scholarly journals Predicting the infiltration characteristics for semi-arid regions using regression trees

2021 ◽  
Author(s):  
Parveen Sihag ◽  
Munish Kumar ◽  
Saad Sh. Sammen
Keyword(s):  
Input Parameter ◽  
Regression Tree ◽  
Soil Surface ◽  
Infiltration Rate ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Infiltration Process ◽  
Data Set ◽  
Cumulative Infiltration ◽  
Tree Methods

Abstract The study of infiltration process is considered as essential and necessary for all hydrology studies. Therefore, accurate predictions of infiltration characteristics are required to understand the behavior of subsurface flow of water through the soil surface. The aim of the current study is to simulate and improve the prediction accuracy of infiltration rate and cumulative infiltration of soil using regression tree methods. Experimental data recorded with a double ring infiltrometer for 17 different sites are used in this study. Three regression tree methods: Random tree, Random forest (RF) and M5 tree are employed to modelling the infiltration characteristics using the basic soil characteristics. The performance of the modelling approaches is compared in predicting the infiltration rate as well as cumulative infiltration, obtained results suggest that performance of RF model is better than other applied models with coefficient of determination (R2) = 0.97 & 0.97, root mean square error (RMSE) = 8.10 & 6.96 and mean absolute error (MAE) = 5.74 & 4.44 for infiltration rate and cumulative infiltration respectively. RF model is used to represent the infiltration characteristics of the study area. Moreover, parametric sensitivity is adopted to study the significance of each input parameter in estimating the infiltration process. Results suggest that time (t) is the most influencing parameter in predicting the infiltration process using this data set.

scholarly journals Assessment of Soft Computing Techniques for the Prediction of Compressive Strength of Bacterial Concrete

Materials ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 489
Author(s):  
Fadi Almohammed ◽  
Parveen Sihag ◽  
Saad Sh. Sammen ◽  
Krzysztof Adam Ostrowski ◽  
Karan Singh ◽  
...  
Keyword(s):  
Compressive Strength ◽  
Performance Evaluation ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Curing Time ◽  
Data Set ◽  
Soft Computing Techniques ◽  
Bacterial Concrete

In this investigation, the potential of M5P, Random Tree (RT), Reduced Error Pruning Tree (REP Tree), Random Forest (RF), and Support Vector Regression (SVR) techniques have been evaluated and compared with the multiple linear regression-based model (MLR) to be used for prediction of the compressive strength of bacterial concrete. For this purpose, 128 experimental observations have been collected. The total data set has been divided into two segments such as training (87 observations) and testing (41 observations). The process of data set separation was arbitrary. Cement, Aggregate, Sand, Water to Cement Ratio, Curing time, Percentage of Bacteria, and type of sand were the input variables, whereas the compressive strength of bacterial concrete has been considered as the final target. Seven performance evaluation indices such as Correlation Coefficient (CC), Coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Bias, Nash-Sutcliffe Efficiency (NSE), and Scatter Index (SI) have been used to evaluate the performance of the developed models. Outcomes of performance evaluation indices recommend that the Polynomial kernel function based SVR model works better than other developed models with CC values as 0.9919, 0.9901, R2 values as 0.9839, 0.9803, NSE values as 0.9832, 0.9800, and lower values of RMSE are 1.5680, 1.9384, MAE is 0.7854, 1.5155, Bias are 0.2353, 0.1350 and SI are 0.0347, 0.0414 for training and testing stages, respectively. The sensitivity investigation shows that the curing time (T) is the vital input variable affecting the prediction of the compressive strength of bacterial concrete, using this data set.

scholarly journals Predicted Infiltration for Sodic/Saline Soils from Reclaimed Coastal Areas: Sensitivity to Model Parameters

2014 ◽  
Vol 2014 ◽  
pp. 1-12
Author(s):  
Dongdong Liu ◽  
Dongli She ◽  
Shuang’en Yu ◽  
Guangcheng Shao ◽  
Dan Chen
Keyword(s):  
Water Movement ◽  
Soil Surface ◽  
Coastal Areas ◽  
Model Parameters ◽  
Wetting Front ◽  
Sodic Soils ◽  
Infiltration Process ◽  
Infiltration Model ◽  
Soil Physical Quality ◽  
Cumulative Infiltration

