Regional yield estimation for winter wheat with MODIS-NDVI data in Shandong, China

The significance of crop yield estimation is well known in agricultural management and policy development at regional and national levels. The primary objective of this study was to test the suitability of the method, depending on predicted crop production, to estimate crop yield with a MODIS-NDVI-based model on a regional scale. In this paper, MODIS-NDVI data, with a 250 m resolution, was used to estimate the winter wheat (Triticum aestivum L.) yield in one of the main winter-wheat-growing regions. Our study region is located in Jining, Shandong Province. In order to improve the quality of remote sensing data and the accuracy of yield prediction, especially to eliminate the cloud-contaminated data and abnormal data in the MODIS-NDVI series, the Savitzky–Golay filter was applied to smooth the 10-day NDVI data. The spatial accumulation of NDVI at the county level was used to test its relationship with winter wheat production in the study area. A linear regressive relationship between the spatial accumulation of NDVI and the production of winter wheat was established using a stepwise regression method. The average yield was derived from predicted production divided by the growing acreage of winter wheat on a county level. Finally, the results were validated by the ground survey data, and the errors were compared with the errors of agro-climate models. The results showed that the relative errors of the predicted yield using MODIS-NDVI are between −4.62% and 5.40% and that whole RMSE was 214.16 kg ha⁻¹ lower than the RMSE (233.35 kg ha⁻¹) of agro-climate models in this study region. A good predicted yield data of winter wheat could be got about 40 days ahead of harvest time, i.e. at the booting-heading stage of winter wheat. The method suggested in this paper was good for predicting regional winter wheat production and yield estimation.     

遥感定量反演华北平原地区冬小麦含水量

针对现有植被水分反演算法在华北平原地区适用性差、反演精度低、不能实施有效监测的问题,该文基于地面实测冬小麦植被含水量(VWC)数据,基于归一化型和比值型植被水分指数这两种常见的指数类型,提出调节植被水分指数以削弱土壤背景的影响,使用多个波段反射率数据反演VWC,提高拟合精度80%以上,发展适用于华北平原的农作物水分含量反演模型。拟合冬小麦植被含水量的决定系数为0.51,均方根误差为0.95(kg·m^-2)。结果表明:调节植被水分指数能够削弱土壤背景影响,大幅度提高植被水分反演精度;同一种指数计算形式中,在水汽吸收谷内,基于更长波段反射率的植被水分指数反演精度更高;归一化型和比值型植被水分指数在反演精度方面无明显优劣,归一化型植被水分指数反演精度。     

Effects of water and heat on growth of winter wheat in the North China Plain

The North China Plain (NCP) was selected as the study area and the effects of water and heat were analysed to determine the dominant factor affecting winter wheat growth. The mean, minimum and maximum temperatures, precipitation and soil moisture data were selected to analyse the correlations between the leaf area index (the growth indicator) and these factors using long time series half-monthly data (2–5 months) (from 1982 to 2010). The results showed that temperature was the main factor affecting the growth of winter wheat in the NCP. The growth of winter wheat had weak correlations with precipitation and soil moisture and the influence of water on winter wheat growth was smaller than the influence of heat. In the northern part of the NCP, mainly including the north-west region of Shandong Province and the southern region of Hebei Province, irrigation was necessary in late February and early March.     

多源遥感与作物模型同化模拟作物物生长参数时空域连续变化

本文将遥感信息与作物模型同化实现作物生长参数的时空域连续模拟,进而监测生长参数的时空域变化.首先将作物模型WOFOST(World food studies) 与冠层辐射传输模型PROSAIL 耦合构建WOPROSAIL 模型,利用微粒群算法(PSO) 通过最小化从CCD 数据获取的土壤调节植被指数观测值SAVI(soil adjusted vegetation index) 与耦合模型得到的模拟值SAVI’之间差值优化作物模型初始参数.通过MODIS 数据反演实现参数的区域化,并将区域参数作为优化后作物模型输入参数驱动模型逐像元计算生长参数,实现生长参数的时空域连续模拟与监测,最终建立区域尺度遥感-作物模拟同化框架模型RS-WOPROSAIL .结果表明：同化模型解决了作物模型模拟空间域和遥感信息时间域的不连续问题.模型模拟的叶面积指数(LAI) 、穗重(WSO) 、地上总生物量(TAGP) 等生长参数较好地体现了水稻生长状况时空域变化,研究区水稻模拟产量与实际产量的误差为27.4% .     

