Mapping and detection of land use change in a coal mining area using object-based image analysis

Object-based image analysis was used to map land use in the Panxie coal mining area, East China, where long-term underground coal mines have been exploited since the 1980s. A rule-based classification approach was developed for a Pleiades image to identify the desired land use classes, and the same rule-based classification strategies, after the threshold values had been modified slightly, were applied to the Landsat series images. Five land use classes were successfully captured with overall accuracies of between 80 and 94%. The classification approach was validated for its flexibility and robustness. Multitemporal classification results indicated that land use changed considerably in the Panxie coal mining area from 1989 to 2013. The urban, coal and coal gangue, and water areas increased rapidly in line with the growth in mine production. Urban areas increased from 9.38 to 20.92% and showed a tendency to increase around the coal mines. From 1989 to 2013 the coal and coal gangue area increased by 40-fold, from 0.02 to 0.58%. Similarly, the water area increased from 2.77 to 7.84% over this time period, mainly attributable to the spread of waterlogged areas. The waterlogged areas increased to about 2900 ha in 2013, which was about 80 times more than their area in 1989. In contrast, the area of cultivated land was negatively related to the increase in mine production and decreased from 73.11 to 57.25%. The results of this study provide a valuable basis for sustainable land management and environmental planning in the Panxie coal mining area.     

Landslide detection in the Himalayas using machine learning algorithms and U-Net

Landslides - Event-based landslide inventories are essential sources to broaden our understanding of the causal relationship between triggering events and the occurring landslides. Moreover,...     

Landslide detection using visualization techniques for deep convolutional neural network models

Natural Hazards - Landslides occur when masses of rock, earth, and other debris move down a slope. The slope of an area is directly responsible for the magnitude of the landslide. Being...     

Landslide identification using machine learning

Landslide identification is critical for risk assessment and mitigation.This paper proposes a novel machinelearning and deep-learning method to identify natural-terrain landslides using integrated geodatabases.First,landslide-related data are compiled,including topographic data,geological data and rainfall-related data.Then,three integrated geodatabases are established;namely,Recent Landslide Database(Rec LD),Relict Landslide Database(Rel LD)and Joint Landslide Database(JLD).After that,five machine learning and deep learning algorithms,including logistic regression(LR),support vector machine(SVM),random forest(RF),boosting methods and convolutional neural network(CNN),are utilized and evaluated on each database.A case study in Lantau,Hong Kong,is conducted to demonstrate the application of the proposed method.From the results of the case study,CNN achieves an identification accuracy of 92.5%on Rec LD,and outperforms other algorithms due to its strengths in feature extraction and multi dimensional data processing.Boosting methods come second in terms of accuracy,followed by RF,LR and SVM.By using machine learning and deep learning techniques,the proposed landslide identification method shows outstanding robustness and great potential in tackling the landslide identification problem.     

An object-based image analysis for building seismic vulnerability assessment using high-resolution remote sensing imagery

Building seismic vulnerability assessment plays an important role in formulating pre-disaster mitigation strategies for developing countries. The occurrence of high-resolution satellite sensors has greatly motivated it by providing a promising approach to obtain building information. However, this also brings a big challenge to the accurate building extraction and its coherent integration with the assessment model. The main objective of this paper is to investigate how to extract building attributes from high-resolution remote sensing imagery using the object-based image analysis (OBIA) method, so as to accurately and conveniently assess building seismic vulnerability by the combination of in situ field data. A general framework for the assessment of building seismic vulnerability is presented, including (1) the extraction of building information using OBIA, (2) building height estimation, and (3) the support vector machine (SVM)-based building seismic vulnerability assessment. Particularly, an integrated solution is proposed that merges the strengths of multiple spatial contextual relationships and some typical image object measures, under the unified framework to improve building information extraction at different scale levels as well as for different interest objects. With the aid of 35 building samples from two powerful earthquakes in China, the cloud-free WorldView-2 images and some building structure parameters from field survey were used to quantity the grades of building seismic vulnerability in Wuhan Optics Valley, China. The results show that all 48 buildings among the study area have been well detected with an overall accuracy of 80.67 % and the mean error of heights estimated from building shadow is less than 2 m. This indicates that the integrated analysis strategy based on OBIA is suitable for extracting the building information from high-resolution remote sensing imagery. Additionally, the assessment results using SVM show that the building seismic vulnerability is statistically significantly related to structure types and building heights. Both the proposed OBIA method and its integration strategy with SVM are easily implemented and provide readily interpretable assessment results for building seismic vulnerability. This reveals that the proposed method has a great potential to assist urban planners for making local disaster mitigation planning through the prioritization of intervention measures, such as the reinforcement of walls and the dismantlement of endangered houses.     

