Spatial Modeling in GIS and R for Earth and Environmental Sciences

Hamid Reza Pourghasemi, Candan Gokceoglu

• Publisher: Elsevier
• Year: 2019
• ISBN:
  9780128156957
• Topic: Physical Sciences
• Subtopic: Geology & Earth Sciences

Spatial Modeling in GIS and R for Earth and Environmental Sciences offers an integrated approach to spatial modelling using both GIS and R. Given the importance of Geographical Information Systems and geostatistics across a variety of applications in Earth and Environmental Science, a clear link between GIS and open source software is essential for the study of spatial objects or phenomena that occur in the real world and facilitate problem-solving. Organized into clear sections on applications and using case studies, the book helps researchers to more quickly understand GIS data and formulate more complex conclusions.

The book is the first reference to provide methods and applications for combining the use of R and GIS in modeling spatial processes. It is an essential tool for students and researchers in earth and environmental science, especially those looking to better utilize GIS and spatial modeling.

• Offers a clear, interdisciplinary guide to serve researchers in a variety of fields, including hazards, land surveying, remote sensing, cartography, geophysics, geology, natural resources, environment and geography
• Provides an overview, methods and case studies for each application
• Expresses concepts and methods at an appropriate level for both students and new users to learn by example

1

Spatial Analysis of Extreme Rainfall Values Based on Support Vector Machines Optimized by Genetic Algorithms

The Case of Alfeios Basin, Greece

Paraskevas Tsangaratos¹, Ioanna Ilia¹ and Ioannis Matiatos², ¹Laboratory of Engineering Geology – Hydrogeology, Department of Geological Studies, School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens, Greece, ²Faculty of Geology and Geoenvironment, National and Kapodistrian University of Athens, Panepistimioupoli, Greece

Abstract

The main objective of this study was to provide a methodological approach in order to identify the spatial patterns of extreme rainfall values for events with return periods of 5 years and to construct a continuous surface that represented the spatial distribution by utilizing support vector machines (SVMs). A genetic algorithm (GA) was implemented to optimize the parameters cost, epsilon, and gamma used in SVM. Several R packages, namely, “e1071,” “GA,” and “raster,” were implemented in R in order to use SVM and GA, whereas a geographic information system was utilized to process spatial data and create the continuous surface. In order to evaluate the developed methodology, the Alfeios water basin, Peloponnesus, Greece, was selected as an appropriate test site. Based on the available intensity–duration–frequency curves concerning 38 meteorological stations located within the research area, the daily extreme rainfall value for a 5-year return period was estimated, which served as the depended variable. The model had as independent variables, the longitude, latitude, elevation, slope angle, and slope aspect of the meteorological stations, the minimum, mean and maximum elevation, the mean slope angle, and the mean slope aspect within a radius of 5 km around the stations, the distance of each station from the coastline. The results of a basic statistical analysis revealed that the elevation variables were highly correlated, with values between 0.83 and 0.93. The results of a basic statistical analysis revealed that the elevation variables were highly correlated, with values between 0.82 and 0.93. Also, the analysis revealed that the most important variables among the 1 variables were longitude, distance from the coastline, mean slope aspect, within a 5-km radius and elevation. The performance of the methodology was evaluated using three standard statistical evaluation criteria, the root mean squared error (RMSE), the r square (r²) and the mean squared error (MSE), applied to the study area, and showed good performance. The outcomes of the SVM-GA model were compared with the results of a multilinear regression analysis. The optimized SVM-GA model achieved higher predictive accuracy, with RMSE, r², and MSE values of 6.35, 0.63, and 40.31, respectively. The developed SVM-GA model proved to be an excellent alternative spatial interpolation tool, producing highly accurate results, whereas the information and knowledge gained could improve the accuracy of analysis concerning hydrology and hydrogeological models, ground water studies, flood-related applications, and climate analysis studies.

Keywords

Extreme rainfall; support vector machine; genetic algorithm; GIS

1.1 Introduction

The rainfall intensity–duration–frequency (IDF) curves are one of the most commonly used investigational tools in water resources engineering (Alemaw & Chaoka, 2016; Fadhel, Rico-Ramirez, & Han, 2017). The IDF curves provide essential information in planning, designing, operating, and protecting water resource projects or engineering projects against floods (Minh Nhat, Tachikawa, & Takara, 2006). In general, the IDF curve is a mathematical relationship between the rainfall intensity i, the duration d, and the return period T. Through the use of IDF curves one can estimate the return period of an observed rainfall event or the rainfall amount corresponding to a given return period for different aggregation times (Koutsoyiannis, 2003; Koutsoyiannis, Kozonis, & Manetas, 1998). The IDF curve estimation at gauged sites requires the analysis of precipitation extremes, which are reported as the annual maximum precipitation amounts measured in time intervals of a predefined duration.

However, due to the low density and sparse distribution of rain-gauged sites, problems arose that have to do with the uncertainty and accuracy when trying to interpolate spatially the estimated extreme values and providing a spatial distribution map (El-Sayed, 2011; Liew, Raghavan, & Liong, 2014). Moreover, it has been stated that spatial variability of rainfall is sensitive to the location of the rain gauge from which rainfall data are collected (Bell et al., 2002; Looper & Vieux, 2011). It is also well known that besides elevation, which is considered to be a strong determinant of climate, rainfall may be influenced by the geo-environmental settings of the surroundings, such as geographical location, slope, aspect or bearing of the steepest slope, exposure, wind direction, proximity to the sea or other water bodies, and proximity to the crest or ridge of a mountain range (Agnew & Palutikof, 2000; Al-Ahmadi & Al-Ahmadi, 2013; Alijani, 2008; Buytaert, Celleri, Willems, Bievre, & Wyseure, 2006; Daly et al., 1994; Ding et al., 2014; Eris & Agiralioglu, 2009; Wang et al., 2017; Yao, Yang, Mao, Zhao, & Xu, 2016).

