Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Case revision has always been challenging in case-based reasoning (CBR) processes. Most CBR methods used for analyzing geological disasters fail to consider the spatial relationships among geological environmental factors. Therefore, conventional case revision rules do not allow for effective case-based reasoning for geologic disaster assessment. I...
Context in source publication
Context 1
... traditional data mining method is comprised of several widely-used methods for geological disaster assessments and risk predictions, such as the analytic hierarchy process (AHP) ( Liang et al. 2011;Liu et al. 2013;Sun et al. 2015), artificial neural network (ANN) ( Chen et al. 2013;Lv et al. 2014), and bayesian network (BN) (Sousa and Einstein 2012). Table 7 lists the results obtained using these methods. ...Citations
... As a mature branch of artificial intelligence, case-based reasoning (CBR) has been widely applied in other fields [23]. CBR has greater classification performance compared with traditional data mining methods [24] and it has also shown excellent performance in fields like fault diagnosis [25][26][27], risk assessment [28,29], and forest fire prediction [30][31][32]. It should be noted that the weights of case characteristic attributes in CBR have a significant impact on the prediction performance of the model. ...
Accurate prediction of the coal spontaneous combustion hazard grades is of great significance to ensure the safe production of coal mines. However, traditional coal temperature prediction models have low accuracy and do not predict the coal spontaneous combustion hazard grades. In order to accurately predict coal spontaneous combustion hazard grades, a prediction model of coal spontaneous combustion based on principal component analysis (PCA), case-based reasoning (CBR), fuzzy clustering (FM), and the snake optimization (SO) algorithm was proposed in this manuscript. Firstly, based on the change rule of the concentration of signature gases in the process of coal warming, a new method of classifying the risk of spontaneous combustion of coal was established. Secondly, MeanRadius-SMOTE was adopted to balance the data structure. The weights of the prediction indicators were calculated through PCA to enhance the prediction precision of the CBR model. Then, by employing FM in the case base, the computational cost of CBR was reduced and its computational efficiency was improved. The SO algorithm was used to determine the hyperparameters in the PCA-FM-CBR model. In addition, multiple comparative experiments were conducted to verify the superiority of the model proposed in this manuscript. The results indicated that SO-PCA-FM-CBR possesses good prediction performance and also improves computational efficiency. Finally, the authors of this manuscript adopted the Random Balance Designs—Fourier Amplitude Sensitivity Test (RBD-FAST) to explain the output of the model and analyzed the global importance of input variables. The results demonstrated that CO is the most important variable affecting the coal spontaneous combustion hazard grades.
... Prior studies have shown that the information in the case base can be updated in a timely and effective manner through a case revision strategy (Deng and Li 2020). It is advisable to use multiperiod data to form the original case base and correct incorrectly predicted landslide cases to expand the case base, thus improving the prediction efficiency and accuracy of the model. ...
Predicting landslide hazards benefits geological disaster prevention and control. A novel cellular automaton (CA) integrating spatial case-based reasoning (SCBR), namely SCBR-CA, is proposed in this paper to predict landslide hazards at a local scale. The proposed model not only extracts spatial scene features for computations but also achieves dynamic prediction, which means that only one input is needed to obtain continuous predictions. Experiments were performed in Lushan, Sichuan, China. After using a convolutional neural network (CNN) to obtain the initial static landslide hazard zoning results, the landslide hazard zoning results for 2016–2025 were predicted with the SCBR-CA model. For comparison, a CA combined with a CNN (CNN-CA), was introduced. The area under the curve (AUC) of the receiver operating characteristic curve and Moran’s I index were used to assess the performance of the model. The experimental results showed that SCBR-CA yields slightly better AUC and Moran’s I index values than CNN-CA, and the dynamically predicted landslide hazard zoning results are equivalent or superior to those of static zoning, which indicates that the SCBR-CA model effectively predict local landslide hazards.
