Multiscale spatiotemporal characteristics of landscape patterns, hotspots, and influencing factors for soil erosion

Predicting Rainfall-Induced Soil Erosion Based on a Hybridization of Adaptive Differential Evolution and Support Vector Machine Classification

Mathematical Problems in Engineering ◽

10.1155/2021/6647829 ◽

2021 ◽

Vol 2021 ◽

pp. 1-20

Author(s):

Tuan Vu Dinh ◽

Hieu Nguyen ◽

Xuan-Linh Tran ◽

Nhat-Duc Hoang

Keyword(s):

Neural Network ◽

Machine Learning ◽

Artificial Neural Network ◽

Support Vector Machine ◽

Soil Erosion ◽

Differential Evolution ◽

Influencing Factors ◽

Support Vector ◽

Adaptive Differential Evolution ◽

Artificial Neural

Soil erosion induced by rainfall is a critical problem in many regions in the world, particularly in tropical areas where the annual rainfall amount often exceeds 2000 mm. Predicting soil erosion is a challenging task, subjecting to variation of soil characteristics, slope, vegetation cover, land management, and weather condition. Conventional models based on the mechanism of soil erosion processes generally provide good results but are time-consuming due to calibration and validation. The goal of this study is to develop a machine learning model based on support vector machine (SVM) for soil erosion prediction. The SVM serves as the main prediction machinery establishing a nonlinear function that maps considered influencing factors to accurate predictions. In addition, in order to improve the accuracy of the model, the history-based adaptive differential evolution with linear population size reduction and population-wide inertia term (L-SHADE-PWI) is employed to find an optimal set of parameters for SVM. Thus, the proposed method, named L-SHADE-PWI-SVM, is an integration of machine learning and metaheuristic optimization. For the purpose of training and testing the method, a dataset consisting of 236 samples of soil erosion in Northwest Vietnam is collected with 10 influencing factors. The training set includes 90% of the original dataset; the rest of the dataset is reserved for assessing the generalization capability of the model. The experimental results indicate that the newly developed L-SHADE-PWI-SVM method is a competitive soil erosion predictor with superior performance statistics. Most importantly, L-SHADE-PWI-SVM can achieve a high classification accuracy rate of 92%, which is much better than that of backpropagation artificial neural network (87%) and radial basis function artificial neural network (78%).

Download Full-text

Characteristics of Soil Erodibility K Value and Its Influencing Factors in the Changyan Watershed, Southwest Hubei, China

Land ◽

10.3390/land11010134 ◽

2022 ◽

Vol 11 (1) ◽

pp. 134

Author(s):

Xiaofang Huang ◽

Lirong Lin ◽

Shuwen Ding ◽

Zhengchao Tian ◽

Xinyuan Zhu ◽

...

Keyword(s):

Land Use ◽

Soil Erosion ◽

Spatial Variability ◽

Influencing Factors ◽

Soil Type ◽

Soil Survey ◽

Purple Soil ◽

Soil Erodibility ◽

K Value ◽

K Factor

Soil erodibility K factor is an important parameter for evaluating soil erosion vulnerability and is required for soil erosion prediction models. It is also necessary for soil and water conservation management. In this study, we investigated the spatial variability characteristics of soil erodibility K factor in a watershed (Changyan watershed with an area of 8.59 km2) of Enshi, southwest of Hubei, China, and evaluated its influencing factors. The soil K values were determined by the EPIC model using the soil survey data across the watershed. Spatial K value prediction was conducted by regression-kriging using geographic data. We also assessed the effects of soil type, land use, and topography on the K value variations. The results showed that soil erodibility K values varied between 0.039–0.052 t·hm2·h/(hm2·MJ·mm) in the watershed with a block-like structure of spatial distribution. The soil erodibility, soil texture, and organic matter content all showed positive spatial autocorrelation. The spatial variability of the K value was related to soil type, land use, and topography. The calcareous soil had the greatest K value on average, followed by the paddy soil, the yellow-brown soil (an alfisol), the purple soil (an inceptisol), and the fluvo-aquic soil (an entisol). The soil K factor showed a negative correlation with the sand content but was positively related to soil silt and clay contents. Forest soils had a greater ability to resist to erosion compared to the cultivated soils. The soil K values increased with increasing slope and showed a decreasing trend with increasing altitude.