Quantifying winter wheat residue biomass with a spectral angle index derived from China Environmental Satellite data

Quantification of crop residue biomass on cultivated lands is essential for studies of carbon cycling of agroecosystems, soil-atmospheric carbon exchange and Earth systems modeling. Previous studies focus on estimating crop residue cover (CRC) while limited research exists on quantifying crop residue biomass. This study takes advantage of the high temporal resolution of the China Environmental Satellite (HJ-1) data and utilizes the band configuration features of HJ-1B data to establish spectral angle indices to estimate crop residue biomass. Angles formed at the NIR_IRS vertex by the three vertices at R, NIR_IRS, and SWIR (ANIR_IRS) of HJ-1B can effectively indicate winter wheat residue biomass. A coefficient of determination (R²) of 0.811 was obtained between measured winter wheat residue biomass and ANIR_IRS derived from simulated HJ-1B reflectance data. The ability of ANIR_IRS for quantifying winter wheat residue biomass using HJ-1B satellite data was also validated and evaluated. Results indicate that ANIR_IRS performed well in estimating winter wheat residue biomass with different residue treatments; the root mean square error (RMSE) between measured and estimated residue biomass was 0.038 kg/m². ANIR_IRS is a potential method for quantifying winter wheat residue biomass at a large scale due to wide swath width (350 km) and four-day revisit rate of the HJ-1 satellite. While ANIR_IRS can adequately estimate winter wheat residue biomass at different residue moisture conditions, the feasibility of ANIR_IRS for winter wheat residue biomass estimation at different fractional coverage of green vegetation and different environmental conditions (soil type, soil moisture content, and crop residue type) needs to be further explored.     

Evaluating the relationship between biomass,percent groundcover and remote sensing indices across six winter cover crop fields in Maryland,United States

Winter cover crops are an essential part of managing nutrient and sediment losses from agricultural lands. Cover crops lessen sedimentation by reducing erosion, and the accumulation of nitrogen in aboveground biomass results in reduced nutrient runoff. Winter cover crops are planted in the fall and are usually terminated in early spring, making them susceptible to senescence, frost burn, and leaf yellowing due to wintertime conditions. This study sought to determine to what extent remote sensing indices are capable of accurately estimating the percent groundcover and biomass of winter cover crops, and to analyze under what critical ranges these relationships are strong and under which conditions they break down. Cover crop growth on six fields planted to barley, rye, ryegrass, triticale or wheat was measured over the 2012–2013 winter growing season. Data collection included spectral reflectance measurements, aboveground biomass, and percent groundcover. Ten vegetation indices were evaluated using surface reflectance data from a 16-band CROPSCAN sensor. Restricting analysis to sampling dates before the onset of prolonged freezing temperatures and leaf yellowing resulted in increased estimation accuracy. There was a strong relationship between the normalized difference vegetation index (NDVI) and percent groundcover (r² = 0.93) suggesting that date restrictions effectively eliminate yellowing vegetation from analysis. The triangular vegetation index (TVI) was most accurate in estimating high ranges of biomass (r² = 0.86), while NDVI did not experience a clustering of values in the low and medium biomass ranges but saturated in the higher range (>1500 kg/ha). The results of this study show that accounting for index saturation, senescence, and frost burn on leaves can greatly increase the accuracy of estimates of percent groundcover and biomass for winter cover crops.     

Estimation of winter wheat crop growth parameters using time series Sentinel-1A SAR data

In the present study, Sentinel-1A Synthetic Aperture Radar analysis of time series data at C-band was carried out to estimate the winter wheat crop growth parameters. Five different date images were acquired during January 2015–April 2015 at different growth stages from tillering to ripening in Varanasi district, India. The winter wheat crop parameters, i.e. leaf area index, vegetation water content (VWC), fresh biomass (FB), dry biomass (DB) and plant height (PH) were estimated using random forest regression (RFR), support vector regression (SVR), artificial neural network regression (ANNR) and linear regression (LR) algorithms. The Ground Range Detected products of Interferometric Wide (IW) Swath were used at VV polarization. The three different subplots of 1 m² area were taken for the measurement of crop parameters at every growth stage. In total, 73 samples were taken as the training data-sets and 39 samples were taken as testing data-sets. The highest sensitivity (adj. R^2?=?0.95579) of backscattering with VWC was found using RFR algorithm, whereas the lowest sensitivity (adj. R^2?=?0.66201) was found for the PH using LR algorithm. Overall results indicate more accurate estimation of winter wheat parameters by the RFR algorithm followed by SVR, ANNR and LR algorithms.     

