Winter wheat planting area extraction using SAR change detection

In this letter, we propose a method to reduce the number of false alarms in a wavelength–resolution synthetic aperture radar (SAR) change detection scheme by using a convolutional neural network (CNN). The detection is performed in two steps: change analysis and object classification. A simple technique for wavelength–resolution SAR change detection is implemented to extract potential targets from the image of interest. A CNN is then used for classifying the change map detections as either a target or nontarget, further reducing the false alarm rate (FAR). The scheme is tested for the CARABAS-II data set, where only three false alarms over a testing area of 96 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> are reported while still sustaining a probability of detection above 96%. We also show that the network can still reduce the FAR even when the flight heading of the SAR system measurement campaign differs by up to 100° between the images used for training and test.

Due to the speckle effect of coherent imaging the detection of lines in SAR scenes is considerably move difficult than in optical images. A new approach to detect lines in noisy images using a Markov random field (MRF) model and Bayesian classification is proposed. The unobservable object classes of single pixels are assumed to fulfil the Markov condition, i.e. to depend on the object classes of neighboring pixels only. The influence of neighboring line pixels is formulated based on potentials derived from a random walk model. Locally, the image data is evaluated with a rotating template. As SAR intensity data is deteriorated by multiplicative noise, the response of the local line detector is a normalized intensity ratio which results in a constant false alarm rate. The approach integrates intensity, coherence from interferometric processing of a SAR scene pair, and given Geographic Information System (GIS) data.

Winter wheat is one of the most important crops planted in Beijing suburb. In recent 20 years, winter wheat planted area decreased obviously in Beijing area owning to the urbanization process. This study focuses on the winter wheat planted area transformation monitoring of Beijing suburb from 1992 to 2009 through remote sensing technique. Multi-temporal Landsat- TM images are collected during the winter wheat growth season of 1992，2000 and 2009 and used to analyze the trend and characteristics of winter wheat field variation in Beijing suburb in recent two decades years. The PCA analysis and Tasseled Cap transform technique are adopted in this study for feature classification. The study result shows that the winter wheat planted area in 1992，2000 and 2009 in Beijing is 113671 ha，84322 ha and 61529 ha, respectively. It indicates that winter wheat planting area in Beijing has a significantly decreasing trend and the total reduced area is 52143 ha from 1992 to 2009. Winter wheat planted area is decreased by 29349 ha from 1992 to 2000. Most of reduced wheat fields are transformed into bare land or used for urban land accounting for 42.8% and 39.7%. Others wheat fields are used for greenhouse and water bodies (fish ponds and water fields), accounting for 13.3% and 3%. The winter wheat field decreased by 22794 ha from 2000 to 2009, more than 41.93% of wheat field is turned into bare land. Reduce field for greenhouse land and water bodies (ponds or water fields) are account for21.61% and 7.79%, respectively.

This research utilized “GaoFen-1” 2 m panchromatic, 8 m and 16 m multispectral satellite data to monitor the planting area of winter wheat. Calculate the correction coefficient by the results of planting area of winter wheat gotten from “GaoFen-1” 16 m multispectral satellite data and micro unmanned aerial vehicle data. Correct the area extraction result of “GaoFen-1” 16 m multispectral satellite data and verify the accuracy of the results got from fusion data of 2 m resolution and 8 m resolution of “GaoFen-1” by micro unmanned aerial vehicle data. Then compare with the area extraction results, extracted from the data of fusion data of 2 m resolution and 8 m resolution of “GaoFen-1” and the corrected 16 m multispectral satellite data, in Jizhou. The study result show that the corrected extraction result of planting area of winter wheat, from “GaoFen-1” 16 m multispectral satellite data, is accurate relatively and could better meet the requirements of the crop dynamic monitoring business operational running.

This paper presents a supervised polarimetric synthetic aperture radar (PolSAR) change detection method applied to specific land cover types. For each pixel of a PolSAR image, its target scattering vector can be modeled as having a complex multivariate normal distribution. Based on this assumption, the joint distribution of two corresponding vectors in a pair of PolSAR images is derived. Then, a generalized likelihood ratio test statistic for the equality of two likelihood functions of such joint distribution is considered and a maximum likelihood distance measure for specific land cover types is presented. Subsequently, the Kittler and Illingworth minimum error threshold segmentation method is applied to extract the specific changed areas. Experiments on two repeat-pass Radarsat-2 fully polarimetric images of Suzhou, China, demonstrate that the proposed change detection method gives a good performance in determining the specific changed areas in PolSAR images, especially the areas that have changed to water.

In this paper, a novel moving target detection and tracking approach is presented based on Gaussian mixture probability hypothesis density (GMPHD) filter in synthetic aperture radar (SAR). Based on the advantages of GMPHD filter and the characteristics of moving target in SAR imagery, GMPHD filter is employed on potential moving target candidates extracted from a sequence of temporal and spatial sub-aperture SAR images to detect and track the moving targets in heavy clutter environment. Utilizing the tracking algorithm, the states and the number of moving targets are obtained over time. Simultaneously, the strong ground stationary clutter lacking of the dynamic behavior is eliminated finally. Both simulation and real Gotcha data set processing results are provided to demonstrate the effectiveness of the proposed approach.