Download Full-text

Assessment of landscape changes under different urban dynamics based on a multiple-scenario modeling approach

Environment and Planning B Urban Analytics and City Science ◽

10.1177/2399808320910161 ◽

2020 ◽

Vol 47 (8) ◽

pp. 1361-1379

Author(s):

Chao Xu ◽

Dagmar Haase ◽

Meirong Su ◽

Yutao Wang ◽

Stephan Pauleit

Keyword(s):

Influencing Factors ◽

Landscape Pattern ◽

Urban Landscape ◽

Diversity Index ◽

Housing Demand ◽

Landscape Patterns ◽

Urban Region ◽

Aggregation Index ◽

Rapid Urbanization ◽

Urban Dynamics

In the context of rapid urbanization, it remains unclear how urban landscape patterns shift under different urban dynamics, in particular taking different influencing factors of urban dynamics into consideration. In the present study, three key influencing factors were considered, namely, housing demand, spatial structure, and growth form. On this basis, multiple urban dynamic scenarios were constructed and then calculated using either an autologistic regression–Markov chain–based cellular automata model or an integer programming-based urban green space optimization model. A battery of landscape metrics was employed to characterize and quantitatively assess the landscape pattern changes, among which the redundancy was pre-tested and reduced using principal component analysis. The case study of the Munich region, a fast-growing urban region in southern Germany, demonstrated that the changes of the patch complexity index and the landscape aggregation index were largely similar at sub- and regional scales. Specifically, low housing demand, monocentric and compact growth scenarios showed higher levels of patch complexity but lower levels of landscape aggregation, compared to high housing demand, polycentric and sprawl growth scenarios, respectively. In contrast, the changes in the landscape diversity index under different scenarios showed contrasting trends between different sub-regional zones. The findings of this study provide planners and policymakers with a more in-depth understanding of urban landscape pattern changes under different urban planning strategies and its implications for landscape functions and services.

Download Full-text

The tradeoff between soil erosion protection and water consumption in revegetation: Evaluation of new indicators and influencing factors

Geoderma ◽

10.1016/j.geoderma.2019.02.003 ◽

2019 ◽

Vol 347 ◽

pp. 32-39 ◽

Cited By ~ 1

Author(s):

Daili Pan ◽

Shiwei Yang ◽

Yaqian Song ◽

Xiaodong Gao ◽

Pute Wu ◽

...

Keyword(s):

Soil Erosion ◽

Influencing Factors ◽

Water Consumption ◽

Erosion Protection

Download Full-text

Forestland change and soil erosion in karst watershed under the Grain to Green Project

10.5194/egusphere-egu2020-4456 ◽

2020 ◽

Author(s):

Siwen Feng ◽

Hongya Wang ◽

Hongyan Liu ◽

Chenyi Zhu ◽

Shuai Li

Keyword(s):

Soil Erosion ◽

Influencing Factors ◽

Southwest China ◽

Drainage Basin ◽

Karst Area ◽

Karst Region ◽

Vegetation Growth ◽

The Past ◽

Pixel Scale ◽

River Drainage Basin

<div>With the implementation of the Grain to Green Project, the vegetation growth in karst region in southwest China has increased. In order to explore whether the growth of trees can be sustained after artificial afforestation in karst area and the influence of the forestland change on soil erosion, the WaTEM/SEDEM model was used to simulate the 11 stages of annual soil erosion in the past 33 years in Chongan river drainage basin in Guizhou, and the dominant influencing factors of soil erosion change in the past 33 years were discussed based the pixel scale in this study. The results showed that the forestland increased in a fluctuating way after the conversion project, and the decrease of forestland was mainly caused by drought, especially in the area where the dolomites were distributed. Therefore, the change of forestland caused no significant improvement in soil erosion since the Grain to Green Project.</div><p></p>

Download Full-text

A New Indicator to Better Represent the Impact of Landscape Pattern Change on Basin Soil Erosion and Sediment Yield in the Upper Reach of Ganjiang, China

Land ◽

10.3390/land10090990 ◽

2021 ◽

Vol 10 (9) ◽

pp. 990

Author(s):

Yongfen Zhang ◽

Nong Wang ◽

Chongjun Tang ◽

Shiqiang Zhang ◽

Yuejun Song ◽

...

