Agricultural Remote Sensing
遥感以其快速、简便、宏观、无损及客观等优点，广泛应用于农业生产各个环节。农田作物信息的快速获取与解析是开展精准农业实践的前提和基础，是突破制约中国现代农业应用发展瓶颈的关键，在农业田间信息获取上，遥感技术优势明显。小编整理了近年来发表的湿地遥感的论文请您赏析。
- The Paper
- Abstract：Crop stubble cover is an important method of conservation tillage. Obtaining the distribution of different corn stubble cover modes quickly and accurately is vital to the implementation status monitoring and effect evaluation of conservation tillage. Microwave remote sensing has characteristics of all-weather and strong penetration. Thus, it not only can ensure the acquisition of data in a short period for stubble monitoring but also can be sensitive to the information of surface roughness and crop residue structure, which provides rich information for the identification of stubble modes. Some studies consider the stubble monitoring with microwave data, but they mainly focus on the estimation of stubble coverage, and the identification of different stubble modes is rarely explored. In addition, the microwave backscattering coefficient is affected by many factors, such as soil moisture and roughness. Thus, the accuracy using microwave data simply to monitor stubble is limited.In this study, an identification method for corn stubble modes by removing soil backscatter is proposed using Sentinel-1 SAR data as the main data source. Based on the autumn field sample data in 2019 in Lishu County, Jilin Province, the backscattering model of the corn stubble is designed to separate the corn stubble scattering contribution from the soil scattering contribution and reduce the interference of soil scattering contribution on the identification of the corn stubble modes. A new Fusion Radar Index (FRI), which is produced with Sentinel-1 SAR data and Sentinel-2 optical image, is combined with traditional commonly used SAR features such as radar index and SAR textures. It is used to analyze the backscattering coefficient characteristic of field surface with different stubble modes. The best feature combination for stubble recognition is selected through the analysis of identification ability. A convolution neural network model based on 1D CNN is constructed using the optimal feature set selected to identify the corn stubble modes. The corn stubble modes are also mapped for the study area. Results show that (1) the overall accuracy of stubble identification is above 83% based on VH polarized data, FRI, and GLCM1–GLCM6 with backscattering values, which proves that the feature set obtained from Sentinel-1 radar scattering characteristics is feasible and effective for identification of the corn stubble modes. (2) The identification performance of the corn stubble modes based on data without the soil backscatter contribution improves significantly. The OA and kappa coefficients are 89.28% and 0.84, respectively. Compared with those before removing the influence of soil scattering, the recognition accuracy and kappa coefficient are improved by 5.44% and 0.09. Therefore, separating the soil scattering contribution from the total scattering contribution based on the stubble radar backscattering model can effectively reduce the influence of soil factors on the monitoring of corn stubble and improve the accuracy of the corn stubble mode recognition.This study demonstrates the great potential of Sentinel-1 SAR data and backscattering models to access the distribution map of corn stubble modes. It also provides a new idea for the wide application of Sentinel-1 SAR image in the research of corn stubble.Keywords：remote sensing;Sentinel-1 SAR data;corn stubble;recognition of stubble modes;backscatter model;optimal feature set1391|2660|1
<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2023-12-08 - Abstract：Rice is one of the most productive food crops of Asian countries. Timely and accurate access to rice cultivation information can provide professional support for farming management and agricultural policy-making. Space-borne Synthetic Aperture Radar (SAR) imaging is free from meteorological interference and can sensitively respond to rice plant development and soil moisture changes. Therefore, satellites equipped with various SAR sensors are important data sources for rice growth monitoring in cloudy and foggy areas. The research progress of microwave remote sensing in rice growth monitoring has been made on all fronts, but the technical evolution and relationship of different research topics are complex and relatively confusing.The development history, current focus, and innovation prospect of rice radar remote sensing should be reviewed and analyzed, considering the key scientific problems and main experimental approaches. Based on the collation and statistics of relevant literature in the recent 30 years, the key problems of rice radar remote sensing are summarized into three study focuses: planting area identification, biophysical parameter retrieval, and phenology and cropping intensity recognition. Then, the technical methods are summarized into three research strategies: mathematical and physical analysis, machine learning, and multisource data synergism.Specifically, rice planting area identification methods are divided into four schemes: time domain change analysis, machine learning, object-oriented classification, and multisource data synergism. Rice biophysical parameter retrieval methods are divided into five models: empirical model, physical model, semi-empirical model, data