Abstract
Food is very essential in our daily life and demand for food is increasing day by day. Crop classification can be used to identify the suitable crops to grow on the land in such a way that crop production can be increased. Accurate and mapping of land at correct time can be used in numerous applications such as management of sustainable agriculture and food security. With the growing technology, deep learning methods along with high resolution Sentinel-2 images can be used for mapping crops and crop classification. In this study, we have proposed a new model that works with Convolutional Neural Network as the base layer along with Gated Recurrent Unit to improve its performance and accuracy. The farming land images are collected from different dates of the growing season covering all growing stages of the crop. For acquiring multispectral data, bands from the Sentinel-2 images shall be used, and the features in each patch of the image will be extracted and used. Following this proposed ideology, by feeding both the multitemporal and the multispectral data to the model, several crop classes can be identified directly using the satellite images easily and efficiently. To measure the performance, we have compared the models by finding their accuracy. On concluding, our study found that using CNN model along with GRU by remote sensing produces higher accuracy than just CNN alone in classifying the crops using the satellite imagery.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Seydi ST, Amani M, Ghorbanian A (2022) A dual attention convolutional neural network for crop classification using time-series sentinel-2 imagery. Remote Sens 14:498 https://doi.org/10.3390/rs14030498
Wang L, Wang J, Liu Z, Zhu J, Qin F (2022) Evaluation of a deep-learning model for multispectral remote sensing of land use and crop classification. Crop J 2214–5141. https://doi.org/10.1016/j.cj.2022.01.009
Ji S, Zhang C, Xu A, Shi Y, Duan Y (2018) 3D convolutional neural networks for crop classification with multi-temporal remote sensing images. Remote Sens 10:75. https://doi.org/10.3390/rs10010075
Pott L, Amado T, Schwalbert R, Corassa G, Ciampitti I (2021) Satellite-based data fusion crop type classification and mapping in Rio Grande do Sul, Brazil. ISPRS J Photogrammetry Remote Sens 176:196–210 https://doi.org/10.1016/j.isprsjprs.2021.04.015
Wang Z, Zhao Z, Yin C (2022) Fine crop classification based on UAV hyperspectral images and random forest. ISPRS Int J Geo-Inf 11:252. https://doi.org/10.3390/ijgi11040252
Turkoglu M et al (2021) Crop mapping from image time series: deep learning with multi-scale label hierarchies. Remote Sens Environ 264. https://doi.org/10.1016/j.rse.2021.112603
Zhao H, Chen Z, Jiang H, Jing W, Sun L, Feng M (2019) Evaluation of three deep learning models for early crop classification using sentinel-1A imagery time series—a case study in Zhanjiang, China. Remote Sens 11:2673. https://doi.org/10.3390/rs11222673
Yang S, Gu L, Li X, Jiang T, Ren R (2020) Crop classification method based on optimal feature selection and hybrid CNN-RF networks for multi-temporal remote sensing imagery. Remote Sens 12:3119. https://doi.org/10.3390/rs12193119
Viskovic L, Kosovic IN, Mastelic T (2019) Crop classification using multi-spectral and multitemporal satellite imagery with machine learning. In: International conference on software, telecommunications and computer networks, pp 1–5. https://doi.org/10.23919/SOFTCOM.2019.8903738
Murmu S, Biswas S (2015) Application of fuzzy logic and neural network in crop classification: a review. Aquatic Procedia 4:1203–1210. https://doi.org/10.1016/j.aqpro.2015.02.153
Orynbaikyzy A, Gessner U, Conrad C (2019) Crop type classification using a combination of optical and radar remote sensing data: a review. Int J Remote Sens 6553–6595. https://doi.org/10.1080/01431161.2019.1569791
Desai G, Gaikwad A (2021) Deep learning techniques for crop classification applied to SAR imagery: a survey. Asian Conf Innov Technol 1–6. https://doi.org/10.1109/ASIANCON51346.2021.9544707
Sun Z, Di L, Fang H, Burgess A (2020) Deep learning classification for crop types in North Dakota. IEEE J Sel Top Appl Earth Obser Remote Sens 13:2200–2213. https://doi.org/10.1109/JSTARS.2020.2990104
Zhang X, Sun Y, Shang K, Zhang L, Wang S (2016) Crop Classification based on feature band set construction and object-oriented approach using hyperspectral images. IEEE J Sel Top Appl Earth Obser Remote Sens 9:4117–4128. https://doi.org/10.1109/JSTARS.2016.2577339
Henning S, Francesco M, Giuseppe S (2011) Crop classification using short-revisit multitemporal SAR data. IEEE J Sel Top Appl Earth Obser Remote Sens 4:423–431. https://doi.org/10.1109/JSTARS.2011.2106198
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sagana, C. et al. (2023). Crop Classification Based on Multispectral and Multitemporal Images Using CNN and GRU. In: Hasteer, N., McLoone, S., Khari, M., Sharma, P. (eds) Decision Intelligence Solutions. InCITe 2023. Lecture Notes in Electrical Engineering, vol 1080. Springer, Singapore. https://doi.org/10.1007/978-981-99-5994-5_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-5994-5_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5993-8
Online ISBN: 978-981-99-5994-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)