A Crop Classification Method Integrating GF-3 PolSAR and Sentinel-2A Optical Data in the Dongting Lake Basin

Monitoring the Wetland of the Yellow River Delta by Combining GF-3 Polarimetric Synthetic Aperture Radar and Sentinel-2A Multispectral Data

Wetlands in estuary deltas functionally protect biodiversity, store water, and regulate ecological balance. However, wetland monitoring accuracy is low when using only synthetic aperture radar (SAR) images or optical images. This study proposes a novel method for extracting ground objects in a wetland using principal component analysis (PCA) and random forest (RF) classification, which combines the features of fully polarimetric SAR images and optical images. Firstly, polarization decomposition features and texture features were extracted based on polarimetric SAR data, and spectral features were extracted based on optical data. Secondly, the optical image was registered to SAR image. Then PCA was performed on the nine polarimetric features of the SAR images and the four spectral features of the optical images to obtain the first two principal components of each. After combining these components, a RF classification algorithm was used to extract the objects. The objects in the Yellow River Delta wetland were successfully extracted using our proposed method with Gaofen-3 fully polarimetric SAR data and Sentinel-2A optical data acquired in November 2018. The overall accuracy of the proposed method was 86.18%, and the Kappa coefficient was 0.84. This was an improvement of 18.96% and 0.22, respectively, over the GF-3 polarimetric features classification, and 11.02% and 0.13, respectively, over the Sentinel-2A spectral features classification. Compared with the results of the support vector machine, maximum likelihood, and minimum distance classification algorithms, the overall accuracy of the RF classification based on joint features was 2.03, 5.69, and 23.36% higher, respectively, and the Kappa coefficient was 0.03, 0.07, and 0.27 higher, respectively. Therefore, this novel method can increase the accuracy of the extraction of objects in a wetland, providing a reliable technical means for wetland monitoring.

Multiple Classifiers Based Semi-Supervised Polarimetric SAR Image Classification Method

Polarimetric synthetic aperture radar (PolSAR) image classification has played an important role in PolSAR data application. Deep learning has achieved great success in PolSAR image classification over the past years. However, when the labeled training dataset is insufficient, the classification results are usually unsatisfactory. Furthermore, the deep learning approach is based on hierarchical features, which is an approach that cannot take full advantage of the scattering characteristics in PolSAR data. Hence, it is worthwhile to make full use of scattering characteristics to obtain a high classification accuracy based on limited labeled samples. In this paper, we propose a novel semi-supervised classification method for PolSAR images, which combines the deep learning technique with the traditional scattering trait-based classifiers. Firstly, based on only a small number of training samples, the classification results of the Wishart classifier, support vector machine (SVM) classifier, and a complex-valued convolutional neural network (CV-CNN) are used to conduct majority voting, thus generating a strong dataset and a weak dataset. The strong training set are then used as pseudo-labels to reclassify the weak dataset by CV-CNN. The final classification results are obtained by combining the strong training set and the reclassification results. Experiments on two real PolSAR images on agricultural and forest areas indicate that, in most cases, significant improvements can be achieved with the proposed method, compared to the base classifiers, and the improvement is approximately 3–5%. When the number of labeled samples was small, the superiority of the proposed method is even more apparent. The improvement for built-up areas or infrastructure objects is not as significant as forests.

A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

Classification based on polarimetric synthetic aperture radar (PolSAR) images is an emerging technology, and recent years have seen the introduction of various classification methods that have been proven to be effective to identify typical features of many terrain types. Among the many regions of the study, the Hunshandake Sandy Land in Inner Mongolia, China stands out for its vast area of sandy land, variety of ground objects, and intricate structure, with more irregular characteristics than conventional land cover. Accounting for the particular surface features of the Hunshandake Sandy Land, an unsupervised classification method based on new decomposition and large-scale spectral clustering with superpixels (ND-LSC) is proposed in this study. Firstly, the polarization scattering parameters are extracted through a new decomposition, rather than other decomposition approaches, which gives rise to more accurate feature vector estimate. Secondly, a large-scale spectral clustering is applied as appropriate to meet the massive land and complex terrain. More specifically, this involves a beginning sub-step of superpixels generation via the Adaptive Simple Linear Iterative Clustering (ASLIC) algorithm when the feature vector combined with the spatial coordinate information are employed as input, and subsequently a sub-step of representative points selection as well as bipartite graph formation, followed by the spectral clustering algorithm to complete the classification task. Finally, testing and analysis are conducted on the RADARSAT-2 fully PolSAR dataset acquired over the Hunshandake Sandy Land in 2016. Both qualitative and quantitative experiments compared with several classification methods are conducted to show that proposed method can significantly improve performance on classification.

