Spatial Modeling in GIS and R for Earth and Environmental Sciences

Description

1. Spatial Analysis of Extreme Rainfall Values Based on Support Vector Machines Optimized by Genetic Algorithms: The Case of Alfeios Basin, Greece Paraskevas Tsangaratos, Ioanna Ilia, and Ioannis Matiatos 2. Remotely Sensed Spatial and Temporal Variations of Vegetation Indices Subjected to Rainfall Amount and Distribution Properties Mohammad Hossein Shahrokhnia and Seyed Hamid Ahmadi 3. Numerical Recipes for Landslide Spatial Prediction by Using R-INLA: A Step-By-Step Tutorial Luigi Lombardo, Thomas Opitz, and Raphaël Huser 4. An Integrative Approach of Geospatial Multi-Criteria Decision Analysis for Forest Operational Planning Sattar Ezzati 5. Parameters Optimization of KINEROS2 Using Particle Swarm Optimization Algorithm within R Environment for Rainfall-Runoff Simulation Hadi Memarian, Mohsen Pourreza Bilondi, and Zinat Komeh 6. Land-Subsidence Spatial Modeling Using Random Forest Data Mining Technique Hamid Reza Pourghasemi and Mohsen Mohseni Saravi 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 Mahdi Panahi, Mohammad Yekrangnia, Zohre Bagheri, Hamid Reza Pourghasemi, Fahtemeh Rezai, Iman Nasiri Aghdam, and Ali Akbar Damavandi 8. Application of SWAT and MCDM Models for Identifying and Ranking the Suitable Sites for Subsurface Dams Javad Chezgi 9. Habitat Suitability Mapping of Artemisia Aucheri Boiss Based on GLM Model in R Gholamabbas Ghanbarian , Mohammad Reza Raoufat, Hamid Reza Pourghasemi, and Roja Safaeian 10. Flood-Hazard Assessment Modeling Using Multi-Criteria Analysis and GIS: A Case Study: Ras Gharib Area, Egypt Ahmed M. Youssef and Mahmoud A. Hegab 11. Landslide Susceptibility Survey Using Modelling Methods Hamidreza Moradi, Mohammad Taqhi Avand, and Saeid Janizadeh 12. Prediction of Soil Disturbance Susceptibility Maps of Forest Harvesting Using R and GIS-Based Data Mining Techniques Saeid Shabani 13. Spatial Modeling of Gully Erosion Using Linear and Quadratic Discriminant Analyses in GIS and R Alireza Arabameri and Hamid Reza Pourghasemi 14. Artificial Neural Networks for Flood Susceptibility Mapping in Data-Scarce Urban Areas Fatemeh Falah, Omid Rahmati, Mohammad Rostami, Ebrahim Ahmadisharaf, Ioannis N. Daliakopoulos, and Hamid Reza Pourghasemi 15. Modelling the Spatial Variability of Forest Fire Susceptibility Using Geographical Information Systems (GIS) and Analytical Hierarchy Process (AHP) Gigović Ljubomir, Dragan Pamučar, Siniša Drobnjak, and Hamid Reza Pourghasemi 16. Prioritization of Flood Inundation of Maharloo Watershed in Iran Using Morphometric Parameters Analysis and TOPSIS MCDM Model Mahdis Amiri, Hamid Reza Pourghasemi, Alireza Arabameri, Arya Vazirzadeh, Hossein Yousefi, and Sasan Kafaei 17. A Robust R-M-R (Remote Sensing – Spatial Modeling – Remote Sensing) Approach for Flood Hazard Assessment Stathopoulos Nikolaos, Kalogeropoulos Kleomenis, Chalkias Christos, Dimitriou Elias, Skrimizeas Panagiotis, Louka Panagiota, and Papadias Vagelis 18. Prioritization of Effective Factors on Zataria Multiflora Habitat Suitability and Its Spatial Modeling Mohsen Edalat, Enayat Jahangiri, Emran Dastras, and Hamid Reza Pourghasemi 19. Prediction of Soil Organic Carbon Using Regression Kriging Model and Remote Sensing Data Gouri Sankar Bhunia, Pravat Kumar Shit, Hamid Reza Pourghasemi, and Mohsen Edalat 20. 