A remote sensing aided multi-layer perceptron-Markov chain analysis for land use and land cover change prediction in Patna district (Bihar), India

Satellite based remote sensing technology has proven to be an effectual tool in analysis of drainage networks, study of surface morphological features and their correlation with groundwater management prospect at basin level. The present study highlights the effectiveness and advantage of remote sensing and GIS-based analysis for quantitative and qualitative assessment of flood plain region of lower Kosi river basin based on morphometric analysis. In this study, ASTER DEM is used to extract the vital hydrological parameters of lower Kosi river basin in ARC GIS software. Morphometric parameters, e.g., stream order, stream length, bifurcation ratio, drainage density, drainage frequency, drainage texture, form factor, circularity ratio, elongation ratio, etc., have been calculated for the Kosi basin and their hydrological inferences were discussed. Most of the morphometric parameters such as bifurcation ratio, drainage density, drainage frequency, drainage texture concluded that basin has good prospect for water management program for various purposes and also generated data base that can provide scientific information for site selection of water-harvesting structures and flood management activities in the basin. Land use land cover (LULC) of the basin were also prepared from Landsat data of 2005, 2010 and 2015 to assess the change in dynamic of the basin and these layers are very noteworthy for further watershed prioritization.

show abstract

“…The drainage channel has divided into number of segments for determination of sinuosity parameter (Miller 1953).…”

Section: Channel Index (Ci) and Valley Index (Vi)mentioning

confidence: 99%

“…Initially, very important and innovative research work on the river morphometry has been completed by Horton (1932Horton ( , 1945, Miller (1953), Smith (1950), Strahler (1964) and others. These techniques have been deliberated by a number of researchers on varied geographical areas of India.…”

Section: Introductionmentioning

confidence: 99%

Hydrological inferences through morphometric analysis of lower Kosi river basin of India for water resource management based on remote sensing data

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to result of MLP model process between training and test dataset was observed 76.10% accuracy rate. The production of potential change maps by taking advantage of the transformations were input data set required for MC analysis (Mishra, 2016). The number of outputs of the transformation potential maps (Figure 7) are equal to the number of major change input groupings.…”

Section: Multi-temporal Lulc Mapping and Accuracy Assessmentmentioning

confidence: 99%

Land Use/Cover Change Modelling in a Mediterranean Rural Landscape Using Multi-Layer Perceptron and Markov Chain (Mlp-Mc)

Mirici¹

2018

Appl. Ecol. Env. Res.

View full text Add to dashboard Cite

Abstract. Mediterranean land use and land cover (LULC) have a very dynamic structure as a result of continuous transformation process due to anthropogenic effects and environmental gradients. LULC dynamics are important indicator of environmental condition in temporal and spatial scales. The aim of this paper was to simulate the future LULC of a Mediterranean type watershed located at the Eastern Mediterranean Region of Turkey by incorporating multi-layer perceptron (MLP), artificial neural network (ANN) and Markov chain (MC) approaches. Landsat TM/OLI images in 1990, 2003 and 2014 over the study area were classified using hybrid classification approach. The Kappa statistics of the hybrid classification that combines K-means, decision tree and object based classification method for these three images were 0.81, 0.85 and 0.87 respectively. The LULC map of 2014 was simulated using LULC maps of 1990 and 2003 for calibration and validation. The simulation results were compared with the actual 2014 LULC map to assess the accuracy of the simulation, and the rate of overlap was found as 89%. LULC map of 2025 was estimated using LULC maps of 2003 and 2014. These results indicated that, the area of bareground will reduce 13.31% whereas the rate of forest and agricultural area will increase 8.70% and 6.51% respectively.

show abstract

“…The 'Cellular Automata' and 'Markov Chain' models are considered to be advantageous for modeling land use changes (Mishra and Rai, 2016;Parsa et al, 2016). The issues involved when a Markov chain model lacks spatially referred output and transition probabilities may be accurate on a categorical basis, there are no specifications on spatial distribution of each land use category occurrence (Arsanjani et al, 2013).…”

Section: Ca-markov Chain Modelmentioning

confidence: 99%

“…Cellular automata added into a Markov model lead to probable spatial transitions occurring in particular area over a period time (Subedi et al, 2013). In other words, the quantity of changes from the Markov Chain model then are made geo-referred and spatial through cellular automata (Mishra and Rai, 2016). The CA-Markov model uses Markov Chain analysis outputs, particularly the Transition Area file, to apply a contiguity filter to enable the development of other land use characteristics from time two into a later time period (Parsa et al, 2016).…”

Section: Ca-markov Chain Modelmentioning

confidence: 99%

Application of Ca-Markov Model and Land Use/Land Cover Changes in Malacca River Watershed, Malaysia

Hua¹

2017

Appl. Ecol. Env. Res.

View full text Add to dashboard Cite

(between 2001, 2008, 2015, and 2029). This analysis consisted of the entire Malacca River watershed area. Changes may provide information on determinant of river water quality in future. Based on LULC monitoring and future simulation approach, the results may be used in an early warning system by demonstrating trend and consequences of changes in watershed. Continuous downward trends for vegetation area, open space area, and water bodies are due to expansion in non-industrial area, industrial area, and farming areas that increase contamination in the Malacca River. The findings demonstrate the need for more regulation in land use policy design, planning, and development for the protection of river water quality.

show abstract

A remote sensing aided multi-layer perceptron-Markov chain analysis for land use and land cover change prediction in Patna district (Bihar), India

Cited by 246 publications

References 55 publications

Hydrological inferences through morphometric analysis of lower Kosi river basin of India for water resource management based on remote sensing data

Hydrological inferences through morphometric analysis of lower Kosi river basin of India for water resource management based on remote sensing data

Land Use/Cover Change Modelling in a Mediterranean Rural Landscape Using Multi-Layer Perceptron and Markov Chain (Mlp-Mc)

Application of Ca-Markov Model and Land Use/Land Cover Changes in Malacca River Watershed, Malaysia

Contact Info

Product

Resources

About