Track 1-1-1: Global Database on Availability, Productivity and Composition of Grasslands, Forests and Protected Areas
Description
Remotely sensed satellite imagery can be used to classify and monitor vegetation dynamics (Tucker, 1979). The Normalized Difference Vegetation Index (NDVI) computed from satellite data is a good measure of photosynthetic activity at landscape scales, and can be used to estimate vegetation biomass and Net Primary Production (NPP) (Tucker, 1979; Myneni et al., 1995, Nemani et al., 2003). As in the present environmental condition the climate change has adversely affected the ecosystem and the forest cover, NDVI has an important role to play to track and quantify the change taking place in plant ecosystem process (Myneni et al., 1995, Nemani et al., 2003). Biomass estimation using NDVI is easy to implement, harvesting of trees is not required and also effectively reduce the time and cost required in case of any other estimation process. In this study regression models and ANN (Artificial Neural Network) model were tried to simulate and predict total biomass production from different districts of Bundelkhand region. NDVI values collected from remote sensing images at particular season of the year to characterize above ground biomass of the study area. The performance of the ANN model was compared with several other commonly used linear and nonlinear models and validation was done based on the model’s stability.
Citation
Deb, Dibyendu; Singh, J. P.; and Chaurasia, R. S., "Estimating above Ground Tree Biomass of Semi-Arid Bundelkhand Region Using Satellite Data, Regression Modelling and ANN Technique" (2020). IGC Proceedings (1993-2023). 5.
https://uknowledge.uky.edu/igc/23/1-1-1/5
Included in
Estimating above Ground Tree Biomass of Semi-Arid Bundelkhand Region Using Satellite Data, Regression Modelling and ANN Technique
Remotely sensed satellite imagery can be used to classify and monitor vegetation dynamics (Tucker, 1979). The Normalized Difference Vegetation Index (NDVI) computed from satellite data is a good measure of photosynthetic activity at landscape scales, and can be used to estimate vegetation biomass and Net Primary Production (NPP) (Tucker, 1979; Myneni et al., 1995, Nemani et al., 2003). As in the present environmental condition the climate change has adversely affected the ecosystem and the forest cover, NDVI has an important role to play to track and quantify the change taking place in plant ecosystem process (Myneni et al., 1995, Nemani et al., 2003). Biomass estimation using NDVI is easy to implement, harvesting of trees is not required and also effectively reduce the time and cost required in case of any other estimation process. In this study regression models and ANN (Artificial Neural Network) model were tried to simulate and predict total biomass production from different districts of Bundelkhand region. NDVI values collected from remote sensing images at particular season of the year to characterize above ground biomass of the study area. The performance of the ANN model was compared with several other commonly used linear and nonlinear models and validation was done based on the model’s stability.