Landslide susceptibility assessment using SVM machine learning algorithm

This paper introduces the current machine learning approach to solving spatial modeling problems in the domain of landslide susceptibility assessment. The latter is introduced as a classification problem, having multiple (geological, morphological, environmental etc.) attributes and one referent landslide inventory map from which to devise the classification rules. Three different machine learning algorithms were compared: Support Vector Machines, Decision Trees and Logistic Regression. A specific area of the Fruška Gora Mountain (Serbia) was selected to perform the entire modeling procedure, from attribute and referent data preparation/processing, through the classifiers' implementation to the evaluation, carried out in terms of the model's performance and agreement with the referent data. The experiments showed that Support Vector Machines outperformed the other proposed methods, and hence this algorithm was selected as the model of choice to be compared with a common knowledge-driven method – the Analytical Hierarchy Process – to create a landslide susceptibility map of the relevant area. The SVM classifier outperformed the AHP approach in all evaluation metrics (κ index, area under ROC curve and false positive rate in stable ground class).     

Earthquake risk assessment in NE India using deep learning and geospatial analysis

Earthquake prediction is currently the most crucial task required for the probability, hazard, risk mapping, and mitigation purposes. Earthquake prediction attracts the researchers' attention from both academia and industries. Traditionally, the risk assessment approaches have used various traditional and machine learning models. However, deep learning techniques have been rarely tested for earthquake probability mapping. Therefore, this study develops a convolutional neural network (CNN) model for earthquake probability assessment in NE India. Then conducts vulnerability using analytical hierarchy process (AHP), Venn's intersection theory for hazard, and integrated model for risk mapping. A prediction of classification task was performed in which the model predicts magnitudes more than 4 Mw that considers nine indicators. Prediction classification results and intensity variation were then used for probability and hazard mapping, respectively. Finally, earthquake risk map was produced by multiplying hazard, vulnerability, and coping capacity. The vulnerability was prepared by using six vulnerable factors, and the coping capacity was estimated by using the number of hospitals and associated variables, including budget available for disaster management. The CNN model for a probability distribution is a robust technique that provides good accuracy. Results show that CNN is superior to the other algorithms, which completed the classification prediction task with an accuracy of 0.94, precision of 0.98, recall of 0.85, and F1 score of 0.91. These indicators were used for probability mapping, and the total area of hazard (21,412.94 km²), vulnerability (480.98 km²), and risk (34,586.10 km²) was estimated.     

A maximum entropy method using fractional moments and deep learning for geotechnical reliability analysis

Acta Geotechnica - The spatial variability of the properties of natural soils is one of the major sources of uncertainties that can influence the performance of geotechnical structures. The direct...     