Predicting grain protein content of winter wheat using remote sensing data based on nitrogen status and water stress

Advanced site-specific knowledge of grain protein content of winter wheat from remote sensing data would provide opportunities to manage grain harvest differently, and to maximize output by adjusting input in fields. In this study, remote sensing data were utilized to predict grain protein content. Firstly, the leaf nitrogen content at winter wheat anthesis stage was proved to be significantly correlated with grain protein content (R² = 0.36), and spectral indices significantly correlated to leaf nitrogen content at anthesis stage were potential indicators for grain protein content. The vegetation index, VI_green, derived from the canopy spectral reflectance at green and red bands, was significantly correlated to the leaf nitrogen content at anthesis stage, and also highly significantly correlated to the final grain protein content (R² = 0.46). Secondly, the external conditions, such as irrigation, fertilization and temperature, had important influence on grain quality. Water stress at grain filling stage can increase grain protein content, and leaf water content is closely related to irrigation levels, therefore, the spectral indices correlated to leaf water content can be potential indicators for grain protein content. The spectral reflectance of TM channel 5 derived from canopy spectra or image data at grain filling stage was all significantly correlated to grain protein content (R² = 0.31 and 0.37, respectively). Finally, not only this study proved the feasibility of using remote sensing data to predict grain protein content, but it also provided a tentative prediction of the grain protein content in Beijing area using the reflectance image of TM channel 5.     

Object detection in remote sensing imagery using a discriminatively trained mixture model

Automatically detecting objects with complex appearance and arbitrary orientations in remote sensing imagery (RSI) is a big challenge. To explore a possible solution to the problem, this paper develops an object detection framework using a discriminatively trained mixture model. It is mainly composed of two stages: model training and object detection. In the model training stage, multi-scale histogram of oriented gradients (HOG) feature pyramids of all training samples are constructed. A mixture of multi-scale deformable part-based models is then trained for each object category by training a latent Support Vector Machine (SVM), where each part-based model is composed of a coarse root filter, a set of higher resolution part filters, and a set of deformation models. In the object detection stage, given a test imagery, its multi-scale HOG feature pyramid is firstly constructed. Then, object detection is performed by computing and thresholding the response of the mixture model. The quantitative comparisons with state-of-the-art approaches on two datasets demonstrate the effectiveness of the developed framework.     

Development and implementation of a multiscale biomass model using hyperspectral vegetation indices for winter wheat in the North China Plain

Crop monitoring during the growing season is important for regional management decisions and biomass prediction. The objectives of this study were to develop, improve and validate a scale independent biomass model. Field studies were conducted in Huimin County, Shandong Province of China, during the 2006–2007 growing season of winter wheat (Triticum aestivum L.). The field design had a multiscale set-up with four levels which differed in their management, such as nitrogen fertilizer inputs and cultivars, to create different biomass conditions: small experimental fields (L1), large experimental fields (L2), small farm fields (L3), and large farm fields (L4). L4, planted with different winter wheat varieties, was managed according to farmers’ practice while L1 through L3 represented controlled field experiments. Multitemporal spectral measurements were taken in the fields, and biomass was sampled for each spectral campaign. In addition, multitemporal Hyperion data were obtained in 2006 and 2007. L1 field data were used to develop biomass models based on the relation between the winter wheat spectra and biomass: several published vegetation indices, including NRI, REP, OSAVI, TCI, and NDVI, were investigated. A new hyperspectral vegetation index, which uses a four-band combination in the NIR and SWIR domains, named GnyLi, was developed. Following the multiscale concept, the data of higher levels (L2 through L4) were used stepwise to validate and improve the models of the lower levels, and to transfer the improved models to the next level. Lastly, the models were transferred and validated at the regional scale using Hyperion images of 2006 and 2007. The results showed that the GnyLi and NRI models, which were based on the NIR and SWIR domains, performed best with R² > 0.74. All the other indices explained less than 60% model variability. Using the Hyperion data for regionalization, GnyLi and NRI explained 81–89% of the biomass variability. These results highlighted that GnyLi and NRI can be used together with hyperspectral images for both plot and regional level biomass estimation. Nevertheless, additional studies and analyses are needed to test its replicability in other environmental conditions.     