Improving the Accuracy of Multiple Algorithms for Crop Classification by Integrating Sentinel-1 Observations with Sentinel-2 Data

The availability of an unprecedented amount of open remote sensing data, such as Sentinel-1 and -2 data within the Copernicus program, has boosted the idea of combining the use of optical and radar data to improve the accuracy of agricultural applications such as crop classification. Sentinel-1’s Synthetic Aperture Radar (SAR) provides co- and cross-polarized backscatter, which offers the opportunity to monitor agricultural crops using radar at high spatial and temporal resolution. In this study, we assessed the potential of integrating Sentinel-1 information (VV and VH backscatter and their ratio VH/VV with Sentinel-2A data (NDVI) to perform crop classification and to define which are the most important input data that provide the most accurate classification results. Further, we examined the temporal dynamics of remote sensing data for cereal, horticultural, and industrial crops, perennials, deciduous trees, and legumes. To select the best SAR input feature, we tried two approaches, one based on classification with only SAR features and one based on integrating SAR with optical data. In total, nine scenarios were tested. Furthermore, we evaluated the performance of 22 nonparametric classifiers on which most of these algorithms had not been tested before with SAR data. The results revealed that the best performing scenario was the one integrating VH and VV with normalized difference vegetation index (NDVI) and cubic support vector machine (SVM) (the kernel function of the classifier is cubic) as the classifier with the highest accuracy among all those tested.

A Novel Image Fusion Method of Multi-Spectral and SAR Images for Land Cover Classification

The fusion of multi-spectral and synthetic aperture radar (SAR) images could retain the advantages of each data, hence benefiting accurate land cover classification. However, some current image fusion methods face the challenge of producing unexpected noise. To overcome the aforementioned problem, this paper proposes a novel fusion method based on weighted median filter and Gram–Schmidt transform. In the proposed method, Sentinel-2A images and GF-3 images are respectively subjected to different preprocessing processes. Since weighted median filter does not strongly blur edges while filtering, it is applied to Sentinel-2A images for reducing noise. The processed Sentinel images are then transformed by Gram–Schmidt with GF-3 images. Two popular methods, principal component analysis method and traditional Gram–Schmidt transform, are used as the comparison methods in the experiment. In addition, random forest, a powerful ensemble model, is adopted as the land cover classifier due to its fast training speed and excellent classification performance. The overall accuracy, Kappa coefficient and classification map of the random forest are used as the evaluation criteria of the fusion method. Experiments conducted on five datasets demonstrate the superiority of the proposed method in both objective metrics and visual impressions. The experimental results indicate that the proposed method can improve the overall accuracy by up to 5% compared to using the original Sentinel-2A and has the potential to improve the satellite-based land cover classification accuracy.

Integration of GF2 Optical, GF3 SAR, and UAV Data for Estimating Aboveground Biomass of China’s Largest Artificially Planted Mangroves

Accurate methods to estimate the aboveground biomass (AGB) of mangroves are required to monitor the subtle changes over time and assess their carbon sequestration. The AGB of forests is a function of canopy-related information (canopy density, vegetation status), structures, and tree heights. However, few studies have attended to integrating these factors to build models of the AGB of mangrove plantations. The objective of this study was to develop an accurate and robust biomass estimation of mangrove plantations using Chinese satellite optical, SAR, and Unmanned Aerial Vehicle (UAV) data based digital surface models (DSM). This paper chose Qi’ao Island, which forms the largest contiguous area of mangrove plantation in China, as the study area. Several field visits collected 127 AGB samples. The models for AGB estimation were developed using the random forest algorithm and integrating images from multiple sources: optical images from Gaofen-2 (GF-2), synthetic aperture radar (SAR) images from Gaofen-3 (GF-3), and UAV-based digital surface model (DSM) data. The performance of the models was assessed using the root-mean-square error (RMSE) and relative RMSE (RMSEr), based on five-fold cross-validation and stratified random sampling approach. The results showed that images from the GF-2 optical (RMSE = 33.49 t/ha, RMSEr = 21.55%) or GF-3 SAR (RMSE = 35.32 t/ha, RMSEr = 22.72%) can be used appropriately to monitor the AGB of the mangrove plantation. The AGB models derived from a combination of the GF-2 and GF-3 datasets yielded a higher accuracy (RMSE = 29.89 t/ha, RMSEr = 19.23%) than models that used only one of them. The model that used both datasets showed a reduction of 2.32% and 3.49% in RMSEr over the GF-2 and GF-3 models, respectively. On the DSM dataset, the proposed model yielded the highest accuracy of AGB (RMSE = 25.69 t/ha, RMSEr = 16.53%). The DSM data were identified as the most important variable, due to mitigating the saturation effect observed in the optical and SAR images for a dense AGB estimation of the mangroves. The resulting map, derived from the most accurate model, was consistent with the results of field investigations and the mangrove plantation sequences. Our results indicated that the AGB can be accurately measured by integrating images from the optical, SAR, and DSM datasets to adequately represent canopy-related information, forest structures, and tree heights.

