scholarly journals Spatial Pattern Analysis and Prediction of Gully Erosion Using Novel Hybrid Model of Entropy-Weight of Evidence

Water ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 1129 ◽  
Author(s):  
Alireza Arabameri ◽  
Artemi Cerda ◽  
John P. Tiefenbacher
Keyword(s):  
Land Use ◽  
Hybrid Model ◽  
Land Use Planning ◽  
Drainage Density ◽  
Gully Erosion ◽  
Weight Of Evidence ◽  
Spatial Pattern Analysis ◽  
Entropy Weight ◽  
Northern Iran ◽  
Environmental Conditioning

Gully erosion is an environmental problem in arid and semi-arid areas. Gullies threaten the soil and water resources and cause off- and on-site problems. In this research, a new hybrid model combines the index-of-entropy (IoE) model with the weight-of-evidence (WoE) model. Remote sensing and GIS techniques are used to map gully-erosion susceptibility in the watershed of the Bastam district of Semnan Province in northern Iran. The performance of the hybrid model is assessed by comparing the results with from models that use only IoE or WoE. Three hundred and three gullies were mapped in the study area and were randomly classified into two groups for training (70% or 212 gullies) and validation (30% or 91 gullies). Eighteen topographical, hydrological, geological, and environmental conditioning factors were considered in the modeling process. Prediction-rate curves (PRCs) and success-rate curves (SRCs) were used for validation. Results from the IoE model indicate that drainage density, slope, and rainfall factors are the most important factors promoting gullying in the study area. Validation results indicate that the ensemble model performed better than either the IoE or WoE models. The hybrid model predicted that 38.02 percent of the study area has either high or very high susceptible to gullying. Given the high accuracy of the novel hybrid model, this scientific methodology may be very useful for land use management decisions and for land use planning in gully-prone regions. Our research contributes to achieve Land Degradation Neutrality as will help to design remediation programs to control non-sustainable soil erosion rates.

scholarly journals Using the analytic hierarchy process to create an erosion risk map. A case study in Malakasiotiko stream, Trikala perfecture

2007 ◽  
Vol 40 (4) ◽  
pp. 1904 ◽  
Author(s):  
G. Bathrellos ◽  
H. Skilodimou
Keyword(s):  
Land Use ◽  
Analytic Hierarchy Process ◽  
Land Use Planning ◽  
Drainage Basin ◽  
Drainage Density ◽  
Risk Map ◽  
Analytic Hierarchy ◽  
Erosion Risk ◽  
The Impact ◽  
Hierarchy Process

This study is aimed at the evaluation of the erosion risk at the drainage basin of Malakasiotiko stream in Trikala prefecture, using a Geographic Information System (GIS). A database from six factors that influence erosion namely slope, lithology, drainage density, tectonic features density, land use and rainfall inserted into GIS. Each factor was grouped in various classes. A method known as Analytic Hierarchy Process (ΑΗΡ) was applied to rate the individual classes of each factor and weight the impact of one factor against the other in order to determination their importance to erosion process. The results of the ΑΗΡ application in combination with GIS techniques were used to estimate the overall erosion risk and create the erosion risk map. The study area was divided into three zones of erosion risk. High erosion risk zones are mostly located on the northwest, west and south parts of the drainage basin of Malakasiotiko stream. The erosion risk map of the study area can be a useful geologic and géomorphologie criterion for the land use planning.

scholarly journals Reconstructing long-term gully dynamics in Mediterranean agricultural areas

2016 ◽  
Author(s):  
Antonio Hayas ◽  
Tom Vanwalleghem ◽  
Ana Laguna ◽  
Adolfo Peña ◽  
Juan V. Giráldez
Keyword(s):  
Land Use ◽  
Temporal Resolution ◽  
Land Use Changes ◽  
Mediterranean Area ◽  
Drainage Density ◽  
Gully Erosion ◽  
Aerial Photographs ◽  
High Temporal Resolution ◽  
Erosion Rates ◽  
Erosion Processes

