Accurate Crop Classification Research Articles

A dual-path model merging CNN and RNN with attention mechanism for crop classification

Rapid and accurate crop classification is essential for estimating crop information and improving cropland management. The application of deep learning models for crop classification using time-series data has become the most promising method. However, most approaches rely on single models for data processing result in lower classification accuracy and poor stability. Therefore, this study proposes a dual-path approach with attention mechanisms (DPACR) to promote the performance of this model architecture in crop classification using time series data. Specifically, the model comprises two branches, the Recurrent neural network (RNN) branch with bidirectional gated recurrent units (GRU) with a self-attention mechanism, and the convolutional neural network (CNN) branch based on SE-ResNet. Crop classification is accomplished by a main classifier, supported by auxiliary classifiers from the two branches. Using the Google Earth Engine and the Sentinel-2 satellite data, DPACR was tested in the Hetao irrigation district in Inner Mongolia, China. The comparison experiment demonstrated that the DPACR achieved the highest overall accuracy (OA = 0.959) and Kappa coefficient (Kappa = 0.941) compared to other five models (MLP, SE-ResNet, Bi-At-GRU, SVM, and RF). DPACR excelled in classifying six crops, maintaining high accuracy across multiple classes. Compared to attention mechanisms, auxiliary classifiers can significantly improve classification performance. This study highlights the effective combination of cloud computing and deep learning for large-scale crop classification, providing a practical method for agricultural monitoring and management.

A multi-scale semantic feature fusion method for remote sensing crop classification

The efficient and accurate acquisition of crop spatial planting structure information is of great significance to ensure national food security. Current crop classification studies have still not achieved optimal results in accurate crop classification identification due to the complex heterogeneous details of clear images and insufficient analysis and utilization of information. This study takes the Yuncheng-Linfen Basin in Shanxi, China as the study area and uses the ReliefF-RFE feature selection algorithm to achieve data dimensionality reduction. Contextual semantic feature aggregation, spatial channel attention mechanism, and hierarchical refinement strategy are used to fuse the multi-scale feature information in the extracted remote sensing images from the top down and bottom up. This study shows that 1) the ReliefF-RFE algorithm can effectively reduce the dimensionality of 224-dimensional multisource features and generate a 31-dimensional optimal feature space subset with strong interpretation to improve the computational efficiency of the model; 2) the multi-scale feature fusion model constructed in this study is better than UNet, ResNet, DeepLabv3+, HRNet and Swin Transformer in classification recognition of winter wheat and corn, with an overall accuracy of 95.76% and 93.44%; 3) A multiple feature fusion strategy designed through ablation experiments was evaluated to evaluate the reasonableness of each module and validate the irreplaceability and superiority of the model for improving crop accuracy in complex and heterogeneous terrain; 4) the multi-scale feature fusion model converts deep abstract features into local detail information by cross-scale contextual aggregation of deep and shallow multi-scale features, it obtains good extraction effect on fragmented small plots, and the reduction of local fine details of features is significantly better than other models. The multi-scale feature fusion classification model constructed in this study fully considers the interpretability of the input features and fuses the semantic features at different scales to eliminate the “semantic gap”, which shows that the model has strong stability and robustness and provides a reference for fast and accurate mapping of Sentinel-2 images of crops in large areas.

Cross-Regional Crop Classification Based on Sentinel-2

Accurate crop classification is of vital importance for agricultural water management. Most researchers have achieved crop classification by model optimization in the same temporal and regional domain by adjusting the value of input features. This study aims to improve the accuracy of crop classification across temporal and spatial domains. Sentinel-2 satellite imagery is employed for crop classification training and prediction in selected farming areas of Heilongjiang Province by calculating vegetation indices and constructing sequential input feature datasets. The HUNTS filtering method was used to mitigate the influence of cloud cover, which increased the stability and completeness of the input feature data across different years. To address the issue of shifts in the input feature values during cross-scale classification, this study proposes the hypothesis testing distribution method (HTDM). This method balances the distribution of input feature values in the test set even without knowing the crop distribution, thereby enhancing the accuracy of the classification test set. The results indicate that the HTDM significantly improves prediction accuracy in cases of substantial image quality variance. In 2022, the recognition accuracy for crop types at all farms processed by the HTDM was above 87%, showcasing the strong robustness of the HTDM.

