Remote Sensing and GIS in Simulation and Prediction Perspective


The rapid growth of megacities causes severe social, economical and ecological issues. This growth can be nurtured in a sustainable way. The challenge for land professionals is to provide the megacity ‘managers’, both political and professional, with appropriate ‘actionable intelligence’ that is up-to-date, citywide and in a timely manner to support more proactive decision making that encourages more effective sustainable development. 
  • Spatial data has become indispensable for numerous aspects of urban development, planning and management. 
  • The increasing importance of remote sensing and GIS has been due to recent strides in acquiring spatial information (especially satellite Images and positioning), management (utilizing geographic information systems and database tools) and access (witness the growth in web mapping services), as well as the development of analytical techniques such as high resolution mapping of urban environments. 
  • These more efficient techniques can lead to a wider diversity of information that is more up-to-date.
  • In some circumstances, a wealth of existing map, image and measurement data can already be found in areas such as land administration, natural resource management, marine administration, transportation, defense, communications, utility services and statistical collections. 
  • The challenge is for users both within and outside these areas of activity to break down the information silos and to discover, to access and to use the shared information to improve decision-making, business outcomes and customer services.
Simulation and prediction is important from many perspectives, especially for urban planning and management. Artificial Neural Networks (ANNs) are a powerful tool for simulation studies, as it uses a machine-learning approach to quantify and model complex behavior and patterns, and allow the integration of GIS tools and remote sensing data. The multi-layer perceptron (MLP) network is one of the most widely used ANNs. Artificial Neural Networks (ANN) can be used with regression for land use change and urban change analysis. Artificial Neural Networks (ANN) can also use with the spatial transition-based model for land use simulation studies. The spatial-transition-based model is rooted in a stochastic Markov-chain technique, requires less data with no restriction for spatial resolution, and is useful for descriptive and predictive modeling. Therefore, the spatial transition-based approach can be implemented for simulation by integrating MLP with the Markov model. In simulation and prediction of based on ANN approach always use predictive variables, which influence the change patterns.
For example, in case of urban change simulation, variables can be
  • Proximity to road,
  • Proximity to existing urban area,
  • Proximity to lake view etc.
The use of simulated urban data, for interpretation of conceived plan and policies is a real representation of city development prospects. However, this fact is poorly represented using conventional methods of urban change studies. Therefore, it is important to conduct a thorough urban change study based on urban land suitability and also with urban development plans.

Comments

  1. Thanks for sharing the best information and suggestions, If you are looking for the best Land capability Assessment Gippsland, then The 4 Spheres. Highly energetic blog, I’d love to find out some additional information.


    ReplyDelete
  2. first off, a hearty thanks to you. Your blog is awesome and completely knowledgeable and I completely satisfied with the reading. Keep your work spread till long after. For more House Versus Condo related information visit The Shoreline Condominium.Certainly, you are Right!

    ReplyDelete

Post a comment

Popular posts from this blog

Digital Image Processing Tutorial-Image Enhancement Part-I

Introduction of GIS

About GIS OUTLOOK Webpage