Abstract. Gully erosion is an important erosive process, especially in Mediterranean basins. However, the longterm dynamics of gully networks and the variation of sediment production in gullies is not well known. Available studies are often done over a few years only, while many gully networks form, grow, and change in response to environmental and land use or management changes over a long period. In order to clarify the effect of these changes, it is important to analyze the evolution of the gully network with a high temporal resolution. This study aims at analyzing gully morphodynamics over a long time scale (1956–2013) in a large Mediterranean area in order to quantify gully erosion processes and its contribution to overall sediment dynamics. A gully network of 20 km2 located in SW Spain, has been analyzed using a sequence of 10 aerial photographs in the period 1956–2013. The extension of the gully network both increased and decreased in the study period. Gully drainage density varied between 1.93 km km−2 in 1956, with a minimum of 1.37 km km−2 in 1980 and a maximum of 5.40 km km−2 in 2013. The main controlling factor of gully activity appeared to be rainfall, while land use changes were found to have only an indirect effect. A new Monte Carlo-based approach was proposed to reconstruct gully erosion rates from orthophotos. Gully erosion rates were found to be relatively stable between 1956–2009, with a mean value of 11.2 ton ha−1 yr−1, while in the period 2009–2011, characterized by extreme winter rainfalls, this value increased significantly, to 591 ton ha−1 yr−1. These results show that gully erosion rates are highly variable and that a simple interpolation between the start and end date would highly underestimate gully contribution during certain years, such as for example between 2009–2011. This illustrates the importance of the applied methodology using a high temporal resolution of orthophotos.

Hydro-meteorological hazard analysis for new settlements framed in the Colombian peace process

2021 ◽  
Author(s):  
Edier Vicente Aristizábal Giraldo ◽  
Keyword(s):  
Land Use ◽  
Land Use Planning ◽  
Flood Hazard ◽  
Peace Process ◽  
Weight Of Evidence ◽  
Hazard Evaluation ◽  
Left Wing ◽  
Peace Agreement ◽  
Field Samples ◽  
New Settlements

<p>Colombia is a country with a recent history of an armed conflict from 1960. In 2012, a negotiation process started between the Colombian National Government and the largest left-wing guerrilla group (FARC - Fuerzas Armadas Revolucionarias de Colombia in Spanish). Finally, in 2016 a final peace agreement was signed, where several compromises were taken by both sides. For starting, one of the most important element of the agreement was to define concentration areas into the Colombia territory, where the entire FARC members should be located transitory, and posteriorly those areas must change to permanent settlements following the current regulation related to land use planning in Colombia. This study shows the hazard, vulnerability and risk assessment for 5 concentration areas, which were prioritized, of 24 total areas established. The multi-hazard assessment was analysed from a regional (10-m resolution) and detailed (0.5-m resolution) approach.</p><p>For the regional approach, landslide susceptibility was assessed through analytic hierarchy process and weight of evidence methodologies compared to logistic regression and landslide hazard was evaluated with SHALSTAB and Newmark's models for rainfall and seismic triggers. Floods hazard was analysed through a combined methodology using unit hydrograph and the morphometric descriptor HAND. Meanwhile, torrential flows hazard was analysed from a morphometric evaluation and sediment availability from SHALSTAB unstable areas joined with the flood methodology using sediment and water volumes to establish the corresponding area of impact.</p><p>For the detailed approach, through field samples and local geotechnical parameters and using TRIGRS and SCOOPS 3D models, the hazard evaluation was carried out for a deterministic result and using FOSM model results can be processed to obtain a probabilistic hazard map. Flood hazard was estimated using the bidimensional hydrodynamic model IBER and the discharge was enhanced simulating the sediment volumes from unstable areas to assess torrential flows hazard but also the mass flow simulation model r.avaflow was employed for a better simulation of the rheology of the flow using the same discharge rates.</p><p>This study shows the role of multi-hazard studies as a fundamental element in a peace process, to establish new settlements in the rural area according to the Colombian land-use planning regulation, and under very complex and mountainous terrains conditions. One of the critical points in the short and long term for the sustainability of this peace process is to provide safe areas where FARC members may start a new life.</p>

scholarly journals Analisis Kesesuaian Lahan Kawasan Lahan Basah (Wetland) untuk Perencanaan Tata Guna Lahan Berkelanjutan di Kabupaten Tulang Bawang

2021 ◽  
Vol 5 (1) ◽  
pp. 58
Author(s):  
Dwi Bayu Prasetya ◽  
Hediyati Anisia
Keyword(s):  
Land Use ◽  
Land Use Planning ◽  
Agricultural Land ◽  
Economic Value ◽  
Land Suitability ◽  
Sustainable Land Use ◽  
Spatial Pattern Analysis ◽  
Suitability Analysis ◽  
Wetland Area ◽  
Bird Populations

