Exploring machine learning and statistical approach techniques for landslide susceptibility mapping in Siwalik Himalayan Region using geospatial technology

Landslides are a natural threat that poses a severe risk to human life and the environment. In the Kumaon mountains region in Uttarakhand (India), Nainital is among the most vulnerable areas prone to landslides inflicting harm to livelihood and civilization due to frequent landslides. Developing a landslide susceptibility map (LSM) in this Nainital area will help alleviate the probability of landslide occurrence. GIS and statistical-based approaches like the certainty factor (CF), information value (IV), frequency ratio (FR) and logistic regression (LR) are used for the assessment of LSM. The landslide inventories were prepared using topography, satellite imagery, lithology, slope, aspect, curvature, soil, land use and land cover, geomorphology, drainage density and lineament density to construct the geodatabase of the elements affecting landslides. Furthermore, the receiver operating characteristic (ROC) curve was used to check the accuracy of the predicting model. The results for the area under the curves (AUCs) were 87.8% for logistic regression, 87.6% for certainty factor, 87.4% for information value and 84.8% for frequency ratio, which indicates satisfactory accuracy in landslide susceptibility mapping. The present study perfectly combines GIS and statistical approaches for mapping landslide susceptibility zonation. Regional land use planners and natural disaster management will benefit from the proposed framework for landslide susceptibility maps.

GIS-based landslide susceptibility zoning using a coupled model: a case study in Badong County, China

Landslide susceptibility zoning is necessary for landslide risk management. This study aims to conduct the landslide susceptibility evaluation based on a model coupled with information value (IV) and logistic regression (LR) for Badong County in Hubei Province, China. Through the screening of landslide predisposing factors based on correlation analysis, a spatial database including 11 landslide factors and 588 historical landslides was constructed in ArcGIS. The IV, LR and their coupled model were then developed. To validate the accuracy of the three models, the receiver operating characteristic curves (ROC) and the landslide density curves were correspondingly created. The results showed that the areas under the receiver operating characteristic curve (AUCs) of the three models were 0.758, 0.786 and 0.818, respectively. Moreover, the landslide density increased exponentially with the landslide susceptibility, but the coupled model exhibited a higher growth rate among the three models, indicating good performance of the proposed model in landslide susceptibility evaluation. The landslide susceptibility map generated by the coupled model demonstrated that the high and very high landslide susceptibility area mainly concentrated along rivers and roads. Furthermore, by counting the landslide numbers and analyzing the landslide susceptibility within each town in Badong County, it was discovered that Yanduhe, Xinling, Dongrangkou and Guandukou were the main landslide-prone areas. This research will contribute to landslide prevention and mitigation and serve as a reference for other areas.

Prediction of gold mineralization zones using spatial techniques and geophysical data: A case study of the Josephine prospecting licence, NW Ghana

In this study, predictive models that characterize gold potential zones within the Josephine Prospecting Licence (PL) Area of Northwestern Ghana have been created by data-driven methods comprising frequency ratio and information value. These predictive models were evaluated using known locations of gold (Au) occurrence datasets and compared to each other. The mineral prospectivity models (MPMs) of gold occurrence areas within the Josephine PL Area were constructed by determining the spatial correlation between known locations of Au occurrences and eight mineralization related factors. The locations of these known Au occurrences, which characterize regions of anomalously high Au geochemical concentration and regions of previous or ongoing artisanal mining operations were identified by using geographic positioning systems (GPS). Eight mineralization related factors (geoscientific thematic layers) over the entire study area composed of analytic signal, lineament density, uranium-thorium ratio, uranium, potassium-thorium ratio, potassium, reduction-to-equator and geology were used to generate the MPMs. The predictive capacity of each of the MPMs generated was determined by employing the area under the receiver operating characteristics curve (AUC). The AUC score obtained for the predictive models produced based on the information value and the frequency ratio approaches were respectively 0.794 and 0.815. The AUC scores generated indicate that the MPMs produced are good predictive models (with an AUC greater than 0.7) and can therefore assist in narrowing down the highly prospective zones of mineral occurrences within the study area. However, the overall predictive potential of the frequency ratio approach was better than the model produced by the information value approach.