... Although these methods can develop reliable landslide susceptibility results , they show significant limitations and low robustness in complex and heterogeneous environments Du et al., 2020;Huang et al., 2020c). And even when some spatial features as spatial drivers were integrated to construction of models, but integrating actual spatial computation into the processes of CBR, including case retrieval, case revision, and case reuse, has been a challenge (Deng and Li, 2020;Du et al., 2012). Thus, how to effectively explore and integrate the spatial drivers of geographic events into CBR should be considered. ...
Traditional case-based reasoning methods overlook non-stationary spatial drivers of geographical events such as heterogeneity, dependence, and accumulation in case representation, and directly obtain the solution of the most similar cases in case reuse instead of considering the interference of fake similar cases to eliminate the contingency of reasoning, which leads to poor interpretations and low efficiency decisions in complex and heterogeneous geographical environments. This study proposes an improved spatial case-based reasoning (SCBR) considering multiple spatial drivers to overcome above problems and uses landslide susceptibility mapping as an example. Specifically, these spatial drivers were captured, extracted, and integrated into case representation by using geographic self-organizing mapping algorithm, spatial statistic, and spatial adjacent matrix, respectively. Additionally, the K-nearest neighbor method as case retrieval was introduced to retrieve the K similar cases based on the local and global similarity reasoning. Finally, the Gaussian process regression as case reuse method was generated to landslide susceptibility index under the assumption that K similar cases follows Gaussian distribution. Our experimental results show that the precision, F1, recall, and kappa of the proposed SCBR method are 0.974, 0.976, 0.979, and 0.953 which are higher than those of the traditional case-based reasoning (0.931, 0.941, 0.953, and 0.881), long short-term memory (0.951, 0.933, 0.915, and 0.870), and extreme gradient boosting decision tree (0.963, 0.967, 0.972, and 0.945), respectively. In general, the novel approach with better predictive performance can help decision makers to develop policies that reduce the loess of landslides and apply to similar geological events.
... Moreover, the input to the current deep learning models consists largely of attribute data (Xiong et al., 2021;Yang et al., 2022). In contrast, for geological or geographic problems, the typical parameters consist of spatial data (Deng and Li, 2020). When solving such problems, the spatial parameters should be mined and included in the model calculations to obtain more effective results. ...
Differentiating strata is a prerequisite for subsequent stratum outcropping research. Because of the large scale of outcropping strata and the complex surrounding terrain environments, differentiating the layers in traditional artificial field geological surveys is time-consuming and laborious. The emergence of oblique photogrammetry technology provides a new way to overcome the inherent challenges in traditional methods. This paper proposes a new method for differentiating outcropping strata from oblique photogrammetric data using an octree-based convolutional neural network (O–CNN) with spatial parameters. This method enables O–CNN to obtain high-level semantic information of point clouds and additional prior knowledge by fine-tuning network parameters and mining attributes and spatial parameters as network input, thereby improving the performance of the network for outcropping stratum differentiation. This study used the outcrop Xuankongsi in Fugu, Shaanxi, China as an example for stratum differentiation experiments. Compared with the O–CNN models using only attributes or spatial parameters as network input, the O–CNN model integrating both attributes and spatial parameters obtained better results, reaching an overall accuracy of 87.5%. After the stratum differentiation results were further optimized, the accuracy reached 97.2%, and the differentiation results were more consistent with the manual results of stratum differentiation. The experimental results show that the method proposed is effective and provides an intelligent way to differentiate outcropping strata.
... ere are many domestic studies on the mechanism of single geological disasters such as landslides, but the research progress on the development and distribution of regional geological disasters is relatively slow [4]. Exploring and forming a set of scientific, complete, and practical research methods for the development and distribution of regional geological disasters, and evaluating the risk of regional geological disasters, is of great practical significance for the prevention and control of regional geological disasters [5]. ...
