Assessment of magnetite as a magnetic tracer for sediments in the study of ephemeral gully erosion: conditioning factors of magnetic susceptibility

In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811).

Download Full-text

A field investigation on ephemeral gully erosion processes under different upslope inflow and sediment conditions

Journal of Hydrology ◽

10.1016/j.jhydrol.2019.03.037 ◽

2019 ◽

Vol 572 ◽

pp. 517-527 ◽

Cited By ~ 6

Author(s):

Tongjia Wu ◽

Chengzhong Pan ◽

Changjia Li ◽

Mingjie Luo ◽

Xiaoyu Wang

Keyword(s):

Field Investigation ◽

Gully Erosion ◽

Erosion Processes ◽

Ephemeral Gully

Download Full-text

An experimental study on dynamic processes of ephemeral gully erosion in loess landscapes

Geomorphology ◽

10.1016/j.geomorph.2010.09.016 ◽

2011 ◽

Vol 125 (1) ◽

pp. 203-213 ◽

Cited By ~ 33

Author(s):

J.G. Gong ◽

Y.W. Jia ◽

Z.H. Zhou ◽

Y. Wang ◽

W.L. Wang ◽

...

Keyword(s):

Experimental Study ◽

Gully Erosion ◽

Dynamic Processes ◽

Ephemeral Gully

Download Full-text

Degradation of soil physicochemical quality by ephemeral gully erosion on sloping cropland of the hilly Loess Plateau, China

Soil and Tillage Research ◽

10.1016/j.still.2015.07.012 ◽

2016 ◽

Vol 155 ◽

pp. 9-18 ◽

Cited By ~ 29

Author(s):

Mingxiang Xu ◽

Qiang Li ◽

Glenn Wilson

Keyword(s):

Loess Plateau ◽

Gully Erosion ◽

Physicochemical Quality ◽

Ephemeral Gully ◽

Hilly Loess Plateau

Download Full-text

Implementation of Artificial Intelligence Based Ensemble Models for Gully Erosion Susceptibility Assessment

Remote Sensing ◽

10.3390/rs12213620 ◽

2020 ◽

Vol 12 (21) ◽

pp. 3620

Author(s):

Indrajit Chowdhuri ◽

Subodh Chandra Pal ◽

Alireza Arabameri ◽

Asish Saha ◽

Rabin Chakrabortty ◽

...

Keyword(s):

Land Use Changes ◽

Area Under The Curve ◽

Regression Tree ◽

Gully Erosion ◽

Support Vector ◽

Boosted Regression Tree ◽

Conditioning Factors ◽

Susceptibility Maps ◽

Chotanagpur Plateau ◽

Additive Regression

The Rarh Bengal region in West Bengal, particularly the eastern fringe area of the Chotanagpur plateau, is highly prone to water-induced gully erosion. In this study, we analyzed the spatial patterns of a potential gully erosion in the Gandheswari watershed. This area is highly affected by monsoon rainfall and ongoing land-use changes. This combination causes intensive gully erosion and land degradation. Therefore, we developed gully erosion susceptibility maps (GESMs) using the machine learning (ML) algorithms boosted regression tree (BRT), Bayesian additive regression tree (BART), support vector regression (SVR), and the ensemble of the SVR-Bee algorithm. The gully erosion inventory maps are based on a total of 178 gully head-cutting points, taken as the dependent factor, and gully erosion conditioning factors, which serve as the independent factors. We validated the ML model results using the area under the curve (AUC), accuracy (ACC), true skill statistic (TSS), and Kappa coefficient index. The AUC result of the BRT, BART, SVR, and SVR-Bee models are 0.895, 0.902, 0.927, and 0.960, respectively, which show very good GESM accuracies. The ensemble model provides more accurate prediction results than any single ML model used in this study.

Download Full-text

Analysis and assessment of ephemeral gully erosion in wide areas of Navarre (Spain) from routinely obtained ortophotographs

10.5194/egusphere-egu2020-10866 ◽

2020 ◽

Author(s):

Youssef Chahor ◽

Javier Casalí ◽

Rafae Giménez

Keyword(s):

