Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.     

Mineral potential mapping for rare earth elements mineralization with AHP method in the Kerman-Kashmar Tectonic Zone,Central Iran

One of the major strengths of a GIS is the ability to integrate and combine multiple layers of geoscience data for producing mineral potential maps showing favorable areas for mineral exploration. Once the data is prepared properly, the GIS, jointly with other statistical and geostatistical software packages, can be used to manipulate and visualize the data in order to produce a mineral prospectivity map. Many spatial modeling techniques can be employed to produce mineral potential maps. This paper demonstrates a technique to define favorable areas for REE mineralization with AHP technique using geological, geochemical, geophysical, alteration and faults density spatial data in the Kerman-Kashmar Tectonic Zone of central Iran. The AHP is a powerful and flexible multi-criteria decision-making tool for dealing with complex problems where both qualitative and quantitative aspects need to be considered. This approach is knowledgedriven method and can be applied in other areas for conventional use in mineral exploration.     

一种基于机器学习算法的岩性填图方法

通过野外地质调查与机器学习方法的有机融合,提出了一种基于梯度提升决策树算法的岩性单元填图方法.研究以多龙矿集区为模型试验区,选择1:5万勘查地球化学数据为基础预测数据,以1:5万区域地质图为参考,进行基于梯度提升决策树算法的岩性预测填图模型试验.首先选择研究区内小范围空白区开展野外填图,建立原始数据集并初步构建岩性单元...     

结合场梯度的位场数据图像非均匀映射技术

利用图像表达位场数据时,位场数据根据色标被映射成颜色,生成的图像能否客观真实地表达出位场数据的内涵特征,关键取决于采用的色标是否合理。为了提高图像表达位场数据细节信息的能力,借鉴图像灰度非均匀整量的思想,给出了一种基于场值梯度的色标文件生成方法。对比于传统的采用根据位场场值大小平均分配色阶的方法,理论模型试验和实际资料的应用结果,都显示了本方法在提高图像表达位场数据细节信息能力上的有效性和优越性。     

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3% of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.     

Using digital mapping techniques to evaluate beneficiation potential in a coal ash pond

Coal-fired power plants produce energy and many by-products (unburned carbon, fly ash, and bottom ash) that are normally stored in permitted ponds and landfills. When the storage facility fills to capacity, it is necessary to haul material off-site for disposal, construct a new storage facility, or find a use for some of the material. Because certain criteria must be met to successfully beneficiate the ash, mapping the ash reserve provides data that shows where the most promising recovery sites will be.The University of Kentucky Center for Applied Energy Research (CAER) in conjunction with Western Kentucky Energy (WKE) and the US Department of Energy are constructing an ash beneficiation plant to recover high quality fuel and lightweight aggregate from the ash ponds at WKE's Coleman Station in Hawesville, KY. To determine the locations of the most productive areas, an extensive sampling and mapping project is underway. An amphibious ATV-mounted hydraulic drill has been employed to take core samples throughout the pond. These samples are then evaluated for particle size distribution, carbon content, chemical and leaching properties. With this information as well as each drill-hole's GPS coordinates and aerial photographs of the plant site, digital maps have been produced showing trends of deposition of material in the pond. Using a Geographical Information System to compile the data, the feasibility of removing ash for beneficial re-use can assessed.     

An optimization on machine learning algorithms for mapping snow avalanche susceptibility

Natural Hazards - Mapping avalanche-prone areas to mitigate damages is important and vital for safety and development planning. New hybrid models are introduced for snow avalanche susceptibility...     

Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping

This study compares the predictive performance of GIS-based landslide susceptibility mapping (LSM) using four different kernel functions in support vector machines (SVMs). Nine possible causal criteria were considered based on earlier similar studies for an area in the eastern part of the Khuzestan province of southern Iran. Different models and the resulting landslide susceptibility maps were created using information on known landslide events from a landslide inventory dataset. The models were trained using landslide inventory dataset. A two-step accuracy assessment was implemented to validate the results and to compare the capability of each function. The radial basis function was identified as the most efficient kernel function for LSM with the resulting landslide susceptibility map showing the highest predictive accuracy, followed by the polynomial kernel function. According to the obtained results, it concluded that using SVMs can generally be considered to be an effective method for LSM while it demands careful consideration of kernel function. The results of the present research will also assist other researchers to select the best SVM kernel function to use for LSM.     

Flood risk mapping for the lower Narmada basin in India: a machine learning and IoT-based framework

Natural Hazards - Floods have a significant economic, social, and environmental impact in developing countries like India. Settlements in flood hazard zones increase flood risk due to a lack of...     

Flood-prone area mapping using machine learning techniques: a case study of Quang Binh province,Vietnam

Natural Hazards - Vietnam’s central coastal region is the most vulnerable and always at flood risk, severely affecting people’s livelihoods and socio-economic development. In...     

Modelling flood events with a cumulant CO lattice Boltzmann shallow water model

Natural Hazards - In this work the development of a semiautomatic procedure based on the coupled use of a GIS subroutine and a two-dimensional hydraulic lattice Boltzmann model solving the shallow...     

