Rice Mapping Research Articles

High Resolution Distribution Dataset of Double-Season Paddy Rice in China

Although China is the largest producer of rice, accounting for about 25% of global production, there are no high-resolution maps of paddy rice covering the entire country. Using time-weighted dynamic time warping (TWDTW), this study developed a pixel- and phenology-based method to identify planting areas of double-season paddy rice in China, by comparing temporal variations of synthetic aperture radar (SAR) signals of unknown pixels to those of known double-season paddy rice fields. We conducted a comprehensive evaluation of the method’s performance at pixel and regional scales. Based on 145,210 field surveyed samples from 2018 to 2020, the producer’s and user’s accuracy are 88.49% and 87.02%, respectively. Compared to county-level statistical data from 2016 to 2019, the relative mean absolute errors are 34.11%. This study produced distribution maps of double-season rice at 10 m spatial resolution from 2016 to 2020 over nine provinces in South China, which account for more than 99% of the planting areas of double-season paddy rice of China. The maps are expected to contribute to timely monitoring and evaluating rice growth and yield.

Mapping and forecasting of rice cropping systems in central China using multiple data sources and phenology-based time-series similarity measurement

Precise mapping and forecasting of rice cropping systems are essential for guaranteeing regional and even global food security. The central areas of China are the dominant Chinese rice-producing areas. However, due to limited land and a scarcity of skilled rural labourers in China, it has been difficult to meet the growing demand for rice production in recent years. Furthermore, the complex topography and climate in central China make it difficult to map paddy rice accurately. This paper maps the spatial pattern of rice in central China by using multiple data sources and a phenology-based time-series similarity approach, explores the driving forces for rice patterns through grey relational analysis (GRA), and presents a simulated future rice cropping system map by adding socio-economic factors to a cellular automata-Markov (CA-Markov) model. This study concluded that for 2015, the overall classification accuracy of rice was 88.12%, with a Kappa coefficient of 0.90. The planting acreage accuracies for single- and double-season rice in 2015 were 89.51% and 77.00%, respectively, and the corresponding R2 value for both were 0.80. From 2005 to 2015, the planting acreage of single-season rice significantly increased, while the planting acreage of double-season rice generally decreased. The planting acreage of total rice exhibited an overall increasing trend during 10 years. The cumulative temperature, slope and distance to water bodies were key influencing factors for the spatial distribution of rice. Compared with that for 2015, the simulated total planting area of rice for 2030 was slightly higher, and the spatial pattern of double-season rice exhibited an obvious southward trend. These findings show that the proposed rice mapping and forecasting method is effective. This method allows us to predict future rice patterns precisely under the influence of human activities in complex cropping conditions and various rice cropping systems.

Mapping a Paddy Rice Area in a Cloudy and Rainy Region Using Spatiotemporal Data Fusion and a Phenology-Based Algorithm

The timely and accurate mapping of paddy rice is important to ensure food security and to protect the environment for sustainable development. Existing paddy rice mapping methods are often remote sensing technologies based on optical images. However, the availability of high-quality remotely sensed paddy rice growing area data is limited due to frequent cloud cover and rain over the southwest China. In order to overcome these limitations, we propose a paddy rice field mapping method by combining a spatiotemporal fusion algorithm and a phenology-based algorithm. First, a modified neighborhood similar pixel interpolator (MNSPI) time series approach was used to remove clouds on Sentinel-2 and Landsat 8 OLI images in 2020. A flexible spatiotemporal data fusion (FSDAF) model was used to fuse Sentinel-2 data and MODIS data to obtain multi-temporal Sentinel-2 images. Then, the fused remote sensing data were used to construct fusion time series data to produce time series vegetation indices (NDVI\LSWI) having a high spatiotemporal resolution (10 m and ≤16 days). On this basis, the unique physical characteristics of paddy rice during the transplanting period and other auxiliary data were combined to map paddy rice in Yongchuan District, Chongqing, China. Our results were validated by field survey data and showed a high accuracy of the proposed method indicated by an overall accuracy of 93% and the Kappa coefficient of 0.85. The paddy rice planting area map was also consistent with the official data of the third national land survey; at the town level, the correlation between official survey data and paddy rice area was 92.5%. The results show that this method can effectively map paddy rice fields in a cloudy and rainy area.

