scholarly journals Susceptibility Mapping of Soil Water Erosion Using Machine Learning Models

Water ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1995 ◽  
Author(s):  
Amirhosein Mosavi ◽  
Farzaneh Sajedi-Hosseini ◽  
Bahram Choubin ◽  
Fereshteh Taromideh ◽  
Gholamreza Rahi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Erosion ◽  
Vegetation Index ◽  
Water Erosion ◽  
Kappa Coefficient ◽  
Probability Of Detection ◽  
Susceptibility Mapping ◽  
Rainfall Erosivity ◽  
Critical Factors ◽  
Effective Factors

Soil erosion is a serious threat to sustainable agriculture, food production, and environmental security. The advancement of accurate models for soil erosion susceptibility and hazard assessment is of utmost importance for enhancing mitigation policies and laws. This paper proposes novel machine learning (ML) models for the susceptibility mapping of the water erosion of soil. The weighted subspace random forest (WSRF), Gaussian process with a radial basis function kernel (Gaussprradial), and naive Bayes (NB) ML methods were used in the prediction of the soil erosion susceptibility. Data included 227 samples of erosion and non-erosion locations through field surveys to advance models of the spatial distribution using predictive factors. In this study, 19 effective factors of soil erosion were considered. The critical factors were selected using simulated annealing feature selection (SAFS). The critical factors included aspect, curvature, slope length, flow accumulation, rainfall erosivity factor, distance from the stream, drainage density, fault density, normalized difference vegetation index (NDVI), hydrologic soil group, soil texture, and lithology. The dataset cells of samples (70% for training and 30% for testing) were randomly prepared to assess the robustness of the different models. The functional relevance between soil erosion and effective factors was computed using the ML models. The ML models were evaluated using different metrics, including accuracy, the kappa coefficient, and the probability of detection (POD). The accuracies of the WSRF, Gaussprradial, and NB methods were 0.91, 0.88, and 0.85, respectively, for the testing data; 0.82, 0.76, and 0.71, respectively, for the kappa coefficient; and 0.94, 0.94, and 0.94, respectively, for POD. However, the ML models, especially the WSRF, had an acceptable performance regarding producing soil erosion susceptibility maps. Maps produced with the most robust models can be a useful tool for sustainable management, watershed conservation, and the reduction of soil and water loss.

scholarly journals SVM-Based Geospatial Prediction of Soil Erosion Under Static and Dynamic Conditioning Factors

2018 ◽  
Vol 203 ◽  
pp. 04004
Author(s):  
Muhammad Raza Ul Mustafa ◽  
Abdulkadir Taofeeq Sholagberu ◽  
Khamaruzaman Wan Yusof ◽  
Ahmad Mustafa Hashim ◽  
Muhammad Waris Ali Khan ◽  
...  
Keyword(s):  
Soil Erosion ◽  
Watershed Management ◽  
Land Use Planning ◽  
Land Surface ◽  
Vegetation Index ◽  
Support Vector ◽  
Susceptibility Map ◽  
Rainfall Erosivity ◽  
Kappa Index ◽  
Conditioning Factors

Land degradation caused by soil erosion remains an important global issue due to its adverse consequences on food security and environment. Geospatial prediction of erosion through susceptibility analysis is very crucial to sustainable watershed management. Previous susceptibility studies devoid of some crucial conditioning factors (CFs) termed dynamic CFs whose impacts on the accuracy have not been investigated. Thus, this study evaluates erosion susceptibility under the influence of both non-redundant static and dynamic CFs using support vector machine (SVM), remote sensing and GIS. The CFs considered include drainage density, lineament density, length-slope and soil erodibility as non-redundant static factors, and land surface temperature, soil moisture index, vegetation index and rainfall erosivity as the dynamic factors. The study implements four kernel tricks of SVM with sequential minimal optimization algorithm as a classifier for soil erosion susceptibility modeling. Using area under the curve (AUC) and Cohen’s kappa index (k) as the validation criteria, the results showed that polynomial function had the highest performance followed by linear and radial basis function. However, sigmoid SVM underperformed having the lowest AUC and k values coupled with higher classification errors. The CFs’ weights were implemented for the development of soil erosion susceptibility map. The map would assist planners and decision makers in optimal land-use planning, prevention of soil erosion and its related hazards leading to sustainable watershed management.