Zircon classification from cathodoluminescence images using deep learning

Zircon is a widely-used heavy mineral in geochronological and geochemical research because it can extract important information to understand the history and genesis of rocks. Zircon has various types, and an accurate examination of zircon type is a prerequisite procedure before further analysis. Cathodoluminescence (CL) imaging is one of the most reliable ways to classify zircons. However, current CL image examination is conducted by manual work, which is time-consuming, bias-prone, and requires expertise. An automated and bias-free method for zircon classification is absent but necessary. To this end, deep convolutional neural networks (DCNNs) and transfer learning are applied in this study to classify the common types of zircons, i.e., igneous, metamorphic, and hydrothermal zircons. An atlas with over 4000 CL images of these three types of zircons is created, and three DCNNs are trained using these images. The results of this study indicate that the DCNNs can distinguish hydrothermal zircons from other zircons, as indicated by the highest accuracy of 100%. Although similar textures in igneous and metamorphic zircons pose great challenges for zircon classification, the DCNNs successfully classify 95% igneous and 92% metamorphic zircons. This study demonstrates the high accuracy of DCNNs in zircon classification and presents the great potentiality of deep learning techniques in numerous geoscientific disciplines.     

Landslide prediction from machine learning

Predicting where and when landslides are likely to occur in a specific region of interest remains a key challenge in natural hazards research and mitigation. While the basic mechanics of slope‐failure initiation and runout can be cast into physical and numerical models, a scarcity of sufficiently detailed and real‐time measurements of soil, rock‐mass and groundwater conditions prohibits accurate landslide forecasting. Researchers are therefore increasingly exploring multivariate data analysis techniques from the fields of data mining or machine learning in order to approximate future occurrences of landslides from past distribution patterns. This work has elucidated patterns of spatial susceptibility, but temporal forecasts have remained largely empirical. Most machine learning techniques achieve overall success rates of 75–95 percent. Whilst this may seem very promising, issues remain with data input quality, potential overfitting and commensurate inadequate choice of prediction models, inadvertent inclusion of redundant or noise variables, and technical limits to predicting only certain types and sizes of landslides. Simpler models provide only slightly inferior predictions to more complex models, and should guide the way for a more widespread application of data mining in regional landslide prediction. This approach should especially be communicated to planners and decision makers. Future research may want to develop: (1) further best‐practice guidelines for model selection; (2) predictions of occurrence and runout of large slope failures at the regional scale; and (3) temporal forecasts of landslides.     

Landslide susceptibility zonation using statistical and machine learning approaches in Northern Lecco,Italy

This study deals with landslide susceptibility mapping in the northern part of Lecco Province, Lombardy Region, Italy. In so doing, a valid landslide inventory map and thirteen predisposing factors (including elevation, slope aspect, slope degree, plan curvature, profile curvature, distance to waterway, distance to road, distance to fault, soil type, land use, lithology, stream power index, and topographic wetness index) form the spatial database within geographic information system. The used predictive models comprise a bivariate statistical approach called frequency ratio (FR) and two machine learning tools, namely multilayer perceptron neural network (MLPNN) and adaptive neuro-fuzzy inference system (ANFIS). These models first use landslide and non-landslide records for comprehending the relationship between the landslide occurrence and predisposing factors. Then, landslide susceptibility values are predicted for the whole area. The accuracy of the produced susceptibility maps is measured using area under the curve (AUC) index, according to which, the MLPNN (AUC?=?0.916) presented the most accurate map, followed by the ANFIS (AUC?=?0.889) and FR (AUC?=?0.888). Visual interpretation of the susceptibility maps, FR-based correlation analysis, as well as the importance assessment of predisposing factors, all indicated the significant contribution of the road networks to the crucial susceptibility of landslide. Lastly, an explicit predictive formula is extracted from the implemented MLPNN model for a convenient approximation of landslide susceptibility value.

     

An optimized object-based analysis for vegetation mapping using integration of Quickbird and Sentinel-1 data

This study proposed a workflow for an optimized object-based analysis for vegetation mapping using integration of Quickbird and Sentinel-1 data. The method is validated on a set of data captured over a part of Selangor located in the Peninsular Malaysia. The method comprised four components including image segmentation, Taguchi optimization, attribute selection using random forest, and rule-based feature extraction. Results indicated the robustness of the proposed approach as the area under curve of forest; grassland, old oil palm, rubber, urban tree, and young oil palm were calculated as 0.90, 0.89, 0.87, 0.87, 0.80, and 0.77, respectively. In addition, results showed that SAR data is very useful for extracting rubber and young oil palm trees (given by random forest importance values). Finally, further research is suggested to improve segmentation results and extract more features from the scene.     

