Assessing the suitability of data from Sentinel-1A and 2A for crop classification |
| |
| Authors: | Rei Sonobe Yuki Yamaya Hiroshi Tani Xiufeng Wang Nobuyuki Kobayashi Kan-ichiro Mochizuki |
| |
| Institution: | 1. Faculty of Agriculture, Shizuoka University, 836 Ohya, Suruga-ku, Shizuoka 422-8529, Japan;2. Graduate School of Agriculture, Hokkaido University, Kita-ku Kita 9, Nishi 9, Sapporo, Hokkaido 060-8589, Japan;3. Research Faculty of Agriculture, Hokkaido University, Kita-ku Kita 9, Nishi 9, Sapporo, Hokkaido 060-8589, Japan;4. Smart Link Hokkaido, 1-12 Ariakecho-minami, Iwamizawa, Hokkaido 068-0034, Japan;5. PASCO Research Institute, PASCO Corporation, 2-8-10 Higashiyama, Meguro-Ku, Tokyo 153-0043, Japan |
| |
| Abstract: | Sentinel-1A C-SAR and Sentinel-2A MultiSpectral Instrument (MSI) provide data applicable to the remote identification of crop type. In this study, six crop types (beans, beetroot, grass, maize, potato, and winter wheat) were identified using five C-SAR images and one MSI image acquired during the 2016 growing season. To assess the potential for accurate crop classification with existing supervised learning models, the four different approaches namely kernel-based extreme learning machine (KELM), multilayer feedforward neural networks, random forests, and support vector machine were compared. Algorithm hyperparameters were tuned using Bayesian optimization. Overall, KELM yielded the highest performance, achieving an overall classification accuracy of 96.8%. Evaluation of the sensitivity of classification models and relative importance of data types using data-based sensitivity analysis showed that the set of VV polarization data acquired on 24 July (Sentinel-1A) and band 4 data (Sentinel-2A) had the greatest potential for use in crop classification. |
| |
| Keywords: | agricultural fields classification Hokkaido machine learning Sentinel-1A Sentinel-2A |
|
|