Rice Mapping Using a BiLSTM-Attention Model from Multitemporal Sentinel-1 Data

Timely and accurate rice distribution information is needed to ensure the sustainable development of food production and food security. With its unique advantages, synthetic aperture radar (SAR) can monitor the rice distribution in tropical and subtropical areas under any type of weather condition. This study proposes an accurate rice extraction and mapping framework that can solve the issues of low sample production efficiency and fragmented rice plots when prior information on rice distribution is insufficient. The experiment was carried out using multitemporal Sentinel-1A Data in Zhanjiang, China. First, the temporal characteristic map was used for the visualization of rice distribution to improve the efficiency of rice sample production. Second, rice classification was carried out based on the BiLSTM-Attention model, which focuses on learning the key information of rice and non-rice in the backscattering coefficient curve and gives different types of attention to rice and non-rice features. Finally, the rice classification results were optimized based on the high-precision global land cover classification map. The experimental results showed that the classification accuracy of the proposed framework on the test dataset was 0.9351, the kappa coefficient was 0.8703, and the extracted plots maintained good integrity. Compared with the statistical data, the consistency reached 94.6%. Therefore, the framework proposed in this study can be used to extract rice distribution information accurately and efficiently.

Paddy Rice Mapping in Thailand Using Time-Series Sentinel-1 Data and Deep Learning Model

The elimination of hunger is the top concern for developing countries and is the key to maintain national stability and security. Paddy rice occupies an essential status in food supply, whose accurate monitoring is of great importance for human sustainable development. As one of the most important paddy rice production countries in the world, Thailand has a favorable hot and humid climate for paddy rice growing, but the growth patterns of paddy rice are too complicated to construct promising growth models for paddy rice discrimination. To solve this problem, this study proposes a large-scale paddy rice mapping scheme, which uses time-series Sentinel-1 data to generate a convincing annual paddy rice map of Thailand. The proposed method extracts temporal statistical features of the time-series SAR images to overcome the intra-class variability due to different management practices and modifies the U-Net model with the fully connected Conditional Random Field (CRF) to maintain the edge of the fields. In this study, 758 Sentinel-1 images that covered the whole country from the end of 2018 to 2019 were acquired to generate the annual paddy rice map. The accuracy, precision, and recall of the resultant paddy rice map reached 91%, 87%, and 95%, respectively. Compared to SVM classifier and the U-Net model based on feature selection strategy (FS-U-Net), the proposed scheme achieved the best overall performance, which demonstrated the capability of overcoming the complex cultivation conditions and accurately identifying the fragmented paddy rice fields in Thailand. This study provides a promising tool for large-scale paddy rice monitoring in tropical production regions and has great potential in the global sustainable development of food and environment management.

Irrigated rice crop identification in Southern Brazil using convolutional neural networks and Sentinel-1 time series

Rice is one of the world’s staple food sources, with millions of tonnes produced and consumed every year. Therefore, mapping rice paddies is essential for agricultural management and ensuring food security. This study aimed to classify rice crops in southern Brazil using the SENTINEL-1 SAR time series and deep learning models, comparing two architectures (U-net and LinkNet) and four backbones (ResNet-34, ResNeXt-50, DenseNet-121, and VGG16). The time series construction considered ten images, each for a month, covering the rice planting cycle. The Convolutional Neural Network architectures were adapted to use multi-band data, allowing the extraction of features from all-temporal images. This approach provides capturing spatiotemporal information from rice plantations, which favors its detection. Besides, the research evaluated three data sets considering the polarizations: (a) VV-only, (b) VH-only, and (c) both VV and VH (VV + VH). The classification accuracies used to measure the performance of the models were the overall accuracy, F1-measure, area under the precision-recall curve (AUPRC), and the intersection over union (IoU). Results show that the VH + VV polarization combination yielded the best results, followed by VH-only and VV-only. The VV-only polarization had significantly worst results (nearly 10% less IoU than VH-only and nearly 15% less IoU compared to VV + VH). The results show that rice fields can be successfully classified with deep learning models and through our evaluation the LinkNet architecture with the ResNeXt-50 backbone showed the best results with an accuracy of 0.98, F1 of 0.93, AUPRC of 0.93, and IoU of 0.91.