Estimating fractional cover of crop,crop residue,and soil in cropland using broadband remote sensing data and machine learning

The fractional vegetation cover (FVC), crop residue cover (CRC), and bare soil (BS) are three important parameters in vegetation–soil ecosystems, and their correct and timely estimation can improve crop monitoring and environmental monitoring. The triangular space method uses one CRC index and one vegetation index to create a triangular space in which the three vertices represent pure vegetation, crop residue, and bare soil. Subsequently, the CRC, FVC, and BS of mixed remote sensing pixels can be distinguished by their spatial locations in the triangular space. However, soil moisture and crop-residue moisture (SM-CRM) significantly reduce the performance of broadband remote sensing CRC indices and can thus decrease the accuracy of the remote estimation and mapping of CRC, FVC, and BS. This study evaluated the use of broadband remote sensing, the triangular space method, and the random forest (RF) technique to estimate and map the FVC, CRC, and BS of cropland in which SM-CRM changes dramatically. A spectral dataset was obtained using: (1) from a field-based experiment with a field spectrometer; and (2) from a laboratory-based simulation that included four distinct soil types, three types of crop residue (winter-wheat, maize, and rice), one crop (winter wheat), and varying SM-CRM. We trained an RF model [designated the broadband crop-residue index from random forest (CRRF)] that can magnify spectral features of crop residue and soil by using the broadband remote sensing angle indices as input, and uses a moisture-resistant hyperspectral index as the target. The effects of moisture on crop residue and soil were minimized by using the broadband CRRF. Then, the CRRF-NDVI triangular space method was used to estimate and map CRC, FVC, and BS. Our method was validated by using both laboratory- and field-based experiments and Sentinel-2 broadband remote-sensing images. Our results indicate that the CRRF-NDVI triangular space method can reduce the effect of moisture on the broadband remote-sensing of CRC, and may also help to obtain laboratory and field CRC, FVC, and BS. Thus, the proposed method has great potential for application to croplands in which the SM-CRM content changes dramatically.     

Monitoring land-use change by combining participatory land-use maps with standard remote sensing techniques: Showcase from a remote forest catchment on Mindanao,Philippines

This paper combines participatory activities (PA) with remote sensing analysis into an integrated methodology to describe and explain land-cover changes. A remote watershed on Mindanao (Philippines) is used to showcase the approach, which hypothesizes that the accuracy of expert knowledge gained from remote sensing techniques can be further enhanced by inputs from vernacular knowledge when attempting to understand complex land mosaics and past land-use changes. Six participatory sessions based on focus-group discussions were conducted. These were enhanced by community-based land-use mapping, resulting in a final total of 21 participatory land-use maps (PLUMs) co-produced by a sample of stakeholders with different sociocultural and ecological perspectives. In parallel, seven satellite images (Landsat MSS, Landsat TM, Landsat ETM+, and SPOT4) were classified following standard techniques and provided snapshots for the years 1976, 1996, and 2010. Local knowledge and collective memory contributed to define and qualify relevant land-use classes. This also provided information about what had caused the land-use changes in the past. Results show that combining PA with remote-sensing analysis provides a unique understanding of land-cover change because the two methods complement and validate one another. Substantive qualitative information regarding the chronology of land-cover change was obtained in a short amount of time across an area poorly covered by scientific literature. The remote sensing techniques contributed to test and to quantify verbal reports of land-use and land-cover change by stakeholders. We conclude that the method is particularly relevant to data-poor areas or conflict zones where rapid reconnaissance work is the only available option. It provides a preliminary but accurate baseline for capturing land changes and for reporting their causes and consequences. A discussion of the main challenges encountered (i.e. how to combine different systems of knowledge), and options for further methodological improvements, are also provided.     

Detecting winter wheat phenology with SPOT-VEGETATION data in the North China Plain

Monitoring phenological change in agricultural land improves our understanding of the adaptation of crops to a warmer climate. Winter wheat–maize and winter wheat–cotton double-cropping are practised in most agricultural areas in the North China Plain. A curve-fitting method is presented to derive winter wheat phenology from SPOT-VEGETATION S10 normalized difference vegetation index (NDVI) data products. The method uses a double-Gaussian model to extract two phenological metrics, the start of season (SOS) and the time of maximum NDVI (MAXT). The results are compared with phenological records at local agrometeorological stations. The SOS and MAXT have close agreement with in situ observations of the jointing date and milk-in-kernel date respectively. The phenological metrics detected show spatial variations that are consistent with known phenological characteristics. This study indicates that time-series analysis with satellite data could be an effective tool for monitoring the phenology of crops and its spatial distribution in a large agricultural region.     

