GIS-Based Deep Reinforcement Learning For Dynamic Resource Management in Environmental Systems

  • Authors

    • Dr. Grace Ndlovu Associate Professor, University of Pretoria, South Africa. Author
    • Samuel Johnson Senior Operations Manager, MTN Group, South Africa. Author

    DOI:

    https://doi.org/10.67228/30715636/IJETMR-2021PII1N7F

    Published 07-03-2021

  • Geographic Information Systems, Deep Reinforcement Learning, Dynamic Resource Management, Environmental Systems, Spatial Optimization, Sustainable Decision-Making

    Issue

    Vol. 4 No. 2 (2021)

    Section

    Articles

    How to Cite

    [1]
    G. Ndlovu and S. Johnson, “GIS-Based Deep Reinforcement Learning For Dynamic Resource Management in Environmental Systems”, IJETMR, vol. 4, no. 2, pp. 01–08, Jul. 2021, doi: 10.67228/30715636/IJETMR-2021PII1N7F.

  • Abstract

    The integration of Geographic Information Systems (GIS) with Deep Reinforcement Learning (DRL) presents a novel approach to dynamic resource management in environmental systems. This paper explores the synergistic application of GIS and DRL to optimize the allocation and utilization of resources in complex environmental contexts. We review existing methodologies, highlight the challenges and opportunities inherent in this integration, and present case studies demonstrating its effectiveness. The findings underscore the potential of GIS-based DRL frameworks to enhance decision-making processes, leading to more sustainable and efficient management of environmental resources.​

  • References

    [1] Viseu, A., 2015. Integration of social science into research is crucial. Nature 525, 291.

    [2] Jaeger, J.-J., Marivaux, L., 2005. Paleontology. Shaking the earliest branches of anthropoid primate evolution. Science 310, 244–245.

    [3] Greiner, M., Regal, C.A., Jin, D.S., 2003. Emergence of a molecular Bose-Einstein condensate from a Fermi gas. Nature 426, 537–540.

    [4] Wang, Z., Wang, J., Li, M., Sun, K., Liu, C.-J., 2014. Three-dimensional printed acrylonitrile butadiene styrene framework coated with Cu-BTC metal-organic frameworks for the removal of methylene blue. Sci. Rep. 4, 5939.

    [5] Center for Chemical Process Safety, 1992. Guidelines for Auditing Process Safety Management Systems. John Wiley & Sons, Inc., Hoboken, NJ.

    [6] Topolov, V.Y., 2009. Electromechanical Properties in Composite Based on Ferroelectrics, in: Engineering Materials and Processes. Springer, London.

    [7] Limpouchová, Z., Procházka, K., 2016. Theoretical Principles of Fluorescence Spectroscopy, in: Procházka, K. (Ed.), Fluorescence Studies of Polymer Containing Systems, Springer Series on Fluorescence. Springer International Publishing, Cham, pp. 91–149.

    [8] Government Accountability Office, 2015. Farm Program Modernization: Farm Service Agency Needs to Demonstrate the Capacity to Manage IT Initiatives (No. GAO-15-506). U.S. Government Printing Office, Washington, DC.

    [9] Buckley, M.K., 2012. A study of at-risk students’ perceptions of an online academic credit recovery program in an urban North Texas independent school district (Doctoral dissertation). Pepperdine University, Malibu, CA.

    [10] Greenhouse, L., 2008. Court Blocks Plans for New Gas Plant in New Jersey. New York Times B4.

    [11] Hale, T., 2016. Sonar Images Reveal A WW2 Submarine Sunk By A Nazi Ship. IFLScience. URL (accessed 10.30.18).

  • Downloads