The combination of multi-temporal images and deep learning is an efficient way to obtain accurate crop distributions and so has drawn increasing attention. However, few studies have compared deep learning models with different architectures, so it remains unclear how a deep learning model should be selected for multi-temporal crop classification, and the best possible accuracy is. To address this issue, the present work compares and analyzes a crop classification application based on deep learning models and different time-series data to exploit the possibility of improving crop classification accuracy. Using Multi-temporal Sentinel-2 images as source data, time-series classification datasets are constructed based on vegetation indexes (VIs) and spectral stacking, respectively, following which we compare and evaluate the crop classification application based on time-series datasets and five deep learning architectures: (1) one-dimensional convolutional neural networks (1D-CNNs), (2) long short-term memory (LSTM), (3) two-dimensional-CNNs (2D-CNNs), (4) three-dimensional-CNNs (3D-CNNs), and (5) two-dimensional convolutional LSTM (ConvLSTM2D). The results show that the accuracy of both 1D-CNN (92.5%) and LSTM (93.25%) is higher than that of random forest (~ 91%) when using a single temporal feature as input. The 2D-CNN model integrates temporal and spatial information and is slightly more accurate (94.76%), but fails to fully utilize its multi-spectral features. The accuracy of 1D-CNN and LSTM models integrated with temporal and multi-spectral features is 96.94% and 96.84%, respectively. However, neither model can extract spatial information. The accuracy of 3D-CNN and ConvLSTM2D models is 97.43% and 97.25%, respectively. The experimental results show limited accuracy for crop classification based on single temporal features, whereas the combination of temporal features with multi-spectral or spatial information significantly improves classification accuracy. The 3D-CNN and ConvLSTM2D models are thus the best deep learning architectures for multi-temporal crop classification. However, the ConvLSTM architecture combining recurrent neural networks and CNNs should be further developed for multi-temporal image crop classification.

The forest fire burned area is one of the most basic factors used to describe forest fires and plays a vital role in damage assessment. The development of the NSSI-NDVI vegetation index triangular space method enables simultaneous calculation of the flammable non-photosynthetic vegetation (NPV), combustible photosynthetic vegetation (PV), and incombustible bare soil (BS) fractional cover in forest areas. This can be used to compensate for the calculation method that was based on NDVI vegetation index only by comparing vegetation cover before and after forest fires, with the omission of the NPV burned area. To this end, the NSSI-NDVI triangular space shape consistency before and after forest fires was elucidated through combustion and ash wetting experiments. In addition, the feasibility of the NSSI-NDVI triangular space method for the accurate calculation of the post-fire vegetation damage area was verified. Finally, the applicability and accuracy of this research method were verified based on 10 m spatial resolution satellite hyperspectral images from before and after the forest fire in Lushan, Sichuan Province, China. The NSSI-NDVI triangular space method was used to calculate the PV, NPV, and BS coverage simultaneously, and component transformation was used to calculate the burned area and burned site separately.