3D Reconstruction of Landslides for the Acquisition of Digital Databases and Monitoring Spatio-Temporal Dynamics of Landslides based on GIS Spatial Analysis and UAV Techniques Ştefan Bilaşco, Sanda Roşca, Dănuț Petrea, Iuliu Vescan, Ioan Fodorean, and Sorin Filip 21. A Comparative Study of Functional Data Analysis and Generalized Linear Model Data Mining Techniques for Landslide Spatial Modelling Wei Chen, Hamid Reza Pourghasemi, Shuai Zhang, and Jiale Wang 22. Regional Groundwater Potential Analysis Using Classification and Regression Trees Bahram Choubin, Omid Rahmati, Freidoon Soleimani, Hossein Alilou, Ehsan Moradi, and Nasrin Alamdari 23. Comparative Evaluation of Decision-Forest Algorithms in Object-Based Land Use and Land Cover Mapping Ismail Colkesen and Taskin Kavzoglu 24. Statistical Modelling of Landslides: Landslide Susceptibility and Beyond Stefan Steger and Christian Kofler 25. Assessing the Vulnerability of Groundwater to Salinization Using GIS-Based Data Mining Techniques in a Coastal Aquifer Alireza Motevalli, Hamid Reza Pourghasemi, Hossein Hashemi, and Vahid Gholami 26. A Framework for Multiple Moving Objects Detection in Aerial Videos Bahareh Kalantar, Alfian Abdul Halin, Husam Abdulrasool H. Al-Najjar, Shattri Mansor, John L. van Genderen, Helmi Zulhaidi M. Shafri, and Mohsen Zand 27. Modelling Soil Burn Severity Prediction for Planning Measures to Mitigate Post Wildfire Soil Erosion in NW Spain José M. Fernández-Alonso, Cristina Fernández, Stefano Arellano, and José A. Vega 28. Factors Influencing Regional Scale Wildfire Probability in Iran: An Application of Random Forest and Support Vector Machine Abolfazl Jaafari and Hamid Reza Pourghasemi 29. Land Use/Land Cover Change Detection and Urban Sprawl Analysis Cláudia M. Viana, Sandra Oliveira, Sérgio C. Oliveira, and Jorge Rocha 30. Spatial Modeling of Gully Erosion: A New Ensemble of CART and GLM Data Mining Algorithms Amiya Gayen and Hamid Reza Pourghasemi 31. Multi-Hazard Exposure Assessment on the Valjevo City Road Network Marjanović Miloš, Abolmasov Biljana, Milenković Svetozar, Đurić Uroš, Krušić Jelka, and Mileva Samardžić-Petrović 32. Producing a Spatially Focused Landslide Susceptibility Map Using an Ensemble of Shannon's Entropy and Fractal Dimension (The Ziarat Watershed, Iran) Aiding Kornejady and Hamid Reza Pourghasemi 33. A Conceptual Model on Relationship between Plant Spatial Distribution and Desertification Trend in Rangeland Ecosystems Hamid Reza Pourghasemi, Narges Kariminejad, and Mohsen Hosseinalizadeh Cover......Page 1 Spatial Modeling in GIS and R for Earth and Environmental Sciences......Page 3 Copyright......Page 4 Dedication......Page 5 List of Contributors......Page 6 1.1 Introduction......Page 14 1.2 The Study Area......Page 17 1.3 Methodology and Data......Page 18 1.4 Results......Page 23 1.5 Performance Criteria......Page 25 1.6 Discussion......Page 27 1.7 Conclusions......Page 28 References......Page 29 2.1 Introduction......Page 33 2.2.1 Study Area......Page 35 2.2.2 Data......Page 36 2.2.3 Vegetation Indices......Page 39 2.3.1.1 Normalized Difference Vegetation Index......Page 40 2.3.1.3 Green Normalized Difference Vegetation Index......Page 44 2.3.1.4 Global Environmental Monitoring Index......Page 47 2.3.2 Spatial Normalized Differential Reflectance and Shortwave Crop Reflectance Index......Page 49 2.3.3.1 Prespring Rainfall......Page 55 2.3.3.2 Cumulative Rainfall......Page 56 2.3.3.3 Rainfall Distribution......Page 58 References......Page 60 Further Reading......Page 64 3.1 Introduction......Page 66 3.2.1 Multiple Occurrence Regional Landslide Event, Messina, 2009......Page 68 3.2.2 Computing Slope Units in GIS......Page 71 3.3.1 Preprocessing......Page 72 3.3.2 Fitting a Cox Point Process Model Using R-INLA......Page 74 3.4.1 Estimated Fixed and Random Effects......Page 77 3.4.2 Estimated Landslide Intensity at Various Spatial Resolutions......Page 82 3.4.3 Model Checking and Goodness-of-Fit Assessment......Page 83 3.4.4 Cross-Validation Study and Out-of-Sample