assimilation, and multi-source data synergism. Rice phenology and cropping intensity recognition methods are divided into two algorithms: time-series feature detection and multi-temporal machine learning. From the perspective of data attributes and model structure, the theoretical basis and applicable conditions of different methods are introduced, and their advantages and limitations are explained. Finally, in view of the rapid advancement of SAR imaging capability and computer science, the future research issues are discussed.Therefore, the three difficult points to be solved in rice radar remote sensing monitoring are as follows: (1) fragmented farmlands and fluctuant terrain; (2) diverse cultivation conditions, and (3) asynchronous phenology and complex interplant. The future study should focus on the following: (1) high temporal-spatial resolution of rice planting area identification relying on less prior information; (2) dynamic retrieval of rice biophysical parameters balancing model efficiency and accuracy; (3) automatic recognition of rice phenology and cropping intensity combining plant growth mechanism and time series observation. The improvement of these research topics profoundly promotes the practical application of rice radar remote sensing.Keywords：SAR;rice;Planting area;biophysical parameters;phenology;cropping intensity3242|7622|11<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2023-12-05
- Abstract：Multiangle remote sensing can provide richer, multidirectional features for ground object observation, improve the distinguishability between land types, and lay a solid data foundation for the accurate identification of ground cover. GF-7 is the first domestic sub meter surveying and mapping satellite after ZY-3 satellite, which brings an opportunity to solve the problem of “foreign matter homospectrum” using multiangle characteristics and to improve the identification accuracy of crops. In this paper, GF-7 forward-looking and backward-looking panchromatic and backward-looking multispectral data are used, and various features combinations are input to the support vector machine classifier to analyze the influence of multiangle features on crop recognition accuracy relative to the spectral and texture features. Results show that compared with only spectral features, with the addition of the angle difference feature, the production accuracy of garlic and winter wheat increased by 4.07% and 3.15%, respectively, and the user accuracy increased by 6.73% and 2.12%, respectively. Compared with the combination of spectral and texture features, with the addition of the angle difference feature, the production accuracy of garlic and winter wheat increased by 3.14% and 1.01%, respectively, and the user accuracy increased by 5.11% and 0.67%, respectively. Through the analysis of McNemar test, the improvement of classification accuracy is stable, angle difference feature can effectively improve the identification accuracy of crops. Tracing it to its cause, the multiangle characteristics of GF-7 satellite have unique differences in the spectral response of different crop types during multiangle observation. The difference improves the separability between crops to ensure the accuracy of crop remote sensing mapping.Keywords：GF-7;SVM;angle difference;remote sensing;winter wheat;garlic;agriculture1603|1555|3<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2026-04-08
- Abstract：Searching for an efficient, high-precision method for mapping paddy rice planting distribution in Northeast China has important implications for accurate paddy rice yield estimation and agricultural policy making.In this paper, paddy rice planting distribution was mapped by feature optimization random forest method in Panjin City, Liaoning Province. Based on the land coverage types, 2000 samples of 1000 paddy rice samples, 250 water samples, 300 wetland samples, 150 dry land samples, and 300 construction land samples were acquired. Training samples and testing samples accounted for 70% and 30%, respectively. In addition, 36 paddy rice field validation points were obtained through field surveys. The spectrum features, vegetation indexes, water index, and red edge indexes were constructed by using the GF-6 WFV images taken in the periods of May 11, May 25, June 1, June 6, July 20, and August 22 in 2020, and these images corresponded to the trefoil stage, transplanting stage, returning green stage, booting stage, and heading stage according to the phenological phase of paddy rice in Panjin City, respectively. The returning greening stage image was covered by June 1 and June 6. The feature importances of single temporal images and time series images were calculated, and out-of-bag (OOB) estimations on different feature combination models were performed based on OOB data. The optimal input features were selected after comprehensively considering the accuracy and complexity. Then, the feature optimization random forest model was established to extract the paddy rice planting area and spatial distribution information in Panjin City in 2020.According to the testing samples and the paddy rice field validation points, the accuracy evaluation of classification results showed the following: (1) Based on the single temporal images with different phenological phases, all the classification accuracies were 94% and above. The classification result of the image in the