Dipper throated optimization with deep convolutional neural network-based crop classification for remote sensing image analysis.

With the rapid advancement of remote sensing technology is that the need for efficient and accurate crop classification methods has become increasingly important. This is due to the ever-growing demand for food security and environmental monitoring. Traditional crop classification methods have limitations in terms of accuracy and scalability, especially when dealing with large datasets of high-resolution remote sensing images. This study aims to develop a novel crop classification technique, named Dipper Throated Optimization with Deep Convolutional Neural Networks based Crop Classification (DTODCNN-CC) for analyzing remote sensing images. The objective is to achieve high classification accuracy for various food crops. The proposed DTODCNN-CC approach consists of the following key components. Deep convolutional neural network (DCNN) a GoogleNet architecture is employed to extract robust feature vectors from the remote sensing images. The Dipper throated optimization (DTO) optimizer is used for hyper parameter tuning of the GoogleNet model to achieve optimal feature extraction performance. Extreme Learning Machine (ELM): This machine learning algorithm is utilized for the classification of different food crops based on the extracted features. The modified sine cosine algorithm (MSCA) optimization technique is used to fine-tune the parameters of ELM for improved classification accuracy. Extensive experimental analyses are conducted to evaluate the performance of the proposed DTODCNN-CC approach. The results demonstrate that DTODCNN-CC can achieve significantly higher crop classification accuracy compared to other state-of-the-art deep learning methods. The proposed DTODCNN-CC technique provides a promising solution for efficient and accurate crop classification using remote sensing images. This approach has the potential to be a valuable tool for various applications in agriculture, food security, and environmental monitoring.

MP-Net: An efficient and precise multi-layer pyramid crop classification network for remote sensing images

Accurate crop classification map is of great significance in various fields such as the survey of agricultural resource, the analysis of existing circumstance on land application, the yield estimation of crop and the disaster warning. The methods based on machine learning and deep learning are popularly used in crop classification and recognition of remote sensing images. However, the crop classification task based on neural networks still faces significant challenges due to the spatial and temporal distribution of crops and the inherent characteristics of remote sensing images. Therefore, this study proposes the multi-layer pyramid crop classification network (MP-Net) to solve the above problems. To reduce the feature loss during the crop extraction, the proposed model uses the pyramid pooling module to improve the ability of global information acquisition, and the information concatenation module to retain the upper features. Using the GF-6 and Sentinel-2 satellite data, the proposed model was tested in Erhai Lake Basin and Beian City. Compared with other five deep learning models, such as FCN, SegNet, U-Net, PSPNet and DeepLabv3+, the experimental results indicate that the proposed model achieves the highest accuracy in both study areas. Meanwhile, the proposed model has the advantages of short training time and high efficiency under the same running conditions. Overall, this study is beneficial to improve the efficiency and accuracy of crop classification task in the unbalanced temporal and spatial distribution. It also brings a feasible scheme for crop classification tasks in complex growing areas. The code has been publicly available at https://github.com/Xu-Chang-Hong/MP-Net.

Selection of Machine Learning Algorithms and Bands for Highly Accurate Crop Classification Using Synthetic Aperture Radar

Selection of Machine Learning Algorithms and Bands for Highly Accurate Crop Classification Using Synthetic Aperture Radar

Crop classification of modern agricultural park based on time-series Sentinel-2 images

