Soil science
Omid Rahmati; Seyed Masoud Soleimanpour; Samad Shadfar; Salahudin Zahedi
Abstract
Extended Abstract
Introduction
Gully erosion is one of the most important factors affecting sediment production and land degradation, and predicting its occurrence is one of the practical solutions to prevent gully erosion. Since the occurrence of gully erosion is directly related to environmental factors ...
Read More
Extended Abstract
Introduction
Gully erosion is one of the most important factors affecting sediment production and land degradation, and predicting its occurrence is one of the practical solutions to prevent gully erosion. Since the occurrence of gully erosion is directly related to environmental factors and human activities, it is possible to identify areas prone to gully erosion using models based on artificial intelligence and data mining. Modeling helps to save time and cost of measuring gutters. Also, because artificial intelligence and data mining models have a high ability to analyze environmental information; they are able to identify nonlinear and complex relationships between variables, and for this reason, they have been widely accepted by researchers in various sciences worldwide. For this purpose, this study aimed to predict gully erosion susceptibility using random forest models and boosted regression trees in the Talwar watershed located in the southeast of Kurdistan province.
Materials and Methods
Initially, 99 gullies were identified during field visits, the location of the gully head-cut was recorded, and a map of the spatial distribution of the gullies was prepared. The recorded gullies were randomly divided into two groups: training and validation in a ratio of 70:30, such that 70% of the gullies were in the training group and the rest in the validation group. In addition, maps of factors affecting gully erosion including elevation, slope gradient, slope aspect, lithology, distance from the stream, topographic wetness index, land use, plan curvature, profile curvature, average annual rainfall, relative slope position, stream power index, distance from the road, soil order, and soil texture were prepared in geographic information system. Subsequently, in the modeling process, environmental factors were considered as independent variables and the creation of gullies as a dependent variable. In order to model gully erosion, the training group gullies were used in this stage to calibrate the models. In this study, Random Forest (RF) and Boosted Regression Trees (BRT) machine learning models were used to predict gully erosion. In these models, raster layers related to environmental factors affecting gully erosion were introduced as independent variables to the model. Also, the layer of gully front points, which were previously named after the training group, was introduced as a dependent variable to the model. The process of running the models was carried out in the R software environment. The prediction accuracy of the models was also evaluated using the area under the receiver operating characteristic curve (AUC) method.
Results and Discussion
The spatial pattern of gully erosion by these two models showed that in this basin, generally the middle, eastern and northern parts, which are adjacent to waterways and rivers, have a higher tendency to cause gully erosion. Since the prediction interval of gully erosion in artificial intelligence models varies between zero and one, it can be considered as the probability of gully erosion. The lowest and highest values of the probability of gully erosion by the random forest model were obtained as 0.006 and 0.996, respectively. The median value of the prediction of gully erosion in the prediction of the random forest model was also calculated as 0.322. Therefore, fifty percent of the pixels in this basin have a tendency to cause gully erosion greater than 0.322 and the other half of its tendency is less than 0.322. The spatial pattern of gully erosion prediction from the boosted regression tree model also varied from 0.011 to 0.799. This model generally introduced the adjacent sections of the drainage network in the middle, eastern, and northern parts as the most favorable lands for the creation and formation of gully erosion. The median value in the prediction made using this model was 0.387. The prediction accuracy of the models was also obtained based on the area under the receiver operating characteristic curve in the random forest and boosted regression tree models, 0.952 and 0.891, respectively.
Conclusion
The findings showed that the random forest model has more accuracy in the spatial prediction of gully erosion in the Talwar watershed. Also, based on the AUC criterion, the random forest model was placed in the excellent group (AUC>0.9) and the boosted regression tree model was placed in the very good group (AUC<0.8). According to the findings of this study, executive agencies can use artificial intelligence and data mining models, such as the random forest model, to prepare a gully erosion map and plan and prioritize areas for implementing soil conservation measures. Certainly, focusing soil conservation executive measures and management programs in areas prone to gully erosion in the country's watersheds will improve the performance and optimize the financial resources of natural resources and watershed management departments.
S.H.R. Sadeghi; M.B. Raisi; Z. Hazbavi
Abstract
Introduction: The capability of a soil to resist erosion depends on soil-particle size and distribution, soil structure and structural stability, soil permeability, water content, organic matter content, and mineral and chemical constituents. Among many affecting factors on aforesaid characteristics, ...
Read More
Introduction: The capability of a soil to resist erosion depends on soil-particle size and distribution, soil structure and structural stability, soil permeability, water content, organic matter content, and mineral and chemical constituents. Among many affecting factors on aforesaid characteristics, the freezing-thawing processes may considerably affects. Freeze–thaw fluctuation is a natural phenomenon that is frequently encountered by soils in the higher latitude and altitude regions in late autumn and early spring. Effects of freezing and freezing-thawing phenomena on soil erosion and sediment yield are important. Nevertheless, soil conservation under these phenomena by using different methods as well as soil amendments has not been yet considered. Surface application of anionic polyacrylamide (PAM) in solution has been found to be very effective in decreasing seal formation, runoff, and erosion.PAM stabilizes soil structure due to the ability of the polymer chains to adsorb onto clay particles and bridge them together forming stable domains. This adsorption can be a result of interactions between the negatively-charged functional groups of the PAM molecules and the positively-charged edges of clay minerals, orexchangeable polycations (mainly Ca2+) acting as ‘bridges’ between the negative charges of the PAM's functional groups and the negatively- charged planar surfaces of the clay. The PAM is adsorbed on the external surfaces of the aggregates and binds soil particles far apart together, thereby were shorter and evidently less effective in enhancing increasing their resistance to splash by raindrop impact and detachment by runoff. A lot of research work focused on freezing effects in soils on aggregation or increase aggregate stability and emphasis corresponding effects. But the effects of application of soil amendments on soil induced freeze and thaw cycle have not been studied yet.
Materials and Methods: The present study evaluated the performance of PAM in controlling freeze-thaw cycle effects on splash erosion from a silty loam soil. A freeze-thaw cycle was simulated in Soil Erosion and Rainfall Simulation Laboratory of TarbiatModares University. The present study was conducted under controlled laboratory conditions with a simulated rainfall. The maximum efforts were made to mimic natural conditions to get access to results with high level of fidelity. Towards this attempt, air and different soil depth temperatures were analyzed in natural condition and 10 cm soil depth was targeted for the soil laboratory experiments. The rainfall storm with 72 mm h-1 and 30 min duration was simulated and conducted for the study treatments. The soil was poured in small erosion box with 0.25 m2 surface area in three replicates. A thick filter, draining the lower 20 cm of the soil profile was generated using mineral pumices.The prepared soil sample was evenly packed into the soil plots at a bulk density of 1.3 Mg m−3 similar to that measured under natural conditions. The plots were then placed in saturated pool for 24 h and then left to be drained to achieve an average moisture content of 35% similar to that recorded for the realities in the study area. So, splash erosion rates were measured using splash cups in two control treatments without PAM subjected to freezing and freezing-thawing processes, and two other plots treated by freezing and freezing-thawing processesplus application of 20 kg ha-1 of PAM. After securing thenormality ofdata, the average net splash erosionand the average upward and downward rates of splash erosion in allexperimental treatmentswere comparedby paired sampled T-test.
Results and Discussion: According to the results of statistical analyses, the PAM application had a significant effect (p