Predictive Skill......Page 85 3.5 Discussion......Page 87 3.6 Conclusion......Page 90 References......Page 91 4.1 Introduction......Page 95 Criteria and Subcriteria......Page 96 4.1.1.4 Interpretation Findings......Page 97 4.1.2 Classification of Spatial Decision Support System......Page 98 4.1.2.1 Geostatistical Analysis With R packages......Page 99 Tactical Planning......Page 100 Operational Planning......Page 101 4.1.3.1 General Information......Page 102 4.2 Planning Problems......Page 103 4.3.1 Multicriteria Decision Analysis......Page 105 4.3.2 Geostatistical Analysis......Page 107 4.3.3 Spatial Modeling Procedure......Page 108 4.4.1 The Current Conditions of the Terrain......Page 111 4.5 Discussion......Page 116 4.6 Conclusions......Page 121 References......Page 122 Further Reading......Page 126 5.1 Introduction......Page 127 5.2.1 Study Area......Page 131 5.2.3.1 KINEROS......Page 132 5.2.3.2 Optimization Algorithm......Page 135 5.2.3.3 Model Evaluation......Page 136 5.2.3.4 Parameters of Model in Optimization Process......Page 137 5.3 Results and Discussion......Page 138 5.4 Conclusion......Page 149 References......Page 151 Further Reading......Page 156 6.1 Introduction......Page 157 6.3.1 Land-Subsidence Inventory Mapping......Page 158 6.3.2 Effective Factors on Land Subsidence......Page 159 6.3.3 Spatial Relationship Between Land-Subsidence Locations and Different Effective Factors......Page 160 6.4.1 Investigating the Spatial Relationship Between Effective Factors and the Occurrence of Land Subsidence Using the FR Model......Page 161 6.4.3 Preparing the Land-Subsidence Susceptibility Map Using an RF Model......Page 164 References......Page 167 7.1 Introduction......Page 170 7.3 Methodology......Page 172 7.3.1 Multicriteria Decision-Making Drawbacks......Page 177 7.3.2 Radial Basic Function......Page 178 7.3.3.1 Initial Empires Creation......Page 179 7.3.3.2 Assimilation Policy......Page 180 7.3.3.5 The Calculation of Empires’ Power......Page 181 7.3.3.6 Empires’ Competition......Page 182 7.3.4 Combination of SWARA, RBF, and ICA......Page 183 7.4 Results......Page 184 7.4.2 The Location of Schools Regarding the Population Density and Proximity to Residential Areas......Page 186 7.4.3 The Location of Schools Regarding Accessibility to the Urban Road Network......Page 189 7.4.5 The Location of Schools Regarding Cultural and Recreational Centers......Page 190 7.5 Discussions......Page 191 7.6 Conclusions......Page 192 References......Page 193 8.1 Introduction......Page 198 8.2 Study Area and Data Analysis......Page 200 8.2.1 Data......Page 201 8.2.2 Methodology......Page 204 8.2.2.2 Fault Criteria......Page 205 8.2.2.4 Geology......Page 206 8.2.3 Nomination Criteria for Evaluating and Ranking Suitable Sites......Page 207 Analytic Hierarchy Process......Page 209 Technique for Order Performance by Similarity to Ideal Solution......Page 211 8.3.1 First Step (Boolean Algorithm)......Page 213 8.3.2 Secondary Step......Page 214 8.5 Conclusions......Page 216 References......Page 217 Further Reading......Page 220 9.1 Introduction......Page 221 9.2.1 Study Area......Page 222 9.2.3 Geo-Environmental Variables......Page 223 9.2.4.1 Generalized Linear Model (GLM)......Page 225 9.2.5 Model Validation......Page 227 9.3.1 Application of GLM......Page 228 9.3.2 Validation of the Habitat Suitability Map......Page 230 9.4 Conclusion......Page 231 References......Page 232 10.1 Introduction......Page 236 10.2 Study Area......Page 238 10.4 Data Used and Methodology......Page 241 10.4.1 Flood-Related Factors......Page 243 10.4.2 Application of AHP Approach......Page 248 10.4.3 Application of Remote Sensing to Establish a Flood Inventory Map......Page 249 