RiceENCODE: A comprehensive epigenomic database as a rice Encyclopedia of DNA Elements

RiceENCODE: A comprehensive epigenomic database as a rice Encyclopedia of DNA Elements

Mitogen-Activated Protein Kinase OsMEK2 and OsMPK1 Signaling Is Required for Ferroptotic Cell Death in Rice-Magnaporthe oryzae Interactions.

Mitogen-activated protein kinase (MAPK) signaling is required for plant cell death responses to invading microbial pathogens. Iron- and reactive oxygen species (ROS)-dependent ferroptotic cell death occurs in rice (Oryza sativa) during an incompatible rice–Magnaporthe oryzae interaction. Here, we show that rice MAP kinase (OsMEK2 and OsMPK1) signaling cascades are involved in iron- and ROS-dependent ferroptotic cell death responses of rice to M. oryzae infection using OsMEK2 knock-out mutant and OsMEK2 and OsMPK1 overexpression rice plants. The OsMPK1:GFP and OsWRKY90:GFP transcription factor were localized to the nuclei, suggesting that OsMPK1 in the cytoplasm moves into the nuclei to interact with the WRKY90. M. oryzae infection in ΔOsmek2 knock-out plants did not trigger iron and ROS accumulation and lipid peroxidation, and also downregulated OsMPK1, OsWRKY90, OsRbohB, and OsPR-1b expression. However, 35S:OsMEK2 overexpression induced ROS- and iron-dependent cell death in rice. The downstream MAP kinase (OsMPK1) overexpression induced ROS- and iron-dependent ferroptotic cell death response to virulent M. oryzae infection. The small-molecule ferroptosis inhibitor ferrostatin-1 suppressed iron- and ROS-dependent ferroptotic cell death in 35S:OsMPK1 overexpression plants. However, the small-molecule inducer erastin triggered iron- and lipid ROS-dependent, but OsMEK2-independent, ferroptotic cell death during M. oryzae infection. Disease (susceptibility)-related cell death was lipid ROS-dependent, but iron-independent in the ΔOsmek2 knock-out mutant during the late M. oryzae infection stage. These combined results suggest that OsMEK2 and OsMPK1 expression positively regulates iron- and ROS-dependent ferroptotic cell death, and blast disease (susceptibility)-related cell death was ROS-dependent but iron-independent in rice–M. oryzae interactions.

An enhanced pixel-based phenological feature for accurate paddy rice mapping with Sentinel-2 imagery in Google Earth Engine

Accurate paddy rice mapping with remote sensing at a regional scale plays critical roles in agriculture and ecology. Previous studies mainly employed a single key phenological period (i.e., transplanting) for paddy rice mapping. However, the prominentpoor spectral separability between paddy rice and others (e.g., wetland vegetation) exists in this period. To this end, we developed an enhanced pixel-based phenological feature composite method (Eppf-CM). Subsequently, the feature derived from Eppf-CM was served as the input data to a one-class classifier (One-Class Support Vector Machine, OCSVM). Eppf-CM includes two steps: (1) four distinctive phenological periods, specifically designed for rice mapping, were identified by time-series analysis of Sentinel-2 imagery. (2) We strived to choose one or two vegetation indices for each phenological period, and then stacking all the indices together. The new developed paddy rice mapping method with Eppf-CM and OCSVM is low costs and high precision. To fully demonstrate the outstanding precision of Eppf-CM based paddy rice map (Eppf map) in this study, three different sources of reference data were employed for comparison purposes. Compared with the field survey data, Eppf map achieved an overall accuracy higher than 0.98. The paddy rice area in Northeast China from Eppf map is only 1.86% less than that of the National Bureau of Statistics in 2019. Compared with a latest paddy rice map at the same spatial resolution (10-m), Eppf map significantly reduced commission and omission errors. To the best of our knowledge, the Eppf-CM has obtained one of the highest accuracy rice maps in Northeast China up-to-date. As a whole, we expect that: (1) Eppf-CM will advance the phenology-based agricultural remote sensing mapping method. (2) The paddy rice map will provide a new baseline data for the study of agriculture and ecology.