This study was conducted to assess the influences of soil surface conditions and initial soil water content on water movement in unsaturated sodic soils of reclaimed coastal areas. Data was collected from column experiments in which two soils from a Chinese coastal area reclaimed in 2007 (Soil A, saline) and 1960 (Soil B, nonsaline) were used, with bulk densities of 1.4 or 1.5 g/cm3. A 1D-infiltration model was created using a finite difference method and its sensitivity to hydraulic related parameters was tested. The model well simulated the measured data. The results revealed that soil compaction notably affected the water retention of both soils. Model simulations showed that increasing the ponded water depth had little effect on the infiltration process, since the increases in cumulative infiltration and wetting front advancement rate were small. However, the wetting front advancement rate increased and the cumulative infiltration decreased to a greater extent whenθ0was increased. Soil physical quality was described better by theSparameter than by the saturated hydraulic conductivity since the latter was also affected by the physical chemical effects on clay swelling occurring in the presence of different levels of electrolytes in the soil solutions of the two soils.

scholarly journals Fluxes from soil moisture measurements (FluSM v1.0): a data-driven water balance framework for permeable pavements

2021 ◽  
Vol 14 (4) ◽  
pp. 2127-2142
Author(s):  
Axel Schaffitel ◽  
Tobias Schuetz ◽  
Markus Weiler
Keyword(s):  
Soil Moisture ◽  
Water Balance ◽  
Input Parameter ◽  
Infiltration Rate ◽  
Data Driven ◽  
Minor Role ◽  
Water Fluxes ◽  
Parameter Uncertainties ◽  
Data Set ◽  
Permeable Pavements

Abstract. Water fluxes at the soil–atmosphere interface are a key piece of information for studying the terrestrial water cycle. However, measuring and modeling water fluxes in the vadose zone poses great challenges. While direct measurements require costly lysimeters, common soil hydrologic models rely on a correct parametrization, a correct representation of the involved processes, and the selection of correct initial and boundary conditions. In contrast to lysimeter measurements, soil moisture measurements are relatively cheap and easy to perform. Using such measurements, data-driven approaches offer the possibility to derive water fluxes directly. Here we present FluSM (fluxes from soil moisture measurements), which is a simple, parsimonious and robust data-driven water balancing framework. FluSM requires only a single input parameter (the infiltration rate) and is especially valuable for cases where the application of Richards-based models is critical. Since permeable pavements (PPs) present such a case, we apply FluSM on a recently published soil moisture data set to obtain the water balance of 15 different PPs over a period of 2 years. Consistent with findings from previous studies, our results show that vertical drainage dominates the water balance of PPs, while surface runoff plays only a minor role. An additional uncertainty analysis demonstrates the ability of the FluSM-approach for water balance studies, since input and parameter uncertainties only have a small effect on the characteristics of the derived water balances. Due to the lack of data on the hydrologic behavior of PPs under field conditions, our results are of special interest for urban hydrology.

scholarly journals Developing a fuzzy logic model for predicting soil infiltration rate based on soil texture properties

Water SA ◽  
2019 ◽  
Vol 45 (3 July) ◽  
Author(s):  
Ahmed Z Dewidar ◽  
Hussein Al-Ghobari ◽  
Abed Alataway
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Model ◽  
Clay Content ◽  
Infiltration Rate ◽  
Influential Factor ◽  
Coefficient Of Determination ◽  
Soil Infiltration ◽  
Infiltration Process ◽  
Soil Infiltration Rate ◽  
Mlr Model

