A Regional Mapping Method for Oilseed Rape Based on HSV Transformation and Spectral Features

CARM30: China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 using multi-source data

Rapeseed is a critical cash crop globally, and understanding its distribution can assist in refined agricultural management, ensuring a sustainable vegetable oil supply, and informing government decisions. China is the leading consumer and third-largest producer of rapeseed. However, there is a lack of widely available, long-term, and large-scale remotely sensed maps on rapeseed cultivation in China. Here this study utilizes multi-source data such as satellite images, GLDAS environmental variables, land cover maps, and terrain data to create the China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 (CARM30). Our product was validated using independent samples and showed average F1 scores of 0.869 and 0.971 for winter and spring rapeseed. The CARM30 has high spatial consistency with existing 10 m and 20 m rapeseed maps. Additionally, the CARM30-derived rapeseed planted area was significantly correlated with agricultural statistics (R2 = 0.65-0.86; p < 0.001). The obtained rapeseed distribution information can serve as a reference for stakeholders such as farmers, scientific communities, and decision-makers.

Abundance considerations for modeling yield of rapeseed at the flowering stage

Introduction

To stabilize the edible oil market, it is necessary to determine the oil yield in advance, so the accurate and fast technology of estimating rapeseed yield is of great significance in agricultural production activities. Due to the long flowering time of rapeseed and the characteristics of petal color that are obviously different from other crops, the flowering period can be carefully considered in crop classification and yield estimation.

Methods

A field experiment was conducted to obtain the unmanned aerial vehicle (UAV) multispectral images. Field measurements consisted of the reflectance of flowers, leaves, and soils at the flowering stage and rapeseed yield at physiological maturity. Moreover, GF-1 and Sentinel-2 satellite images were collected to compare the applicability of yield estimation methods. The abundance of different organs of rapeseed was extracted by the spectral mixture analysis (SMA) technology, which was multiplied by vegetation indices (VIs) respectively to estimate the yield.

Results

For the UAV-scale, the product of VIs and leaf abundance (AbdLF) was closely related to rapeseed yield, which was better than the VIs models for yield estimation, with the coefficient of determination (R2) above 0.78. The yield estimation models of the product of normalized difference yellowness index (NDYI), enhanced vegetation index (EVI) and AbdLF had the highest accuracy, with the coefficients of variation (CVs) below 10%. For the satellite scale, most of the estimation models of the product of VIs and rapeseed AbdLF were also improved compared with the VIs models. The yield estimation models of the product of AbdLF and renormalized difference VI (RDVI) and EVI (RDVI×AbdLF and EVI×AbdLF) had the steady improvement, with CVs below 13.1%. Furthermore, the yield estimation models of the product of AbdLF and normalized difference VI (NDVI), visible atmospherically resistant index (VARI), RDVI, and EVI had consistent performance at both UAV and satellite scales.

Discussion

The results showed that considering SMA could improve the limitation of using only VIs to retrieve rapeseed yield at the flowering stage. Our results indicate that the abundance of rapeseed leaves can be a potential indicator of yield prediction during the flowering stage.

Recognition of spider mite infestations in jujube trees based on spectral-spatial clustering of hyperspectral images from UAVs

Spider mite infestations are a serious hazard for jujube trees in China. The use of remote sensing technology to evaluate the health of jujube trees in large-scale intensive agricultural production is an effective means of agricultural control. Hyperspectral remote sensing has a higher spectral resolution and richer spectral information than conventional multispectral remote sensing, which improves the detection of crop pests and diseases. We used hyperspectral remote sensing data from jujube fields infested with spider mite in Hotan Prefecture, Xinjiang to evaluate their use in monitoring this important pest. We fused spectral and spatial information from the hyperspectral images and propose a method of recognizing spider mite infestations of jujube trees. Our method is based on the construction of spectral features, the fusion of spatial information and clustering of these spectral-spatial features. We evaluated the effect of different spectral-spatial features and different clustering methods on the recognition of spider mite in jujube trees. The experimental results showed that the overall accuracy of the method for the recognition of spider mites was >93% and the overall accuracy of the band clustering-density peak clustering model for the recognition of spider mite reached 96.13%. This method can be applied to the control of jujube spider mites in agricultural production.