Assessment of the SASI Spectral Shape Index Time Series for Mapping Rice Ecosystems in the Mediterranean Region

There is a growing need to map rice ecosystems and to develop methods for monitoring rice distribution in order to account for rapid land use changes worldwide. In this study, we evaluated a methodology based on Vegetation Indices time series derived from an 8-day MODIS composite to identify rice fields and develop rice maps that can be timely updated in the long term. We have assessed the potential of the Spectral Shape Index time series and compared its performance with the Normalized Difference Vegetation Index in two coastal locations and in an inland location in the Mediterranean Region for 2012. A profile similarity comparison method, the Spectral Angle Mapper, was accomplished between the reference rice annual profile and the annual profiles of both indices in a pixel basis in order to determine rice pixels. The resultant maps were validated with rice masks, where available, or ortophotos and crop surface statistics where not. The results obtained demonstrated the potential of both indices to provide accurate rice maps when applied together with spectral matching techniques. The overall accuracy was 92.8%, 98.1% and 90.1% for the Spectral Shape Index and 92.4%, 77.24% and 82.8% for the Normalized Difference Vegetation Index in each location. The excellent performance of the Spectral Shape Index in the three locations highlighted the importance of exploring angular indices to improve the identification of land cover dynamics.

Detection of paddy rice cropping systems in southern China with time series Landsat images and phenology-based algorithms

ABSTRACT Southern China is a major rice-producing region where mixed rice cropping systems (single cropping rice (SCR) and double-cropping rice (DCR)) are widely practiced. An accurate estimation of the spatiotemporal changes in cropping systems is important for understanding the dynamic of paddy rice system and for developing suitable agricultural policies. However, few studies focus on mapping long-term changes in cropping systems in this subtropical region. The objective of this research is 1) to improve the phenology- and pixel-based paddy rice mapping (PPPM) algorithm by simultaneously considering the phenology signatures in the rice transplanting and heading periods; 2) to better identify different rice cropping systems and analyze their changes. Based on the improved PPPM method, we generated annual maps of SCR and DCR in southern China with image collection of Landsat 5, 7, and 8 from 1999 to 2019 using the Google Earth Engine platform. The overall accuracies of cropping system results for the study regions range from 81.0% to 98.1% depending on the areas of interest created in our study area. Then, the spatiotemporal patterns of the annual SCR and DCR time series were analyzed. In 2000, the total rice area was 208,614.6 km2, decreased sharply in 2003, and thereafter, the total increase in the paddy rice area fluctuated until 2011. From 2000 to 2019, the total rice area decreased to 171,474.3 km2 in 2019. The results showed that relatively stable SCR mainly distributed in Anhui, Hubei, and Jiangsu provinces whereas DCR occurred in Guangdong, Hunan and Jiangxi provinces. DCR-to-SCR conversion occurred drastically in Hunan, Hubei, and Jiangxi provinces. Rice-to-non-rice conversion was more prevalent in Hunan and Hubei provinces. Detailed spatiotemporal information over 20 years suggested that the plans for agricultural resources utilization in some specific provinces should be proposed, which is of great significance for food security in the major rice-producing area in southern China.

The magic of genomics in creating hybrid potato

The magic of genomics in creating hybrid potato

Spatial Delineation of Rice Yield and Production by the Combination of Rice Crop Modelling and Remote Sensing: A Case Study in Soc Trang Province, Vietnam

Vietnam's economy mainly depends on the growth of agricultural production. The forecasting yields to consolidate information to assure food security, monitoring, and mapping rice accurately are essential. The study is aimed to (i) delineate the rice distribution status; (ii) simulate the rice yield by using the AQUACROP model; (iii) integrate maps and rice yield to delineate the rice production extent in Soc Trang province. The method involves combining MODIS remote sensing data (MOD13Q1, MOD13A1 at 250m resolution, eight-day intervals) with the AQUACROP rice yield prediction results at 9 study sites within the area. The study delineated three primary rice cropping seasons (Winter-Spring, Spring-Autumn, Autumn-Summer), separated into eight specific rice cropping seasons, depending on the date or rice sowing/transplanting and harvesting. Besides, the difference in rice sowing time of the three main rice cropping seasons was identified and delineated. The simulated rice yield always higher observed rice yields at all seasons, from -8.65 to 22.20% in the Winter-Spring season, 5 to 28.6% in Spring-Summer season, and -1 to 49% in Summer-Autumn. The results were validated by comparing with the government statistical results, which was a very close correlation. The results suggested that we can use the MODIS satellite image for delineating rice cropping status. The rice yield and production can be simulated and delineated by the combination with the rice crop model.

