Retrieving vegetation cover by using BP neural network based on Beijing-1 microsatellite data

Chen, Tao; Li, Pingxiang; Zhang, Liangpei

doi:10.1117/12.812495

Cited by 4 publications

(3 citation statements)

References 10 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The crop management factor (C) is the ratio of soil loss from an area with specified cover and management to soil loss from an identical area in tilled continuous fallow. In the present study, the factor C was calculated from the predominant crops using the back propagation (BP) neural network (Chen et al 2008(Chen et al , 2010. Numerous researchers built up the relationship between vegetation index and the vegetation cover, and obtained satisfied results (Chen et al 2011a;Dutta et al 2015;Mokarram et al 2015).…”

Section: Soil Erodibility Factor (K)mentioning

confidence: 90%

See 1 more Smart Citation

Spatial modelling of soil erosion susceptibility mapping in lower basin of Subarnarekha river (India) based on geospatial techniques

Samanta¹,

Bhunia²,

Shit³

2016

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

This paper applied GIS based Revised Universal Soil Loss Equation (RUSLE), remote sensing and ground based data to develop the soil erosion risk mapping in lower Subarnarekha Watershed in India. The soil erosion input parameters were assessed in different ways: the R factor map was developed from the daily rainfall data and spatial distribution using Ordinary Kriging (OK) interpolation techniques, the K factor map was obtained from the soil map, the C factor map was generated based on a back propagation (BP) neural network model of Landsat ETM? data with a correlation coefficient (r) of 0.921 to the ground truth collection and LS factor was derived from a digital elevation model (DEM) with a spatial resolution of 30 m. P factor map was generated using standard table proposed by USDA-SCS for conservation practices. By integrating the six factor maps in GIS platform through pixel-based computing, the spatial distribution of soil loss was obtained by the RUSLE model. The spatial distribution of erosion risk classes was 26.2 % (796.97 km 2) very low erosion (\5 ton ha-1 year-1), 12.88 % (394.66 km 2) low erosion (5-10 ton ha-1 year-1), 20.77 % (636.37 km 2) moderate erosion (10-20 ton ha-1 year-1), 20.75 % (635.67 km 2) high erosion (20-30 ton ha-1 year-1), and 19.58 % (599.71 km 2) very high ([30 ton ha-1 year-1), soil erosion prone zone. The highest volume of very severe soil loss was observed in Keshiary [ Dantan-I [ Jaleswar [ Sankrail blocks. However, the southern part of lower Subarnarekha watershed areas which are in the extremely severe level of soil erosion risk need immediate attention from soil conservation practices.

show abstract

Section: Soil Erodibility Factor (K)mentioning

confidence: 90%

“…Inaccuracies in image classification are also presented in the C-factor map (Alejandro and Omasa 2007). Therefore, in this study, the factor C was estimated from the principal crops using the back proliferation neural network (Chen et al 2008(Chen et al , 2010. The estimated C factor is represented in Fig.…”

Section: Rusle Factorsmentioning

confidence: 99%

Spatial modelling of soil erosion susceptibility mapping in lower basin of Subarnarekha river (India) based on geospatial techniques

Samanta¹,

Bhunia²,

Shit³

2016

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

show abstract

“…In this study, the factor C was calculated from the predominant crops using the back propagation neural network (Chen et al 2008). The BP algorithm is an error-based learning process consisting of two phases.…”

Section: Soil Erodibility Factor (K)mentioning

confidence: 99%

Assessment of spatial distribution of soil loss over the upper basin of Miyun reservoir in China based on RS and GIS techniques

Chen

Niu

Wang

et al. 2010

Environ Monit Assess

Self Cite

View full text Add to dashboard Cite

Soil conservation planning often requires estimates of the spatial distribution of soil erosion at a catchment or regional scale. This paper applied the Revised Universal Soil Loss Equation (RUSLE) to investigate the spatial distribution of annual soil loss over the upper basin of Miyun reservoir in China. Among the soil erosion factors, which are rainfall erosivity (R), soil erodibility (K), slope length (L), slope steepness (S), vegetation cover (C), and support practice factor (P), the vegetative cover or C factor, which represents the effects of vegetation canopy and ground covers in reducing soil loss, has been one of the most difficult to estimate over broad geographic areas. In this paper, the C factor was estimated based on back propagation neural network and the results were compared with the values measured in the field. The correlation coefficient (r) obtained was 0.929. Then the C factor and the other factors were used as the input to RUSLE model. By integrating the six factor maps in geographical information system (GIS) through pixel-based computing, the spatial distribution of soil loss over the upper basin of Miyun reservoir was obtained. The results showed that the annual average soil loss for the upper basin of Miyun reservoir was 9.86 t ha(-1) ya(-1) in 2005, and the area of 46.61 km(2) (0.3%) experiences extremely severe erosion risk, which needs suitable conservation measures to be adopted on a priority basis. The spatial distribution of erosion risk classes was 66.9% very low, 21.89% low, 6.18% moderate, 2.89% severe, and 1.84% very severe. Thus, by using RUSLE in a GIS environment, the spatial distribution of water erosion can be obtained and the regions which susceptible to water erosion and need immediate soil conservation planning and application over the upper watershed of Miyun reservoir in China can be identified.

show abstract

A Review of RUSLE Model

Ghosal

Bhattacharya

2020

J Indian Soc Remote Sens

144

View full text Add to dashboard Cite

Retrieving vegetation cover by using BP neural network based on Beijing-1 microsatellite data

Cited by 4 publications

References 10 publications

Spatial modelling of soil erosion susceptibility mapping in lower basin of Subarnarekha river (India) based on geospatial techniques

Spatial modelling of soil erosion susceptibility mapping in lower basin of Subarnarekha river (India) based on geospatial techniques

Assessment of spatial distribution of soil loss over the upper basin of Miyun reservoir in China based on RS and GIS techniques

A Review of RUSLE Model

Contact Info

Product

Resources

About