On the Use of Neumann Decomposition for Crop Classification Using Multi-Temporal RADARSAT-2 Polarimetric SAR Data

In previous studies, parameters derived from polarimetric target decompositions have proven as very effective features for crop classification with single/multi-temporal polarimetric synthetic aperture radar (PolSAR) data. In particular, a classical eigenvalue-eigenvector-based decomposition approach named after Cloude–Pottier decomposition (or “H/A/α”) has been frequently used to construct classification approaches. A model-based decomposition approach proposed by Neumann some years ago provides two parameters with very similar physical meanings to polarimetric scattering entropy H and the alpha angle α in Cloude–Pottier decomposition. However, the main aim of the Neumann decomposition is to describe the morphological characteristics of vegetation. Therefore, it is worth investigating the performance of Neumann decomposition on crop classification, since vegetation is the principal type of targets in agricultural scenes. In this paper, a multi-temporal supervised classification method based on Neumann decomposition and Random Forest Classifier (named “ND-RF”) is proposed. The three parameters from Neumann decomposition, computed along the time series of data, are used as classification features. Finally, the Random Forest Classifier is applied for supervised classification. For comparison, an analogue classification scheme is constructed by replacing the Neumann decomposition with the Cloude–Pottier decomposition, hence named CP-RF. For validation, a time series of 11 polarimetric RADARSAT-2 SAR images acquired over an agricultural site in London, Ontario, Canada in 2015 is employed. Totally, 10 multi-temporal combinations of datasets were tested by adding images one by one sequentially along the SAR observation time. The results show that the ND-RF method generally produces better classification performance than the CP-RF method, with the largest improvement of over 12% in overall accuracy. Further tests show that the two parameters similar to entropy and alpha angle produce classification results close to those of CP-RF, whereas the third parameter in the Neumann decomposition is more effective in improving the classification accuracy with respect to the Cloude–Pottier decomposition.

Forest Growing Stock Volume Estimation in Subtropical Mountain Areas Using PALSAR-2 L-Band PolSAR Data

Forest growing stock volume (GSV) extraction using synthetic aperture radar (SAR) images has been widely used in climate change research. However, the relationships between forest GSV and polarimetric SAR (PolSAR) data in the mountain region of central China remain unknown. Moreover, it is challenging to estimate GSV due to the complex topography of the region. In this paper, we estimated the forest GSV from advanced land observing satellite-2 (ALOS-2) phased array-type L-band synthetic aperture radar (PALSAR-2) full polarimetric SAR data based on ground truth data collected in Youxian County, Central China in 2016. An integrated three-stage (polarization orientation angle, POA; effective scattering area, ESA; and angular variation effect, AVE) correction method was used to reduce the negative impact of topography on the backscatter coefficient. In the AVE correction stage, a strategy for fine terrain correction was attempted to obtain the optimum correction parameters for different polarization channels. The elements on the diagonal of covariance matrix were used to develop forest GSV prediction models through five single-variable models and a multi-variable model. The results showed that the integrated three-stage terrain correction reduced the negative influence of topography and improved the sensitivity between the forest GSV and backscatter coefficients. In the three stages, the POA compensation was limited in its ability to reduce the impact of complex terrain, the ESA correction was more effective in low-local incidence angles area than high-local incidence angles, and the effect of the AVE correction was opposite to the ESA correction. The data acquired on 14 July 2016 was most suitable for GSV estimation in this study area due to its correlation with GSV, which was the strongest at HH, HV, and VV polarizations. The correlation coefficient values were 0.489, 0.643, and 0.473, respectively, which were improved by 0.363, 0.373, and 0.366 in comparison to before terrain correction. In the five single-variable models, the fitting performance of the Water-Cloud analysis model was the best, and the correlation coefficient R2 value was 0.612. The constructed multi-variable model produced a better inversion result, with a root mean square error (RMSE) of 70.965 m3/ha, which was improved by 22.08% in comparison to the single-variable models. Finally, the space distribution map of forest GSV was established using the multi-variable model. The range of estimated forest GSV was 0 to 450 m3/ha, and the mean value was 135.759 m3/ha. The study expands the application potential of PolSAR data in complex topographic areas; thus, it is helpful and valuable for the estimation of large-scale forest parameters.

Optimization of Reconfigurable Satellite Constellations Using Simulated Annealing and Genetic Algorithm

Agile Earth observation can be achieved with responsiveness in satellite launches, sensor pointing, or orbit reconfiguration. This study presents a framework for designing reconfigurable satellite constellations capable of both regular Earth observation and disaster monitoring. These observation modes are termed global observation mode and regional observation mode, constituting a reconfigurable satellite constellation (ReCon). Systems engineering approaches are employed to formulate this multidisciplinary problem of co-optimizing satellite design and orbits. Two heuristic methods, simulated annealing (SA) and genetic algorithm (GA), are widely used for discrete combinatorial problems and therefore used in this study to benchmark against a gradient-based method. Point-based SA performed similar or slightly better than the gradient-based method, whereas population-based GA outperformed the other two. The resultant ReCon satellite design is physically feasible and offers performance-to-cost(mass) superior to static constellations. Ongoing research on observation scheduling and constellation management will extend the ReCon applications to radar imaging and radio occultation beyond visible wavelengths and nearby spectrums.