STIF: Intuitionistic fuzzy Gaussian membership function with statistical transformation weight of evidence and information value for private information preservation

Data sharing to the multiple organizations are essential for analysis in many situations. The shared data contains the individual's private and sensitive information and results in privacy breach. To overcome the privacy challenges, privacy preserving data mining (PPDM) has progressed as a solution. This work addresses the problem of PPDM by proposing statistical transformation with intuitionistic fuzzy (STIF) algorithm for data perturbation. The STIF algorithm contains statistical methods weight of evidence, information value and intuitionistic fuzzy Gaussian membership function. The STIF algorithm is applied on three benchmark datasets adult income, bank marketing and lung cancer. The classifier models decision tree, random forest, extreme gradient boost and support vector machines are used for accuracy and performance analysis. The results show that the STIF algorithm achieves 99% of accuracy for adult income dataset and 100% accuracy for both bank marketing and lung cancer datasets. Further, the results highlights that the STIF algorithm outperforms in data perturbation capacity and privacy preserving capacity than the state-of-art algorithms without any information loss on both numerical and categorical data.

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

BACKGROUND

Schistosomiasis control is striving forward to transmission interruption and even elimination, evidence-lead control is of vital importance to eliminate the hidden dangers of schistosomiasis. This study attempts to identify high risk areas of schistosomiasis in China by using information value and machine learning.

METHODS

The local case distribution from schistosomiasis surveillance data in China between 2005 and 2019 was assessed based on 19 variables including climate, geography, and social economy. Seven models were built in three categories including information value (IV), three machine learning models [logistic regression (LR), random forest (RF), generalized boosted model (GBM)], and three coupled models (IV + LR, IV + RF, IV + GBM). Accuracy, area under the curve (AUC), and F1-score were used to evaluate the prediction performance of the models. The optimal model was selected to predict the risk distribution for schistosomiasis.

RESULTS

There is a more prone to schistosomiasis epidemic provided that paddy fields, grasslands, less than 2.5 km from the waterway, annual average temperature of 11.5-19.0 °C, annual average rainfall of 1000-1550 mm. IV + GBM had the highest prediction effect (accuracy = 0.878, AUC = 0.902, F1 = 0.920) compared with the other six models. The results of IV + GBM showed that the risk areas are mainly distributed in the coastal regions of the middle and lower reaches of the Yangtze River, the Poyang Lake region, and the Dongting Lake region. High-risk areas are primarily distributed in eastern Changde, western Yueyang, northeastern Yiyang, middle Changsha of Hunan province; southern Jiujiang, northern Nanchang, northeastern Shangrao, eastern Yichun in Jiangxi province; southern Jingzhou, southern Xiantao, middle Wuhan in Hubei province; southern Anqing, northwestern Guichi, eastern Wuhu in Anhui province; middle Meishan, northern Leshan, and the middle of Liangshan in Sichuan province.

CONCLUSIONS

The risk of schistosomiasis transmission in China still exists, with high-risk areas relatively concentrated in the coastal regions of the middle and lower reaches of the Yangtze River. Coupled models of IV and machine learning provide for effective analysis and prediction, forming a scientific basis for evidence-lead surveillance and control.

Maximum entropy distributions with quantile information

Quantiles are available in various problems for developing probability distributions. In some problems quantiles are elicited from experts and used for fitting parametric models, which induce non-elicited information. In some other problems comparisons are made with a quantile of an assumed model which is noncommittal to the quantile information. The maximum entropy (ME) principle provides models that avoid these issues. However, the information theory literature has been mainly concerned about models based on moment information. This paper explores the ME models that are the minimum elaborations of the uniform and moment-based ME models by quantiles. This property provides diagnostics for the utility of elaboration in terms of the information value of each type of information over the other. The ME model with quantiles and moments is represented as the mixture of truncated distributions on consecutive intervals whose shapes and existence are determined by the moments. Elaborations of several ME distributions by quantiles are presented. The ME model based only on quantiles elicited by the fixed interval method possesses a useful property for pooling information elicited from multiple experts. The elaboration of Laplace distribution is an extension of the information theory connection with minimum risk under symmetric loss functions to the asymmetric linear loss. This extension produces a new Asymmetric Laplace distribution. Application examples compare ME priors with a parametric model fitted to elicited quantiles, illustrate measuring uncertainty and disagreement of economic forecasters based on elicited probabilities, and adjust ME models for a fundamental quantile in an inventory management problem.

Modeling crash severity by considering risk indicators of driver and roadway: A Bayesian network approach

INTRODUCTION

Traffic crashes could result in severe outcomes such as injuries and deaths. Thus, understanding factors associated with crash severity is of practical importance. Few studies have deeply examined how prior violation and crash experience of drivers and roadways are associated with crash severity.

