzy, Gene expression programming, and Random Forest Methods

نویسندگان [English]

• Mahsa Hasanpour Kashani ¹
• Shokrollah Asghari ²

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

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

چکیده [English]

Introduction Soil available water (SAW) is defined as the difference between field capacity (FC) and permanent wilting point (PWP). FC is the amount of soil water content held by the soil after the gravitational water was drained from the soil. PWP is defined as a minimum water content of a soil which is needed for the crop survival and if the water content decreases lower than PWP, a plant wilts and can no longer recover itself. The direct measurement of FC and PWP soil water contents is very costly and time consuming; Therefore, it is useful the use of different intelligent models such as neuro-fuzzy (NF), gene expression programming (GEP) and random forest (RF) to estimate FC, PWP and SAW through easily accessible and low-cost soil characteristics. The objectives of this research were: (1) to obtain NF, GEP and RF models for estimating SAW from the easily accessible soil variables in the cultivated lands of Ardabil plain (2) to compare the accuracy of the mentioned models in estimating SAW using the coefficient of determination (R2), root mean square error (RMSE), mean error (ME) and Nash-Sutcliffe coefficient (NS) criteria.



Materials and methods The measured data from 102 soil samples taken from 0-10 cm soil depth of the cultivated lands of Ardabil plain, northwest of Iran, were used in this study. Sand, clay, mean geometric diameter (dg) and geometric standard deviation (σg) of soil particles, bulk density (BD) and organic carbon (OC) were introduced as input variables to the applied three intelligent models for estimating soil available water (SAW). Data randomly were divided in two series as 82 data for training and 20 data for testing of models. In all models, six different input variables combinations were used; SPSS 22 software with stepwise method was applied to select the input variables. MATLAB, Gene Xpro Tools 4.0 and Weka softwares were used to derive neuro-fuzzy (NF), gene expression programming (GEP) and random forest (RF) models, respectively. One of the important steps using NF method is selecting the appropriate membership functions (MFs) and its numbers. Based on a trial and error procedure, 3 numbers of MFs and 50 to 100 optimum replications were found for the NF modeling. Also, the input MFs were chosen as “triangular”, “trapezoid”, “generalized bell” and “pi” and the output MF was selected as “constant”. A set of optimal parameters were chosen before developing a best GEP model. 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 literature studies. Various tree numbers were analyzed for choosing the best random forest (RF) method. Increasing the tree numbers beyond 100 made lower variations in the average squared error values for the SAW estimation cases. The accuracy of NF, GEP and RF models in estimating SAW was evaluated by coefficient of determination (R2), root mean square error (RMSE), mean error (ME) and Nash-Sutcliffe coefficient (NS) statistics.



Results and discussion The studied soils had loam (n= 53), clay loam (n= 26), sandy loam (n= 15), silt loam (n= 6) and clay (n= 2) textural classes. The values of sand (24.40 to 68.00 %), clay (3.80 to 42.90 %), dg (0.02 to 0.26 mm), σg (7.48 to 19.41), BD (1.04 to 1.70 g cm-3), OC (0.31 to 1.52 %) and SAW (5.10 to 25.10 % g g-1) indicated good variations in the soils of studied region. There were found significant correlations between SAW with BD (r= - 0.59**), clay (r= 0.56**), OC (r= 0.45**) and sand (r= - 0.44**). NF, GEP and RF models were applied to estimate SAW using six different combinations of input soil variables (sand, clay, dg, σg, BD and OC). The results of the best NF, GEP and RF models indicated that the most appropriate input variables to predict SAW were OC and BD. The values of R2, RMSE, ME and NS criteria were obtained equal 0.73, 2.51 % g g-1, 0.09 % g g-1and 0.71, and 0.76, 3.10 % g g-1, - 1.41 % g g-1 and 0.56, 0.68, 3.30 % g g-1, - 1.45 % g g-1, 0.50 for the best NF, GEP and RF models in the testing data set, respectively. Numerous investigations also showed that there are significant negative correlation between SAW with BD and sand and positive correlation between SAW with OC and clay.

Conclusion The results of three investigated intelligent models showed that OC and BD were the most important and readily available soil variables to predict soil available water (SAW) in the studied area. According to the lowest values of RMSE and the highest values of NS, the accuracy of NF models to estimate SAW was more than GEP and RF models. RF approach gave the worst estimates for SAW in this research.

کلیدواژه‌ها [English]

• Intelligent models
• Prediction
• Readily variables
• Soil water