Quickly and accurately grasping the spatial distribution of crops, estimating the area and scope of different crops were of great significance for the country to formulate macroscopic agricultural policies and guide farmers in agricultural production. To explore an efficient and accurate crop classification method, this paper took the agricultural area of Jalaid Banner of Hinggan League in Inner Mongolia Autonomous Region of China as the study area and extracted main crop classification based on the Sentinel-2 satellite remote sensing image data from May to October 2019. By analyzing the time-series curves of the four characteristic indexes of NDVI, RVI, EVI and Ref (NIR) in the study area, a total of four classification methods including Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Maximum Likelihood (ML) were used to classify various crops in the study area. The RF results were compared with the classification results of DT, SVM and ML, and the spatial distribution of major crops such as rice, corn, stevia, dry rice and soybean were successfully extracted and identified. The results showed that RF had the highest overall classification accuracy of 95.8% with a Kappa coefficient of 0.944, DT, SVM and ML had classification accuracy of 92.2%, 91.6% and 86.5%, respectively. The above results indicate that the multitemporal Sentinel-2 remote sensing images can be extracted by spectral index time-varying features, and the crop classification using the random forest algorithm can obtain high accuracy results, which provides effective technical support for the fine guidance of large-scale agricultural production in the park.

Crop Classification Using Multi-Temporal Sentinel-2 Data in the Shiyang River Basin of China

Timely and accurate crop classification is of enormous significance for agriculture management. The Shiyang River Basin, an inland river basin, is one of the most prominent water resource shortage regions with intensive agriculture activities in northwestern China. However, a free crop map with high spatial resolution is not available in the Shiyang River Basin. The European Space Agency (ESA) satellite Sentinel-2 has multi-spectral bands ranging in the visible-red edge-near infrared-shortwave infrared (VIS-RE-NIR-SWIR) spectrum. Understanding the impact of spectral-temporal information on crop classification is helpful for users to select optimized spectral bands combinations and temporal window in crop mapping when using Sentinel-2 data. In this study, multi-temporal Sentinel-2 data acquired in the growing season in 2019 were applied to the random forest algorithm to generate the crop classification map at 10 m spatial resolution for the Shiyang River Basin. Four experiments with different combinations of feature sets were carried out to explore which Sentinel-2 information was more effective for higher crop classification accuracy. The results showed that the augment of multi-spectral and multi-temporal information of Sentinel-2 improved the accuracy of crop classification remarkably, and the improvement was firmly related to strategies of feature selections. Compared with other bands, red-edge band 1 (RE-1) and shortwave-infrared band 1 (SWIR-1) of Sentinel-2 showed a higher competence in crop classification. The combined application of images in the early, middle and late crop growth stage is significant for achieving optimal performance. A relatively accurate classification (overall accuracy = 0.94) was obtained by utilizing the pivotal spectral bands and dates of image. In addition, a crop map with a satisfied accuracy (overall accuracy > 0.9) could be generated as early as late July. This study gave an inspiration in selecting targeted spectral bands and period of images for acquiring more accurate and timelier crop map. The proposed method could be transferred to other arid areas with similar agriculture structure and crop phenology.

Cloud Approach to Automated Crop Classification Using Sentinel-1 Imagery

For accurate crop classification, it is necessary to use time-series of high-resolution satellite data to better discriminate among certain crop types. This task brings the following challenges: a large amount of satellite data for download, Big data processing and computational resources for utilization of state-of-the-art classification approaches. For solving these problems, we have developed an automated crop classification workflow, which is based on machine-learning techniques. By deployment of the workflow on the cloud platform, we can overcome challenges of Big data downloading and processing. In this paper, we present the system architecture and describe the experiments on structural and parametric identification of machine learning models utilized in the system.

Synchronous Response Analysis of Features for Remote Sensing Crop Classification Based on Optical and SAR Time-Series Data.

Accurate crop classification is the basis of agricultural research, and remote sensing is the only effective measuring technique to classify crops over large areas. Optical remote sensing is effective in regions with good illumination; however, it usually fails to meet requirements for highly accurate crop classification in cloud-covered areas and rainy regions. Synthetic aperture radar (SAR) can achieve active data acquisition by transmitting signals; thus, it has strong resistance to cloud and rain interference. In this study, we designed an improved crop planting structure mapping framework for cloudy and rainy regions by combining optical data and SAR data, and we revealed the synchronous-response relationship of these two data types. First, we extracted geo-parcels from optical images with high spatial resolution. Second, we built a recurrent neural network (RNN)-based classifier suitable for remote sensing images on the geo-parcel scale. Third, we classified crops based on the two datasets and established the network. Fourth, we analyzed the synchronous response relationships of crops based on the results of the two classification schemes. This work is the basis for the application of remote sensing data for the fine mapping and growth monitoring of crop planting structures in cloudy and rainy areas in the future.