10.5.1 Drainage Networks and Their Characteristics......Page 250 10.5.2 Flash Flood Susceptibility Map......Page 251 10.5.3 Real Flood Area Extraction From Satellite Images......Page 254 10.6 Model Validation......Page 255 References......Page 258 Further Reading......Page 264 11.1 Introduction......Page 265 11.2.1 Case Study......Page 266 11.2.2 Methodology......Page 267 11.2.2.1 Binary Logistic Regression......Page 268 11.2.2.2 Bayesian Theory......Page 269 11.2.2.3 SINMAP Model......Page 270 11.2.2.5 Random Forest Algorithm......Page 271 11.3.1 Binary Logistic Regression......Page 272 11.3.2 Landslide Susceptibility Map Using ANFIS......Page 274 11.4 Conclusion......Page 278 References......Page 279 Further Reading......Page 281 12.1 Introduction......Page 282 12.2 Study Area......Page 283 12.3 Data Collection......Page 285 12.4.1 Logistic Regression......Page 289 12.4.2 General Additive Model......Page 290 12.5 Spatial Prediction......Page 291 12.6 Results......Page 292 12.7 Discussion......Page 294 References......Page 299 13.1 Introduction......Page 303 13.2 Study Area......Page 305 13.3.1 Gully Erosion Inventory Map......Page 306 13.3.2.4 Plan Curvature......Page 307 13.3.2.8 Topography Wetness Index......Page 310 13.3.2.11 Normalized Difference Vegetation Index......Page 311 13.3.3 Multicollinearity Test......Page 312 13.3.5 Validation of Models......Page 313 13.4.1 Multicollinearity......Page 314 13.4.2 Applying the Linear Discriminant Analysis Model......Page 315 13.4.3 Applying the Quadratic Discriminant Analysis Model......Page 317 13.4.4 Validation of Models......Page 318 13.5 Conclusion......Page 320 References......Page 321 Further Reading......Page 325 14.1 Introduction......Page 326 14.2.2 Methodology......Page 327 14.2.2.2 Flood Conditioning Factors......Page 329 14.2.2.4 Variable Contribution Analysis......Page 331 14.3 Results and Discussion......Page 332 References......Page 335 Further Reading......Page 339 15.1 Introduction......Page 340 15.2.1 Study Area......Page 343 15.2.2 Used Data......Page 344 15.3.1 Interval Rough Numbers......Page 346 15.3.2 Rough Analytical Hierarchy Process Method......Page 348 15.4 Results......Page 352 15.4.2 The Application of the IR’AHP Model......Page 353 15.4.3 Weighted Linear Combination Aggregation......Page 360 15.4.4 Validation and Final Results......Page 363 15.5 Discussion......Page 364 15.6 Conclusion......Page 366 References......Page 367 Further Reading......Page 372 16.1 Introduction......Page 373 16.1.1 Background Research......Page 374 16.2.2 Research Methodology......Page 376 16.2.2.1 AHP Model......Page 378 16.2.2.2 Technique for Order of Preference by Similarity to the Ideal Solution Model......Page 380 16.3 Results and Discussion......Page 382 References......Page 389 Further Reading......Page 392 17.1 Introduction......Page 393 17.2 Study Area......Page 396 17.3.1 Data......Page 398 17.3.2 Methodology......Page 401 17.4 Results and Discussion......Page 406 References......Page 409 Further Reading......Page 412 18.1 Introduction......Page 413 18.2.1 Study Area......Page 414 18.3.1 Dataset Preparation for Habitat Suitability Modeling......Page 415 18.3.3 Modeling of Habitat Suitability of Zataria multiflora Using the Support Vector Machine Model......Page 420 18.3.5 Accuracy Assessment......Page 421 18.4.2 Results of Variable Importance of Effective Factors......Page 422 18.4.3 Habitat Suitability Using the S V M Model......Page 423 18.4.4 Validation of Habitat Suitability Map of Zataria multiflora......Page 425 References......Page 426 Further Reading......Page 429 19.1 Introduction......Page 430 19.2.1 Study Area......Page 431 19.2.2 Soil Organic Carbon Analysis From Field