Prediction of land use/cover change in the Bharathapuzha river basin, India using geospatial techniques

摘要

The Bharathapuzha river basin, once endowed with dense vegetation and abundant water, has been experiencing acute water shortage and extreme climatic conditions in recent times. To understand the influence of human interventions on the natural environmental conditions, including the problems mentioned above, it is essential to critically examine the changes in land use/cover over these years. The objective of this study is to assess land use/cover change in the Bharathapuzha river basin, Kerala during the period 1990-2017 using LANDSAT series satellite images. The dynamics of land use/cover change were quantified and mapped using geospatial techniques. The multi-temporal LANDSAT images were classified by supervised maximum likelihood method to generate the corresponding land use/cover maps; changes in land use/cover in the river basin were subsequently detected by the post-classification technique. Results of the study revealed a drastic change in land use/cover in the period 1990-2017; the primary causes of this were deforestation and urbanization. The near- and long-term future land use/cover maps of the basin for 2020 and 2035 were generated from the historically retrieved land use/cover change pattern. Multi-Layer Perceptron Neural Network and Markov chain techniques were used to generate future land use/cover maps. These maps reveal that the predominant land use/cover class in the basin will be barren land and about 46.13% of the existing (in 2017) dense vegetation will diminish by 2035. The efficiency of sustainable watershed management activities in the river basin can be improved based on the critical observations from this study.