paddy rice transplanting stage was the best that the overall accuracy, F1 score (paddy rice), Kappa coefficient, and field validation point accuracy were 97.67%, 98.84%, 0.97, and 97.22%, respectively. (2) On the basis of comparison with the classification results of single temporal images, using time-series images for land coverage classification and paddy rice information extraction effectively improved the classification accuracy and reduced misclassification and omission, and the paddy rice classification map polygons were more regular. The overall accuracy, F1 score (paddy rice), Kappa coefficient, and field validation points accuracy with time series images were 99.33%, 100%, 0.99, and 97.22%, respectively. (3) Through analyzing of the paddy rice extraction results with or without red edge bands and red edge indexes, the classification accuracy was improved by the introduction of red edge information. This paper proved that based on the feature optimization random forest model, the paddy rice information was accurately extracted by using the single temporal image of paddy rice transplanting stage. Compared with single temporal image, using time-series images improved the classification accuracy. Considering the complexity and running speed of the model, the single temporal image of paddy rice transplanting stage was used to extract paddy rice planting area to meet the accuracy requirement in practical applications. (4) Through analyzing the results of paddy rice extraction without purple band and the yellow band, this paper proved the introduction of purple and yellow bands can improve the classification accuracy, but the effect of improving the accuracy of the classification result was inferior to the red edge information.Improving the classification accuracy of paddy rice and enhancing crop recognition capabilities by red edge information, purple band, and yellow band, showed the GF-6 satellite had broad application prospects in crop precise identification and area extraction.Keywords：remote sensing;Random Forest;red edge band;feature optimization;GF-6;paddy rice;purple band;yellow band2491|3608|17<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2026-04-08
- Abstract：As an important parameter of vegetation canopy structure, the Leaf Area Index (LAI) has become a standard land surface parameter product for many earth observation systems and an important input parameter for several quantitative remote sensing models. Rapid and accurate acquisition of vegetation LAI is of great significance for the verification of remote sensing products and promotion of the development of remote sensing models. With the improvement of smartphone sensor performance and the functions of application software, smartphones have become a new alternative to vegetation LAI measurement instruments. However, due to the limitation of the narrow Field Of View (FOV) angle of the smartphone camera sensor, the existing algorithm relies on the assumption that the leaf inclination belongs to the spherical distribution, which is that the G function (the projection of a unit leaf area on a plane perpendicular to the observed zenith angle) is equal to 0.5. Therefore, the traditional algorithm cannot solve the problem of unknown leaf inclination distribution. In this paper, a G function estimation method based on shape matching was proposed. Based on the finite length method and the gap fraction of multiple images, the vegetation canopy clumping index in the quadrat was calculated, and the effective LAI (LAIeff) and the real LAI (LAItru) were obtained by using the Poisson distribution model. The algorithm was validated by data obtained from destructive measurements (LAIdes) of two crop types (maize and soybean) at Hailun Farm in Heilongjiang Province, China. The measured time covers the main growth stages of the crop. The results showed that the Root Mean Square Error (RMSE) of the estimated LAI using the algorithm before improvement was 0.84 (vertical shooting) and 1.33 (tilted 57° shooting), and the RMSE of LAIeff and LAItru after the improvement was 0.58 and 0.56, respectively. The LAI values retrieved by the new algorithm are more consistent with the growing trend of LAI in the time series. The algorithm in this paper extends the measurement method of crop LAI, which provides the possibility to quickly and accurately extract vegetation LAI from smartphone-captured images. Further research will be considered in two directions: analyzing the influence of external light environment changes on the measurement results and adding validation data of different vegetation types.Keywords：remote sensing;smartphone;leaf area index;multi-angle gap fractions;G function;clumping index;effective leaf area index1652|1749|0<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2023-06-30