Combining ASNARO-2 XSAR HH and Sentinel-1 C-SAR VH/VV Polarization Data for Improved Crop Mapping

The Advanced Satellite with New system ARchitecture for Observation-2 (ASNARO-2), which carries the X-band Synthetic Aperture Radar (XSAR), was launched on 17 January 2018 and is expected to be used to supplement data provided by larger satellites. Land cover classification is one of the most common applications of remote sensing, and the results provide a reliable resource for agricultural field management and estimating potential harvests. This paper describes the results of the first experiments in which ASNARO-2 XSAR data were applied for agricultural crop classification. In previous studies, Sentinel-1 C-SAR data have been widely utilized to identify crop types. Comparisons between ASNARO-2 XSAR and Sentinel-1 C-SAR using data obtained in June and August 2018 were conducted to identify five crop types (beans, beetroot, maize, potato, and winter wheat), and the combination of these data was also tested. To assess the potential for accurate crop classification, some radar vegetation indices were calculated from the backscattering coefficients for two dates. In addition, the potential of each type of SAR data was evaluated using four popular supervised learning models: Support vector machine (SVM), random forest (RF), multilayer feedforward neural network (FNN), and kernel-based extreme learning machine (KELM). The combination of ASNARO-2 XSAR and Sentinel-1 C-SAR data was effective, and overall classification accuracies of 85.4 ± 1.8% were achieved using SVM.

Method for crop classification based on multi-source remote sensing data

Using remote sensing images to classify crops to obtain spatial distribution of different crops is of great significance for crop yield estimation and agricultural policy formulation. Due to the phenomenon of the same spectrum from different materials or the phenomenon of the same materials with different spectrum, it is difficult to obtain accurate crop classification results from single-phase images. We take a farm in Lintong District of Xi’an as the research area. The crops in this study area are mostly cross-planted, and the planting area is small, so it is difficult for the traditional classification method. In order to increase classification accuracy, a multi-level classification method is proposed in this paper. The Sentinel-1 backscattering coefficient (Sigma) of image is used to pre-classify the ground in the study area, and the Sentinel-2 images which cover the crop growth cycle in the study area are used to construct a normalized vegetation index (NDVI) time series to distinguish the growth differences of different crops. Combined with field survey data and phenological characteristics of crops, on the basis of pre-classification, SVM (Support Vector Machine) method is used to classify Sentinel-2 images. The classification accuracy reaches 98.07%, which is much higher than the minimum distance, Mahalanobis distance, neural network, expert decision tree, object-oriented and other classification methods.

Agricultural Monitoring, an Automatic Procedure for Crop Mapping and Yield Estimation: The Great Rift Valley of Kenya Case

Agricultural activities conducted in the Great Rift Valley of Kenya show a significant decline of productivity levels. This phenomenon is mainly related to limited availability of water resources, lack of supporting irrigation, and harvesting techniques ineffectiveness. Production risks reduction is closely related with a better use of water resources and a better understanding of the effects resulting from the multiple interactions between climate, agricultural vegetation, soil type, and crops management techniques. In this paper, a remote and automatic agricultural monitoring system is presented as an effective alternative to the most traditional in situ measurements and observations. We investigated the use of phenological information extracted from satellite imagery combined with crop calendar and supported by agro-ecological zoning (AEZ) in accurate crop classification and monitoring. Vegetation indices extracted from Landsat 8 imagery are capable to track the vegetation development through the year, then phenological profiles can be extracted and implemented into a multitemporal automatic classification process to detect agricultural areas and to discriminate among different crop species. The phenological profiles extracted by satellite imagery are compared with crop calendar data compiled by FAO for the area of interest. The classification procedure is supported by AEZs based on crop modeling and environmental matching procedures in order to identify crop-specific environmental limitations under assumed levels of inputs and management conditions. The FAO crop water productivity model AquaCrop is calibrated for wheat and maize yield mapping in the central highland of Kenya, handling both environmental and phenological data. The combined use of phenological data and AEZs results in a robust methodology with a classification overall accuracy of 91.35%. A good model performance is obtained relative to yield predictions, with R of 0.69 and 0.72.