With the rapid development of the economy and society, geological disasters such as landslides, collapses, and mudslides have shown an intensifying trend, seriously endangering the safety of people’s lives and property, and affecting the sustainable development of the economy and society. Aiming at the problems of merging different data layers and determining the weighting of data stacking in the statistical analysis model based on GIS technology in the evaluation of the risk of geological disasters, this study proposes a logistic regression model combined with the RBFNN-GA algorithm, that is, the determination of the occurrence of geological disasters. The fusion coefficient (CF value) with the RBFNN-GA algorithm model, and with the help of SPSS statistical analysis software, solves the problem of factor selection, heterogeneous data merging, and weighting of each data layer in the risk assessment. In the experimental stage, this study adopts the method of geological hazard certainty coefficients to carry out the sensitivity analysis of the geological hazards in the study area. Using homogeneous grid division, the spatial quantitative evaluation of the risk of geological disasters is realized, and at the same time, the results of the spatial quantitative evaluation of the risk of geological disasters are tested according to the latest landslide points in the region. The existing classification mainly depends on the acquisition of land use/cover information or the processing method of the acquired information, but the existing information acquisition will be limited by time, space, and spectral resolution. The results show that the number of landslide points per unit area in the extremely unstable zone and the unstable zone is 0.0395 points/km² and 0.0251 points/km², respectively, which is much higher than 0.0038 points/km² in the stable zone, indicating the evaluation results and actual landslide conditions.
... However, existing studies aimed at disaster prediction using CBR have encouraged us to conduct this research. Deng and Li [77] used CBR to assess the risk of geological disasters by combining a genetic algorithm and geographic information system technology. San Pedro et al. [78] integrated the fuzzy multicriteria decision method and CBR to forecast potential locations of cyclone tracks. ...
Predicting the spatial distribution of direct economic losses from typhoon storm surge disasters is crucial for supporting emergency response efforts. Using case-based reasoning, we developed a preliminary method for completing predictions about the impact of typhoon storm surge disasters for multiple coastal regions. We proposed retrieval, reuse, and revision algorithms to predict the following effects of a typhoon storm surge disaster: total direct economic losses and their grades, the affected regions, and individual direct economic losses and their grades in each affected region. We tested 33 such disaster cases using the developed method, and the predicted results were as follows. In about 70% of the cases, all recorded affected regions were predicted; the grades of the total direct economic losses were accurate in over 70% of the cases; in 63% of the cases, the grades of direct economic losses in each affected region were partly accurate, and they were all accurate in 30% of the cases. These promising results suggest that the proposed method can support disaster managers to respond adequately to typhoon storm surge disasters for multiple coastal regions.
... The CBR method obtains results through case similarity calculations . Compared with traditional data mining methods, it has higher classification performance (Deng and Li, 2020). However, most CBR methods have been applied to landslide monitoring (Dou et al., 2015), flood control , disaster management (Wang and Huang, 2010), land use (Du et al., 2010), environmental emergencies (Liao et al., 2012), and other fields. ...
... Fourth, the basic steps of CBR models for solving problems can be summarized as case retrieval, case reuse, case revision, and case storage. Case revision can improve the accuracy and efficiency of experiments, and the size and richness of the case base are also crucial for CBR (Deng and Li, 2020). Therefore, optimizing the case library by considering case revision will improve the proposed spatial CBR model performance. ...
Various machine learning methods have been applied to study regional landslide risk assessment problems, but most of them mainly consider the influencing factors associated with landslide occurrences and ignore the spatial features. Therefore, by combining the advantages of traditional case-based reasoning (CBR) and by fully mining the spatial features, this paper proposes a novel spatial case-based reasoning method for landslide risk assessment. In this method, the spatial proximity and spatial topological relationships were extracted as spatial features, and the influencing factors associated with landslide occurrences were selected as attribute features. Then, the integrated expression of the spatial and attribute features of a landslide case was further constructed. Finally, attribute similarity and spatial similarity were used for joint reasoning. This study then carried out experiments in Lushan, China. Upon comparison of the three CBR models, the proposed integrated CBR outperformed the other models. Furthermore, an optimized support vector machine and a deep convolutional neural network were selected as experimental methods in the control group. The results show that the proposed integrated CBR has better performance. In conclusion, the proposed integrated CBR can be effectively applied to regional landslide risk evaluation and other similar geospatial problems.