Keyword(s):

Land Use ◽

Soil Erosion ◽

River Basin ◽

Landscape Metrics ◽

Landscape Pattern ◽

Sediment Yield ◽

River Basins ◽

Landscape Patterns ◽

Soil Erodibility ◽

Land Use Pattern

Landscape patterns are a result of the combined action of natural and social factors. Quantifying the relationships between landscape pattern changes, soil erosion, and sediment yield in river basins can provide regulators with a foundation for decision-making. Many studies have investigated how land-use changes and the resulting landscape patterns affect soil erosion in river basins. However, studies examining the effects of terrain, rainfall, soil erodibility, and vegetation cover factors on soil erosion and sediment yield from a landscape pattern perspective remain limited. In this paper, the upper Ganjiang Basin was used as the study area, and the amount of soil erosion and the amount of sediment yield in this basin were first simulated using a hydrological model. The simulated values were then validated. On this basis, new landscape metrics were established through the addition of factors from the revised universal soil loss equation to the land-use pattern. Five combinations of landscape metrics were chosen, and the interactions between the landscape metrics in each combination and their effects on soil erosion and sediment yield in the river basin were examined. The results showed that there were highly similar correlations between the area metrics, between the fragmentation metrics, between the spatial structure metrics, and between the evenness metrics across all the combinations, while the correlations between the shape metrics in Combination 1 (only land use in each year) differed notably from those in the other combinations. The new landscape indicator established based on Combination 4, which integrated the land-use pattern and the terrain, soil erodibility, and rainfall erosivity factors, were the most significantly correlated with the soil erosion and sediment yield of the river basin. Finally, partial least-squares regression models for the soil erosion and sediment yield of the river basin were established based on the five landscape metrics with the highest variable importance in projection scores selected from Combination 4. The results of this study provide a simple approach for quantitatively assessing soil erosion in other river basins for which detailed observation data are lacking.

Download Full-text

Test of the RUSLE and Key Influencing Factors Using GIS and Probability Methods: A Case Study in Nanling National Nature Reserve, South China

Advances in Civil Engineering ◽

10.1155/2019/7129639 ◽

2019 ◽

Vol 2019 ◽

pp. 1-15

Author(s):

Jun Wang ◽

Qian He ◽

Ping Zhou ◽

Qinghua Gong

Keyword(s):

Spatial Distribution ◽

Soil Erosion ◽

Influencing Factors ◽

South China ◽

Nature Reserve ◽

Ground Truth ◽

Landsat 8 ◽

Erosion Risk ◽

Soil Erosion Risk ◽

National Nature Reserve

The main purposes of the study were to test the performance of the Revised Universal Soil Loss Equation (RUSLE) and to understand the key factors responsible for generating soil erosion in the Nanling National Nature Reserve (NNNR), South China, where soil erosion has become a very serious ecological and environmental problem. By combining the RUSLE and geographic information system (GIS) data, we first produced a map of soil erosion risk at 30 m-resolution pixel level with predicted factors. We then used consecutive Landsat 8 satellite images to obtain the spatial distribution of four types of soil erosion and carried out ground truth checking of the RUSLE. On this basis, we innovatively developed a probability model to explore the relationship between four types of soil erosion and the key influencing factors, identify high erosion area, and analyze the reason for the differences derived from the RUSLE. The results showed that the overall accuracy of image interpretation was acceptable, which could be used to represent the currently actual spatial distribution of soil erosion. Ground truth checking indicated some differences between the spatial distribution and class of soil erosion derived from the RUSLE and the actual situation. The performance of the RUSLE was unsatisfactory, producing differences and even some errors when used to estimate the ecological risks posed by soil erosion within the NNNR. We finally produced a probability table revealing the degree of influence of each factor on different types of soil erosion and quantitatively elucidated the reason for generating these differences. We suggested that soil erosion type and the key influencing factors should be identified prior to soil erosion risk assessment in a region.