METHOD

In this study, a set of risk indicators of road users and roadways were developed based on their prior violation and crash records (e.g., cumulative crash frequency of a roadway), in order to reflect certain aspect or degree of their driving risk. To explore the impacts of those indicators on crash severity and complex interactions among all contributing factors, a Bayesian network approach was developed, based on citywide crash data collected in Kunshan, China from 2016 to 2018. A variable selection procedure based on Information Value (IV) was developed to identify significant variables, and the Bayesian network was employed to explicitly explore statistical associations between crash severity and significant variables.

RESULTS

In terms of balanced accuracy and AUCs, the proposed approach performed reasonably well. Bayesian modeling results indicated that the prior crash/violation experiences of road users and roadways were very important risk indicators. For example, migrant workers tend to have high injury risk due to their dangerous violation behaviors, such as retrograding, red-light running, and right-of-way violation. Furthermore, results showed that certain variable combinations had enhanced impacts on severity outcome than single variables. For example, when a migrant worker and a non-motorized vehicle are involved in a crash happening on a local road with high cumulative violation frequency in the previous year, the probability for drivers suffering serious injury or fatality is much higher than that caused by any single factor. Practical applications: The proposed methodology and modeling results provide insights for developing effective countermeasures to reduce crash severity and improve traffic system safety performance.

Exploring the determinants of students' academic performance at university level: The mediating role of internet usage continuance intention

This study investigates the impact of integrating essential factors on academic performance in university students' context. The proposed model examines the influence of continuance intention, satisfaction, information value, and Internet addiction on academic performance. Additionally, it investigates the mediating role of continuance intention on the relationship of satisfaction and information value on academic performance among university students. A survey questionnaire method was adopted to collect data from university students in Jordan. Data was collected from 476 voluntary participants, and the analysis was conducted using SPSS and AMOS. The analysis results show that continuance intention, satisfaction, information value have a significant positive influence on academic performance. Besides, the results show that satisfaction and information value positively and significantly influence continuance intention. While continuance intention full mediation the relationship between satisfaction and academic performance, it partial mediation the relationship between information value and academic performance. This study is the first to examine the integrating of continuance intention, satisfaction, information value, and Internet addiction on students' academic performance. Furthermore, this study is also distinguished from other studies by investigating the mediating role of continuance intention gap.

How children use accuracy information to infer informant intentions and to make reward decisions

The ability to assess the value of the information one receives and the intentions of the source of that information can be used to establish cooperative relationships and to identify cooperative partners. Across two experiments, 4- to 8-year-old children (N = 204) received a note with correct, incorrect, or no information that affected their efforts on a search task. Children were told that all informants had played the game before and knew the location of the hidden reward. In the no information condition, children were told that the informant needed to leave before finishing the note and, thus, was not intentionally uninformative. Children rated the note with correct information as more helpful than the note with no information; incorrect information was rated least helpful. When asked about the informant's intentions, children attributed positive intentions when the information was correct and when they received unhelpful information but knew the informant was not intentionally uninformative. Children attributed less positive intentions to the informant when they received incorrect information. When given the chance to reward the informant, children rewarded the informant who provided correct information and no information equally; the informant who provided incorrect information received fewer rewards. Combined, these results suggest that young children assume that informants have positive intentions even when they provide no useful information. However, when the information provided is clearly inaccurate, children infer more negative intentions and reward those informants at lower rates. These results suggest that children tend to reward informants more based on their presumed intentions, placing less weight on the value of the information they provide.

Endogenous information, adverse selection, and prevention: Implications for genetic testing policy

We examine public policy toward the use of genetic information by insurers. Individuals engage in unobservable primary prevention and have access to different prevention technologies. Thus, insurance markets are affected by moral hazard and adverse selection. Individuals can choose to take a genetic test to acquire information about their prevention technology. Information has positive decision-making value, that is, individuals may adjust their behavior based on the result of the test. However, testing also exposes individuals to uncertainty over the available insurance contract, so-called classification risk, which lowers the value of information. In our analysis we distinguish between four different policy regimes, determine the value of information under each regime and associated equilibrium outcomes on the insurance market. We show that the policy regimes can be Pareto ranked, with a duty to disclose being the preferred regime and an information ban the least preferred one.