Search

Currently, remote sensing crop identification is mostly based on all available images acquired throughout crop growth. However, the available image and data resources in the early growth stage are limited, which makes early crop identification challenging. Different crop types have different phenological characteristics and seasonal rhythm characteristics, and their growth rates are different at different times. Therefore, making full use of crop growth characteristics to augment crop growth difference information at different times is key to early crop identification. In this study, we first calculated the differential features between different periods as new features based on images acquired during the early growth stage. Secondly, multi-temporal difference features of each period were constructed by combination, then a feature optimization method was used to obtain the optimal feature set of all possible combinations in different periods and the early key identification characteristics of different crops, as well as their stage change characteristics, were explored. Finally, the performance of classification and regression tree (Cart), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Support Vector Machine (SVM) classifiers in recognizing crops in different periods were analyzed. The results show that: (1) There were key differences between different crops, with rice changing significantly in period F, corn changing significantly in periods E, M, L, and H, and soybean changing significantly in periods E, M, N, and H. (2) For the early identification of rice, the land surface water index (LSWI), simple ratio index (SR), B11, and normalized difference tillage index (NDTI) contributed most, while B11, normalized difference red-edge3 (NDRE3), LSWI, the green vegetation index (VIgreen), red-edge spectral index (RESI), and normalized difference red-edge2 (NDRE2) contributed greatly to corn and soybean identification. (3) Rice could be identified as early as 13 May, with PA and UA as high as 95%. Corn and soybeans were identified as early as 7 July, with PA and UA as high as 97% and 94%, respectively. (4) With the addition of more temporal features, recognition accuracy increased. The GBDT and RF performed best in identifying the three crops in the early stage. This study demonstrates the feasibility of using crop growth difference information for early crop recognition, which can provide a new idea for early crop recognition. [ABSTRACT FROM AUTHOR]

Early or in-season crop type mapping using remote sensing data is important for crop managements to maximize crop yield. Existing remote sensing-based approaches in the literature rely mainly on the timing and temporal frequency of satellite data acquisition during a growing season to obtain optimal identification feature (OIF) to complete crop mapping. At present, the optimal features for mapping crop types are commonly generated by using different feature selection methods, and thereby are not generic in nature. In this paper, a novel approach based on the OIF knowledge graph is proposed for identification of crop types within the crop growing season. The concept of OIF was proposed based on the one-class classification and optimization theory, which relates a specific crop type to its OIF. The OIF knowledge graph can be created to describe the seasonal trend of OIF in a season. Eventually, the OIF knowledge graphs can be incorporated into the moment-preserving segmentation method to automatically identify crop types within the growing season. To evaluate the performance of the new method, crop mapping was conducted using 2019 Sentinel-2 data in Heilongjiang province, China, and Illinois, USA, respectively. Results demonstrate that integrating the OIF knowledge graph and moment-preserving thresholding method is effective in identifying crop types without ground-truth data. The overall accuracy higher than 90 % (Kappa coefficient greater than 0.90), and the producer's accuracies for corn, soybean, and rice are generally greater than 93 % in Heilongjiang province. The proposed approach has the advantage of simplifying crop identification process while maintaining a satisfactory identification accuracy in shorter time than conventional methods. [ABSTRACT FROM AUTHOR]

Early crop identification can provide timely and valuable information for agricultural planting management departments to make reasonable and correct decisions. At present, there is still a lack of systematic summary and analysis on how to obtain real-time samples in the early stage, what the optimal feature sets are, and what level of crop identification accuracy can be achieved at different stages. First, this study generated training samples with the help of historical crop maps in 2019 and remote sensing images in 2020. Then, a feature optimization method was used to obtain the optimal features in different stages. Finally, the differences of the four classifiers in identifying crops and the variation characteristics of crop identification accuracy at different stages were analyzed. These experiments were conducted at three sites in Heilongjiang Province to evaluate the reliability of the results. The results showed that the earliest identification time of corn can be obtained in early July (the seven leaves period) with an identification accuracy up to 86%. In the early stages, its accuracy was 40~79%, which was low, and could not reach the satisfied accuracy requirements. In the middle stages, a satisfactory recognition accuracy could be achieved, and its recognition accuracy was 79~100%. The late stage had a higher recognition accuracy, which was 90~100%. The accuracy of soybeans at each stage was similar to that of corn, and the earliest identification time of soybeans could also be obtained in early July (the blooming period) with an identification accuracy up to 87%. Its accuracy in the early growth stage was 35~71%; in the middle stage, it was 69~100%; and in the late stage, it was 92~100%. Unlike corn and soybeans, the earliest identification time of rice could be obtained at the end of April (the flooding period) with an identification accuracy up to 86%. In the early stage, its accuracy was 58~100%; in the middle stage, its accuracy was 93~100%; and in the late stage, its accuracy was 96~100%. In terms of crop identification accuracy in the whole growth stage, GBDT and RF performed better than other classifiers in our three study areas. This study systematically investigated the potential of early crop recognition in Northeast China, and the results are helpful for relevant applications and decision making of crop recognition in different crop growth stages. [ABSTRACT FROM AUTHOR]