Download Full-text

To link landscape pattern with soil erosion risk at watershed scale based on SPSM model in the loess hilly area

10.5194/egusphere-egu2020-4995 ◽

2020 ◽

Author(s):

Liding Chen

Keyword(s):

Soil Erosion ◽

Matrix Model ◽

Landscape Pattern ◽

Pattern Analysis ◽

Sustainable Land Use ◽

Landscape Patterns ◽

Landscape Index ◽

Risk Area ◽

Ecological Processes ◽

Landscape Pattern Analysis

<p>Linking landscape patterns to specific ecological processes has been and will continue to be a key topic in landscape ecology. However, the traditional landscape pattern analysis by landscape metrics inspired by patch-matrix model (PMM) may be difficult to reach such a requirement, and thus landscape pattern analysis to denote the significance of ecological process is strongly hindered. To find conceptual and methodological innovations integrating ecological processes with landscape patterns is important. In this paper, we proposed a conceptual model, i.e., the source-pathway-sink model (SPSM) by defining the role of each landscape unit to a specific process before conducting landscape pattern analysis. The traditional landscape matrices derived from the patch-matrix model is visual- or geometrical-oriented but lack of linkage to ecological significance. The source-pathway-sink model is process-oriented, dynamic, and scale dependent. This model as a complementary to the patch-corridor-matrix model can provide a simple and dynamic perspective on landscape pattern analysis. Based on the SPSM model, a landscape index was developed in term of the process of soil erosion, and further testified by using on-site measurements. It was found the new landscape index based on SPSM is useful in evaluating the risk of soil erosion from landscape pattern at watershed. Finally, a case study was conducted in the loess hilly areas to define the risk area of soil erosion that will be useful for sustainable land use management and optimization in future.</p>

Download Full-text

The Spatiotemporal Coupling Characteristics of Regional Urbanization and Its Influencing Factors: Taking the Yangtze River Delta as an Example

Sustainability ◽

10.3390/su11030822 ◽

2019 ◽

Vol 11 (3) ◽

pp. 822 ◽

Cited By ~ 11

Author(s):

Dong Xu ◽

Guolin Hou

Keyword(s):

Spatial Autocorrelation ◽

Spatial Correlation ◽

Influencing Factors ◽

Yangtze River ◽

Yangtze River Delta ◽

River Delta ◽

The Yangtze River ◽

Spatiotemporal Characteristics ◽

The Yangtze River Delta ◽

Coordination Degree

The research on the coupling coordination of regional urbanization is of great significance for achieving sustainable urbanization. Based on the theories of coordinated development, this paper constructs an index system for comprehensive evaluation of the three sub-systems of urbanization (population, economy and land urbanization). Then, the entropy method, coupling coordination degree model and spatial autocorrelation analysis are used to explore the spatiotemporal characteristics of overall and pairwise coordination among population, land and economy urbanization. Finally, the geographic detector model is used to analyze the influencing factors in the urbanization process. The results show that: (1) the levels of population, land and economy urbanization in the Yangtze River Delta have been improved from 2001 to 2016. The overall and pairwise coupling coordination degrees among them also continue to improve and the stage characteristics are presented. (2) The spatial distribution of low-level and high-level coupling coordination cities shows a certain spatial dependence and a Z-shaped pattern, respectively. The spatiotemporal characteristics of pairwise coupling coordination indicate regional imbalance of the urbanization. (3) The overall coupling coordination degree of urbanization has an apparent spatial autocorrelation, with its local spatial correlation patterns dominated by the High–High and Low–Low type agglomeration. Significant differences in local spatial correlation patterns of the pairwise coupling coordination suggest that regional synergy should not be neglected. (4) The economic development level is the main factor influencing the spatiotemporal differentiation of the coupling coordination of urbanization. Location traffic conditions and population agglomeration effect are the second most influencing factors. The evolution mechanisms of coupling coordination of urbanization are affected by factors in change. The findings highlight the importance of dealing with the relationship among population, land and economy in the process of regional urbanization and have implications for promoting the integration of urban agglomerations.

Download Full-text

Soil Erosion Influencing Factors in the Semiarid Area of Northern Shaanxi Province, China

10.5772/intechopen.92979 ◽

2020 ◽

Author(s):

Ning Ai ◽

Qingke Zhu ◽

Guangquan Liu ◽

Tianxing Wei

Keyword(s):

Soil Erosion ◽

Influencing Factors ◽

Shaanxi Province ◽

Semiarid Area ◽

Northern Shaanxi

Download Full-text