Early landslide mapping with slope units division and multi-scale objectbased image analysis——A case study in the Xianshui River basin of Sichuan,China

Previous studies on optical remote sensing mapping of landslides mainly focused on new landslides that have occurred, but little attention was paid to the early landslide due to its high concealment. In SAR technology, a prevalent method to detect early landslides, only can be used to identify the potential hazards of slow deformation. Therefore, it is necessary to explore new method of early landslides mapping by integrating all types of direct and indirect early features, such as cracks on slopes, small collapses inside and topographic features. In this study, an object-oriented image analysis method based on slope unit division and multi-scale segmentation was proposed to obtain accurate location and boundary extraction of early landslides. In the middle-and small-scale segmentation, the object, texture, spectrum, geometric features,topographic features, and other features were obtained to determine the local feature location of early landslides. The slope unit boundary was combined with the feature of a large-scale segmentation object to determine the scope of landslides. This method was tested in the Xianshui River basin in the Daofu County, Sichuan Province, China. The results demonstrate that:(1) Such features as landslide cracks and the small collapse at the bottom of slope can effectively determine the landslide position.(2) The slope unit division and the correct setting of shape factors in multiple segmentation can effectively determine the landslide boundary.(3) The accuracy of landslide location extraction was 83.33%, and the accuracy of boundary extraction for early landslides that were completely identified was evaluated as 82.67%. It is indicated that this method can improve the accuracy of boundary extraction and meet the requirements of the early landslides mapping.

Reliable assessment approach of landslide susceptibility in broad areas based on optimal slope units and negative samples involving priori knowledge

Reliable assessment of landslide susceptibility in broad areas of terrain remains challenging due to complex topography and poor representation of randomly selected negative samples.Assessment in broad areas is now primarily based on grid units,which do not have a clear physical meaning like slope units,and their accuracy is not ideal.Nevertheless,the large amount of manual editing,due to the incorrectly generated horizontal and vertical lines during slope unit partitioning,limits using slope units for rapid assessment over large areas.Hence,this paper proposes a reliable susceptibility assessment approach to solve this problem based on optimal slope units and negative samples involving prior knowledge.Precisely,an algorithm to automatically extract slope units is designed to eliminate fragmented and erroneous units.Second,a samples labeling index(SLI)is defined based on the certainty factors model to select negative samples reasonably.Sichuan Province,China is selected for experimental analysis,with the results demonstrate that the optimized slope unit and the negative samples selection strategy consider prior knowledge achieve better results in the random forest model,support vector machine model,and artificial neural network model.In particular,the composite performance index AUC of artificial neural network model improved from 0.81 to 0.90.

Landslide susceptibility prediction using slope unit-based machine learning models considering the heterogeneity of conditioning factors

To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method proposed by the authors promotes the application of slope units.However,LSP modeling based on these slope units has not been performed.Moreover,the heterogeneity of conditioning factors in slope units is neglected,leading to incomplete input variables of LSP modeling.In this study,the slope units extracted by the MSS method are used to construct LSP modeling,and the heterogeneity of conditioning factors is represented by the internal variations of conditioning factors within slope unit using the descriptive statistics features of mean,standard deviation and range.Thus,slope units-based machine learning models considering internal variations of conditioning factors(variant slope-machine learning)are proposed.The Chongyi County is selected as the case study and is divided into 53,055 slope units.Fifteen original slope unit-based conditioning factors are expanded to 38 slope unit-based conditioning factors through considering their internal variations.Random forest(RF)and multi-layer perceptron(MLP)machine learning models are used to construct variant Slope-RF and Slope-MLP models.Meanwhile,the Slope-RF and Slope-MLP models without considering the internal variations of conditioning factors,and conventional grid units-based machine learning(Grid-RF and MLP)models are built for comparisons through the LSP performance assessments.Results show that the variant Slopemachine learning models have higher LSP performances than Slope-machine learning models;LSP results of variant Slope-machine learning models have stronger directivity and practical application than Grid-machine learning models.It is concluded that slope units extracted by MSS method can be appropriate for LSP modeling,and the heterogeneity of conditioning factors within slope units can more comprehensively reflect the relationships between conditioning factors and landslides.The research results have important reference significance for land use and landslide prevention.

Prediction of the instability probability for rainfall induced landslides:the effect of morphological differences in geomorphology within mapping units

Slope units is an effective mapping unit for rainfall landslides prediction at regional scale.At present,slope units extracted by hydrology and morphological method report very different morphological feature and boundaries.In order to investigate the effect of morphological difference on the prediction performance,this paper presents a general landslide probability analysis model for slope units.Monte Carlo method was used to describe the spatial uncertainties of soil mechanical parameters within slope units,and random search technique was performed to obtain the minimum safety factor;transient hydrological processes simulation was used to provide key hydrological parameters required by the model,thereby achieving landslide prediction driven by quantitative precipitation estimation and forecasting data.The prediction performance of conventional slope units(CSUs)and homogeneous slope units(HSUs)were analyzed in three case studies from Fengjie County,China.The results indicate that the mean missing alarm rate of CSUs and HSUs are 31.4% and 10.6%,respectively.Receiver Operating Characteristics(ROC)analysis also reveals that HSUs is capable of improving the overall prediction performance,and may be used further for rainfall-induced landslide prediction at regional scale.

Landslide Hazard Assessment in the Northern Mountainous Areas of Tianshan Mountains Based on GIS

China is a country prone to geological disasters, especially in the northern mountainous areas of the Tianshan Mountains in Xinjiang, where the surface vegetation is sparse and the rainfall is concentrated, which is prone to landslides and brings a lot of losses to the local people. Based on the field investigation, this paper evaluates the landslide susceptibility in the northern mountainous area of Tianshan Mountains. The frequency ratio method is used to calculate the landslide probability, and the landslide index (LSI) is formed to represent the landslide susceptibility. The slope unit method is used to determine the landslide units, which values were calculated by the average of the landslide index. According to the calculated LSI range of 4.53 - 20.60. It is divided into 4 grades, LSI = 4.53 - 9, which is an area that is not prone to landslides, with an area of 891.69 km2. LSI = 9 - 11 indicates an area where landslides are more likely to occur, with an area of 1252.31 km2. LSI = 11 - 13 indicates the area is more prone to landslides, with an area of 714.86 km2. LSI > 13 indicates the most prone area for landslides, with an area of 924.60 km2.