Sentinel-1A and Landsat 8 images have been combined in this study to map rice fields in urban Shanghai, southeast China, during the 2015 growing season. Rice grown in paddies in this area is characterized by wide inter-field variability in addition to being fragmented by other landuses. Improving rice classification accuracy requires the use of multi-source and multi-temporal high resolution data for operational purposes. In this regard, we first exploited the temporal backscatter of rice fields and background land-cover types at the vertical transmitted and vertical received (VV) and vertical transmitted and horizontal received (VH) polarizations of Sentinel-1A. We observed that the temporal backscatter of rice increased sharply at the early stages of growth, as opposed to the relatively uniform temporal backscatter of the other land-cover classes. However, the increase in rice backscatter is more sustained at the VH polarization, and two-class separability measures further indicated the superiority of VH over VV in discriminating rice fields. We have therefore combined the temporal VH images of Sentinel-1A with the normalized difference vegetation index (NDVI) and the modified normalized difference water index (MNDWI) derived from a single-date cloud-free Landsat 8 image. The integration of these optical indices with temporal backscatter eliminated all commission errors in the Rice class and increased overall accuracy by 5.3%, demonstrating the complimentary role of optical indices to microwave data in mapping rice fields in subtropical and urban landscapes such as Shanghai.

SVM and RF are widely used in rice mapping. However, their performance with single and different combinations of satellite datasets is rarely reported. Hence we report their rice mapping accuracies for two seasons using Sentinel-1A, Landsat-8 and Sentinel-2A images. The VH and VV polarizations of Sentinel-1A, and two spectral indices (SIs) of Landsat-8 and Sentine1-2A were used to obtain seven datasets (VH, VV, SI, VHVV, VHSI, VVSI and VHVVSI), and on which SVM and RF were applied and accuracies were assessed. VHSI showed the highest overall accuracy for both algorithms in both years. SVM with VHSI had a slightly higher accuracy (90.8%) than RF with VHSI (89.2%) in 2015 while in 2016 RF with VHSI showed a slightly higher accuracy (95.2%) than SVM with VHSI (93.4%). Although they produced equivalent accuracies within years, RF is more sensitive to additional data, given a 6.0% increase from 2015 to 2016 with VHSI.

Leaf area index (LAI) is a key input in models describing biosphere processes and has widely been used in monitoring crop growth and in yield estimation. In this study, a hybrid inversion method is developed to estimate LAI values of winter oilseed rape during growth using high spatial resolution optical satellite data covering a test site located in southeast China. Based on PROSAIL (coupling of PROSPECT and SAIL) simulation datasets, nine vegetation indices (VIs) were analyzed to identify the optimal independent variables for estimating LAI values. The optimal VIs were selected using curve fitting methods and the random forest algorithm. Hybrid inversion models were then built to determine the relationships between optimal simulated VIs and LAI values (generated by the PROSAIL model) using modeling methods, including curve fitting, k-nearest neighbor (kNN), and random forest regression (RFR). Finally, the mapping and estimation of winter oilseed rape LAI using reflectance obtained from Pleiades-1A, WorldView-3, SPOT-6, and WorldView-2 were implemented using the inversion method and the LAI estimation accuracy was validated using ground-measured datasets acquired during the 2014–2015 growing season. Our study indicates that based on the estimation results derived from different datasets, RFR is the optimal modeling algorithm amidst curve fitting and kNN with R² > 0.954 and RMSE <0.218. Using the optimal VIs, the remote sensing-based mapping of winter oilseed rape LAI yielded an accuracy of R² = 0.520 and RMSE = 0.923 (RRMSE = 93.7%). These results have demonstrated the potential operational applicability of the hybrid method proposed in this study for the mapping and retrieval of winter oilseed rape LAI values at field scales using multi-source and high spatial resolution optical remote sensing datasets. Details provided by this high resolution mapping cannot be easily discerned at coarser mapping scales and over larger spatial extents that usually employ lower resolution satellite images. Our study therefore has significant implications for field crop monitoring at local scales, providing relevant data for agronomic practices and precision agriculture.

Geographic object-based image analysis (GEOBIA) has been widely used in the remote sensing of agricultural crops. However, issues related to image segmentation, data redundancy and performance of different classification algorithms with GEOBIA have not been properly addressed in previous studies, thereby compromising the accuracy of subsequent thematic products. It is in this regard that the current study investigates the optimal scale parameter (SP) in multi-resolution segmentation, feature subset, and classification algorithm for use in GEOBIA based on multisource satellite imagery. For this purpose, a novel supervised optimal SP selection method was proposed based on information gain ratio, and was then compared with a preexisting unsupervised optimal SP selection method. Additionally, the recursive feature elimination (RFE) and enhanced RFE (EnRFE) algorithms were modified to generate an improved EnRFE (iEnRFE) algorithm, which was then compared with its precursors in the selection of optimal classification features. Based on the above, random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM) were applied to segmented objects for crop classification. The results indicated that the supervised optimal SP selection method is more suitable for application in heterogeneous land cover, whereas the unsupervised method proved more efficient as it does not require reference segmentation objects. The proposed iEnRFE method outperformed the preexisting EnRFE and RFE methods in optimal feature subset selection as it recorded the highest accuracy and less processing time. The RF, GBDT, and SVM algorithms achieved overall classification accuracies of 91.8%, 92.4%, and 90.5%, respectively. GBDT and RF recorded higher classification accuracies and utilized much less computational time than SVM and are, therefore, considered more suitable for crop classification requiring large numbers of image features. These results have shown that the proposed object-based crop classification scheme could provide a valuable reference for relevant applications of GEOBIA in crop recognition using multisource satellite imagery.