The prediction of the soil infiltration rate is advantageous in hydrological design, watershed management, irrigation, and other agricultural studies. Various techniques have been widely used for this with the aim of developing more accurate models; however, the improvement of the prediction accuracy is still an acute problem faced by decision makers in many areas. In this paper, an intelligent model based on a fuzzy logic system (FLS) was developed to obtain a more accurate predictive model for the soil infiltration rate than that generated by conventional methods. The input variables that were considered in the fuzzy model included the silt and clay contents. The developed fuzzy model was tested against both the observed data and multiple linear regression (MLR). The comparison of the developed fuzzy model and MLR model indicated that the fuzzy model can simulate the infiltration process quite well. The coefficient of determination, root mean square error, mean absolute error, model efficiency, and overall index of the fuzzy model were 0.953, 1.53, 1.28, 0.953, and 0.954, respectively. The corresponding MLR model values were 0.913, 2.37, 1.92, 0.913, and 0.914, respectively. The sensitivity results indicated that the clay content is the most influential factor when the FLS-based modelling approach is used for predicting the soil infiltration rate.

scholarly journals Comparison of neural networks and neuro-fuzzy computing techniques for prediction of peak breach outflow

2016 ◽  
Vol 18 (4) ◽  
pp. 724-740 ◽  
Author(s):  
Hasan G. Elmazoghi ◽  
Vail Karakale (Waiel Mowrtage) ◽  
Lubna S. Bentaher
Keyword(s):  
Fuzzy Inference ◽  
Gene Expression Programming ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Regression Equations ◽  
Data Set ◽  
Inference System ◽  
Embankment Dams ◽  
Small Dams ◽  
Neuro Fuzzy

Accurate prediction of peak outflows from breached embankment dams is a key parameter in dam risk assessment. In this study, efficient models were developed to predict peak breach outflows utilizing artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Historical data from 93 embankment dam failures were used to train and evaluate the applicability of these models. Two scenarios were applied with each model by either considering the whole data set without classification or classifying the set into small dams (48 dams) and large dams (45 dams). In this way, nine models were developed and their results were compared to each other and to the results of the best available regression equations and recent gene expression programming. Among the different models, the ANFIS model of the first scenario exhibited better performance based on its higher efficiency (E = 0.98), higher coefficient of determination (R2 = 0.98) and lower mean absolute error (MAE = 840.9). Moreover, models based on classified data enhanced the prediction of peak outflows particularly for small dams. Finally, this study indicated the potential of the developed ANFIS and ANN models to be used as predictive tools of peak outflow rates of embankment dams.

Digital mapping of topsoil pH by random forest with residual kriging (RFRK) in a hilly region

Soil Research ◽  
2019 ◽  
Vol 57 (4) ◽  
pp. 387 ◽  
Author(s):  
Lei Wang ◽  
Wei Wu ◽  
Hong-Bin Liu
Keyword(s):  
Random Forest ◽  
Soil Ph ◽  
Agricultural Development ◽  
Regression Tree ◽  
Absolute Error ◽  
Classification And Regression Tree ◽  
Coefficient Of Determination ◽  
Hilly Region ◽  
Average Annual Temperature ◽  
Residual Kriging

Soil pH is a vital attribute of soil fertility. The accurate and efficient prediction of soil pH can provide the necessary basic information for agricultural development. In the present study, random forest with residual kriging (RFRK) was used to predict soil pH based on stratum, climate, vegetation and topography in a hilly region. The performance of RFRK was compared with those of the classification and regression tree (CART) and the random forest (RF). Comparative results showed that RFRK provided the best performance. The corresponding values of Lin’s concordance correlation coefficient, coefficient of determination, mean absolute error and root mean square error were as follows: 0.70, 0.51, 0.44 and 0.61 for CART; 0.80, 0.70, 0.34 and 0.48 for RF; and 0.88, 0.80, 0.25 and 0.39 for RFRK. Stratum and average annual temperature were the most important factors affecting the soil pH in the study area. Results indicate that RFRK is a feasible and reliable tool for predicting soil pH in hilly regions.

scholarly journals AVALIAÇÃO DO COMPORTAMENTO HIDROGEOLÓGICO DAS FORMAÇÕES GEOLÓGICAS EM UMA VERTENTE DA SERRA DO GANDARELA: RIO ACIMA, MG

e-xacta ◽  
2017 ◽  
Vol 10 (1) ◽  
pp. 1
Author(s):  
Fernanda Bárbaro Franco ◽  
Sidney Portilho ◽  
Juliana Batista de Souza
Keyword(s):  
Soil Surface ◽  
Field Capacity ◽  
Infiltration Rate ◽  
Water Infiltration ◽  
Metropolitan Region ◽  
Infiltration Process ◽  
Important Region ◽  
Quadrilátero Ferrífero ◽  
Water Recharge ◽  
Belo Horizonte