Best optimizer selection for predicting bushfire occurrences using deep learning

Natural Hazards - Natural disasters like bushfires pose a catastrophic threat to the Australia and the world’s territorial areas. This fire spreads in a wide area within seconds, and...     

Optimized object-based image classification: development of landslide knowledge decision support system

Landslide spatial decision support systems (LS-DSS) are computer-based systems that combine the geographic storage, search, and retrieval capabilities of geographic information systems with the decision models and optimizing algorithms used to support decision-making for landslide problems. This study proposes an optimization process of region object-oriented classification (ROC) to analyze the landslide image information. The surface information from the Wan Da reservoir area is collected and studied. We collected different spectrum with several texture information to analyze the surrounding area of the Wan Da reservoir. ROC is used to classify the landslide area. Entropy-based classification is used as a classifier in ROC to determine the landslide/nonlandslide area. The parameters of S (similarity) and A (area) are used and then the best combinations are found. An optimize algorithm is developed to access the above variables to perform the best classification outcomes. The relations of occurrence vs. non-occurrence of landslide which are linked to the attributes of land surface are studied. An improved translation model (Expert Knowledge Translation Platform) is also presented to increase the accuracy. This could be of help to manage/monitor the landslide area near the reservoir.     

Modelling the performance of EPB shield tunnelling using machine and deep learning algorithms

This paper introduces an intelligent framework for predicting the advancing speed during earth pressure balance(EPB) shield tunnelling. Five artificial intelligence(AI) models based on machine and deep learning techniques—back-propagation neural network(BPNN), extreme learning machine(ELM), support vector machine(SVM),long-short term memory(LSTM), and gated recurrent unit(GRU)—are used. Five geological and nine operational parameters that influence the advancing speed are considered. A field case of shield tunnelling in Shenzhen City,China is analyzed using the developed models. A total of 1000 field datasets are adopted to establish intelligent models. The prediction performance of the five models is ranked as GRU LSTM SVM ELM BPNN. Moreover, the Pearson correlation coefficient(PCC) is adopted for sensitivity analysis. The results reveal that the main thrust(MT), penetration(P), foam volume(FV), and grouting volume(GV) have strong correlations with advancing speed(AS). An empirical formula is constructed based on the high-correlation influential factors and their corresponding field datasets. Finally, the prediction performances of the intelligent models and the empirical method are compared. The results reveal that all the intelligent models perform better than the empirical method.     

Landslide detection based on height and amplitude differences using pre- and post-event airborne X-band SAR data

Natural Hazards - The recognition of landslides and making their inventory map are considered to be urgent tasks not only for damage estimation but also for planning rescue and restoration...     

An integrated object-based image analysis and CA-Markov model approach for modeling land use/land cover trends in the Sarab plain

The present paper is an attempt to integrate a semi-automated object-based image analysis (OBIA) classification framework and a cellular automata-Markov model to study land use/land cover (LULC) changes. Land use maps for the Sarab plain in Iran for the years 2000, 2006, and 2014 were created from Landsat satellite data, by applying an OBIA classification using the normalized difference vegetation index, salinity index, moisture stress index, soil-adjusted vegetation index, and elevation and slope indicators. The classifications yielded overall accuracies of 91, 93, and 94% for 2000, 2006, and 2014, respectively. Finally, using the transition matrix, the spatial distribution of land use was simulated for 2020. The results of the study revealed that the number of orchards with irrigated agriculture and dry-farm agriculture in the Sarab plain is increasing, while the amount of bare land is decreasing. The results of this research are of great importance for regional authorities and decision makers in strategic land use planning.