Least square support vector machine and relevance vector machine for evaluating seismic liquefaction potential using SPT

The determination of liquefaction potential of soil is an imperative task in earthquake geotechnical engineering. The current research aims at proposing least square support vector machine (LSSVM) and relevance vector machine (RVM) as novel classification techniques for the determination of liquefaction potential of soil from actual standard penetration test (SPT) data. The LSSVM is a statistical learning method that has a self-contained basis of statistical learning theory and excellent learning performance. RVM is based on a Bayesian formulation. It can generalize well and provide inferences at low computational cost. Both models give probabilistic output. A comparative study has been also done between developed two models and artificial neural network model. The study shows that RVM is the best model for the prediction of liquefaction potential of soil is based on SPT data.     

基于MapGIS平台矿产资源潜力评价地质-地球物理数据库建设

基于MapGIS平台的矿产资源潜力评价地质-地球物理数据库的建立,使多源物探信息得以科学有效的管理,能够方便地建立地质-地球物理模型及进行地质-地球物理空间模拟分析,使得这一地学科学研究进一步向系统化、信息化发展迈进,建立中国金属矿床的综合信息找矿系统模型,成为一项十分重要工作。     

Mineral potential of the Russian Arctic: state and efficient development

The metallogeny of the Russian Arctic zone, with a high potential for U, platinum-group metals, Au, Sn, trace elements, etc., in its different sectors, has been controlled by the type of early continental structures and by the uniform Meso-Cenozoic evolution of the area. The suggested reasonable development strategy is to conserve and further develop the existing mining districts associated with known large fields and to discover new primary (U, Au, etc.) and placer deposits. It is important to provide scientific background and environmental monitoring in the area at the stages of mineral prediction, exploration, and development.     

MODIS-FIRMS and ground-truthing-based wildfire likelihood mapping of Sikkim Himalaya using machine learning algorithms

Natural Hazards - Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent episodes of wildfires of 2019 in Australia and Brazil are sad reminders of their...     

Spinifex biogeochemistry across arid Australia: Mineral exploration potential and chromium accumulation

Spinifex (Triodia spp.) grasslands cover vast areas of arid Australia, across a variety of soils and landscapes. These grasses are deep rooted and long lived, hence have great potential as a biogeochemical sampling medium for mineral exploration. This study discusses the results of analyses of Triodia pungens and Triodia scariosa from field sites over buried Au mineralisation (Coyote, Oberon and Tunkillia Prospects). At each site there is a multi-element anomaly in the vegetation over the projected mineralisation, the haloes are of different scales depending on the local landscape setting and dispersion potential of each element associated with mineralisation. The magnitude of the anomalies is similar for each site independent of underlying substrate. Overall, spinifex chemical composition has the potential to act as a point indicator of substrate geochemistry with very minimal dispersion (hundreds of metres only) that can delineate the extent of a potential ore deposit.This study also discusses the Cr accumulation potential of T. pungens and T. scariosa, discovered during the mineral exploration studies, from several field sites (Coyote, Oberon, Tunkillia and North Miitel Prospects). Triodia species are shown to be able to accumulate Cr up to potentially toxic levels independent of substrate concentration. This could be due to accumulation (active transport) or the lack of a barrier mechanism (passive uptake) within the plant.     

Geospatial mapping of potential recharge zones in parts of Pune city

Runoff has increased many fold in urban areas due to increase in paved areas, training of streams and construction of storm water drains. The recharge is therefore continuously decreasing; resulting in depleting groundwater reserves beneath large cities, especially those situated on water divides. In order to reduce surface runoff and replenish groundwater many advocate artificial recharge through rainwater harvesting. Conventionally, detailed hydrogeological survey is needed by expert hydrogeologists to suggest suitable sites for rooftop rainwater harvesting and storage in the subsurface aquifers. Pune, a rapidly growing city, is under severe stress due to shortage of water in some areas. An effort has been made in this study to identify areas suitable for rooftop rainwater harvesting by integrating traditional hydrogeological survey data with the help of Remote Sensing and Geographic Information System. This endeavour has led to develop a program called SLUGGER-DQL which helps to identify potential sites for rooftop rainwater harvesting and artificial recharge. The program is open ended and several other factors controlling potential recharge can be easily added on. Based on the results of the present study, potential sites for rainwater harvesting and artificial recharge have been identified in the Pune University-Shivajinagar-Kothrud area. The present paper demonstrates the utility of traditional hydrogeological surveys combined with modern techniques in solving problems related to urban hydrogeology and town planning.     

Assessment and mapping of land erosion potential in mountainous recreational areas

The prediction of land erosion rates under different types of land use is difficult because of the large number of variables involved. This paper attempts to isolate the most important characteristics of land contributing to its crodibility, and then describes the geomorphological approach used to assess and map land erosion potential in the Kamberg area of the Drakensberg mountains, South Africa. Emphasis is placed on the fact that land erosion potential varies with land use type, and recreational land use only is considered.The terrain at Kamberg could be divided into four sections, each displaying a degree of internal homogeneity in land erosion potential, yet distinguishable from its neighbours through geomorphological and topographic characteristics. Inherent subjectivity in terrain evaluation techniques, and lack of threshold values for variables concerned constitute the main weaknesses of the method used, and because of this, such work should be undertaken only by an experienced field geomorphologist.