Estimating soil salinity using Gaofen-2 imagery: A novel application of combined spectral and textural features

Gaofen-2 (GF-2) imagery data has been playing an important role in environmental monitoring. However, the scarcity of spectral bands makes GF-2 difficult to use in soil salinity estimation. In this paper, we combined spectral and textual features for soil salinity estimation from GF-2 imagery. The spectral features comprised five classes of predictors: spectral value, vegetation index, salinity index, brightness index, and intensity index. Four gray-level co-occurrence matrix (GLCM) indices were used as the textural features. The least absolute shrinkage and selection operator (LASSO) was applied to select features. Four methods, namely, Random forest (RF), support vector machine (SVM), back propagation neural network (BPNN), and partial least squares regression (PLSR) were applied and compared. To this end, 211 soil samples were collected in the Yellow River Delta through field investigation. The results showed that GF-2 imagery could successfully estimate soil salinity by integrating spectral and texture features, and among the four methods, the RF had the highest accuracy with the determination coefficient for cross-validation (R²_CV), a root mean square error for cross-validation (RMSE_CV), and the ratio of the standard deviation to the root mean square error of prediction (RPD) of 0.82, 2.36 g kg^-1, and 2.28, respectively. Especially, the impact of different scale features on the soil salinity estimation accuracy was evaluated. The optimal window size for features was 9 × 9 pixels, and increasing or decreasing the window size will decrease the estimation accuracy. The study provides a novel application to soil salinity estimation from remote sensing imagery.

An Ultra-Resolution Features Extraction Suite for Community-Level Vegetation Differentiation and Mapping at a Sub-Meter Resolution

This paper presents two categories of features extraction and mapping suite, a very high-resolution suite and an ultra-resolution suite at 2 m and 0.5 m resolutions, respectively, for the differentiation and mapping of land cover and community-level vegetation types. The features extraction flow of the ultra-resolution suite involves pan-sharpening of the multispectral image, color-transformation of the pan-sharpened image, and the generation of panchromatic textural features. The performance of the ultra-resolution features extraction suite was compared with the very high-resolution features extraction suite that involves the calculation of radiometric indices and color-transformation of the multi-spectral image. This research was implemented in three mountainous ecosystems located in a cool temperate region. Three machine learning classifiers, Random Forests, XGBoost, and SoftVoting, were employed with a 10-fold cross-validation method for quantitatively evaluating the performance of the two suites. The ultra-resolution suite provided 5.3% more accuracy than the very high-resolution suite using single-date autumn images. Addition of summer images gained 12.8% accuracy for the ultra-resolution suite and 13.2% accuracy for the very high-resolution suite across all sites, while the ultra-resolution suite showed 4.9% more accuracy than the very high-resolution suite. The features extraction and mapping suites presented in this research are expected to meet the growing need for differentiating land cover and community-level vegetation types at a large scale.

Two-Stepwise Hierarchical Adaptive Threshold Method for Automatic Rapeseed Mapping over Jiangsu Using Harmonized Landsat/Sentinel-2

Rapeseed distribution mapping is a crucial issue for food and oil security, entertainment, and tourism development. Previous studies have used various remote sensing approaches to map rapeseed. However, the time-consuming and labor-intensive sample data used in these supervised classification methods greatly limit the development of large-scale mapping in rapeseed studies. Regarding threshold methods, some empirical thresholding methods still need sample data to select the optimal threshold value, and their accuracies decrease when a fixed threshold is applied in complex and diverse environments. This study first developed the Normalized Difference Rapeseed Index (NDRI), defined as the difference in green and short-wave infrared bands divided by their sum, to find a suitable feature to distinguish rapeseed from other types of crops. Next, a two-stepwise hierarchical adaptive thresholding (THAT) algorithm requiring no training data was used to automatically extract rapeseed in Xinghua. Finally, two adaptive thresholding methods of the standalone Otsu and Otsu with Canny Edge Detection (OCED) were used to extract rapeseed across Jiangsu province. The results show that (1) NDRI can separate rapeseed from other vegetation well; (2) the OCED-THAT method can accurately map rapeseed in Jiangsu with an overall accuracy (OA) of 0.9559 and a Kappa coefficient of 0.8569, and it performed better than the Otsu-THAT method; (3) the OCED-THAT method had a lower but acceptable accuracy than the Random Forest method (OA = 0.9806 and Kappa = 0.9391). This study indicates that the THAT model is a promising automatic method for mapping rapeseed.