scholarly journals Geospatial Analysis of Soil Erosion Susceptibility and Causative Factors in Anambra State, South East, Nigeria

2021 ◽  
pp. 5-32
Author(s):  
Romanus Udegbunam Ayadiuno ◽  
Dominic Chukwuka Ndulue ◽  
Chinemelu Cosmas Ndichie ◽  
Arinze Tagbo Mozie ◽  
Philip O. Phil-Eze ◽  
...  
Keyword(s):  
Soil Erosion ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Soil Loss ◽  
Vegetation Index ◽  
Anthropogenic Activities ◽  
Rainfall Erosivity ◽  
Anambra State ◽  
Causative Factors

Land degradation is a function of soil erosion leading to soil loss and reduction in crop productivity as well as other socio-economic activities. The menace of soil erosion is challenging due to diverse factors including advertent and inadvertent anthropogenic activities. This study looks at soil erosion susceptibility and causative factors in Anambra State, both static and dynamic with the intent of identifying them, investigating spatial variability of soil loss, relate erodibility to soil properties and causative factors to soil erosion. Eight (8) prominent causative factors (CFs), were identified. These causative factors (CFs) were analyzed using ArcGIS 10.2. Sixty (60) soil samples were extracted randomly, analyzed, and tested. The study identified CFs such as Drainage Density, Erosion Density, Lineament Density, Slope Length, Land Surface Temperature, and Rainfall Erosivity, which contribute to Soil Erodibility (K - Factor). Land Surface Temperature, Soil Moisture Index, Rainfall Erosivity, and Normalized Difference Vegetation Index contributed to the loss of 8.97 ton/ha/yr, 9.1288 ton/ha/yr, 1,1134.7 ton/ha/yr, and 0.245 ton/ha/yr respectively to erosion in Anambra State. Conclusively, the dynamic causative factors influence soil susceptibility and trigger erosion in the State.

scholarly journals Soil erosion risk assessment: a case study of the Jos Plateau, Nigeria

2021 ◽  
pp. 109-117
Author(s):  
Ayodele Owonubi
Keyword(s):  
Soil Erosion ◽  
Vegetation Index ◽  
Vegetation Coverage ◽  
Anthropogenic Factors ◽  
Rainfall Erosivity ◽  
Entire Area ◽  
Jos Plateau ◽  
Erosion Rates ◽  
Erosion Processes ◽  
Soil Erosion Rates

Soil erosion is a treat to global food security. The objective of this study was to evaluate factors influencing erosion on the arable lands of the Jos Plateau; and to estimate the extent of soil erosion in the area. Universal Soil Loss Equation (USLE) model was used to evaluate soil erosion processes in the study area. This was facilitated with the aid of Geographic Information System Both for Interpolation and Geospatial analysis. Soil data from field survey was the primary source of data for analysis of soil erodibility. Topographic factor was determined from 90-meter elevation data. Rainfall erosivity was determined from rainfall data at 1 kilometer resolution. Whereas vegetation cover factor was determined from Normalized Difference Vegetation Index. Results of the study indicate that rainfall erosivity values were remarkably high and have mean values of 5117MJ.mm/ ha.h.y. Analysis of percent areal coverage indicate that the entire area had 52, 34, 7, and 7% low, moderate, high and very high topographic factors respectively. Further analysis indicate that anthropogenic factors had severely affected vegetation coverage of the Jos plateau, especially on the arable lands. Furthermore, during this research, the mean annual actual and potential soil erosion rates were estimated spatially over the Jos Plateau area. Soil erosion rates were far more than tolerable rates thereby affecting soil fertility and productivity.

scholarly journals Spatial-Temporal Variability of Future Rainfall Erosivity and Its Impact on Soil Loss Risk in Kenya

