Multi-step ahead soil temperature forecasting at different depths based on meteorological data:Integrating resampling algorithms and machine learning models

Direct soil temperature(ST)measurement is time-consuming and costly;thus,the use of simple and cost-effective machine learning(ML)tools is helpful.In this study,ML approaches,including KStar,instance-based K-nearest learning(IBK),and locally weighted learning(LWL),coupled with resampling algorithms of bagging(BA)and dagging(DA)(BA-IBK,BA-KStar,BA-LWL,DA-IBK,DA-KStar,and DA-LWL)were developed and tested for multi-step ahead(3,6,and 9 d ahead)ST forecasting.In addition,a linear regression(LR)model was used as a benchmark to evaluate the results.A dataset was established,with daily ST time-series at 5 and 50 cm soil depths in a farmland as models’output and meteorological data as models’input,including mean(T_(mean)),minimum(Tmin),and maximum(T_(max))air temperatures,evaporation(Eva),sunshine hours(SSH),and solar radiation(SR),which were collected at Isfahan Synoptic Station(Iran)for 13 years(1992–2005).Six different input combination scenarios were selected based on Pearson’s correlation coefficients between inputs and outputs and fed into the models.We used 70%of the data to train the models,with the remaining 30%used for model evaluation via multiple visual and quantitative metrics.Our?ndings showed that T_(mean)was the most effective input variable for ST forecasting in most of the developed models,while in some cases the combinations of variables,including T_(mean)and T_(max)and T_(mean),T_(max),Tmin,Eva,and SSH proved to be the best input combinations.Among the evaluated models,BA-KStar showed greater compatibility,while in most cases,BA-IBK and-LWL provided more accurate results,depending on soil depth.For the 5 cm soil depth,BA-KStar had superior performance(i.e.,Nash-Sutcliffe efficiency(NSE)=0.90,0.87,and 0.85 for 3,6,and 9 d ahead forecasting,respectively);for the 50 cm soil depth,DA-KStar outperformed the other models(i.e.,NSE=0.88,0.89,and 0.89 for 3,6,and 9 d ahead forecasting,respectively).The results con?rmed that all hybrid models had higher prediction capabilities than the LR model.

Spatial variability of soil water erosion:Comparing empirical and intelligent techniques

Soil water erosion(SWE)is an important global hazard that affects food availability through soil degradation,a reduction in crop yield,and agricultural land abandonment.A map of soil erosion susceptibility is a first and vital step in land management and soil conservation.Several machine learning(ML)algorithms optimized using the Grey Wolf Optimizer(GWO)metaheuristic algorithm can be used to accurately map SWE susceptibility.These optimized algorithms include Convolutional Neural Networks(CNN and CNN-GWO),Support Vector Machine(SVM and SVM-GWO),and Group Method of Data Handling(GMDH and GMDH-GWO).Results obtained using these algorithms can be compared with the well-known Revised Universal Soil Loss Equation(RUSLE)empirical model and Extreme Gradient Boosting(XGBoost)ML tree-based models.We apply these methods together with the frequency ratio(FR)model and the Information Gain Ratio(IGR)to determine the relationship between historical SWE data and controlling geo-environmental factors at 116 sites in the Noor-Rood watershed in northern Iran.Fourteen SWE geo-environmental factors are classified in topographical,hydro-climatic,land cover,and geological groups.We next divided the SWE sites into two datasets,one for model training(70%of the samples=81 locations)and the other for model validation(30%of the samples=35 locations).Finally the model-generated maps were evaluated using the Area under the Receiver Operating Characteristic(AU-ROC)curve.Our results show that elevation and rainfall erosivity have the greatest influence on SWE,while soil texture and hydrology are less important.The CNN-GWO model(AU-ROC=0.85)outperformed other models,specifically,and in order,SVR-GWO=GMDH-GWO(AUC=0.82),CNN=GMDH(AUC=0.81),SVR=XGBoost(AUC=0.80),and RULSE.Based on the RUSLE model,soil loss in the Noor-Rood watershed ranges from 0 to 2644 t ha^(-1)yr^(-1).