Estimating the soil water retention curve: Comparison of multiple nonlinear regression approach and random forest data mining technique

Abstract

This study evaluates the performance of the random forest (RF) method on the prediction of the soil water retention curve (SWRC) and compares its performance with those of nonlinear regression (NLR) and Rosettabased pedotransfer functions (PTFs), which has not been reported so far. Fifteen RF and NLR-based PTFs were constructed using readily-available soil properties for 223 soil samples from Iran. The general performance of RF and NLR-based PTFs was quantified by the integral root mean square error (IRMSE), Akaike's information criterion (AIC) and coefficient of determination (R 2 ). The results showed that the accuracy of the RF-based PTFs was significantly (P < 0.05) better than the NLR-based PTFs, and that the reliability of the NLR-based PTFs was significantly (P < 0.01) better than the RF-based PTFs and all of the Rosetta-based PTFs. The average values of the IRMSE, AIC and R 2 of the RF method were 0.041 cm 3 cm −3 , −16997.7, and 0.987, and 0.053 cm 3 cm −3 , −15547.5, and 0.981 for the training and testing steps of all PTFs, respectively, whereas the values for the NLR method were 0.046 cm 3 cm −3 , −16616.4, and 0.984, and 0.048 cm 3 cm −3 , −16355.6, and 0.983 for the training and testing steps, respectively. The PTF5 of the RF and NLR methods, with inputs of sand and clay contents, bulk density, and the water content at field capacity and permanent wilting point, had the greatest R 2 values (0.987 and 0.989, respectively), and the lowest IRMSE values (0.039 and 0.032 cm 3 cm −3 , respectively) compared to other PTFs for the testing step. Overall, the RF method had less reliability for the prediction of the SWRC compared to the NLR method due to overprediction, uncertainty of determination of forest scale and instability in the testing step. These findings could provide the scientific basis for further research on the RF method.

Data analysis and personalized recommendation of western music history information using deep learning under Internet of Things

“…To sum up, as a novel research direction, EDM has rich research contents and diverse research methods [ 20 ]. Personalized learning is a pivotal research topic of EDM.…”

Analysis of the Forecast Price as a Factor of Sustainable Development of Agriculture

“…As a forecasting method, we will choose extrapolation since the internal transportation of sugar is characterized by the time and volume of the transported cargo. Many models allow forecasting with varying degrees of accuracy: correlation-regression analysis [4][5][6][7], neural network models [8,9], research-based on multiple regression [10][11][12], models based on classification-regression trees [13,14], maximum likelihood sampling models [15][16][17] and many others [18][19][20][21]. For forecasting economic time series, models of the ARIMA class are used [22].…”

Analysis of Influencing Factors on Winter Wheat Yield Estimations Based on a Multisource Remote Sensing Data Fusion

“…The RFR method uses an ensemble of decision trees, which usually vote or are averaged to obtain the final result (Zouggar and Adla, 2019;Rastgou et al, 2020). RFR does not easily fall into overfitting and is more robust than other methods in terms of noise due to the introduction of randomness.…”