Management Practices ◽

Sudden Change ◽

Low Frequency ◽

Direct Methods ◽

Gully Erosion ◽

Aerial Photographs ◽

Large Area ◽

Small Watersheds ◽

Ephemeral Gully ◽

Ephemeral Gullies

Ephemeral gullies (EG) are linear erosion features located in swales where runoff concentrates during or immediately after rainfall events. EG are temporary because they are easily filled by conventional machinery and cause important soil losses in cultivated areas. Casal&#237; et al. (1999) distinguished three types of EG: &#8220;classical&#8221;, formed by concentrated runoff flows within the same field where runoff started; &#8220;drainage&#8221;, created by concentrated flows draining areas upstream from the field; &#8220;discontinuity&#8221;, found in places where management practices create a sudden change in slope. There is still a great lack of knowledge about the true extent and importance of this EG. In this sense, the information obtained from aerial photographs can be of great value. The main objective of this work is to evaluate the possibility of making an exhaustive characterization of the space-time evolution of ephemeral gullies in a relatively large area from color aerial photographs. The effect of precipitation on the EG will be also analyzed.The 570 ha study area is almost completely cultivated with winter cereals and located in the Pitillas district (Navarre). Climate is Continental Mediterranean (on average 550 &#160;mm yr-1). Soil (upper horizons) are loam&#8211;silty loam in texture.EG within cultivated fields were located, classified and digitized using GIS interfaces over seven colour orthophotos (1:5000 with 0.5mx0.5m resolution) taken between 2003 and 2014. Gully length was determined after locating EG down and upstream ends. EG drainage areas and slopes were determined using a 2 m resolution DEM.To determine EG volumes, an empirical power model for the study area defining the relationship between EG lengths and volumes was first obtained from previous field measurement, and then used for the EG lengths from this study. The corresponding erosion rates were also calculated.57 small watersheds affected by EGs were identified, being 39 of them classified as drainage EGs, and the remaining 18 EGs as classic. 70% of the small watersheds were affected by EG only once. In remaining watersheds EG reappeared from twice to seven times. Therefore, it seems that the repeatability is not as high as thought.The average erosion rate in classical EG is about 1.1 Kg m-2 year-1. Previous assessments using accurate direct methods reported an average value of 0.8 Kg m-2 year-1 for very similar watersheds in the same area. Although it is not a conclusive proof, this findings indicate that both methods provide similar results.A very high correlation (r2= 0.84) has been found between the length of the gullies formed in the study area and the total annual precipitation. It would follow that EG erosion would also be controlled by the overall amount of rainfall also in Mediterranean climates, and not only by high intensity-low frequency events.References<ol><li>Casal&#237;, J. J. L&#243;pez, J. V. Gir&#225;ldez, 1999. Ephemeral gully erosion in Southern Navarra (Spain). CATENA 36: 65-84.</li> </ol>

Download Full-text

Evaluation of the magnetite as a magnetic tracer of eroded sediment from ephemeral gullies: conditioning factors of magnetic susceptibility

10.5194/egusphere-egu2020-2199 ◽

2020 ◽

Author(s):

Elena Zubieta ◽

Juan Larrasoaña ◽

Rafael Giménez ◽

Alaitz Aldaz ◽

Javier Casalí

Keyword(s):

Magnetic Susceptibility ◽

Soil Moisture ◽

Moisture Content ◽

Soil Surface ◽

Field Capacity ◽

Field Studies ◽

Silty Clay ◽

Magnetic Signal ◽

Conditioning Factors ◽

Detection Depth

In gully erosion, the soil detached by the action of the erosive flow can be transported over long distances along the drainage network of the watershed. In this long way, the eroded material can be redistributed and/or deposited on the soil surface, and then eventually buried by eroded material from subsequent erosion events. Likewise, the variability of the soil (i.e., in texture and moisture content) over which this material moves can be considerable. The presence of the eroded material could be detected through magnetic tracers attached/mixed with the eroded soil. In this experiment, the degree to which the magnetic signal of the magnetite is conditioned by (i) the burying tracer depth, (ii) the texture and moisture content of the soil covering the tracer and (iii) the tracer concentration was evaluated.The study was carried out in the lab in different containers (0.5 x 0.5 x 0.3 m3). Each container was filled with a given soil. In the filling process, a 0.5-cm layer of a soil-magnetite mixture of a certain concentration was interspersed in the soil profile at a certain depth. Overall, 3 different soil:tracer concentrations (1000:1, 200:1, 100:1), 4 tracer burying depths (0 cm, 3 cm, 5 cm and 10 cm from soil surface), and &#160;2 contrasting soils (silty clay and sandy clay loam) were used. In each case, the magnetic susceptibility was measured with a magnetometer (MS3 by Bartington Instruments). Experiments were repeated with different soil moisture contents (from field capacity to dry soil).If the tracer is located under the soil surface a minimum soil:tracer concentration of 200:1 is required for its correct &#160;detection from the surface using a magnetometer. The intensity of the magnetic signal decreases dramatically with the vertical distance &#160;of the tracer from the soil&#160; surface (burying depth). The maximum detection depth of the tracer magnetic signal is strongly dependent on the natural magnetic susceptibility of the soil which hides the own tracer signal. Variation in soil moisture content does not significantly affect the magnetic signal. For extensive field studies the soil-tracer volume to be handled would be very high. Therefore, it is necessary to explore new tracer application techniques.

Download Full-text