2021 ◽  
Vol 11 (21) ◽  
pp. 9903
Author(s):  
George Watene ◽  
Lijun Yu ◽  
Yueping Nie ◽  
Zongke Zhang ◽  
Yves Hategekimana ◽  
...  
Keyword(s):  
Soil Erosion ◽  
Soil Loss ◽  
National Level ◽  
Water Erosion ◽  
Cmip5 Models ◽  
Rainfall Erosivity ◽  
African Countries ◽  
Maximum Increase ◽  
Rcp Scenarios ◽  
Incremental Change

Ongoing climate change poses a major threat to the soil resources of many African countries that mainly rely on an agricultural economy. While arid and semi-arid lands (ASALs) take up most of Kenya’s land mass, approximately 64% of its total croplands lie within mountainous areas with high rainfall, hence, areas highly vulnerable to water erosion. Flooding of the Great Lakes and increasing desertification of the ASALs are illustrative cases of the implications of recent precipitation dynamics in Kenya. This study applied the Revised Universal Soil Loss Equation (RUSLE) to estimate future soil erosion rates at the national level based on four Coupled Model Intercomparison Project v5 (CMIP5) models under two Representative Concentration Pathway (RCP) scenarios. Results showed the current soil loss rate to be at 4.76 t ha−1 yr−1 and projected an increase in average rainfall erosivity under the two scenarios, except for RCP-2.6 (2030s) and (2080s) for the MIROC-5 model. Future projections revealed an incremental change in rainfall erosivity from the baseline climate by a cumulative average of 39.9% and 61.1% for all scenarios by the 2030s and 2080s, respectively, while soil loss is likely to increase concomitantly by 29% and 60%, respectively. The CCCMA_CANESM2 model under the RCP 8.5 (2080s) scenario projected the highest erosion rate of 15 t ha−1 yr−1 over Kenya, which is a maximum increase of above 200%, with the Rift Valley region recording an increase of up to 100% from 7.05 to 14.66 t ha−1 yr−1. As a first countrywide future soil erosion study, this assessment provides a useful reference for preventing water erosion and improving ecosystem service security.

scholarly journals Mapping erosion prone areas in the Bouhamdane watershed (Algeria) using the Revised Universal Soil Loss Equation through GIS

2017 ◽  
Vol 32 (1) ◽  
pp. 13-23 ◽  
Author(s):  
Hamza Bouguerra ◽  
Abderrazak Bouanani ◽  
Kamel Khanchoul ◽  
Oussama Derdous ◽  
Salah Eddine Tachi
Keyword(s):  
Soil Erosion ◽  
Soil Loss ◽  
Erosion Control ◽  
Water Erosion ◽  
Universal Soil Loss Equation ◽  
Rainfall Erosivity ◽  
Vegetative Cover ◽  
Erosion Risk ◽  
Very High ◽  
Soil Loss Equation

Abstract Soil erosion by water is a major problem that the Northern part of Algeria witnesses nowadays; it reduces: the productivity of agricultural areas due to the loss of lands, and leads to the loss of storage capacity in reservoirs, the deterioration of water quality etc. The aim of this study is to evaluate the soil losses due to water erosion, and to identify the sectors which are potentially sensitive to water erosion in the Bouhamdane watershed, that is located in the northeastern part of Algeria. To this end, the Revised Universal Soil Loss Equation (RUSLE) was used. The application of this equation takes into account five parameters, namely the rainfall erosivity, topography, soil erodibility, vegetative cover and erosion control practices. The product of these parameters under GIS using the RUSLE mathematical equation has enabled evaluating an annual average erosion rate for the Bouhamdane watershed of 11.18 t·ha-1·y-1. Based on the estimates of soil loss in each grid cell, a soil erosion risk map with five risk classes was elaborated. The spatial distribution of risk classes was 16% very low, 41% low, 28% moderate, 12% high and 3% very high. Most areas showing high and very high erosion risk occurred in the lower Bouhamdane watershed around Hammam Debagh dam. These areas require adequate erosion control practices to be implemented on a priority basis in order to conserve soil resources and reduce siltation in the reservoir.

scholarly journals A New Approach For Smart Soil Erosion Modelling: Integration of Empirical And Machine Learning Models