... It not only affects the safety of life and property, but also causes irreversible damage to the human living environment (Jiang et al. 2017). Common geologic hazards include collapse, landslide, mudslide, ground subsidence, ground fissure, and ground subsidence, which all pose a serious threat to life and property (Deng and Li 2020). Geologic hazard will not only bring immeasurable losses to a country or individual's economy, but also greatly destroy people's living conditions and stability. ...
To ensure the proper adoption of new technologies in identifying the potential geologic hazard on tourist routes, convolutional neural network (CNN) is applied in the radar image geologic hazard information extraction. A scientific and practical geologic hazard radar identification model is built based on identification of CNN image and calculation of big data algorithm, which can effectively improve the geologic hazard identification accuracy. Through experiments, the geologic hazard radar image data are verified, and the practicality of radar image intelligent identification under CNN and big data is also verified. The results show that the images of different resolution sizes all play a significant role in identification of geologic hazard performed by CNN. However, there are differences in the performance of different CNN models. With the continuous increase in training samples, the identification accuracy of various network models is also improved. Through radar image test, the identification capability of CNN model is the best, the highest precision is 93.61%, and the geologic hazard recall rate is 98.27%. Apriori algorithm is proposed for data processing, and the running speed and efficiency of identification models are improved, with favorable identification effect in variable data sets. To sum up, this research can provide theoretical ideas and practical value for the development of potential geologic hazard identification on tourist routes.
... It not only affects the safety of life and property, but also causes irreversible damage to the human living environment [4]. Common geologic hazards include collapse, landslide, mudslide, ground subsidence, ground fissure, and ground subsidence, which all pose a serious threat to life and property [5]. Geologic hazard will not only bring immeasurable losses to a country or individual's economy, it will also greatly destroy people's living conditions and stability. ...
... Recall rate (Rec): is taken to measure the coverage of positive samples, that is, the proportion of positive samples that are correctly classified to the total positive samples, as shown in equation (5). ...
To ensure the proper adoption of new technologies in identifying the potential geologic hazard on tourist routes, convolutional neural network (CNN) technology is applied in the radar image geologic hazard information extraction. A scientific and practical geologic hazard radar identification model is built, which is based on CNN’s image identification and big data algorithm calculation, and it can effectively improve the geologic hazard identification accuracy. By designing experiments, the geologic hazard radar image data are verified, and the practicality of radar image intelligent Identification under CNN and big data technology is also verified. The results show that the images of different resolution sizes all play a significant role in identification of geologic hazard performed by CNN. However, there are differences in the performance of different CNN models. With the continuous increase of training samples, the identification accuracy of various network models is also improved. By means of radar image test, the identification capability of CNN model is the best, the highest precision is 93.61%, and the geologic hazard recall rate is 98.27%. Apriori algorithm is introduced into data processing, and the running speed and efficiency of identification models are improved, with favorable identification effect in variable data sets. This research can provide theoretical ideas and practical value for the development of potential geologic hazard identification on tourist routes.
Predicting typhoon losses and victims' demand can be crucial before providing disaster relief to demand points. Considering the importance of losses prediction, this paper uses K Nearest Neighbors (KNN) method to find similar typhoons in history when a certain typhoon is coming. It will give disaster losses prediction 24 hours in advance using certain specific features concerning the coming typhoon and coastal cities. In this paper, we consider six coastal cities in Fujian Province, China, and investigate Typhoon Maria in 2018 to test and verify the accuracy of the loss prediction model, totally collecting 148 typhoon data from 2000 to 2022. After predicting typhoon disaster losses, we use a two-stage stochastic programing model to choose certain potential disaster relief points and allocate relief supplies in the first stage, while repurchasing and distributing the relief supplies in the second stage. In this part, our paper considers satisfying casualties' demands as far as possible in the meanwhile minimizes the total cost. The experiment shows that different decisions will be made under different purchasing and repurchasing prices ratios. Moreover, this paper makes a comparison between two situations-urbans disconnection and urbans connection to show the necessity of constructing city integrated emergency response system.