<p><em>A Serra do Gandarela apresenta uma das maiores reservas hídricas do Quadrilátero Ferrífero e seus aquíferos são de extrema importância para as áreas de drenagens das bacias hidrográficas ali presentes. Possui grande grau de conservação, belezas naturais e uma grande biodiversidade. É uma região que abriga várias espécies vegetais endêmicas e a canga, afloramentos ferruginosos, que é um dos sistemas ecológicos mais ameaçado do Brasil. Esse artigo visa trabalhar a relação entre os solos, coberturas de superfície da Serra do Gandarela e o comportamento hidrológico dos mesmos, demonstrando a capacidade de campo, armazenamento de água, e as taxas de infiltração de água de cada ponto amostrado. Dos três pontos selecionados dois apresentaram bons resultados quanto à recarga hídrica. O primeiro ponto por apresentar um sistema lento de infiltração e percolação e o segundo ponto por infiltrar grande quantidade de água. O terceiro ponto apresentou uma taxa de infiltração menor, por possuir a textura da parte cimentante da matriz coluvionar (argilo – arenosa), o que interferiu negativamente no processo de infiltração. Relacionando todos os pontos com os respectivos resultados verifica-se que a Serra do Gandarela é uma região importante para o processo de recarga hídrica da região metropolitana de Belo Horizonte. </em></p><p>ABSTRACT</p><p><em>Serra do Gandarela presents one of the biggest hydric stock of the Ferriferous Quadrangle and its aquifers are of utmost importance for draining areas of these existing watersheds.It has a great conservation degree, natural beauties, a great biodiversity. It's a region wich shelters several vegetal endemic species and the « canga », ferruginous outcrops, which is one of the most endangered ecological systems in Brazil. <br /> This article aims to work the relationship between the soil surface, covers the Serra do Gandarela and the hydrological behavior of the same, demonstrating the field capacity, water storage,and water infiltration rates of each chozen location. Of the three selected points two showed good results as to water recharge. The first point by presenting a slow infiltration and percolation system and the second point for infiltrating large amount of water. The third point presented a lower infiltration rate by having the texture of the cementitious matrix of the colluvial (clayey - sandy) which negatively interfere with the infiltration process. Listing all the points with the results it appears that the Serra do Gandarela is an important region for the water refilling process of the metropolitan region of Belo Horizonte.</em></p>

scholarly journals Evaluation of Infiltration Models in Soils of Two Land Use Systems in Calabar, Nigeria

2018 ◽  
pp. 81-94
Author(s):  
Isong I.A ◽  
Ogban P.I. ◽  
Antigha N.R.B. ◽  
Okon P.B.
Keyword(s):  
Land Use ◽  
Oil Palm ◽  
Coefficient Of Determination ◽  
Or Efficiency ◽  
Infiltration Process ◽  
Teaching And Research ◽  
Land Use Systems ◽  
Cumulative Infiltration ◽  
Infiltration Models ◽  
The University

Recently, the importance of the infiltration process in agriculture and the environ- ment has resulted in an upsurge of interest by soil and water scientists to model the process for quantitative application. A study was conducted on the University of Cal- abar Teaching and Research Farm, Calabar to evaluate the effect of oil palm (OP) and arable farm (AF) land use systems on the Green-Ampt (GA), Philip (P), Kostiakov (K), Horton (H) and Mezencev (MZ) infiltration models, as well as the applicability or efficiency of the models to predict infiltration into the soils. Infiltration data were obtained with double-ring infiltrometer, and the parameters of the models were obtained through curve-fitting. Model accuracy was evaluated with the Willmott’s index of agreement (W), chi-square (X2), coefficient of determination (R2), root mean square error (RMSE) and mean error (ME) test statistics. The results showed that soil under oil palm had measured cumulative infiltration and infiltration rate of 72.81 cm and 14.10cm/hr while arable farm had 74.76 cm and 12.92 cm/hr, respectively. The cumulative infiltration predicted by Philip and Kostiakov models were very close to the field data for OP and AF. Horton and Mezencev models underestimated the infiltration process because their ME values were negative while Green–Ampt, Kostia- kov, and Philip overestimated the infiltration process as they had positive ME values. In terms of accuracy and applicability, the order of performance was P>K>MZ>GA>H. Therefore, the Philip and Kostiakov models could be used to pre- dict infiltration into the soils, but that the Philip model was superior to the Kostiakov model for the University of Calabar Teaching and Research Farm and similar soils in other ecologies.