2021 ◽  
Author(s):  
Mohammadtaghi Avand ◽  
Maziar Mohammadi ◽  
Fahimeh Mirchooli ◽  
Ataollah Kavian ◽  
John P Tiefenbacher
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Soil Erosion ◽  
Classification Tree ◽  
Slope Angle ◽  
Rainfall Erosivity ◽  
Learning Models ◽  
New Approach ◽  
Erosion Modelling ◽  
Machine Learning Models

Abstract Despite advances in artificial intelligence modelling, the lack of soil erosion data and other watershed information is still one of the important factors limiting soil-erosion modelling. Additionally, the limited number of parameters and the lack of evaluation criteria are major disadvantages of empirical soil-erosion models. To overcome these limitations, we introduce a new approach that integrates empirical and artificial intelligence models. Erosion-prone locations (erosion ≥16 tons/ha/year) are identified using RUSLE model and a soil-erosion map is prepared using random forest (RF), artificial neural network (ANN), classification tree analysis (CTA), and generalized linear model (GLM). This study uses 13 factors affecting soil erosion in the Talar watershed, Iran, to increase prediction accuracy. The results reveal that the RF model has the highest prediction performance (AUC=0.95, Kappa=0.87, Accuracy=0.93, and Bias=0.88), outperforming the three machine-learning models. The results show that slope angle, land use/land cover, elevation, and rainfall erosivity are the factors that contribute the most to soil erosion propensity in the watershed. Curvature and topography position index (TPI) were removed from the analysis due to multicollinearity with other factors. The results can be used to improve the identification of hot spots of soil erosion, especially in watersheds for which soil-erosion data are limited.

ASSESSMENT OF SOIL EROSION USING FOURNIER INDEXES TO ESTIMATE RAINFALL EROSIVITY

2019 ◽  
Vol 18 (8) ◽  
pp. 1739-1745 ◽  
Author(s):  
Gabriel Lazar ◽  
Alina Maria Coman ◽  
Georgiana Lacatusu ◽  
Ana Maria Macsim
Keyword(s):  
Soil Erosion ◽  
Rainfall Erosivity

scholarly journals Soil erosion by snow gliding – a first quantification attempt in a subalpine area in Switzerland

2014 ◽  
Vol 18 (9) ◽  
pp. 3763-3775 ◽  
Author(s):  
K. Meusburger ◽  
G. Leitinger ◽  
L. Mabit ◽  
M. H. Mueller ◽  
A. Walter ◽  
...  
Keyword(s):  
Land Use ◽  
Soil Erosion ◽  
Land Cover ◽  
Sediment Yield ◽  
Soil Loss ◽  
Water Erosion ◽  
Erosion Rates ◽  
The Difference ◽  
Snow Gliding

Abstract. Snow processes might be one important driver of soil erosion in Alpine grasslands and thus the unknown variable when erosion modelling is attempted. The aim of this study is to assess the importance of snow gliding as a soil erosion agent for four different land use/land cover types in a subalpine area in Switzerland. We used three different approaches to estimate soil erosion rates: sediment yield measurements in snow glide depositions, the fallout radionuclide 137Cs and modelling with the Revised Universal Soil Loss Equation (RUSLE). RUSLE permits the evaluation of soil loss by water erosion, the 137Cs method integrates soil loss due to all erosion agents involved, and the measurement of snow glide deposition sediment yield can be directly related to snow-glide-induced erosion. Further, cumulative snow glide distance was measured for the sites in the winter of 2009/2010 and modelled for the surrounding area and long-term average winter precipitation (1959–2010) with the spatial snow glide model (SSGM). Measured snow glide distance confirmed the presence of snow gliding and ranged from 2 to 189 cm, with lower values on the north-facing slopes. We observed a reduction of snow glide distance with increasing surface roughness of the vegetation, which is an important information with respect to conservation planning and expected and ongoing land use changes in the Alps. Snow glide erosion estimated from the snow glide depositions was highly variable with values ranging from 0.03 to 22.9 t ha−1 yr−1 in the winter of 2012/2013. For sites affected by snow glide deposition, a mean erosion rate of 8.4 t ha−1 yr−1 was found. The difference in long-term erosion rates determined with RUSLE and 137Cs confirms the constant influence of snow-glide-induced erosion, since a large difference (lower proportion of water erosion compared to total net erosion) was observed for sites with high snow glide rates and vice versa. Moreover, the difference between RUSLE and 137Cs erosion rates was related to the measured snow glide distance (R2 = 0.64; p < 0.005) and to the snow deposition sediment yields (R2 = 0.39; p = 0.13). The SSGM reproduced the relative difference of the measured snow glide values under different land uses and land cover types. The resulting map highlighted the relevance of snow gliding for large parts of the investigated area. Based on these results, we conclude that snow gliding appears to be a crucial and non-negligible process impacting soil erosion patterns and magnitude in subalpine areas with similar topographic and climatic conditions.