- Abstract：Accurate and rapid regional-scale crop yield estimation can provide effective data support for the formulation of national food security policies. Compared with complex mechanism models, sampling statistical surveys and empirical models based on multi-source data have better reliability and operability for county-level or city-level yield estimation. Previous studies have proposed many factors related to winter wheat yield, but systematic research on the selection and analysis of multi-source factors is lacking. On the basis of remote sensing, meteorological, and statistical data, this study systematically explored the influence of key-phase growth-environment-landscape features on winter wheat yield estimation at the county-level and determined the best time phase and characteristic parameters.The considered features included crop condition, environmental forcing (e.g., precipitation, light, and temperature), and farmland landscape. The key phases were the key periods of winter wheat yield formation (P1—P5), which were extracted from the NDVI curve of the crop growth process. Random Forest (RF) regression models were developed using different combinations of phases and features to simulate statistical wheat yield data and evaluate the importance of different combinations via an accuracy assessment. The performance of the models built from each layer combination was compared using the Mean Relative Error (MRE), Root Mean-Squared Error (RMSE), Normalized Root Mean-Squared Error (NRMSE), and coefficient of determination (R2). Data on years 2014—2017 were used to build the models, and 2018 data were utilized for validation.Results showed that P2, P3, and P4 resulted in higher accuracy than P1 and P5 in terms of single phases. The model accuracy using multi-phase features was higher than that of using single phases, and the combination of P2 and P4 was the best. Among all the features, crop growth features had the greatest impact on yield estimation accuracy, whereas the addition of environmental forcing factors (e.g., water, light, and temperature) did not significantly improve the accuracy. The addition of farmland landscape features could effectively improve the accuracy of yield estimation. Moreover, five important features (PROP, NDVI_P2, B2_P2, ED, and B1_P4) were selected, and a yield estimation model was established to obtain the county-level yield of winter wheat in Hebei Province. The MRE of wheat yield estimation at the county level in 2018 was as low as 2.85%, and the RMSE, NRMSE, and R2 were 253.25 kg/ha, 4.09%, and 0.83, respectively.Conclusion Multi-phase performance is better than single-phase performance. Combining crop growth features with farmland landscape features (RMSE of 247.79 kg/ha) provides more accurate estimates than using crop growth features alone (RMSE of 295.95 kg/ha). Furthermore, the RF model produces good yield estimation results. This study provides insights into and new methods for nationwide estimation of winter wheat yield at the county level.Keywords：remote sensing;yield estimation;winter wheat;statistical data;NDVI;Random Forest;Hebei Province1456|2448|4<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2022-08-08
- Abstract：Timely and accurate estimation of the spatial distribution of cropland is critical for agricultural production management, yield estimation, and planting structure adjustment. Previous studies on cropland mapping mostly focused on using moderate-/low-spatial-resolution images or single-phase high-spatial-resolution images, in which croplands in regions with fragmented landscapes and complex crop planting patterns are challenging to extract. The multi-source Gaofen (GF) satellites launched by China can provide images with high spatiotemporal resolution, thus presenting great potential for fine-scale cropland mapping with high accuracy. This study utilized GF-1, GF-2, and GF-6 satellites to explore a high-accuracy cropland mapping method at metric spatial resolution. Specifically, Cropland Extraction UNet (CEUNet) was developed based on the structure of UNet by integrating multi-temporal information from GF-1/6 and spatial details from GF-2 to fully exploit the spatial and temporal characteristics of cropland.To make full use of the details provided by high-spatial-resolution images, CEUNet adopted the same encoder structure as UNet. It consisted of the repeated application of two 3×3 convolutions (unpadded convolutions), each followed by a 2×2 max pooling operation with stride of 2 for down sampling. The input image size was gradually reduced at each down sampling step, and feature maps of each size were concatenated in the corresponding up-sample layer to extract the hierarchy of spatial information. Meanwhile, time-series feature maps of images with moderate to high spatial resolution were extracted by two consecutive 3×3 convolutional layers and a 1×1 convolutional layer. Then, the time-series and spatial feature maps were integrated via element-wise addition before they were sent to the decoder for pixel-wise classification.Evaluation results from randomly selected sample points showed that CEUNet achieved good performance with an overall accuracy of 92.92% over the whole of Qianjiang City, Hubei Province. The CEUNet-extracted cropland at the meter-level resolution was used to perform a wall-to-wall pixel comparison with the cropland extracted via semantic segmentation based on UNet by using multi-source remote sensing images with different resolutions (UNet_m). Semantic segmentation based on UNet using single-phase high-resolution images (UNet_s), object-based random forest classification (OBIA), and pixel-based random forest classification (RF) were employed to extract the results of cultivated land for comparison. The accuracy of cropland extraction by CEUNet was higher than that by others (the average F1 score was improved by about 0.04, 0.11, 0.21, and 0.21), indicating the effectiveness of the proposed approach for diverse agriculture landscapes. The F1 score of CEUNet was improved by about 0.09, 0.26, 0.27, and 0.27 over regions with high fragmentation and complex landscapes.Keywords：cropland extraction;multi-source remote sensing images;CNN;GF satellites2388|3360|11<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2022-08-08