МЕТОД ДЕТЕКТУВАННЯ МЕЖ НА КАРТІ КЛАСИФІКАЦІЇ НА ОСНОВІ МОДИФІКОВАНОГО АЛГОРИТМУ СОБЕЛЯ

Obtaining reliable and accurate crop classification and land cover map based on satellite data, in particular high resolution data, is one of the most important tasks in remote sensing. Such maps provide basic information for many other applied problems and are vital in remote sensing studies. Despite of which machine learning methods were utilized for maps obtaining: traditional (Random Forest, Support Vector Machine, Multi-layer perceptron, logistic regression) or state-of-the-art approaches (autoencoder, convolutional neural network, recurrent neural network) there is some noise (single pixels or groups and clusters of pixels that wrong classify) on such maps. There are traditional methods for noise reduction, however these methods do not take into account image semantics. Therefore, they are not effective for filtration land cover and crop classification maps based on satellite images. The most complicated task in the filtering such maps is to preserve edges and boundaries between different agricultural fields. Often these boundaries are small and common filters consider them like a noise and remove them. Therefore, final crop classification map after filtration using common methods is smoothed and all edges are loosed. Thus, in this paper we proposed new method for boundaries identification on the crop classification map based on modified Sobel algorithm. It is impossible to use gradient based methods for boundaries detection because important peculiarity of the crop classification map that it has finite discrete set of pixel values. We proposed modification of Sobel algorithm based on using additional steps of processing. These steps consist of convolution with structural element (square), threshold filter (considers all objects that have square less than threshold as a noise and remove them) and morphological closing operation for boundaries detection between agricultural fields but not for other changes in pixel values identification. Accuracy and efficiency of this method with the proposed filtration method have been tested on the independent set and using the visual comparison with the results of utilizing common filters.

МЕТОД ОБ’ЄКТНОЇ ПОСТОБРОБКИ КАРТ КЛАСИФІКАЦІЇ З УРАХУВАННЯМ СПЕЦИФІКИ КОЖНОГО КЛАСУ

Obtaining reliable and accurate crop classification and land cover map based on satellite data, in particular high resolution data, is one of the most important tasks in remote sensing. Such maps provide basic information for many other applied problems and are vital in remote sensing studies. Despite of which machine learning methods were utilized for maps obtaining: traditional (Random Forest, Support Vector Machine, Multi-layer perceptron, logistic regression) or state-of-the-art approaches (autoencoder, convolutional neural network, recurrent neural network) there is some noise (single pixels or groups and clusters of pixels that wrong classify) on such maps. There are traditional methods for noise reduction, however these methods do not take into account image semantics. Therefore, they are not effective for filtration land cover and crop classification maps based on satellite images. The most complicated task in the filtering such maps is to preserve boundaries between different agricultural fields and to remove quite big clusters of incorrect classified pixels (objects) and at the same time save small farmer fields that are right classified. Thus, in this paper we proposed new method for postprocessing crop classification map based on algorithm that takes into account each class specificity and as a result utilizes different thresholds for different classes. We proposed investigate each object in classification map independently and decision should be: “is this whole object a noise or not?”. We consider each class independent and use connected component labeling technique for discriminating objects from classification map. Further different types of conditions based on sharpness and compactness where proposed for the investigated object. Accuracy and efficiency of this method with the proposed filtration method have been tested on the independent set and using the visual comparison with the results of utilizing common filters. Also, McNemar statistical test has been conducted to prove the statistically significant gain of utilizing proposed filtration methodology compare to common voting filter

