Jie Dou

Automatic Case-Based Reasoning Approach for Landslide Detection: Integration of Object-Oriented Image Analysis and a Genetic Algorithm

This paper proposes an automatic method for detecting landslides by using an integrated approach comprising object-oriented image analysis (OOIA), a genetic algorithm (GA), and a case-based reasoning (CBR) technique. It consists of three main phases: (1) image processing and multi-image segmentation; (2) feature optimization; and (3) detecting landslides. The proposed approach was employed in a fast-growing urban region, the Pearl River Delta in South China. The results of detection were validated with the help of field surveys. The experimental results indicated that the proposed OOIA-GA-CBR (0.87) demonstrates higher classification performance than the stand-alone OOIA (0.75) method for detecting landslides. The area under curve (AUC) value was also higher than that of the simple OOIA, indicating the high efficiency of the proposed landslide detection approach. The case library created using the integrated model can be reused for time-independent analysis, thus rendering our approach superior in comparison to other traditional methods, such as the maximum likelihood classifier. The results of this study thus facilitate fast generation of accurate landslide inventory maps, which will eventually extend our understanding of the evolution of landscapes shaped by landslide processes.

Optimization of causative factors for landslide susceptibility evaluation using remote sensing and GIS data in parts of Niigata, Japan

This paper assesses the potentiality of certainty factor models (CF) for the best suitable causative factors extraction for landslide susceptibility mapping in the Sado Island, Niigata Prefecture, Japan. To test the applicability of CF, a landslide inventory map provided by National Research Institute for Earth Science and Disaster Prevention (NIED) was split into two subsets: (i) 70% of the landslides in the inventory to be used for building the CF based model; (ii) 30% of the landslides to be used for the validation purpose. A spatial database with fifteen landslide causative factors was then constructed by processing ALOS satellite images, aerial photos, topographical and geological maps. CF model was then applied to select the best subset from the fifteen factors. Using all fifteen factors and the best subset factors, landslide susceptibility maps were produced using statistical index (SI) and logistic regression (LR) models. The susceptibility maps were validated and compared using landslide locations in the validation data. The prediction performance of two susceptibility maps was estimated using the Receiver Operating Characteristics (ROC). The result shows that the area under the ROC curve (AUC) for the LR model (AUC = 0.817) is slightly higher than those obtained from the SI model (AUC = 0.801). Further, it is noted that the SI and LR models using the best subset outperform the models using the fifteen original factors. Therefore, we conclude that the optimized factor model using CF is more accurate in predicting landslide susceptibility and obtaining a more homogeneous classification map. Our findings acknowledge that in the mountainous regions suffering from data scarcity, it is possible to select key factors related to landslide occurrence based on the CF models in a GIS platform. Hence, the development of a scenario for future planning of risk mitigation is achieved in an efficient manner.

GIS-Based Landslide Susceptibility Mapping Using a Certainty Factor Model and Its Validation in the Chuetsu Area, Central Japan

The principal aim of this study is to assess the landslide susceptibility in the Chuetsu area, Niigata Prefecture, Central Japan, using a certainty factor model in a GIS environment. The landslide inventory data used in this study were obtained from the National Research Institute for Earth Science and Disaster Prevention (NIED). The data were divided into two groups: one for training the model and the other for its validation. Seven relative factors, elevation, slope angle, slope aspect, density of geological boundary, density of drainage network, plan curvature, and lithology were utilized for this susceptibility analysis. Based on the aforementioned correlative factors, a landslide susceptibility map was produced and then verified using receiver operating characteristics (ROC). The value of area under the ROC curve (AUC) of the constructed CF model is 0.82. A model with such a high AUC value is considered good and therefore acceptable in predicting landslides. The landslide susceptibility map prepared in this study can hence be used to mitigate risks associated with landslides in the study area.