Genetic dissection of heterosis of indica\u2013japonica by introgression line, recombinant inbred line and their testcross populations

The successful implementation of heterosis in rice has significantly enhanced rice productivity, but the genetic basis of heterosis in rice remains unclear. To understand the genetic basis of heterosis in rice, main-effect and epistatic quantitative trait loci (QTLs) associated with heterosis for grain yield-related traits in the four related rice mapping populations derived from Xiushui09 (XS09) (japonica) and IR2061 (indica), were dissected using single nucleotide polymorphism bin maps and replicated phenotyping experiments under two locations. Most mid-parent heterosis of testcross F1s (TCF1s) of XS09 background introgression lines (XSILs) with Peiai64S were significantly higher than those of TCF1s of recombinant inbred lines (RILs) with PA64S at two locations, suggesting that the effects of heterosis was influenced by the proportion of introgression of IR2061’s genome into XS09 background. A total of 81 main-effect QTLs (M-QTLs) and 41 epistatic QTLs were identified for the phenotypic variations of four traits of RILs and XSILs, TCF1s and absolute mid-parent heterosis in two locations. Furthermore, overdominance and underdominance were detected to play predominant effects on most traits in this study, suggesting overdominance and underdominance as well as epistasis are the main genetic bases of heterosis in rice. Some M-QTLs exhibiting positive overdominance effects such as qPN1.2, qPN1.5 and qPN4.3 for increased panicle number per plant, qGYP9 and qGYP12.1 for increased grain yield per plant, and qTGW3.4 and qTGW8.2 for enhanced 1000-grain weight would be highly valuable for breeding to enhance grain yield of hybrid rice by marker-assisted selection.

Examining rice distribution and cropping intensity in a mixed single- and double-cropping region in South China using all available Sentinel 1/2 images

Paddy rice agriculture in Southern China, especially Hunan Province, has been suffered from soil contamination. Several policies including rice fallow and decreasing cropping intensity have been implemented for food safety here. It is thus important to monitor rice planting area and cropping intensity to understand the effectiveness of those land-use policies. However, it is challenging to map rice planting areas due to the complex cropping systems (mixed single- and double-cropping), persistent cloud covers, small crop fields, let alone cropping intensity. Here we used all the available Sentinel-2 and all-weather Sentinel-1 imagery to generate a time series data cube to extract paddy rice planting areas and the rice cropping intensity in the Changsha, Zhuzhou, and Xiangtan areas, which is a traditional rice-growing region with small farms in China. Specifically, we investigated the performances of different features (i.e., spectral, seasonal, polarization backscatter) by comparing five scenarios with different combinations of sensors and features, and identified the most suitable features for certain rice types (early, middle, and late rice). The random forest classifier was used for the classification in the Google Earth Engine (GEE) platform, and a reference map in 2017 based on visual interpretation on the GaoFen-2 images were used for collecting the training and validation samples. The results showed the combined data from Sentinel-1/2 generally outperformed classifications using only a single sensor (Sentinel-1/2), but the contribution of different sensors to certain rice types varied. The early, middle and late rice with the highest accuracies within the five scenarios had the overall accuracies of 85%, 95%, and 95%, respectively (F1 = 0.55, 0.85, and 0.85). The compositing of different types of rice allowed us to generate the rice cropping intensity map with an overall accuracy of 81%, which to our limited knowledge is the first effort to map cropping intensity at 10-m resolution in such a fragmented subtropical region. The result showed the single cropping dominated the rice cropping system in the study area 88%, which used to be a typical area with double cropping of rice. Our study demonstrates the potential of mapping rice cropping intensity in a cloudy and highly fragmented region in South China using all the available Sentinel-1/2 data, which would advance our understanding of regional rice production and mitigation of soil contamination.

