Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.

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).

Comparing the Soil Conservation Service model with new machine learning algorithms for predicting cumulative infiltration in semi-arid regions

Water infiltration into soil is an important process in hydrologic cycle;however,its measurement is difficult,time-consuming and costly.Empirical and physical models have been developed to predict cumulative infiltration(CI),but are often inaccurate.In this study,several novel standalone machine learning algorithms(M5Prime(M5P),decision stump(DS),and sequential minimal optimization(SMO))and hybrid algorithms based on additive regression(AR)(i.e.,AR-M5P,AR-DS,and AR-SMO)and weighted instance handler wrapper(WIHW)(i.e.,WIHW-M5P,WIHW-DS,and WIHW-SMO)were developed for CI prediction.The Soil Conservation Service(SCS)model developed by the United States Department of Agriculture(USDA),one of the most popular empirical models to predict CI,was considered as a benchmark.Overall,154 measurements of CI(explanatory/input variables)were taken from 16 sites in a semi-arid region of Iran(Illam and Lorestan provinces).Six input variable combinations were considered based on Pearson correlations between candidate model inputs(time of measuring and soil bulk density,moisture content,and sand,clay,and silt percentages)and CI.The dataset was divided into two subgroups at random:70%of the data were used for model building(training dataset)and the remaining 30%were used for model validation(testing dataset).The various models were evaluated using different graphical approaches(bar charts,scatter plots,violin plots,and Taylor diagrams)and quantitative measures(root mean square error(RMSE),mean absolute error(MAE),Nash-Sutcliffe efficiency(NSE),and percent bias(PBIAS)).Time of measuring had the highest correlation with CI in the study area.The best input combinations were different for different algorithms.The results showed that all hybrid algorithms enhanced the CI prediction accuracy compared to the standalone models.The AR-M5P model provided the most accurate CI predictions(RMSE=0.75 cm,MAE=0.59 cm,NSE=0.98),while the SCS model had the lowest performance(RMSE=4.77 cm,MAE=2.64 cm,NSE=0.23).The differences in RMSE between the best model(AR-M5P)and the second-best(WIHW-M5P)and worst(SCS)were 40%and 84%,respectively.

Shear stress distribution prediction in symmetric compound channels using data mining and machine learning models

Shear stress distribution prediction in open channels is of utmost importance in hydraulic structural engineering as it directly affects the design of stable channels.In this study,at first,a series of experimental tests were conducted to assess the shear stress distribution in prismatic compound channels.The shear stress values around the whole wetted perimeter were measured in the compound channel with different floodplain widths also in different flow depths in subcritical and supercritical conditions.A set of,data mining and machine learning algorithms including Random Forest(RF),M5P,Random Committee,KStar and Additive Regression implemented on attained data to predict the shear stress distribution in the compound channel.Results indicated among these five models;RF method indicated the most precise results with the highest R2 value of 0.9.Finally,the most powerful data mining method which studied in this research compared with two well-known analytical models of Shiono and Knight method(SKM)and Shannon method to acquire the proposed model functioning in predicting the shear stress distribution.The results showed that the RF model has the best prediction performance compared to SKM and Shannon models.