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.
M.J. Roosta; K. Enayati; S.M. Soleimanpour; K. Kamali
Abstract
Introduction: Carbon sequestration (CS) by forests, pastures, afforested stands and soils is the most appropriate way to reduce atmospheric carbon. A combination of all these activities can help balance the global warming process by reducing the concentration of atmospheric CO2. The amount of CS and ...
Read More
Introduction: Carbon sequestration (CS) by forests, pastures, afforested stands and soils is the most appropriate way to reduce atmospheric carbon. A combination of all these activities can help balance the global warming process by reducing the concentration of atmospheric CO2. The amount of CS and quality of carbon storage in the soil depends on the interaction between climate, soil, tree species, litter chemical composition and their management. The results of Dinakaran and Krishnayya (2008) research showed that the type of vegetation cover has a significant effect on soil carbon storage. So that the amount of carbon storage in the soil depends on the amount of carbon entering the soil through plant debris and carbon loss through decomposition. To increase carbon in the soil, management activities such as increasing the amount of carbon entering the soil by adding litter and crop residues as well as reducing the rate of decomposition of soil organic matter should be done. Decomposition rate of soil organic matter is affected by soil condition (humidity, temperature and access to oxygen), sequestration of organic matter, placement of organic matter in the soil profile and the degree of physical protection by aggregates. Evaluating the role of aquifer management in reducing via storing the atmospheric CO2, to organic carbon (O.C) is the aim of this study. Materials and Methods: The studied land uses were as follows: 1-Rangeland-without flood spreading-with grazing (control), 2- Range without grazing-without flood spreading, 3- Six rangelands stripes-with grazing-with flood spreading, 4- Rangeland-Atriplex plantation-with spreading of flood, 5- Eucalyptus control forest-without flood spreading, 6- Eucalyptus forest-first strip-with flood spreading-BisheZard 4 (BZ4), 7- Eucalyptus forest-second strip-with flood spreading-(BZ4), 8- Eucalyptus forest-third strip-with flood spreading-(BZ4), 9- Acacia forest-with flood spreading-(BZ4). Soil and plant were sampled from each land use type. Then, the amount of O.C was measured in the laboratory and CS was calculated. The economic-environmental value of carbon stored in the soil is based on Rivers' proposal, which declares a carbon tax rate of $200 per tonne of CO2. The dollar is equal to 42,000 Iranian rials. Data were analyzed using randomized complete block design and Duncan test (at p < 0.05 ) was used to compare mean values using the SAS software. Results and Discussion: The analysis of variance showed that the effect of different land uses on the bulk density (BD), %O.C and the CS in the soil was significant at the level of 1%. Comparison of the mean of BD in various land uses showed that the eucalyptus forest (third strip) had the lowest BD compared to others, and the difference between this land use and other land uses was statistically significant. The first strip of Eucalyptus forest had the highest %O.C and the highest amount of CS in the soil, and the statistical difference between these two indices in this land use with other land uses was significant. Among the studied land uses, the lowest amounts of CS were related to the control range and range without grazing-without flood spreading. The interaction of plant to plant species on plant dry weight and plant carbon storage showed that the rangeland species of Heliantemum lippii and Dendrostellera lessertii in the range with flood spreading have the highest dry-weight and the species of Helianthomus has the highest amount of carbon storage. This indicates that the impacts of flood spreading on plant biomass production and carbon storage have been greater than the impact of no grazing on these indicators. In all uses, Artemisia sieberi showed the lowest dry weight and carbon storage. Planting of Eucalyptus camaldulensis irrigated with flood water spreading increased the soil O.C from 0.51% in the control to 1.68% in the first strip of eucalyptus forest (3.29 times). By calculating the mean of the three strips in which the eucalyptus was planted, it was found that the highest carbon content of 121.84 ton/ha was stored in the plant, litter and soil of this land use. Given that, each tonne of carbon is equivalent to 3.67 tons of CO2 gas, it can be concluded that 447.15 tonnes of CO2 gas from the air is stored as organic matter. The economic-environmental value of this CS is 3.76 billion rials ($89523.81) per hectare. Conclusion: The studied land that was irrigated with flood spreading, especially the eucalyptus forested area at Kowsar station, captured significant amounts of CO2 from the air and stored it as organic matter in the root and shoot of plants and in the soil. Also, this may lead to the release of a large amount of oxygen gas to the environment which play an important role in reducing air pollution. Considering the economic-environmental value of the carbon stored in the eucalyptus plantation forest areas, the development of this method in flood prone areas is quite economically justifiable. Due to the high potential of tree species in improving soil carbon storage, it seems that increasing the percentage of woody species and their physiological diversity have increased the carbon storage capacity of these species. Therefore, in order to improve the carbon storage capacity of flood distribution systems, it is suggested that the planting of native and perennial compatible species in these systems should be considered.
