Neural networks and landslide susceptibility: a case study of the urban area of Potenza

For those working in the field of landslide prevention, the estimation of hazard levels and the consequent production of thematic maps are principal objectives. They are achieved through careful analytical studies of the characteristics of landslide prone areas, thus, providing useful information regarding possible future phenomena. Such maps represent a fundamental step in the drawing up of adequate measures of landslide hazard mitigation. However, for a complete estimation of landslide hazard, meant as the degree of probability that a landslide occurs in a given area, within a given space of time, detailed and uniformly distributed data regarding their incidence and causes are required. This information, while obtainable through laborious historical research, is usually partial, incomplete and uneven, and hence, unsatisfactory for zoning on a regional scale. In order to carry this out effectively, the utilization of spatial estimation of the relative levels of landslide hazard in the various areas was considered opportune. These areas were classified according to their levels of proneness to landslide activity without taking recurrence periods into account. Various techniques were developed in order to obtain upheaval numerical estimates. The method used in this study, which was applied in the area of Potenza, is based on techniques derived from artificial intelligence (Artificial Neural Network—ANN). This method requires the definition of appropriate thematic layers, which parameterize the area under study. These are recognized by means of specific analyses in a functional relationship to the event itself. The parameters adopted are: slope gradient, slope aspect, topographical index, topographical shape, elevation, land use and lithology.     

Determination and application of the weights for landslide susceptibility mapping using an artificial neural network

The purpose of this study is the development, application, and assessment of probability and artificial neural network methods for assessing landslide susceptibility in a chosen study area. As the basic analysis tool, a Geographic Information System (GIS) was used for spatial data management and manipulation. Landslide locations and landslide-related factors such as slope, curvature, soil texture, soil drainage, effective thickness, wood type, and wood diameter were used for analyzing landslide susceptibility. A probability method was used for calculating the rating of the relative importance of each factor class to landslide occurrence. For calculating the weight of the relative importance of each factor to landslide occurrence, an artificial neural network method was developed. Using these methods, the landslide susceptibility index (LSI) was calculated using the rating and weight, and a landslide susceptibility map was produced using the index. The results of the landslide susceptibility analysis, with and without weights, were confirmed from comparison with the landslide location data. The comparison result with weighting was better than the results without weighting. The calculated weight and rating can be used to landslide susceptibility mapping.     

Implementation of reconstructed geomorphologic units in landslide susceptibility mapping: the Melen Gorge (NW Turkey)

In the international literature, although considerable amount of publications on the landslide susceptibility mapping exist, geomorphology as a conditioning factor is still used in limited number of studies. Considering this factor, the purpose of this article paper is to implement the geomorphologic parameters derived by reconstructed topography in landslide susceptibility mapping. According to the method employed in this study, terrain is generalized by the contours passed through the convex slopes of the valleys that were formed by fluvial erosion. Therefore, slope conditions before landsliding can be obtained. The reconstructed morphometric and geomorphologic units are taken into account as a conditioning parameter when assessing landslide susceptibility. Two different data, one of which is obtained from the reconstructed DEM, have been employed to produce two landslide susceptibility maps. The binary logistic regression is used to develop landslide susceptibility maps for the Melen Gorge in the Northwestern part of Turkey. Due to the high correct classification percentages and spatial effectiveness of the maps, the landslide susceptibility map comprised the reconstructed morphometric parameters exhibits a better performance than the other. Five different datasets are selected randomly to apply proper sampling strategy for training. As a consequence of the analyses, the most proper outcomes are obtained from the dataset of the reconstructed topographical parameters and geomorphologic units, and lithological variables that are implemented together. Correct classification percentage and root mean square error (RMSE) values of the validation dataset are calculated as 86.28% and 0.35, respectively. Prediction capacity of the different datasets reveal that the landslide susceptibility map obtained from the reconstructed parameters has a higher prediction capacity than the other. Moreover, the landslide susceptibility map obtained from the reconstructed parameters produces logical results.     