Recent growth in the tasking and collection of Synthetic Aperture Radar (SAR) imagery, in particular commercial satellite availability, provides new opportunities for wide area change monitoring. Classic applications of change detection in SAR compare individual pixels, but as higher resolution imagery has become widely available there is an opportunity to leverage structural image content to produce more informative change identification. Deep learning techniques encompass the state of the art in identifying structure in imagery, but are notoriously data hungry. A recent body of research has grown around a technique called self-supervised representation learning (SSRL) to help minimize the need for handmade labels. We build on this research and train a model for use in SAR change detection. We leverage a SSRL approach known as contrastive learning, which encourages a deep learning model to identify salient image features through noise and other augmentations without an immediate need for hand engineered labels. The representation learned through this process can then be applied to other supervised, or unsupervised tasks, and we demonstrate the use of this learned embedding to identify change across SAR image pairs.

Timely information on lake ice cover conditions is critical in support of commercial shipping, winter-road transportation, and winter leisure activities such as snowmobiling and ice fishing. Monitoring of lake ice extent and ice phenology (i.e. dates associated with freeze-up/break-up and ice duration) is also valuable for improving numerical weather prediction (NWP) and for climate monitoring. The availability of free synthetic aperture radar (SAR) data from the European Space Agency’s Sentinel-1 A/B constellation provides an unprecedented opportunity to develop operational algorithms for lake ice cover mapping at a temporal frequency not available until now from SAR missions (ca. every 1–5 days depending on latitude). For NWP, rapid and accurate mapping of ice cover and open water areas in lake-rich regions is required. However, the classification of SAR imagery using traditional machine learning (ML) approaches is challenging due to the large data volume generated by imaging systems such as Sentinel-1 SAR as well as the complexity of radar signatures as a function of sensor and target characteristics. For lakes specifically, radar backscatter can vary greatly with incidence angle, polarization and surface properties (e.g. calm and wind-roughed open water, new thin ice, surface roughness due to the presence of pressure ridges, ice type, melting of ice and on-ice snow). To address the challenge of large-scale lake ice mapping, we investigate the GPU-boosted deep neural network approach that is efficient at handling big complex data. In this paper, we design a novel maximum a posterior (MAP) approach combining a convolutional neural network (CNN) and conditional random field (CRF) for better addressing the challenges of operational lake ice mapping. The proposed approach is tested on 17 Sentinel-1 dual-polarization (VV and VH) SAR images, where eight are used for training and validation and nine used for out-of-sample testing. To identify the optimal network architecture, an independent validation set is used to evaluate the performance of a series of six CNNs with increasing model complexity. The best model overcomes the noise effect in Sentinel-1 SAR imagery and the lake ice signature ambiguity issue; it achieves average classification accuracies of 97.10% and 97.14% for open water and ice, respectively, on the validation set. Moreover, the best model outperforms the last-ranked model by about 2% in terms of mean overall accuracy (OA), demonstrating the improvement and importance of model selection. The use of CRF can consistently improve the CNN by reducing the artefacts and noise effect in ice maps, outperforming the CNN model when used alone by about 3% in terms of mean OA on the validation set. The proposed CNN-CRF approach also achieves high accuracy on the nine test scenes, achieving a mean OA of 93.10%, demonstrating strong generalization capability that is important for SAR lake ice mapping.

Change detection is an important synthetic aperture radar (SAR) application, usually used to detect changes on the ground scene measurements in different moments in time. Traditionally, change detection algorithm (CDA) is mainly designed for two synthetic aperture radar (SAR) images retrieved at different instants. However, more images can be used to improve the algorithms performance, witch emerges as a research topic on SAR change detection. Image stack information can be treated as a data series over time and can be modeled by autoregressive (AR) models. Thus, we present some initial findings on SAR change detection based on image stack considering AR models. Applying AR model for each pixel position in the image stack, we obtained an estimated image of the ground scene which can be used as a reference image for CDA. The experimental results reveal that ground scene estimates by the AR models is accurate and can be used for change detection applications.

Coherent multipolarization synthetic aperture radar (SAR) change detection exploiting data collected from $N$ multiple polarimetric channels is addressed in this letter. The problem is formulated as a binary hypothesis testing problem, and a special block-diagonal structure for the polarimetric covariance matrix is forced to design a detector based on the generalized likelihood ratio test (GLRT) criterion. It is shown that the structured decision rule ensures the constant false alarm rate property with respect to the unknown disturbance covariance. Results on both simulated and real high-resolution SAR data show the effectiveness of the considered decision rule and its superiority against the traditional unstructured GLRT in some scenarios of practical interest.