A Scalable Machine Learning Pipeline for Paddy Rice Classification Using Multi-Temporal Sentinel Data

The demand for rice production in Asia is expected to increase by 70% in the next 30 years, which makes evident the need for a balanced productivity and effective food security management at a national and continental level. Consequently, the timely and accurate mapping of paddy rice extent and its productivity assessment is of utmost significance. In turn, this requires continuous area monitoring and large scale mapping, at the parcel level, through the processing of big satellite data of high spatial resolution. This work designs and implements a paddy rice mapping pipeline in South Korea that is based on a time-series of Sentinel-1 and Sentinel-2 data for the year of 2018. There are two challenges that we address; the first one is the ability of our model to manage big satellite data and scale for a nationwide application. The second one is the algorithm’s capacity to cope with scarce labeled data to train supervised machine learning algorithms. Specifically, we implement an approach that combines unsupervised and supervised learning. First, we generate pseudo-labels for rice classification from a single site (Seosan-Dangjin) by using a dynamic k-means clustering approach. The pseudo-labels are then used to train a Random Forest (RF) classifier that is fine-tuned to generalize in two other sites (Haenam and Cheorwon). The optimized model was then tested against 40 labeled plots, evenly distributed across the country. The paddy rice mapping pipeline is scalable as it has been deployed in a High Performance Data Analytics (HPDA) environment using distributed implementations for both k-means and RF classifiers. When tested across the country, our model provided an overall accuracy of 96.69% and a kappa coefficient 0.87. Even more, the accurate paddy rice area mapping was returned early in the year (late July), which is key for timely decision-making. Finally, the performance of the generalized paddy rice classification model, when applied in the sites of Haenam and Cheorwon, was compared to the performance of two equivalent models that were trained with locally sampled labels. The results were comparable and highlighted the success of the model’s generalization and its applicability to other regions.

Mapping Rice Paddy Distribution Using Remote Sensing by Coupling Deep Learning with Phenological Characteristics

Two main approaches are used in mapping rice paddy distribution from remote sensing images: phenological methods or machine learning methods. The phenological methods can map rice paddy distribution in a simple way but with limited accuracy. Machine learning, particularly deep learning, methods that learn the spectral signatures can achieve higher accuracy yet require a large number of field samples. This paper proposed a pheno-deep method to couple the simplicity of the phenological methods and the learning ability of the deep learning methods for mapping rice paddy at high accuracy without the need of field samples. The phenological method was first used to initially delineate the rice paddy for the purpose of creating training samples. These samples were then used to train the deep learning model. The trained deep learning model was applied to map the spatial distribution of rice paddy. The effectiveness of the pheno-deep method was evaluated in Jin’an District, Lu’an City, Anhui Province, China. Results show that the pheno-deep method achieved a high performance with the overall accuracy, the precision, the recall, and AUC (area under curve) being 88.8%, 87.2%, 91.1%, and 94.4%, respectively. The pheno-deep method achieved a much better performance than the phenological alone method and can overcome the noises in the training samples from the phenological method. The overall accuracy of the pheno-deep method is only 2.4% lower than that of the deep learning alone method trained with field samples and this difference is not statistically significant. In addition, the pheno-deep method requires no field sampling, which would be a noteworthy advantage for situations when large training samples are difficult to obtain. This study shows that by combining knowledge-based methods with data-driven methods, it is possible to achieve high mapping accuracy of geographic variables using remote sensing even with little field sampling efforts.