Assessing the suitability of data from Sentinel-1A and 2A for crop classification

Sentinel-1A C-SAR and Sentinel-2A MultiSpectral Instrument (MSI) provide data applicable to the remote identification of crop type. In this study, six crop types (beans, beetroot, grass, maize, potato, and winter wheat) were identified using five C-SAR images and one MSI image acquired during the 2016 growing season. To assess the potential for accurate crop classification with existing supervised learning models, the four different approaches namely kernel-based extreme learning machine (KELM), multilayer feedforward neural networks, random forests, and support vector machine were compared. Algorithm hyperparameters were tuned using Bayesian optimization. Overall, KELM yielded the highest performance, achieving an overall classification accuracy of 96.8%. Evaluation of the sensitivity of classification models and relative importance of data types using data-based sensitivity analysis showed that the set of VV polarization data acquired on 24 July (Sentinel-1A) and band 4 data (Sentinel-2A) had the greatest potential for use in crop classification.

Crop Classification Based on Feature Band Set Construction and Object-Oriented Approach Using Hyperspectral Images

Remote sensing plays a significant role for crop classification. Accurate crop classification is a common requirement to precision agriculture, including crop area estimation, crop yield estimation, precision crop management, etc. This paper developed a new crop classification method involving the construction and optimization of the vegetation feature band set (FBS) and combination of FBS and object-oriented classification (OOC) approach. In addition to the spectral and textural features of the original image, 20 spectral indices sensitive to the vegetation's biological parameters are added to the FBS to distinguish specific vegetation. A spectral dimension optimization algorithm of FBS based on class-pair separability (CPS) is also proposed to improve the separability between class pairs while reducing data redundancy. OOC approach is conducted on the optimized FBS based on CPS to reduce the salt-and-pepper noise. The proposed classification method was validated by two airborne hyperspectral images. The first image acquired in an agricultural area of Japan includes seven crop types, and the second image acquired in a rice breeding area consists of six varieties of rice. For the first image, the proposed method distinguished different vegetation with an overall accuracy of 97.84% and kappa coefficient of 0.96. For the second image, the proposed method distinguished the rice varieties accurately, achieving the highest overall accuracy (98.65%) and kappa coefficient (0.98). Results demonstrate that the proposed method can significantly improve crop classification accuracy and reduce edge effects, and that textural features combined with spectral indices sensitive to the chlorophyll, carotenoid, and Anthocyanin indicators contribute significantly to crop classification. Therefore, it is an effective approach for classifying crop species, monitoring invasive species, as well as precision agriculture related applications.

Impact of Categorical and Spatial Scale on Supervised Crop Classification using Remote Sensing

High temporal revisit frequency over vast geographic areas is necessary to properly use satellite earth observation for monitoring agricultural production. However, this often limits the spatial resolution that can be used. The challenge of discriminating pixels that correspond to a particular crop type, a prerequisite for crop specific monitoring remains daunting when the signal encoded in pixels stems from several land uses (mixed pixels). Naturally, the concept of spatial scale arises but the issue of selecting a proper class legend (the categorical scale) should not be neglected. A framework is presented that addresses these issues and that can be used to quantitatively define pixel size requirements for crop identification and to assess the effect of categorical scale. The framework was applied over two agricultural landscapes. It was demonstrated that there was no unique spatial resolution that provided the best classification result for all classes at once at a given categorical scale. The suitability of pixel populations characterized by pixel size and purity differed for identifying specific crops within tested landscapes, and for one crop there were large differences among the landscapes. In the context of agricultural crop growth monitoring the framework described above can be used to draw guidelines for selecting appropriate imagery, e.g. suitable pixel sizes, and for selecting class legends suitable for accurate crop classification when the interest is only on pixels covering arable land as a prerequisite for crop specific monitoring. The framework could be used to plot the suitability (or accuracy) of pixels as a function of their purity to provide a spatial assessment of classification performance