Loading...

Geo-spatiotemporal intelligence for smart agricultural and environmental eco-cyber-physical systems

Majidi, B ; Sharif University of Technology | 2021

226 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/978-3-030-52067-0_21
  3. Publisher: Springer Science and Business Media Deutschland GmbH , 2021
  4. Abstract:
  5. The rapid changes of the climate and the environment requires smart solutions and deployment of intelligent automated systems in agriculture and environment management. Rural communities should use artificial intelligence and big data analytics solutions in order to be able to mitigate the effects of climate change in the next decades. The Eco-Cyber-Physical-System (ecoCystem) is a combination of the living entities of the ecosystem in conjunction with the Cyber-Physical System (CPS) based components of the smart rural environments, interacting as a system. The goal of the ecoCystem is to use the power of artificial intelligence combined with Internet of Things (IOT) in order to provide smart solutions for rural, agricultural and natural ecosystems. The collected data from satellite and Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicle (UGVs), smart enterprises and smart villages can be used for modelling of the living and farming behaviors of rural communities. The main modules of the proposed system are the Geolyzer and the Modular Rapidly Deployable Internet of Robotic Things (MORAD IoRT). In this paper, the Geolyzer module is the focus of the discussion and the experiments and the results of big data based intelligent geo-spatiotemporal analytics are presented. The applications of intelligent remote sensing solutions including satellite imagery and unmanned aerial vehicles in disaster management, forestry and agriculture are discussed. The presented machine learning based remote sensing solutions give the local governments and various businesses the ability to have an encompassing view of large agricultural, horticultural and grazing fields and the forests. This ability enables them to make optimal decisions in adverse scenarios caused by climate change and drought. A series of projects and solutions to validate the proposed framework are presented in this paper. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
  6. Keywords:
  7. Remote sensing ; Machine learning ; Disaster management ; Smart agriculture ; Big spatial data analytics
  8. Source: Studies in Computational Intelligence ; Volume 911 , 2021 , Pages 471-491 ; 1860949X (ISSN)
  9. URL: https://link.springer.com/chapter/10.1007/978-3-030-52067-0_21