- Abstract：Accurate farmland area identification is the basis of crop yield estimation and an important indicator in food security assessment. As an important data source for farmland identification, remote sensing data can provide dynamic and fast observation results for classification. GF-5, which is the only hyperspectral satellite in the China High-resolution Earth Observation System, has great research and application potential in farmland identification. However, the dimensionality curse caused by the redundant bands in hyperspectral data seriously affects the calculation speed and classification accuracy of models. To solve this problem, this research proposes a hybrid feature selection algorithm for farmland identification. First, on the basis of the feature importance provided by the feature selection algorithm, the feature dimension is gradually reduced from 295 to 5 with a step length of 10. The overall accuracy of the classification results corresponding to each feature dimension is recorded. Second, the turning point (a dimension number whose corresponding overall accuracy hardly decreases when the input variable number is smaller than it) is determined based on the overall accuracy, and the corresponding variables are adopted as the feature subset. Lastly, the Sequential Backward Selection (SBS) method is used to search for the best subset.Three feature selection algorithms (i.e., Random Forest (RF), Multi-Information (MI), and L1 regularization (L1)) and three classification algorithms (RF, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN)) are examined. Results indicate that the autocorrelations of the three subsets differ significantly. Most of the bands selected by the MI method are continuous and concentrated in the blue and shortwave infrared range. Therefore, the extremely high autocorrelation that exists in this subset has a negative effect on classification accuracy. By contrast, the correlation between bands in the RF and L1 feature subsets is relatively weak. However, the two feature sets still result in different classification accuracy. According to the variable distribution, many red-edge and near-infrared bands are contained in the L1 feature subset. These bands demonstrate better ability to distinguish farmland, forest, and soil than the blue and red bands selected by the RF algorithm. The classification algorithms also have different capacities. In the high-dimensional space, the SVM algorithm exhibits high robustness to noise, resulting in high accuracy. However, when the dimension decreases to a critical value, the accuracy of SVM decreases sharply. By contrast, although RF is not as robust as SVM in the high-dimensional space, it has excellent generalization ability in the low-dimensional space. Compared with the subsets obtained after the first dimensionality reduction process, the optimal feature subsets obtained by SBS searching improve the classification accuracy of each model.The L1-SVM-SBS model with a 23-dimensional input achieves the highest overall classification accuracy (94.64%) and cropland recall rate (95.83%). This study provides a new method of farmland identification using hyperspectral data. By selecting numerous representative and informative bands, this method not only improves farmland classification accuracy, but can also be used as a reference for other classification problems involving hyperspectral remote sensing.Keywords：cropland identification;GF-5;feature selection;hyperspectral remote sensing;L1 regularization;sequential backward selection2630|1766|2<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2022-08-08
- Abstract：Driven by big data, deep learning has been widely and successfully applied in many fields, such as computer vision and speech recognition. With the increase in network depth, deep learning models can determine the rules and layers of images and obtain high classification accuracy, so they have become a research hotspot in remote sensing image interpretation. As data-driven algorithms, deep learning models need a large number of labeled samples for training to ensure that the trained model can learn accurate and comprehensive sample features, and they exhibit good classification performance. However, although the development and maturity of remote sensing technology provide abundant remote sensing image sources for deep learning models, the application of deep learning technology in remote sensing is limited by expensive manually labeled samples,. In practical crop classification applications, the quantity and quality of existing ground truth samples are often insufficient to train a classification model with high performance.This study proposes a crop classification strategy for the deep learning model based on weak samples to verify the applicability of the deep learning model with weak samples.GF-1 was used as the data source, and the SVM classifier was used to classify three types of rice, corn, and other ground objects in Liaoning Province at the county level. The results were used as the training label samples of the deep learning model. This process included