Application of fuzzy logic approach for wind erosion hazard mapping in Laghouat region (Algeria) using remote sensing and GIS

Saadoud, Djouher; Hassani, Mohamed; Peinado, F. Martín; Guettouche, Mohamed Saïd

doi:10.1016/j.aeolia.2018.01.002

Cited by 30 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different environmental and climatic factors are controlling wind erosion phenomena in drylands. Environmental variables affecting wind erosion include soil properties, lithology, land use, vegetation cover, topography, and elevation 1,8,27 . Previous research 28 introduced a local wind erosion climatic index based on the wind speed and effective precipitation index developed by 29 for applying in the Chepil wind erosion equation (WEQ).…”

Section: Methodsmentioning

confidence: 99%

Mapping wind erosion hazard with regression-based machine learning algorithms

Gholami

Mohammadifar

Bui

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Land susceptibility to wind erosion hazard in Isfahan province, Iran, was mapped by testing 16 advanced regression-based machine learning methods: Robust linear regression (RLR), Cforest, Non-convex penalized quantile regression (NCPQR), Neural network with feature extraction (NNFE), Monotone multi-layer perception neural network (MMLPNN), Ridge regression (RR), Boosting generalized linear model (BGLM), Negative binomial generalized linear model (NBGLM), Boosting generalized additive model (BGAM), Spline generalized additive model (SGAM), Spike and slab regression (SSR), Stochastic gradient boosting (SGB), support vector machine (SVM), Relevance vector machine (RVM) and the Cubist and Adaptive network-based fuzzy inference system (ANFIS). Thirteen factors controlling wind erosion were mapped, and multicollinearity among these factors was quantified using the tolerance coefficient (TC) and variance inflation factor (VIF). Model performance was assessed by RMSE, MAE, MBE, and a Taylor diagram using both training and validation datasets. The result showed that five models (MMLPNN, SGAM, Cforest, BGAM and SGB) are capable of delivering a high prediction accuracy for land susceptibility to wind erosion hazard. DEM, precipitation, and vegetation (NDVI) are the most critical factors controlling wind erosion in the study area. Overall, regression-based machine learning models are efficient techniques for mapping land susceptibility to wind erosion hazards.

show abstract

Section: Methodsmentioning

confidence: 99%

Mapping wind erosion hazard with regression-based machine learning algorithms

Gholami

Mohammadifar

Bui

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In prior research, wind velocity was considered the main trigger of wind erosion processes [18,19]. Saadoud et al [32] and Mezösi et al [33] further investigated air temperature and precipitation. In a particular area of AP Vojvodina (Deliblato sands), Kadović et al [34] pointed to the drought factor in relation to the soil degradation caused by desertification processes.…”

Section: Climate Factor Analysismentioning

confidence: 99%

Identifying Areas Sensitive to Wind Erosion—A Case Study of the AP Vojvodina (Serbia)

et al. 2019

View full text Add to dashboard Cite

Wind erosion is one of the most significant forms of land degradation which occurs in arid and semi-arid regions. Agricultural land is significantly affected by wind erosion, which leads to soil quality reduction, and consequently to economic losses. This research was conducted in the autonomous province (AP) of Vojvodina (a region dominated by agriculture), which represents one of the most important economic regions in the Republic of Serbia. The aim of this research was to identify areas sensitive to wind erosion (in the month of March) in the AP Vojvodina by using fuzzy logic, remote sensing data, and geographical information systems (GIS). The data of prior research on erosion sediment were used for results validation. The results show that the hazardous sensitivity category covers approximately 60.41% of the research area, while the medium sensitive category accounts for 36% of the area. These findings are primarily a result of the lack of vegetation in almost the entire area, particularly in wind-exposed agricultural areas with no vegetation, which are being prepared for sowing. Another factor putting such a large area at risk is the unfavorable climate (especially in southeastern parts of the area), and slightly less favorable soil properties in the north. The results of this research could be used in decision-making at the regional level, along with the development and implementation of programs aimed at mitigating the effects of wind erosion.

show abstract

“…In general, machine learning techniques allow one to analyze a set of data exhaustively and generate results that might not be evident to the eyes of an expert. Therefore, these techniques have been employed to derive new equations and mathematical models to represent complex systems and interactions [23][24][25]. The following is an analysis of previous research that has employed machine learning techniques to extract the C factor from satellite images.…”

Section: Related Workmentioning

confidence: 99%

Synthesis of Vegetation Indices Using Genetic Programming for Soil Erosion Estimation

et al. 2019

View full text Add to dashboard Cite

Vegetation Indices (VIs) represent a useful method for extracting vegetation information from satellite images. Erosion models like the Revised Universal Soil Loss Equation (RUSLE), employ VIs as an input to determine the RUSLE soil Cover factor (C). From the standpoint of soil conservation planning, the C factor is one of the most important RUSLE parameters because it measures the combined effect of all interrelated cover and management variables. Despite its importance, the results are generally incomplete because most indices recognize healthy or green vegetation, but not senescent, dry or dead vegetation, which can also be an important contributor to C. The aim of this research is to propose a novel approach for calculating new VIs that are better correlated with C, using field and satellite information. The approach followed by this research is to state the generation of new VIs in terms of a computer optimization problem and then applying a machine learning technique, named Genetic Programming (GP), which builds new indices by iteratively recombining a set of numerical operators and spectral channels until the best composite operator is found. Experimental results illustrate the efficiency and reliability of this approach to estimate the C factor and the erosion rates for two watersheds in Baja California, Mexico, and Zaragoza, Spain. The synthetic indices calculated using this methodology produce better approximation to the C factor from field data, when compared with state-of-the-art indices, like NDVI and EVI.

show abstract

Application of fuzzy logic approach for wind erosion hazard mapping in Laghouat region (Algeria) using remote sensing and GIS

Cited by 30 publications

References 39 publications

Mapping wind erosion hazard with regression-based machine learning algorithms

Mapping wind erosion hazard with regression-based machine learning algorithms

Identifying Areas Sensitive to Wind Erosion—A Case Study of the AP Vojvodina (Serbia)

Synthesis of Vegetation Indices Using Genetic Programming for Soil Erosion Estimation

Contact Info

Product

Resources

About