Otsu法、区域生长法及形态学相结合的遥感图像海岸线提取

针对现有的海岸线提取方法精度低,无法满足处理各种传感器卫星图像及对线性多样复杂的海岸线提取的需求,本文提出了一种将Otsu法、区域生长法及形态学相结合的遥感图像海岸线提取方法。并且通过试验证明,该海岸线提取方法可以充分发挥Otsu、区域生长法及形态学方法在提取海岸线方面的各自优势,大大提高了海岸线的提取精度。并利用该方法对两种不同的卫星图像数据进行海岸线提取,验证了该方法在不同条件下均有良好的适用性。     

利用AMSR-E数据反演华北平原冬小麦单散射反照率

首先,基于冬小麦不同生育期的地面实测参数,构建了组成冬小麦冠层的、包括不同尺寸和含水量的介电散射体模拟数据库,并在此基础上建立冬小麦单散射反照率和光学厚度分别在C(6.925 GHz)和X(10.65 GHz)波段之间的依赖关系。然后,根据一阶参数化模型推导得到的微波植被指数MVIs(Microwave Vegetation Indices)的物理表达式,结合AMSR-E被动微波亮温数据,反演了华北平原地区冬小麦不同生育期的单散射反照率。与MODIS日归一化差异植被指数NDVI的对比结果显示:冬小麦单散射反照率与NDVI随时间的变化趋势大致相同,但在冬小麦的抽穗期到乳熟期,NDVI呈现饱和趋势,而单散射反照率对小麦的生长变化仍旧比较敏感,在指示冬小麦生长方面具有一定优势。     

Technical progress of China's national remote sensing mapping:from mapping western China to national dynamic mapping

Remote sensing mapping is an important research direction in the development of geographic surveying and mapping.In order to successfully implement the project of Mapping Western China(MWC),a technical mapping system has been established.In this project,many problems have been solved through technological innovation,such as block adjustment with scarce control points,large-scale aerial/satellite image mapping,and intelligent interpretation of multi-source images.Several softwares were developed,e.g.PixelGrid for aerial/satellite image mapping in a large area,FeatureStation for the integration of multi-source data in the complex terrain areas,and an airborne multi-band and multi-polarization interferometric data acquisition system for SAR mapping.For the first time,full coverage of 1∶50,000 topographic data of China's land territory has been produced,which means the geospatial framework of digital China is basically completed.With the implementation of other key national plans and projects(i.e.national geographic conditions monitoring and national remote sensing map-ping),the focus has changed from MWC to national dynamic mapping.Accordingly,a dynamic mapping system is established.The data acquisition capability has developed from a single source to multiple sources and multiple modalities.The mapping capability has developed into dynamic mapping,and the capability for database update shows the characteristics of colla-boration.The national geographic condition monitoring creates a multi-scale index system for statistical analysis for various needs.A multi-level and multi-dimensional technical system for statistical computing and decision-making service is developed for the transformation from dynamic monitoring to information service.In this paper,we give a brief introduction about the recent development of remote sensing mapping in China with respect to data acquisition,map production,and information service.The purpose of this paper is to motivate the establishment of theory and method for remote sensing mapping,technical and equipment in the smart mapping era,to improve the capability of perceiving,analyzing,mining,and applying geographic data,and to promote the intelligent development of geographic survey-ing and mapping.     

植被物候遥感监测研究进展

植被物候是研究植被与气候、环境变化间关系的重要参量。本文针对目前常用的阈值法、拟合法和延迟滑动平均法等植被物候遥感监测方法进行比较分析;介绍了传感器网络法、物候模型法等物候遥感监测验证方法;从遥感监测方法和数据源两方面分析物候遥感监测的误差来源;针对目前研究中存在的问题,讨论了遥感物候的主要研究方向:从机理层面,应创新植被物候遥感监测方法;建立标准化地面验证数据源;利用多源遥感数据,组成高时间分辨率的原始遥感数据源,提高植被物候遥感监测的时间分辨率和测算精度。     

