Classification of Landsat 8 Images using Neural Networks
Varsha Bhosale1, Archana Patankar2
1Varsha Bhosale*, Research Scholar, Department of Computer Engineering, Vidyalankar Institute of Technology (VIT), Mumbai (Maharashtra), India.
2Dr. Archana Patankar, Professor, Department of Computer Engineering at Thadomal Shahani College of Engineering, Mumbai (Maharashtra), India.
Manuscript received on 11 June 2022. | Revised Manuscript received on 19 June 2022. | Manuscript published on 30 July 2022. | PP: 23-28 | Volume-11 Issue-8, July 2022. | Retrieval Number: 100.1/ijitee.H91330711822 | DOI: 10.35940/ijitee.H9133.0711822
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Several geospatial applications use Classification. Classification is useful in identifying change detection. The Changes amongst various classes are identified at different time periods thus helping to analyze the changes happening in Land Use Land cover (LULC) of the area under consideration over a period. Neural networks have shown its command in majority of fields in solving complex problems, and geospatial field is also benefited by the Neural Networks. Several effective and efficient mechanisms are suggested for supervised satellite image classification. The Neural network’s Machine Learning algorithms are gaining popularity for supervised satellite image classification. The objective of this paper is to show how the Convolution Neural Network (CNN) as a machine learning algorithm is implemented for classification of Satellite image. The study area considered is Mumbai Metropolitan region (MMR), the Financial Capital of India. The work was executed considering the Landsat 8 images. The images were obtained and processed in QGIS Open-Source Software; Machine Learning algorithm was developed using Python Scripting. The NN algorithm was effectively implemented, and results showed the competence of Neural Network in generating classification of Landsat 8 satellite Image using CNN.
Keywords: Supervised Classification, Land Use Land Cover (LULC), Machine Learning, Convolution Neural Networks, Python Script
Scope of the Article: Machine Learning