scholarly journals Characterization and statistical modelling of thermal resistance of cotton/polyester blended double layer interlock knitted fabrics

2017 ◽  
Vol 21 (6 Part A) ◽  
pp. 2393-2403 ◽  
Author(s):  
Ali Afzal ◽  
Sheraz Ahmad ◽  
Abher Rasheed ◽  
Muhammad Mohsin ◽  
Faheem Ahmad ◽  
...  
Keyword(s):  
Thermal Resistance ◽  
Double Layer ◽  
Input Parameter ◽  
Statistical Modelling ◽  
Absolute Error ◽  
Knitted Fabrics ◽  
Data Set ◽  
Unseen Data ◽  
Fabric Layer ◽  
Interlock Knitted Fabrics

The aim of this study was to analyse and model the effect of knitting parameters on the thermal resistance of cotton/polyester double layer interlock knitted fabrics. Fabric samples of areal densities ranging from 310-495 g/m2 were knitted using yarns of three different cotton/polyester blends, each of two different linear densities by systematically varying knitting loop lengths for achieving different cover factors. It was found that by changing the polyester content in the inner and outer fabric layer from 40 to 65% in the double layer knitted fabric has statistically significant effect on the fabric thermal resistance. Fabric thermal resistance increased with increase in relative specific heat of outer fabric layer, yarn linear density, loop length, and fabric thickness while decrease in fabric areal density. It was concluded that response surface regression modelling could be successfully used for the prediction of thermal resistance of double layer interlock knitted fabrics. The model was validated by unseen data set and it was found that the actual and predicted values were in good agreement with each other with less than 10% absolute error. Sensitivity analysis was also performed to find out the relative contribution of each input parameter on the air permeability of the double layer interlock knitted fabrics.

Infiltration and structural changes as influenced by initial moisture content

Soil Research ◽  
1971 ◽  
Vol 9 (2) ◽  
pp. 107 ◽  
Author(s):  
N Collis-George ◽  
R Lal
Keyword(s):  
Moisture Content ◽  
Structural Changes ◽  
Initial Moisture Content ◽  
Infiltration Rate ◽  
Surface Layers ◽  
Infiltration Process ◽  
Moisture Condition ◽  
Heat Of Wetting ◽  
Cumulative Infiltration ◽  
Entrapped Air

The variation of infiltration behaviour, in columns of aggregates of a structurally stable and an unstable soil, caused by pre-equilibrating the aggregates with a range of relative humidities from 0 to 98%, was measured in terms of advance of the front, cumulative infiltration, slaking, and swelling. In this range, the effect of initial moisture condition on the stable soil (krasnozem) was slight compared with that on the unstable soil (black earth); the wetter the soil initially, the greater was the infiltration rate, and the smaller the slaking and swelling. The change in the behaviour of infiltration into systems of stable aggregates is reflected as (1) an increase in the importance of the sorptivity, and (2) a reduction in the importance of the hydraulic conductivity contribution to the steady-state infiltration process. (The aggregates of 1/2-1 mm are of such a size that the sorptivity contribution should not normally be detectable in stable soils.) It is suggested that in the unstable soil, the heat of wetting is associated with aggregate collapse. The degraded structure of the surface layers prevents fast entry of water into the lower layers. The collapse of structure dominates the infiltration process so that the analysis in terms of sorptivity carried out for stable aggregates cannot be made. The effect of entrapped air on slaking of aggregates of these soils is shown to be negligible compared with the effect of initial moisture content. The application of the results to flood irrigation of unstable soils under field conditions is briefly considered.

Sign in / Sign up

Export Citation Format

Share Document