Spatial Grain Effects of Urban Green Space Cover Maps on Assessing Habitat Fragmentation and Connectivity

The scientific evaluation of landscape fragmentation and connectivity is important for habitat conservation. It is strongly influenced by the spatial resolution of source maps, particularly in urban environments. However, there is limited comprehensive investigation of the spatial grain effect on urban habitat and few in-depth analysis across different urban gradients. In this paper, we scrutinize the spatial grain effects of urban green space (UGS) cover maps (derived from remote sensing imagery and survey data) with respect to evaluating habitat fragmentation and connectivity, comparing among different urban gradient scenarios (downtown, urban periphery, and suburban area) in Hangzhou, a megacity in China. The fragmentation was detected from three indices, including Entropy, Contagion, and Hypsometry. Then morphological spatial pattern analysis (MSPA) was applied for the landscape element identification. The possibility of connectivity (PC) and patch importance (dPC) were proposed for measuring the landscape connectivity based on Cores and Bridges from MSPA results. The results indicate that the farther the location is from downtown, the less sensitive the landscape element proportion to the spatial resolution. Among the three fragmentation indices, the overall hypsometry index has the lowest sensitivity to the spatial resolution, which implies this index’s broader application value. Considering connectivity, high spatial resolution maps are appropriate for analyzing highly heterogeneous urban areas, while medium spatial resolution maps are more applicable to urban periphery and suburban area with larger UGS patches and less fragmentation. This study suggests that the spatial resolution of UGS maps substantially influence habitat fragmentation and connectivity, which is critical for decision making in urban planning and management.

Developing a New Method to Identify Flowering Dynamics of Rapeseed Using Landsat 8 and Sentinel-1/2

Identifying the rapeseed (Brassica napus L.) flowering dates are important for planting area estimation, growth monitoring, and yield estimation. However, there is currently a lack of data on rapeseed flowering dates at the parcel scale. In this study, a new spectral index (Normalized Rapeseed Flowering Index, NRFI) is proposed to detect rapeseed flowering dates from time series data generated from Landsat 8 OLI and Sentinel-2 sensors. This study also analyzed the feasibility of using the backscattering coefficients (VV, VH, and VV/VH) of Sentinel-1 to detect the flowering dates of rapeseed at the parcel scale. Based on the spectral and polarization characteristics of 718 rapeseed parcels collected in 2018, we developed a method to automatically identify peak flowering dates by the local maximum of NRFI series and the local minimum of VH and VV, along with the maximum of VV/VH. The results show that most of the peak flowering dates derived from Sentinel-1 and Sentinel-2 can be confirmed by the in-situ phenological observations at the Deutscher Wetterdienst (DWD) stations in Germany. The NRFI outperforms the Normalized Difference Yellow Index (NDYI) in identifying the peak flowering dates from Landsat 8. The derived medians of peak flowering dates by NRFI, NDYI (Sentinel-2), and VH are similar, while a systematic delay is observed by NDYI (Landsat 8). The method with the spectrum and backscattering coefficients will be a potential tool to identify crop flowering dynamics and map crop planting area.

Regional Geotechnical Mapping Employing Kriging on Electronic Geodatabase

A regional geotechnical map was developed by employing kriging using spatial and s geostatistical analysis tools. Many studies have been carried out in the field of topography, digital elevation modeling, agriculture, geological, crop, and precipitation mapping. However, no significant contribution to the development of geotechnical mapping has been made. For the appraisal of a geotechnical map, extensive field explorations were carried out throughout the geotechnically diversified plateau spread over an area of approximately 23,000 km2. In total, 450 soil samples were collected from 75 data stations to determine requisite index properties and soil classification for the subsequent allowable bearing capacity evaluation. The formatted test results, along with associated geospatial information, were uploaded to ArcMap, which created an initial input electronic database. The kriging technique of geostatistical analysis was determined to be more feasible for generating a geotechnical map. The developed map represents the distribution of soil in the region as per the engineering classification system, allowable bearing capacity, and American Association of State Highway and Transportation Officials (AASHTO) subgrade rating for 1.5-, 3.0-, and 4.5-m depths. The accuracy of the maps generated using kriging interpolation technique under spatial analyst tools was verified by comparing the values in the generated surface with the actual values measured at randomly selected validation points. The database was primarily created for the appraisal of geotechnical maps and can also be used for preliminary geotechnical investigations, which saves the cost of soil investigations. In addition, this approach allows establishing useful correlations among the geotechnical properties of soil.

Improved Winter Wheat Spatial Distribution Extraction Using A Convolutional Neural Network and Partly Connected Conditional Random Field

Improving the accuracy of edge pixel classification is crucial for extracting the winter wheat spatial distribution from remote sensing imagery using convolutional neural networks (CNNs). In this study, we proposed an approach using a partly connected conditional random field model (PCCRF) to refine the classification results of RefineNet, named RefineNet-PCCRF. First, we used an improved RefineNet model to initially segment remote sensing images, followed by obtaining the category probability vectors for each pixel and initial pixel-by-pixel classification result. Second, using manual labels as references, we performed a statistical analysis on the results to select pixels that required optimization. Third, based on prior knowledge, we redefined the pairwise potential energy, used a linear model to connect different levels of potential energies, and used only pixel pairs associated with the selected pixels to build the PCCRF. The trained PCCRF was then used to refine the initial pixel-by-pixel classification result. We used 37 Gaofen-2 images obtained from 2018 to 2019 of a representative Chinese winter wheat region (Tai’an City, China) to create the dataset, employed SegNet and RefineNet as the standard CNNs, and a fully connected conditional random field as the refinement methods to conduct comparison experiments. The RefineNet-PCCRF’s accuracy (94.51%), precision (92.39%), recall (90.98%), and F1-Score (91.68%) were clearly superior than the methods used for comparison. The results also show that the RefineNet-PCCRF improved the accuracy of large-scale winter wheat extraction results using remote sensing imagery.