Crop acreage estimation is important for the assurance of food security and establishment of national socio-economic development planning. During the current development period, rapid, accurate and reliable estimation for crop acreage is particularly significant in China since the estimation can be affected by many factors such as ecological degradation and farmland reduction. Spatial sampling technology plays an important and irreplaceable role in crop acreage investigation and estimation. However, the effects of sampling factors on estimation are unclear. This study analyzed data on late-season rice in paddy field of Hunan province of China, an area with significant flooded paddy rice agriculture and mixed rice cropping patterns, in order to quantitatively evaluate the influence and sensibility of various monitoring factors (sampling ratio, sampling grid, and sample distribution) on sampling efficiency of the existing space sampling techniques for estimating crop planting acreage. Nine kinds of sampling units and 31 kinds of sampling ratio levels were designed. Spatial stratified sampling was used, and the late rice planting proportion was considered as the stratification symbol. 1000 times repeated trials were conducted based on every kind of sampling plan. Spatial distribution (Variance to Mean Ratio, VMR) of every sampling units and sampling ratio levels were determined. Spatial statistics methods and manifold accuracy evaluation indices (relative estimation error and standard deviation) were used to analyze the acreage estimation results obtained based on the different sampling plans. Then a comprehensive model based on sampling grid, sampling ratio, and sample distribution was developed to assess the sampling monitoring error rate of crop acreage estimation. The result demonstrated that: 1) With the increasing of the sampling grid, the average estimation error increased (R2=0.92), and when the sampling grid was less than 5 km, the estimation error rate was controlled within 5%, the standard deviation was not more than 0.12; 2) With the increasing of the sampling ratio, the average estimation error decreased (R2=0.82), and when the sampling ratio was greater than 0.4%, the estimation error rate was controlled within 5%, and the standard deviation was less than 0.12; 3) Under the condition in which the sampling ratio had been determined, the sample spatial distribution of the sample was an important factor affecting the accuracy of sampling. With the sample distribution tending to cluster distribution, the average estimation error rate increased, and when the variance to mean ratio (VMR) was less than 0.7 the estimation error rate and the standard deviation was controlled within 5% and 0.1, respectively; 4) The quantitative model reflecting the influence of the three factors on crop acreage estimation accuracy was developed. In summary, this study revealed the influence rules and sensibility of sampling factors (sampling ratio, sampling grid, and sample distribution) on crop acreage estimation. In addition, a good method was developed for optimizing spatial sampling and improving the accuracy of crop acreage estimation based on the particular sampling program. [ABSTRACT FROM AUTHOR]

Monitoring the production of main agricultural crops is important to predict and prepare for disruptions in food supply and fluctuations in global crop market prices. China's global crop-monitoring system (CropWatch) uses remote sensing data combined with selected field data to determine key crop production indicators: crop acreage, yield and production, crop condition, cropping intensity, crop-planting proportion, total food availability, and the status and severity of droughts. Results are combined to analyze the balance between supply and demand for various food crops and if needed provide early warning about possible food shortages. CropWatch data processing is highly automated and the resulting products provide new kinds of inputs for food security assessments. This paper presents a comprehensive overview of CropWatch as a remote sensing-based system, describing its structure, components, and monitoring approaches. The paper also presents examples of monitoring results and discusses the strengths and limitations of the CropWatch approach, as well as a comparison with other global crop-monitoring systems. [ABSTRACT FROM PUBLISHER]