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.

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3%of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.

Modelling of piping collapses and gully headcut landforms: Evaluating topographic variables from different types of DEM

The geomorphic studies are extremely dependent on the quality and spatial resolution of digital elevation model(DEM)data.The unique terrain characteristics of a particular landscape are derived from DEM,which are responsible for initiation and development of ephemeral gullies.As the topographic features of an area significantly influences on the erosive power of the water flow,it is an important task the extraction of terrain features from DEM to properly research gully erosion.Alongside,topography is highly correlated with other geo-environmental factors i.e.geology,climate,soil types,vegetation density and floristic composition,runoff generation,which ultimately influences on gully occurrences.Therefore,terrain morphometric attributes derived from DEM data are used in spatial prediction of gully erosion susceptibility(GES)mapping.In this study,remote sensing-Geographic information system(GIS)techniques coupled with machine learning(ML)methods has been used for GES mapping in the parts of Semnan province,Iran.Current research focuses on the comparison of predicted GES result by using three types of DEM i.e.Advanced Land Observation satellite(ALOS),ALOS World 3D-30 m(AW3D30)and Advanced Space borne Thermal Emission and Reflection Radiometer(ASTER)in different resolutions.For further progress of our research work,here we have used thirteen suitable geo-environmental gully erosion conditioning factors(GECFs)based on the multi-collinearity analysis.ML methods of conditional inference forests(Cforest),Cubist model and Elastic net model have been chosen for modelling GES accordingly.Variable’s importance of GECFs was measured through sensitivity analysis and result show that elevation is the most important factor for occurrences of gullies in the three aforementioned ML methods(Cforest=21.4,Cubist=19.65 and Elastic net=17.08),followed by lithology and slope.Validation of the model’s result was performed through area under curve(AUC)and other statistical indices.The validation result of AUC has shown that Cforest is the most appropriate model for predicting the GES assessment in three different DEMs(AUC value of Cforest in ALOS DEM is 0.994,AW3D30 DEM is 0.989 and ASTER DEM is 0.982)used in this study,followed by elastic net and cubist model.The output result of GES maps will be used by decision-makers for sustainable development of degraded land in this study area.

Soil Physical Quality of Citrus Orchards Under Tillage, Herbicide, and Organic Managements

Soil capacity to support life and to produce economic goods and services is strongly linked to the maintenance of good soil physical quality(SPQ). In this study, the SPQ of citrus orchards was assessed under three different soil managements, namely no-tillage using herbicides, tillage under chemical farming, and no-tillage under organic farming. Commonly used indicators, such as soil bulk density,organic carbon content, and structural stability index, were considered in conjunction with capacitive indicators estimated by the Beerkan estimation of soil transfer parameter(BEST) method. The measurements taken at the L'Alcoleja Experimental Station in Spain yielded optimal values for soil bulk density and organic carbon content in 100% and 70% of cases for organic farming. The values of structural stability index indicated that the soil was stable in 90% of cases. Differences between the soil management practices were particularly clear in terms of plant-available water capacity and saturated hydraulic conductivity. Under organic farming, the soil had the greatest ability to store and provide water to plant roots, and to quickly drain excess water and facilitate root proliferation.Management practices adopted under organic farming(such as vegetation cover between the trees, chipping after pruning, and spreading the chips on the soil surface) improved the SPQ. Conversely, the conventional management strategies unequivocally led to soil degradation owing to the loss of organic matter, soil compaction, and reduced structural stability. The results in this study show that organic farming has a clear positive impact on the SPQ, suggesting that tillage and herbicide treatments should be avoided.

Contrasted Impact of Land Abandonment on Soil Erosion in Mediterranean Agriculture Fields

Abandonment of agricultural land results in on-and off-site consequences for the ecosystem. In this study, 105 rainfall simulations were carried out in agriculture lands of the Mediterranean belt in Spain(vineyards in Málaga, almond orchards in Murcia, and orange and olive orchards in Valencia) and in paired abandoned lands to assess the impact of land abandonment on soil and water losses. After abandonment, soil detachment decreased drastically in the olive and orange orchards, while vineyards did not show any difference and almond orchards registered higher erosion rates after the abandonment. Terraced orchards of oranges and olives recovered a dense vegetation cover after the abandonment, while the sloping terrain of almond orchards and vineyards enhanced the development of crusts and rills and a negligible vegetation cover resulted in high erosion rates. The contrasted responses to land abandonment in Mediterranean agricultural lands suggest that land abandonment should be programmed and managed with soil erosion control strategies for some years to avoid land degradation.