Extracting Crop Spatial Distribution from Gaofen 2 Imagery Using a Convolutional Neural Network

Using satellite remote sensing has become a mainstream approach for extracting crop spatial distribution. Making edges finer is a challenge, while simultaneously extracting crop spatial distribution information from high-resolution remote sensing images using a convolutional neural network (CNN). Based on the characteristics of the crop area in the Gaofen 2 (GF-2) images, this paper proposes an improved CNN to extract fine crop areas. The CNN comprises a feature extractor and a classifier. The feature extractor employs a spectral feature extraction unit to generate spectral features, and five coding-decoding-pair units to generate five level features. A linear model is used to fuse features of different levels, and the fusion results are up-sampled to obtain a feature map consistent with the structure of the input image. This feature map is used by the classifier to perform pixel-by-pixel classification. In this study, the SegNet and RefineNet models and 21 GF-2 images of Feicheng County, Shandong Province, China, were chosen for comparison experiment. Our approach had an accuracy of 93.26%, which is higher than those of the existing SegNet (78.12%) and RefineNet (86.54%) models. This demonstrates the superiority of the proposed method in extracting crop spatial distribution information from GF-2 remote sensing images.

Winter Wheat Green-up Date Variation and its Diverse Response on the Hydrothermal Conditions over the North China Plain, Using MODIS Time-Series Data

Vegetation phenology plays a critical role in the dynamic response of terrestrial ecosystems to climate change. However, the relationship between the phenology of winter wheat and hydrothermal factors is inadequate, especially in typical agricultural areas. In this study, the possible effects of preseason climate changes on the green-up date (GUD) of winter wheat over the North China Plain (NCP) was investigated, using the MODIS EVI 8-day time-series data from 2000 to 2015, as well as the concurrent monthly mean temperature (Tm), mean maximum (Tmax) and minimum temperature (Tmin) and total precipitation (TP) data. Firstly, we quantitatively identified the time lag effects of winter wheat GUD responses to different climatic factors; then, the major driving factors for winter wheat GUD were further explored by applying multiple linear regression models. The results showed that the time lag effects of winter wheat GUD response to climatic factors were site- and climatic parameters-dependent. Negative temperature effects with about a 3-month time lag dominated in most of the NCP, whereas positive temperature effects with a zero-month lag were most common in some of the southern parts. In comparison, total precipitation had a negative zero-month lag effect in the northern region, but two lagged months occurred in the south. Regarding the time lag effects, the explanation power of climatic factors improved relatively by up to 77%, and the explanation area increased by 41.20%. Additionally, change in winter wheat GUD was primarily determined by temperature rather than by TP, with a marked spatial heterogeneity of the Tmax and Tmin effect. Our results confirmed different time lag effects from different climatic factors on phenological processes in spring, and further suggested that both Tmax and Tmin should be considered to improve the performance of spring phenology models.

A New CNN-Bayesian Model for Extracting Improved Winter Wheat Spatial Distribution from GF-2 imagery

When the spatial distribution of winter wheat is extracted from high-resolution remote sensing imagery using convolutional neural networks (CNN), field edge results are usually rough, resulting in lowered overall accuracy. This study proposed a new per-pixel classification model using CNN and Bayesian models (CNN-Bayesian model) for improved extraction accuracy. In this model, a feature extractor generates a feature vector for each pixel, an encoder transforms the feature vector of each pixel into a category-code vector, and a two-level classifier uses the difference between elements of category-probability vectors as the confidence value to perform per-pixel classifications. The first level is used to determine the category of a pixel with high confidence, and the second level is an improved Bayesian model used to determine the category of low-confidence pixels. The CNN-Bayesian model was trained and tested on Gaofen 2 satellite images. Compared to existing models, our approach produced an improvement in overall accuracy, the overall accuracy of SegNet, DeepLab, VGG-Ex, and CNN-Bayesian was 0.791, 0.852, 0.892, and 0.946, respectively. Thus, this approach can produce superior results when winter wheat spatial distribution is extracted from satellite imagery.