Optimal multi-temporal Sentinel-1A SAR imagery for paddy rice field discrimination; a recommendation for operational mapping initiatives

Phenology-based rice mapping has mostly employed all satellite data over the growing season. This approach is not only time consuming but also requires huge data storage and is thus unsuitable for operational initiatives. Even with the use of feature selection algorithms that minimise data redundancy, the huge amount of time in data processing prior to optimal image subset selection is unavoidable. Thus, this study seeks to identify the rice development phase(s) whose Sentinel-1A data in vertical transmitted and horizontal received (VH) and vertical transmitted and vertical received (VV) polarizations offer the most accurate rice field discrimination. Using an area in southeast China during the 2017 growing season, VH + VV data of the vegetative and maturity phases recorded the highest overall accuracy (89.3%) based on Random Forest (RF). For the agro-ecology investigated in this study, therefore, potential users of Sentinel-1A in rice mapping can ex-ante select images acquired over the crop's vegetative and maturity phases to avoid the enormous computational time and storage attendant with entire-season data. These findings would complement algorithms like Support Vector Machine (SVM) that lack feature section tools. However, replications of this study at multiple years and ecologies, and comparison with classifications obtained from optimal data selection tools (variable importance) are strongly recommended to arrive at universally applicable conclusions.

The spatial data of paddy rice classification over Northeast Asia using COMS geostationary satellite

The Korea Aerospace Research Institute (KARI) estimated paddy rice classification maps over Northeast Asia using the Cheonian geostationary orbiting satellite (COMS: Communication, Ocean and Meteorological Satellite) data. In the case of classification map of rice paddy, it is not only used as input data for estimating rice yield, but also for various fields such as agriculture, weather, climate change, bio energy, and ecology. The spatial resolution of the classified rice map is 500 m, and the classification map was estimated yearly temporal resolution from 2011 to 2017. The spatial coverage of the classification map was the Northeast Asia with the latitude 25 ° N ~ 47 ° N and the longitude 115 ° E ~ 145 ° E as shown in Fig. 1 including Heilongjiang Sheng, Jilin Sheng, and Liaoning Sheng. In this classification map of paddy rice, it was calculated by applying geostationary orbiting satellites based on value-added products from Geostationary Ocean Color Imager (GOCI). In this study, we additionally used MODIS Land Surface Water Indices (LSWI) to support rice classification by considering the physical characteristics of rice cultivation area in the transplanting season. Basically, the radiance value of the top of atmosphere (TOP) observed in GOCI satellite was corrected to the surface reflectance at the top of the canopy through radiative transfer model. After that, NDVI, which can reflect the time series growth characteristics of rice, was estimated first. In addition, the MODIS LSWI index was used to determine the rice cultivation area with the NDVI in Northeast Asia by reflecting the water characteristics of the rice cultivation area during the transplanting period. More details of validation results for this algorithm can be found in previous studies.

A systematic method for spatio-temporal phenology estimation of paddy rice using time series Sentinel-1 images

Spatio-temporal phenological information is essential for regional crop monitoring and accurate management. This study aimed to obtain the spatio-temporal distribution of rice phenology using time series Sentinel-1A images. In this study, a systematic method for spatial and temporal phenological estimation was developed based on multi-temporal Sentinel data. This method consisted of: (1) the Spectral Similarity Measures (SSM) approach for rice mapping, and (2) the DTHT-PF approach, which includes a dynamic threshold algorithm (DT), a hierarchical tree (HT), and a particle filter (PF) used for phenology estimation. Thereinto, a dynamic threshold algorithm for transplanting date retrieval and a hierarchical tree for obtaining an initial phenology, which is then run through a PF, are proposed based on the SAR backscatter time series. In brief, we found that the VH backscatter has the potential to provide accurate phenological estimations for paddy rice. Furthermore, rice mapping at a high accuracy level of 92.97%, transplanting date retrieval, and initial phenology estimations lay a good foundation for understanding the spatio-temporal distribution of rice phenology. A determination factor (R2) and a root mean square error (RMSE) obtained using the DTHT-PF method were much higher (approximately 0.52 in the difference) and lower (approximately 14.67 in the difference), respectively, than those obtained using the PF approach with uniform initialization. R2 and RMSE values obtained using the real-time DTHT-PF method are slightly different from those obtained using the non-real-time DTHT-PF method. Map analysis revealed that the transplanting dates and the spatial distribution phenology were larger in the west and north of the study area near the South China Sea because of higher temperatures and earlier transplanting. Altogether, our results suggest that the DTHT-PF method and the VH backscatter obtained from the Sentinel-1A images have great potential for furthering our understanding of the spatio-temporal distribution of phenology estimation. This information can greatly contribute to the improvement of precision agriculture, including crop monitoring and yield predictions.