A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas

Landslides are one of the most destructive phenomena of nature that cause damage to both property and life every year, and therefore, landslide susceptibility zonation (LSZ) is necessary for planning future developmental activities. In this paper, apart from conventional weighting system, objective weight assignment procedures based on techniques such as artificial neural network (ANN), fuzzy set theory and combined neural and fuzzy set theory have been assessed for preparation of LSZ maps in a part of the Darjeeling Himalayas. Relevant thematic layers pertaining to the causative factors have been generated using remote sensing data, field surveys and Geographic Information System (GIS) tools. In conventional weighting system, weights and ratings to the causative factors and their categories are assigned based on the experience and knowledge of experts about the subject and the study area to prepare the LSZ map (designated here as Map I). In the context of objective weight assignments, initially the ANN as the black box approach has been used to directly produce an LSZ map (Map II). In this approach, however, the weights assigned are hidden to the analyst. Next, the fuzzy set theory has then been implemented to determine the membership values for each category of the thematic layer using the cosine amplitude method (similarity method). These memberships are used as ratings for each category of the thematic layer. Assuming weights of each thematic layer as one (or constant), these ratings of the categories are used for the generation of another LSZ map (Map III). Subsequently, a novel weight assignment procedure based on ANN is implemented to assign the weights to each thematic layer objectively. Finally, weights of each thematic layer are combined with fuzzy set derived ratings to produce another LSZ map (Map IV). The maps I–IV have been evaluated statistically based on field data of existing landslides. Amongst all the procedures, the LSZ map based on combined neural and fuzzy weighting (i.e., Map IV) has been found to be significantly better than others, as in this case only 2.3% of the total area is found to be categorized as very high susceptibility zone and contains 30.1% of the existing landslide area.     

An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps

The main purpose of this study is to highlight the conceptual differences of produced susceptibility models by applying different sampling strategies: from all landslide area with depletion and accumulation zones and from a zone which almost represents pre-failure conditions. Variations on accuracy and precision values of the models constructed considering different algorithms were also investigated. For this purpose, two most popular techniques, logistic regression analysis and back-propagation artificial neural networks were taken into account. The town Ispir and its close vicinity (Northeastern part of Turkey), suffered from landsliding for many years was selected as the application site of this study. As a result, it is revealed that the back-propagation artificial neural network algorithms overreact to the samplings in which the presence (1) data were taken from the landslide masses. When the generalization capacities of the models are taken into consideration, these reactions cause imprecise results, even though the area under curve (AUC) values are very high (0.915 < AUC < 0.949). On the other hand, the susceptibility maps, based on the samplings in which the presence (1) data were taken from a zone which almost represents pre-failure conditions constitute more realistic susceptibility evaluations. However, considering the spatial texture of the final susceptibility values, the maps produced using the outputs of the back-propagation artificial neural networks could be interpreted as highly optimistic, while of those generated using the resultant probabilities of the logistic regression equations might be evaluated as pessimistic. Consequently, it is evident that, there are still some needs for further investigations with more realistic validations and data to find out the appropriate accuracy and precision levels in such kind of landslide susceptibility studies.     

HyLogger-3, a visible to shortwave and thermal infrared reflectance spectrometer system for drill core logging: functional description

Australian Geological Surveys are the custodians of a major national asset in the form of historically drilled and archived drill cores of the top few kilometres of the continent acquired by government agencies and companies over many decades. The AuScope National Virtual Core Library (NVCL) component of the AuScope Earth Model comprises geological/rock samples, technology, people and database/delivery infrastructure located in six nationally distributed nodes and is aimed at extracting additional value from this asset. The technology components of the NVCL comprise an integrated suite of hardware (HyLogger-3) and software (TSG-Core) systems for the imaging and hyperspectral characterisation of drill cores in their original core trays and the interpretation of their contained oxide, carbonate, hydrous and anhydrous silicate mineralogy. The HyLogger-3 includes state-of-the-art Fourier Transform Spectrometers that continuously measure calibrated spectral reflectance from nominal 10 by 18 mm fields of view. These spectra are in turn passed through a series of automatic and semi-automatic pre-processing and mineralogical unmixing algorithms. These, along with numerous other tools in TSG-Core, output a variety of mineralogical and image products for use by scientists in many branches of the earth sciences. This paper provides a functional overview of the HyLogging hardware and software tools available in each of Australia's Geological Surveys.