Data......Page 433 19.2.3 Data Collection and Processing......Page 434 19.2.4 The Predicted Variables (NDVI, MSAVI, RDVI, and MNLI)......Page 435 19.2.6 Model Validation......Page 437 19.3.2 Predictor Variables......Page 438 19.3.3 Analysis of Predictor Variables and Soil Organic Carbon Relationship......Page 440 19.3.4.1 Validation of Results......Page 442 19.4 Discussion......Page 445 References......Page 447 20.1 Introduction......Page 452 20.2 Study Area......Page 453 20.3 Methodology......Page 454 20.3.1 Aerial Image Acquisition Using Unmanned Aerial Vehicle Technology......Page 455 20.3.2 The Processing Stage of Aerial Images......Page 457 20.4 Results......Page 460 20.5 Conclusions......Page 463 References......Page 464 Further Reading......Page 466 21.1 Introduction......Page 467 21.3.1 Landslide Inventory Mapping......Page 468 21.3.2 Landslide Conditioning Factors......Page 470 21.3.3.1 Functional Data Analysis......Page 471 21.3.3.2 Generalized Linear Model......Page 474 21.4.1 Variable Importance......Page 475 21.4.2 Application of Functional Data Analysis......Page 476 21.4.4 Validation of Landslide Susceptibility Models......Page 477 21.5 Discussion......Page 478 References......Page 481 22.1 Introduction......Page 485 22.3 Methodology......Page 486 Topographic Factors......Page 488 Geological Factors......Page 491 22.3.3 Sensitivity Analysis and Model Performance......Page 492 22.4.1 Application of the Classification and Regression Tree Model for Groundwater Potentiality Mapping......Page 493 22.4.3 Sensitivity Analysis......Page 494 References......Page 496 Further Reading......Page 498 23.1 Introduction......Page 499 23.2 Study Area and Data......Page 501 23.3.1 Creation of Image Objects......Page 503 23.3.2 Selection of the Most Effective Object Features......Page 505 23.3.5 Canonical Correlation Forest Classifier......Page 506 23.4 Results and Discussion......Page 508 23.5 Conclusions......Page 513 References......Page 515 24.1 Introduction......Page 518 24.2.1 Theoretical Background and Practical Implementation......Page 520 24.2.2 Preparation and Selection of Spatial Data......Page 522 24.2.3 Modeling Algorithms......Page 526 24.3 Results: How to Evaluate a Statistical Landslide Susceptibility Model......Page 528 24.4.1 Challenges in Statistical Landslide Susceptibility Modeling......Page 531 24.4.2 Beyond a Data-Driven Identification of Landslide-Prone Zones......Page 533 24.5 Conclusion: A Word of Caution......Page 536 References......Page 537 25.1 Introduction......Page 546 25.2.1 Study Area......Page 547 25.2.2 Data Collection......Page 548 25.2.5.1 Groundwater Occurrence......Page 549 25.2.5.3 Groundwater Table Drawdown......Page 550 25.2.5.8 Bedrock Depth......Page 553 25.2.6.1 Generalized Linear Model......Page 554 25.2.6.3 Support Vector Machine......Page 555 25.3.1 Training/Calibration of Data-Mining Models......Page 556 25.3.2 Vulnerability Map of Data-Mining Models......Page 557 25.3.3 Importance of Factors by Learning Vector Quantization......Page 558 25.3.4 Validation Map of Data-Mining Models......Page 560 25.4 Discussion......Page 561 25.5 Conclusions......Page 562 References......Page 563 Further Reading......Page 570 26.1 Introduction......Page 571 26.2.1 Study Area and Dataset......Page 573 26.2.2.1 Segmentation and Region Merging......Page 574 26.2.2.2 Region Adjacency Graph Construction......Page 575 26.2.2.4 Multigraph Matching......Page 576 26.2.2.5 Correspondence Discovery......Page 577 26.2.2.6 Occlusion Detection......Page 578 26.2.2.8 Moving Object Detection......Page 579 26.3.2 Region Merging......Page 580 26.3.3 Multigraph Matching......Page 581 26.3.5 Moving Object Detection......Page 582 