Automatic detection of sinkhole collapses at finer resolutions using a multi-component remote sensing approach

Abstract Sinkhole development is a typical geological disaster found in areas of carbonate bedrock. Compared with other geological disasters, sinkholes are considerably smaller and scattered according to scale and spatial distribution. Nevertheless, detecting and investigating sinkholes have become increasingly challenging. This study proposes a novel method by applying case-based reasoning (CBR) combined with object-based image analysis and genetic algorithms (GAs) to detect the sinkholes using high-resolution aerial images. This case study was performed in Paitan Town, Guangdong Province, China. The method comprises three major steps: (1) multi-image segmentation, (2) GA-based feature selection, and (3) application of CBR techniques. The detected sinkholes were categorized into three classes: buried, collapse type I, and collapse type II. The experiment demonstrated that the proposed method can obtain higher accuracy compared with the traditional supervised maximum likelihood classifier (MLC). The overall accuracy of CBR classification and MLC for the collapse area was 0.88 and 0.71, respectively. In addition, the kappa coefficient for CBR classification (0.81) was higher than that for MLC (0.5). A similar case library was also applied to another trial area for validation, the satisfactory results of which suggested that CBR is applicable for independently detecting sinkholes. The proposed method will be useful for preparing hazard maps that express the relative probability of a collapse in similar regions.

On the Kaolinite Floc Size at the Steady State of Flocculation in a Turbulent Flow.

The flocculation of cohesive fine-grained sediment plays an important role in the transport characteristics of pollutants and nutrients absorbed on the surface of sediment in estuarine and coastal waters through the complex processes of sediment transport, deposition, resuspension and consolidation. Many laboratory experiments have been carried out to investigate the influence of different flow shear conditions on the floc size at the steady state of flocculation in the shear flow. Most of these experiments reported that the floc size decreases with increasing shear stresses and used a power law to express this dependence. In this study, we performed a Couette-flow experiment to measure the size of the kaolinite floc through sampling observation and an image analysis system at the steady state of flocculation under six flow shear conditions. The results show that the negative correlation of the floc size on the flow shear occurs only at high shear conditions, whereas at low shear conditions, the floc size increases with increasing turbulent shear stresses regardless of electrolyte conditions. Increasing electrolyte conditions and the initial particle concentration could lead to a larger steady-state floc size.

Shoreline and Coastal Morphological Changes Induced by the 2004 Indian Ocean Tsunami in the Katchal Island, Andaman and Nicobar – A Study Using Archived Satellite Images

The December 24, 2004 Sumatra earthquake and Tsunami had caused large damage to the coastal environment in the Indian Ocean countries. Continuous monitoring of shorelines are needed to understand the causes and consequences of recent changes and to assess the long term impact of tsunami waves. Assessment of the shoreline and coastal morphological changes due to tsunami in Katchal Island have been lacking due to obstacles in the field data acquisition owing to their remote location. As access to the ground information is limited, the only possibility is the monitoring of shorelines from multi-temporal satellite images.

TXT-tool 1.081-6.1 A Comparative Study of the Binary Logistic Regression (BLR) and Artificial Neural Network (ANN) Models for GIS-Based Spatial Predicting Landslides at a Regional Scale

This teaching tool is to present how to generate the landslide susceptibility maps using binary logistic regression (BLR) and artificial neural network (ANN) methods at a regional scale. The study area is one of most landslide-prone areas in Japan. First, the landslide inventory data from the National Research Institute for Earth Science and Disaster Prevention (NIED) were randomly partitioned into two parts: training and testing data. Then, 10 m DEM data and geology map were analyzed to extract the landslide predisposing factors. Next, the susceptibility maps were produced in a geographic information system (GIS) environment. Then, the receiver operating characteristics (ROC) was used to assess the model accuracy. Validation results show that both of two methods can be obtained with acceptable results. The maps can provide useful information for the future planning of hazard mitigation.

Characteristics of the Torrential Rainfall-Induced Shallow Landslides by Typhoon Bilis, in July 2006, Using Remote Sensing and GIS

During July 14–16, 2006 Typhoon Bilis swept over the southern China. The typhoon brought torrential downpour, resulting in many shallow landslides in the region. This study describes the characteristics of the landslides in an area around the Dongjiang Reservoir, Hunan Province, which was seriously affected by the event. We sketch the landslide occurrences and extreme rainfall event in the study area based on the high-resolution QuickBird images, medium-scale China-Brazil Earth Resources Satellite (CBERS) images, rain gauge data, a digital elevation model, and field surveys. All the satellite images, rain gauge points, geological maps, and field notes were processed and constructed into a spatial database in a GIS platform. The landslide occurrences in the study area before the event was low, and significantly increased during and after Typhoon Bilis of 2006. The short duration, high-intensity rainfall was the major triggering factor. In addition, topographical factors such as slope and aspect also contributed to landslide occurrence. The combined influence of rainfall and the topographic factors. The paper attempts to provide a better understanding of the rainfall and causative factors of landslides in the wake of typhoon Bilis.