Forest Change Detection Using an Optimized Convolution Neural Network

Abstract

Forest plays a pivotal role in maintaining the ecological balance. It is necessary to detect the changes in forest cover as the forests have a significant role in promoting carbon cycle. Remote sensing domain has shown a promising potential for monitoring forest degradation. However, the problem arising due to missing satellite images in temporal domain and problems due to artefacts such as clouds need to be addressed. To detect the changes in the forest area, an index for mapping forest cover known as Normalized Difference Fraction Index (NDFI) has been used. NDFI is calculated for three satellite images (Landsat7, Landsat8, and Sentinal2) and for the fusion of all these satellite images. Following this, the missing image is predicted by applying regression methods and the best regression method was identified. For change detection problem, optimal values for Convolution Neural Network (CNN) parameters were obtained using the Genetic Algorithm (GA). Later, various filters were applied for the optimal CNN and best filter was identified.

KEYWORDS:

• Band fusion
• Change detection
• Deep Learning
• Genetic algorithm
• Missing data prediction
• Remote sensing
• Time series

Additional information

Notes on contributors

Radha Senthilkumar

Radha Senthilkumar received her PhD degree in web database from the Faculty of ICE, Madras Institute of Technology. She is currently working as associate professor in Department of Information Technology, Madras Institute of Technology, Anna University, Chennai. Her areas of specialization include XML technology, database management systems, web information retrieval, data mining, fuzzy logic, big data and machine learning. E-mail:[email protected]

V. Srinidhi

V Srinidhi is currently pursuing final year in the department of Information Technology in Madras Institute of Technology, Anna University, Chennai.

S. Neelavathi

S Neelavathi is currently pursuing final year in the department of Information Technology in Madras Institute of Technology, Anna University, Chennai. E-mail:[email protected]

S. Renuga Devi

S Renuga Devi is currently pursuing final year in the department of Information Technology in Madras Institute of Technology, Anna University, Chennai. E-mail:[email protected]