Prediction of paddy cultivation using deep learning on land cover variation for sustainable agriculture

@incollection{MEEDENIYA2022325,
title = {Chapter 13 - Prediction of paddy cultivation using deep learning on land cover variation for sustainable agriculture},
editor = {Ramesh Chandra Poonia and Vijander Singh and Soumya Ranjan Nayak},
booktitle = {Deep Learning for Sustainable Agriculture},
publisher = {Academic Press},
pages = {325-355},
year = {2022},
series = {Cognitive Data Science in Sustainable Computing},
isbn = {978-0-323-85214-2},
doi = {https://doi.org/10.1016/B978-0-323-85214-2.00009-4},
url = {https://www.sciencedirect.com/science/article/pii/B9780323852142000094},
author = {D.A. Meedeniya and I. Mahakalanda and D.S. Lenadora and I. Perera and S.G.S. Hewawalpita and C. Abeysinghe and Soumya Ranjan Nayak},
keywords = {Spatio-temporal data, Convolutional neural networks, Paddy cultivation, Satellite imagery, GIS data, Data acquisition},
abstract = {Geospatial analytics is a promising method of spatial data processing and analysis. This study presents a deep learning-based geospatial analytics model to classify the satellite images and geographical information system (GIS) data to estimate the agricultural land area under paddy cultivation. The fine-tuned predictive model is validated against GIS data, followed by an evaluation scenario of a selected paddy cultivation area. Deep learning-based geospatial land usage monitoring can be both conceptually and practically appealing to efficiently identify and respond to the diverse needs of agents in the paddy supply chain. The information with a fine-tuned predictive analysis model can lead to possible policy implications for sustainable agriculture directives of the Sri Lankan government.}
}