The wetland area in Tulang Bawang Regency is a stretch of swamps that has an important value ecologically and hydrologically and has economic value. However, currently, the area's condition has begun to change its function to agricultural land, resulting in damage to the habitat and function of swamps, causing a decrease in biological resources such as fish and bird populations. The use of wetlands must be carefully planned and designed with land use principles with a sustainable perspective. The aim of this research is; 1.) Identifying the potential for hydrology, potential land use, and the condition of biodiversity in the Wetland area; 2) Formulating alternative land suitability in the wetland area planning in Tulang Bawang Regency by taking into account biophysical factors and area functions. This research's approach method is spatial pattern analysis, which is to study the patterns, shapes, and distribution of phenomena on the earth's surface. In addition, understand the meaning of these patterns and use them in sustainable land use planning. Based on the results of land suitability analysis for wetland planning in Tulang Bawang Regency, it can be concluded that this area is classified as very suitable (S1) with a score of 93.33. For the development of wetlands through nature conservation and cultural heritage of the Tulang Bawang community as objects and the main attraction of this area.

scholarly journals Credal decision tree based novel ensemble models for spatial assessment of gully erosion and sustainable management

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alireza Arabameri ◽  
Nitheshnirmal Sadhasivam ◽  
Hamza Turabieh ◽  
Majdi Mafarja ◽  
Fatemeh Rezaie ◽  
...  
Keyword(s):  
Decision Tree ◽  
Predictive Accuracy ◽  
Drainage Density ◽  
Gully Erosion ◽  
Rate Curve ◽  
Northern Iran ◽  
Relative Significance ◽  
Ensemble Models ◽  
Testing Dataset ◽  
Sensitivity Specificity

AbstractWe introduce novel hybrid ensemble models in gully erosion susceptibility mapping (GESM) through a case study in the Bastam sedimentary plain of Northern Iran. Four new ensemble models including credal decision tree-bagging (CDT-BA), credal decision tree-dagging (CDT-DA), credal decision tree-rotation forest (CDT-RF), and credal decision tree-alternative decision tree (CDT-ADTree) are employed for mapping the gully erosion susceptibility (GES) with the help of 14 predictor factors and 293 gully locations. The relative significance of GECFs in modelling GES is assessed by random forest algorithm. Two cut-off-independent (area under success rate curve and area under predictor rate curve) and six cut-off-dependent metrics (accuracy, sensitivity, specificity, F-score, odd ratio and Cohen Kappa) were utilized based on both calibration as well as testing dataset. Drainage density, distance to road, rainfall and NDVI were found to be the most influencing predictor variables for GESM. The CDT-RF (AUSRC = 0.942, AUPRC = 0.945, accuracy = 0.869, specificity = 0.875, sensitivity = 0.864, RMSE = 0.488, F-score = 0.869 and Cohen’s Kappa = 0.305) was found to be the most robust model which showcased outstanding predictive accuracy in mapping GES. Our study shows that the GESM can be utilized for conserving soil resources and for controlling future gully erosion.

scholarly journals GENETIC ALGORITHM BASED FEATURE SELECTION FOR LANDSLIDE SUSCEPTIBILITY MAPPING IN NORTHERN IRAN

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 821-825
Author(s):  
Z. Nikraftar ◽  
S. Rajabi-Kiasari ◽  
S. T. Seydi
Keyword(s):  
Genetic Algorithm ◽  
Land Use ◽  
Land Use Planning ◽  
Landslide Susceptibility ◽  
Machine Learning Algorithms ◽  
Landslide Susceptibility Mapping ◽  
Support Vector ◽  
Northern Iran ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Abstract. Recognizing where landslides are most likely to occur is crucial for land use planning and decision-making especially in the mountainous areas. A significant portion of northern Iran (NI) is prone to landslides due to its climatology, geological and topographical characteristics. The main objective of this study is to produce landslide susceptibility maps in NI applying three machine learning algorithms such as K-nearest neighbors (KNN), Support Vector Machines (SVM) and Random Forest (RF). Out of the total number of 1334 landslides identified in the study area, 894 (≈67%) locations were used for the landslide susceptibility maps, while the remaining 440 (≈33%) cases were utilized for the model validation. 21 landslide triggering factors including topographical, hydrological, lithological and Land cover types were extracted from the spatial database using SAGA (System for Automated Geoscientific Analyses), ArcGIS software and satellite images. Furthermore, a genetic algorithm was employed to select the most important informative features. Then, landslide susceptibility was analyzed by assessing the environmental feasibility of influential factors. The obtained results indicate that the RF model with the overall accuracy (OA) of 90.01% depicted a better performance than SVM (OA = 81.06%) and KNN (OA = 83.05%) models. The produced susceptibility maps can be productively practical for upcoming land use planning in NI.

Sign in / Sign up

Export Citation Format

Share Document