scholarly journals Corn Nitrogen Status Diagnosis with an Innovative Multi-Parameter Crop Circle Phenom Sensing System

2021 ◽  
Vol 13 (3) ◽  
pp. 401
Author(s):  
Cadan Cummings ◽  
Yuxin Miao ◽  
Gabriel Dias Paiao ◽  
Shujiang Kang ◽  
Fabián G. Fernández
Keyword(s):  
Machine Learning ◽  
Chlorophyll Content ◽  
Vegetation Index ◽  
Soil Drainage ◽  
Management Information ◽  
Area Index ◽  
Sensing System ◽  
Extreme Gradient Boosting ◽  
Split Plot ◽  
N Status

Accurate and non-destructive in-season crop nitrogen (N) status diagnosis is important for the success of precision N management (PNM). Several active canopy sensors (ACS) with two or three spectral wavebands have been used for this purpose. The Crop Circle Phenom sensor is a new integrated multi-parameter proximal ACS system for in-field plant phenomics with the capability to measure reflectance, structural, and climatic attributes. The objective of this study was to evaluate this multi-parameter Crop Circle Phenom sensing system for in-season diagnosis of corn (Zea mays L.) N status across different soil drainage and tillage systems under variable N supply conditions. The four plant metrics used to approximate in-season N status consist of aboveground biomass (AGB), plant N concentration (PNC), plant N uptake (PNU), and N nutrition index (NNI). A field experiment was conducted in Wells, Minnesota during the 2018 and the 2019 growing seasons with a split-split plot design replicated four times with soil drainage (drained and undrained) as main block, tillage (conventional, no-till, and strip-till) as split plot, and pre-plant N (PPN) rate (0 to 225 in 45 kg ha−1 increment) as the split-split plot. Crop Circle Phenom measurements alongside destructive whole plant samples were collected at V8 +/−1 growth stage. Proximal sensor metrics were used to construct regression models to estimate N status indicators using simple regression (SR) and eXtreme Gradient Boosting (XGB) models. The sensor derived indices tested included normalized difference vegetation index (NDVI), normalized difference red edge (NDRE), estimated canopy chlorophyll content (eCCC), estimated leaf area index (eLAI), ratio vegetation index (RVI), canopy chlorophyll content index (CCCI), fractional photosynthetically active radiation (fPAR), and canopy and air temperature difference (ΔTemp). Management practices such as drainage, tillage, and PPN rate were also included to determine the potential improvement in corn N status diagnosis. Three of the four replicated drained and undrained blocks were randomly selected as training data, and the remaining drained and undrained blocks were used as testing data. The results indicated that SR modeling using NDVI would be sufficient for estimating AGB compared to more complex machine learning methods. Conversely, PNC, PNU, and NNI all benefitted from XGB modeling based on multiple inputs. Among different approaches of XGB modeling, combining management information and Crop Circle Phenom measurements together increased model performance for predicting each of the four plant N metrics compared with solely using sensing data. The PPN rate was the most important management metric for all models compared to drainage and tillage information. Combining Crop Circle Phenom sensor parameters and management information is a promising strategy for in-season diagnosis of corn N status. More studies are needed to further evaluate this new integrated sensing system under diverse on-farm conditions and to test other machine learning models.

Sign in / Sign up

Export Citation Format

Share Document