Abstract. In deep learning based synthetic aperture radar (SAR) change detection, selecting samples of high quality is a crucial step. In this work, we have proposed a refined sample selection algorithm for unsupervised SAR change detection. The propose and incorporation of volume control factors and multi-hierarchical fuzzy c-means (MH-FCM) algorithm generate samples of large diversity and high confidence, thus satisfying the needs for high quality samples. The method includes two phases: firstly, an enhanced difference image is constructed according to the difference consistency between single pixels and their neighbourhoods, and a triangular threshold segmentation method is then proposed to determine the volume control factors for sample selection. MH-FCM is developed to classify the log mean ratio difference image into 4 classes. Secondly, a dual-channel convolution neural network with an adaptive weighted loss is adopted to learn and predict the input and to obtain the change detection result. Experimental results of the Gaofen-3 dataset in Beijing have validated the effectiveness and usefulness of the proposed method.

A valid multiscale classification method of synthetic aperture radar (SAR) imagery is proposed based on multiscale technology and Markov random field (MRF) mode. Firstly, we employ multiscale autoregressive model for extracting the feature of SAR image. which is modeled by Markov random field (MRF) Model that relies on the Gaussian distribution. Secondly, using the joint probability distribution in terms of an energy function, estimation of parameters can be performed by the stochastic relaxation algorithm. Then the maximum posteriori (MAP) is designed as the optimal criterion and the final labels are obtained by the simulated annealing algorithm. Experimental results show that this method is accurate, efficient and robust.

Winter wheat is a staple food crop for most of the world’s population, and the area and spatial distribution of winter wheat are key elements in estimating crop production and ensuring food security. However, winter wheat planting areas contain substantial spatial heterogeneity with mixed pixels for coarse- and moderate-resolution satellite data, leading to large errors in crop acreage estimation. This study has developed a phenology-based approach using moderate-resolution (1 km per pixel) satellite data to estimate sub-pixel planting fractions of winter wheat. Based on unmanned aerial vehicle (UAV) observations, the unique characteristics of winter wheat with high vegetation index values at the heading stage (May) and low values at the ripening stage (June) were investigated. The differences in vegetation index between heading and ripening stages increased with the planting fraction of winter wheat, and therefore the planting fractions were estimated by comparing the NDVI differences of a given pixel with those of predetermined pure winter wheat and non-winter wheat pixels. This approach was evaluated using aerial images and agricultural statistical data in an intensive agricultural region, Shandong Province in North China. The method explained 85% and 60% of the spatial variation in municipal- and county-level statistical data, respectively. More importantly, the predetermined pure winter wheat and non-winter wheat pixels can be automatically identified using MODIS data according to their NDVI differences, which strengthens the potential to use this method at regional and global scales without any field observations as references.

Convolutional Neural Network (CNN) has shown great potential for structural information extraction, however, Synthetic Aperture Radar (SAR) image interpretation via CNN, is still a challenging task due to the pixel- to- pixel variation nature of SAR signal. In this paper, a pattern strengthened deep model for SAR image classification is presented. The main idea underlying this method is to strengthen (or sharpen) the salient patterns contained in SAR image while attenuate the random variation, so as to leverage the enormous potential of deep model. To achieve this goal, max pooling is elaborately designed to form a pattern strengthened deep model. The experimental results on two SAR datasets show that the proposed method increases the classification accuracy by 4.91% and 4.64% compared with the typical CNN, and indicate our innovative attempt is promising for SAR image classification in the case of limited training data.

Agrotechnical and biological measures for regulation and controlling phytopathogens and their impact on the quantitative indicators of the winter wheat harvest under organic cultivation have been determined. It was found that the treatment of winter wheat seed material with the chemical agent «Vitavax» resulted in a yield increase of 10 %. Seed treatment with the organic fertilizer «Amineon», as well as the combination of chemical and biological agents, contributed to a 12.5 % increase in winter wheat yield. At the same time, the weight of 1000 winter wheat seeds in the treated variants was 9-11 % higher than in the control variant (untreated). In the absence of any pre-sowing seed treatment options, the development of common bunt (Tilletia caries Tul.) in winter wheat crops results in grain contamination at a level of 31,250.0 spores/seed, which is 2.6 times higher than in the variant treated with the organic fertilizer «Amineon» and 5.3 times higher than in the variant treated with the chemical agent «Vitavax». The best results were obtained in the variant with a combination of chemical and biological agents, where grain contamination was determined to be ten times lower than in the untreated variant (control). Justification for implementing measures to control and regulate the phytopathogenic state of organic winter wheat crops, combining the use of biological plant protection agents with agronomic practices. The implementation of measures to control and regulate the phytopathogenic state of organic crops of winter wheat, combining the use of biological plant protection agents with agrotechnical methods, is substantiated. The most harmful among fungal diseases of winter wheat is common bunt. Crop loss in winter wheat due to crop infection by the pathogen amounted to 10.0-12.5 %. Pre-sowing treatment of winter wheat seeds reduces grain contamination by Tilletia caries Tul. by 2.6-10.0 times compared to the control, depending on the treatment variant. Implementing measures to control and regulate the phytopathogenic state of crops is a prerequisite for obtaining the highest possible yields of high-quality winter wheat. Key words: pathogen, contamination, common bunt, seed material, fungicidal action.