sub-county SVM classification, manual post-classification processing, cropland masking, and other operations. This human-computer interaction was chosen to ensure the accuracy of the results. In this study, samples with non-100% accuracy were labeled as weak samples. Then, a Deep Convolutional Neural Network (DCNN) model was used to train the weak samples and obtain the spatial distribution of rice and corn in Liaoning Province.Results showed that OA reached 0.90, and the F1 scores of rice and corn were 0.81 and 0.90, respectively. The spatial consistency with the SVM results was 0.90. The model showed good robustness under the different topography and landform types of the agricultural landscape with a median OA that was greater than 0.93. It overcame the influence of topography in the study area to a certain extent through subregion analysis. In the agricultural landscape with a complex planting structure, the proposed method still maintained a certain accuracy in crop classification. Subsequently, noise experiments were designed to analyze the influence of SVM label noise on model classification. The corn distribution in the original SVM training label was expanded from 1 to 40 times to obtain new labels, which were then used to train the DCNN model and predict the testing data. When the model was within five times the sample noise, that is, the sample maximum error area ratio was not more than 0.36, the model was robust to a certain extent, and the results could be maintained within a reliable accuracy range (OA remained to be greater than 0.86).In conclusion, this study verified that crop classification results obtained with the deep learning model whose training labels are based on traditional classification methods can achieve high recognition accuracy good robustness under different topography and landform types of agricultural landscapes and the feasibility of using traditional classification results as weak samples. The experiment on increasing noise in the weak samples showed that weak samples can be used to train DCNN as long as their identification accuracy is guaranteed, that is, the maximum error area ratio of samples is not more than 0.36. This approach further reduces the threshold of obtaining labeled samples via deep learning models. It makes up for the limitation of the deep learning model, which is highly dependent on a large number of manually labeled samples, and provides a new approach for large-area remote sensing crop classification.Keywords：Weak samples;Deep Convolutional Neural Networks (DCNN);deep learning;GF-1;Crop remote sensing classification1526|2204|9<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2022-08-08
- Abstract：Corn and soybean are two major crops maintaining food security, and thus the timely and accurate monitoring of their planting areas are of great importance to forecasting their production and market prices. The objectives of this study were to use a remote-sensing technology in exploring indicative features that can effectively identify corn and soybean in their middle and late growth seasons and provide technical support for the broad geographical application of corn and soybean mapping. This study can facilitate the early release of corn and soybean planting acreages for policy makers. In this study, two typical planting areas of corn and soybean in the provinces of Heilongjiang and Anhui were selected. GaoFen-1 satellite images with 30 m spatial resolution were acquired in the middle and latter growth stages and used as data sources for calculating various vegetation indices and textural features. Then, a feature optimization method was used in evaluating the relative importance scores of input features, and optimal feature combinations for identifying corn and soybean were determined. The random forest classification algorithm was used in analyzing the relationship between the number of input features and classification accuracy, and then the best feature groups in different experimental areas were identified. Finally, according to similarities and differences among the selected features in different regions, the indicative features for mapping corn and soybean in the middle and latter stages were established. The validity and stability were confirmed using our experimental designs. The following results were obtained: (1) indicative remote sensing features for efficiently identifying corn and soybean in their middle and late growing seasons were identified; (2) the classification performance of the indicative features of corn and soybean in both experimental areas was approximately 10% higher than that when original spectral band combinations were used. In different planting areas, high classification accuracy was obtained using the indicative features of corn and soybean as the optimal features selected in individual local area. Our selected indicative features for soybean and corn mapping were found stable, effective, and useful for large areas of implementation. These features included Ratio Vegetation Index (RVI), Difference Vegetation Index (DVI), Conversion Vegetation Index (TVI), improved chlorophyll absorption ratio index (MCARI), and the second moment and entropy in Gray Level Co-occurrence Matrix (GLCM).Keywords：remote sensing;corn;soybean;remote sensing identification;satellite feature;classification;GF-12162|2705|8<HTML><L-PDF><Enhanced-PDF><Meta-XML>Updated：2022-08-08