结合数据融合与特征选择的遥感影像尺度多样目标检测

基于深度神经网络模型的遥感影像地物检测取得了巨大成功,很大程度上得益于大规模数据集的支撑。但是,从现有遥感影像数据集本身来看,不同类别地物的数量分布不一致,同类地物对象以不同尺寸大小呈现,是导致地物样本的尺度不均衡问题的直接因素。对此,本文采用数据集内影像加权融合与地物多尺度特征选择的策略来缓解该问题。首先,将数据集内两张影像的像素值进行加权并得到融合后的影像,从而使不同类别地物样本更加均衡且具有较高的背景多样性;其次,通过选择合适尺度的特征图预测相应尺度的目标类别,且允许同一尺度目标在相邻特征图上进行预测,这样使模型能根据目标尺度进行训练;最后,基于目标中心区域的特征图预测目标边界框,预测的边界框更符合目标本身的尺度。通过在两个遥感数据集上分别进行实验,表明训练的模型在对复杂背景下的类别不均衡目标的识别更加准确,能够适应遥感影像下不同尺度目标的识别。     

Upscaling plot-scale soil respiration in winter wheat and summer maize rotation croplands in Julu County,North China

Soil respiration (R_s) data from 45 plots were used to estimate the spatial patterns of R_s during the peak growing seasons of winter wheat and summer maize in Julu County, North China, by combining satellite remote sensing data, field-measured data, and a support vector regression (SVR) model. The observed R_s values were well reproduced by the model at the plot scale, with a root-mean-square error (RMSE) of 0.31 μmol CO₂ m⁻² s⁻¹ and a coefficient of determination (R²) of 0.73. No significant difference was detected between the prediction accuracy of the SVR model for winter wheat and summer maize. With forcing from satellite remote sensing data and gridded soil property data, we used the SVR model to predict the spatial distributions of R_s during the peak growing seasons of winter wheat and summer maize rotation croplands in Julu County. The SVR model captured the spatial variations of R_s at the county scale. The satellite-derived enhanced vegetation index was found to be the most important input used to predict R_s. Removal of this variable caused an RMSE increase from 0.31 μmol CO₂ m⁻² s⁻¹ to 0.42 μmol CO₂ m⁻² s⁻¹. Soil properties such as soil organic carbon (SOC) content and soil bulk density (SBD) were the second most important factors. Their removal led to an RMSE increase from 0.31 μmol CO₂ m⁻² s⁻¹ to 0.37 μmol CO₂ m⁻² s⁻¹. The SVR model performed better than multiple regression in predicting spatial variations of R_s in winter wheat and summer maize rotation croplands, as shown by the comparison of the R² and RMSE values of the two algorithms. The spatial patterns of R_s are better captured using the SVR model than performing multiple regression, particularly for the relatively high and relatively low R_s values at the center and northeast study areas. Therefore, SVR shows promise for predicting spatial variations of R_s values on the basis of remotely sensed data and gridded soil property data at the county scale.     

Global rain-fed,irrigated, and paddy croplands: A new high resolution map derived from remote sensing,crop inventories and climate data

Irrigation accounts for 70% of global water use by humans and 33–40% of global food production comes from irrigated croplands. Accurate and timely information related to global irrigation is therefore needed to manage increasingly scarce water resources and to improve food security in the face of yield gaps, climate change and extreme events such as droughts, floods, and heat waves. Unfortunately, this information is not available for many regions of the world. This study aims to improve characterization of global rain-fed, irrigated and paddy croplands by integrating information from national and sub-national surveys, remote sensing, and gridded climate data sets. To achieve this goal, we used supervised classification of remote sensing, climate, and agricultural inventory data to generate a global map of irrigated, rain-fed, and paddy croplands. We estimate that 314 million hectares (Mha) worldwide were irrigated circa 2005. This includes 66 Mha of irrigated paddy cropland and 249 Mha of irrigated non-paddy cropland. Additionally, we estimate that 1047 Mha of cropland are managed under rain-fed conditions, including 63 Mha of rain-fed paddy cropland and 985 Mha of rain-fed non-paddy cropland. More generally, our results show that global mapping of irrigated, rain-fed, and paddy croplands is possible by combining information from multiple data sources. However, regions with rapidly changing irrigation or complex mixtures of irrigated and non-irrigated crops present significant challenges and require more and better data to support high quality mapping of irrigation.