The common approach to spatial interpolation is the use of deterministic, geostatistical methods and regression-based models (Begueria & Vicente-Serrano, 2006; Burrough & McDonnell, 1998; Ly, Charles, & Degre, 2013; Naoum & Tsanis, 2004; Vicente-Serrano, Lanjeri, & Lopez-Moreno, 2007). Several comparative studies concerning the interpolation of extreme rainfall values can be found in the literature. Weisse and Bois (2002) applied geostatistical methods and regression models to estimate extreme precipitation, concluding that geostatistical methods performed better only when the rain-gauging network was dense enough. Begueria and Vicente-Serrano (2006) mapped the hazard of extreme precipitation by linking the theory of extreme values analysis and spatial interpolation techniques. The authors applied geo-regression techniques, including location and other spatially independent parameters as predictors and reported that they produced significant and well-fitted models. Similarly, Ly et al. (2011), developed different algorithms of spatial interpolation for daily rainfall and compared the outcomes of geostatistical and deterministic approaches. The authors concluded that spatial interpolation with the geostatistical and ...

Table of contents

• Cover image
• Title page
• Table of Contents
• Copyright
• Dedication
• List of Contributors
• 1. Spatial Analysis of Extreme Rainfall Values Based on Support Vector Machines Optimized by Genetic Algorithms: The Case of Alfeios Basin, Greece
• 2. Remotely Sensed Spatial and Temporal Variations of Vegetation Indices Subjected to Rainfall Amount and Distribution Properties
• 3. Numerical Recipes for Landslide Spatial Prediction Using R-INLA: A Step-by-Step Tutorial
• 4. Geospatial Multicriteria Decision Analysis in Forest Operational Planning
• 5. Parameter Optimization of KINEROS2 Using Particle Swarm Optimization Algorithm Within R Environment for Rainfall–Runoff Simulation
• 6. Land-Subsidence Spatial Modeling Using the Random Forest Data-Mining Technique
• 7. GIS-Based SWARA and Its Ensemble by RBF and ICA Data-Mining Techniques for Determining Suitability of Existing Schools and Site Selection of New School Buildings
• 8. Application of SWAT and MCDM Models for Identifying and Ranking Suitable Sites for Subsurface Dams
• 9. Habitat Suitability Mapping of Artemisia aucheri Boiss Based on the GLM Model in R
• 10. Flood-Hazard Assessment Modeling Using Multicriteria Analysis and GIS: A Case Study—Ras Gharib Area, Egypt
• 11. Landslide Susceptibility Survey Using Modeling Methods
• 12. Prediction of Soil Disturbance Susceptibility Maps of Forest Harvesting Using R and GIS-Based Data-Mining Techniques
• 13. Spatial Modeling of Gully Erosion Using Linear and Quadratic Discriminant Analyses in GIS and R
• 14. Artificial Neural Networks for Flood Susceptibility Mapping in Data-Scarce Urban Areas
• 15. Modeling the Spatial Variability of Forest Fire Susceptibility Using Geographical Information Systems and the Analytical Hierarchy Process
• 16. Prioritization of Flood Inundation of Maharloo Watershed in Iran Using Morphometric Parameters Analysis and TOPSIS MCDM Model
• 17. A Robust Remote Sensing–Spatial Modeling–Remote Sensing (R-M-R) Approach for Flood Hazard Assessment
• 18. Prioritization of Effective Factors on Zataria multiflora Habitat Suitability and its Spatial Modeling
• 19. Prediction of Soil Organic Carbon and its Mapping Using Regression Analyses and Remote Sensing Data in GIS and R
• 20. 3D Reconstruction of Landslides for the Acquisition of Digital Databases and Monitoring Spatiotemporal Dynamics of Landslides Based on GIS Spatial Analysis and UAV Techniques
• 21. A Comparative Study of Functional Data Analysis and Generalized Linear Model Data-Mining Techniques for Landslide Spatial Modeling
• 22. Regional Groundwater Potential Analysis Using Classification and Regression Trees
• 23. Comparative Evaluation of Decision-Forest Algorithms in Object-Based Land Use and Land Cover Mapping
• 24. Statistical Modeling of Landslides: Landslide Susceptibility and Beyond
• 25. Assessing the Vulnerability of Groundwater to Salinization Using GIS-Based Data-Mining Techniques in a Coastal Aquifer
• 26. A Framework for Multiple Moving Objects Detection in Aerial Videos
• 27. Modeling Soil Burn Severity Prediction for Planning Measures to Mitigate Post Wildfire Soil Erosion in NW Spain
• 28. Factors Influencing Regional-Scale Wildfire Probability in Iran: An Application of Random Forest and Support Vector Machine
• 29. Land Use/Land Cover Change Detection and Urban Sprawl Analysis
• 30. Spatial Modeling of Gully Erosion: A New Ensemble of CART and GLM Data-Mining Algorithms
• 31. Multihazard Exposure Assessment on the Valjevo City Road Network
• 32. Producing a Spatially Focused Landslide Susceptibility Map Using an Ensemble of Shannon’s Entropy and Fractal Dimension (Case Study: Ziarat Watershed, Iran)
• 33. A Conceptual Model of the Relationship Between Plant Distribution and Desertification Trend in Rangeland Ecosystems Using R Software
• Index