North Eastern District Resources Plan (NEDRP) is one of the unique initiatives of NESAC to provide geospatial data, services and tools for preparation of Detailed Project Report (DPR), Master plan document and any other inputs essential for various district level developmental planning activity. NEDRP was initiated with 36 selected districts of NE Region and later on expanded to remaining 58 districts (total 94 districts) of the region as per the directive of North Eastern Council and the demands from the various Line Departments to showcase the capability of space technology applications and tools for district level planning. Ensemble of 94 district NEDRP geoportals with 30-35 layers of each district are catalogued into six major information modules of the NEDRP GeoXplorer-Administrative or base data, Infrastructure, Land and Water resources, Planning inputs and Terrain module realized in a single unified platform using open source software and standards with few important Governance applications like ElectionGIS, CensusGIS, Forest Resources Management (FRM), and GeoTourism. In all the applications Bhuvan map services has been effectively used in an optimized way for better and faster display of imageries. Secure data sharing gateway has been established for sharing of geospatial maps to the various users through online registration, validation and authentication. Online decision making tools based on User’s criteria for identification of forest fire vulnerable areas, expansion of horticulture and afforestation activity have been added on the top of the NEDRP.
NEDRP is one of the most enhanced form of GeoPortal realized in a three tier service oriented incremental architecture populated with GeoData derived using GeoData Analytics and Machine Learning (ML) Tools.
GeoData Analytics: NEDRP is populated with 3500+ Geospatial layers generated from various sources of satellite data with different spatial/spectral resolution. It includes CARTOSAT-I, RESOURCESAT-2, ETM+, HYPERION etc. It also uses high resolution QUICKBIRD sensor data including very high resolution aerial images from Drones/UAV (BIG GeoData). Generation of GeoData involves the extraction of meaningful information via visual/digital interpretation/classification using various GeoInformatics as well as ML techniques and tools. Specifically, processing of high dimension GeoData sources requires advanced ML approach like SVM, Random forest, ANN/MLP for extraction of meaningful information for decision making process. In addition, a number of feature extraction tools like PCA/MNF/CFS are required for dimension reduction of data both in spatial as well as feature space. A number of FOSS (QGIS/Weka/Python/R) and COTS (ArcGIS/ENVI/Erdas) software are being used for generation/updation of GeoData. Spatial models powered by spatial as well as fuzzy overly analysis were used for site suitability analysis (LiveGIS of NEDRP).
NEDRP aggregates data (spatial and non-spatial) from various sources for visualization via GeoPortal with decision making tools. Governance Application of NEDRP also captures live feeds of data posted via Mobile Apps for monitoring activity (ElectionGIS). It enables integration of satellite/Drone image and video on the GeoTagged information (nec.nedrp.gov.in).
WebGeoXplorer: Ensemble of 101 district GeoPortals are showcased in a single window platform using open source MS4W (Map Server/map Cache-Apache-PHP) software bundles for efficient and effective dissemination of various services (WMS-WFS-WPS). Powerful GeoServer based architecture integrated with GeoJSON/Leaflet Technology is used for development of various Governance Applications (ElectionGIS/NEC Project Monitoring etc.) with enhanced/optimized rendering of maps/satellite images as well as to capture the live feeds of real-time data from Mobile Apps. The entire architecture is responsive and incremental in nature to catalogue various Governance Applications without disturbing the current configuration.
List of major publications:
1. Geo Portal on North Eastern District Resources Plan to support effective Governance applications, Journal of Administrative Reforms on Minimum Government - Maximum Governance, Vol. IV(1), January-June, 2018
2. Towards generation of effective 3D surface models from UAV imagery using open source tools, Current Science, 114(2), 314-321
3. An effective Ensemble Classification Framework using Random Forests and Correlation Based Feature Selection Technique, Transaction in GIS, 20(4):463-490, doi: 10.1111/tgis.12164.
4. A model on achieving higher performance in the classification of hyperspectral satellite data: A case study on Hyperion data, Applied Geomatics(Springer), 6(3), 181-195.
5. A Novel Geospatial Approach for Identifying Optimal Sites for Setting-up of Mobile Telecom Towers strategically, Geomatics, 10(2), 192-198.
6. Dynamic Shortest Route Finder using pgRouting for emergency management, Applied Geomatics (Springer), DOI 10.1007/s12518-015-0161-4 (2015)
7. Effectiveness of Fuzzy Overlay Function for Multi-Criteria Spatial Modeling—A Case Study on Preparation of Land Resources Map for Mawsynram Block of East Khasi Hills District of Meghalaya, India, Journal of Geographic Information System, 6(6), 605-612.