References......Page 584 27.1 Introduction......Page 587 27.2 Material and Methods......Page 589 27.2.2 Field Sampling......Page 590 27.2.3.2 Weather......Page 591 27.2.3.3 Vegetation......Page 592 27.2.4 Statistical Analysis......Page 593 27.3 Results......Page 594 27.4 Discussion......Page 597 References......Page 600 Further Reading......Page 604 28.1 Introduction......Page 605 28.3 Materials and Methods......Page 606 28.3.1 Data Collection and Processing......Page 607 28.3.3 Probability Modeling Using the Support Vector Machine Model......Page 609 28.4.1 Factor Importance......Page 610 28.4.2 Prediction Map......Page 612 References......Page 614 Further Reading......Page 617 29.1 Introduction......Page 618 29.1.2 Urban Growth Processes......Page 619 29.1.3 Geographic Information Systems and Remote Sensing Techniques in Urban Growth Analysis......Page 621 29.2.1 Study Area......Page 623 29.2.2 Satellite Image Selection and Preprocessing......Page 624 29.2.3.2 Normalized Difference Built-Up Index......Page 625 29.2.3.4 Normalized Difference Water Index......Page 626 29.2.4 Time-Series Image Classification......Page 627 29.2.4.1 Cross-Validation......Page 628 29.2.5 Measuring Urban Sprawl......Page 630 29.3.1 Time-Weighted Dynamic Time Warping Classification......Page 631 29.3.2 Time-Weighted Dynamic Time Warping Validation......Page 634 29.3.3 Urban Footprints......Page 637 29.3.4 Spatiotemporal Changes and Urban Sprawl......Page 638 Acknowledgments......Page 641 References......Page 642 30.1 Introduction......Page 649 30.2.1 Study Area......Page 650 30.2.2 Gully Erosion Inventory Mapping......Page 651 30.2.3.1 Primary Topographical Attributes Maps......Page 652 30.2.3.3 Linear Feature Maps......Page 653 30.3.1 Application of Classification and Regression Tree......Page 656 30.4.1 Gully Erosion Susceptibility models......Page 657 30.4.2 Validation of Machine Learning Models......Page 659 References......Page 661 Further Reading......Page 665 31.1 Introduction......Page 666 31.1.1 The State of the Art......Page 667 31.2 Valjevo Case Study......Page 668 31.2.1 Study Area Setting......Page 669 31.3 Materials and Methods......Page 671 31.3.1 Data Preparation......Page 672 31.3.2 Methodology......Page 673 31.3.2.2 Overlay Code......Page 676 31.4 Results and Discussion......Page 677 31.5 Conclusions......Page 680 References......Page 681 32.1 Introduction......Page 684 32.2 Study Area......Page 687 32.4 Landslide Inventory Mapping and Thematic Layers......Page 689 32.5 Analyzing Fractal Dimensions and Geomorphometric Indices......Page 697 32.5.1 Shannon’s Entropy......Page 699 32.6 Ensemble Modeling of Shannon’s Entropy and Fractal Dimension......Page 700 32.7 Intercomparison and Validation of Model Results......Page 701 32.8.1 Fractal Dimension and Geomorphometric Indices......Page 702 32.8.2 Shannon’s Entropy and the Fractal Dimensions......Page 709 32.8.3 Intercomparison and Validation of Models......Page 712 32.9 Discussion......Page 715 32.10 Limitations and Future Work......Page 719 32.11 Conclusion......Page 720 References......Page 721 Appendix I Different Landslide Types in the Study Area (the Rows Are in Line With Table 32-5)......Page 727 33.1 Introduction......Page 728 33.3.1 Field Measurements......Page 729 33.3.2 Spatial Analysis......Page 730 33.4.1 Ecological Attributes in Rangeland Ecosystems......Page 732 33.4.2 Diagnostic Dynamic Patterns of Desertification in Rangelands......Page 734 33.4.3 Statistical Analysis of Plant Spatial Patterns......Page 735 33.4.5 Introducing the Statistical Results to the New Monitoring Model......Page 736 33.5 Conclusion......Page 738 References......Page 739 Index......Page 742 Back Cover......Page 766