Search

The challenge of global food security in the face of population growth, conflict, and climate change requires a comprehensive understanding of cropped areas, irrigation practices, and the distribution of major commodity crops like maize and wheat. However, such understanding should preferably be updated at seasonal intervals for each agricultural system rather than relying on a single annual assessment. Here we present the European Space Agency-funded WorldCereal system, a global, seasonal, and reproducible crop and irrigation mapping system that addresses existing limitations in current global-scale crop and irrigation mapping. WorldCereal generates a range of global products, including temporary crop extent, seasonal maize and cereal maps, seasonal irrigation maps, seasonal active cropland maps, and model confidence layers providing insights into expected product quality. The WorldCereal product suite for the year 2021 presented here serves as a global demonstration of the dynamic open-source WorldCereal system. Validation of the products was done based on best available reference data per product. A global statistical validation for the temporary crop extent product resulted in user’s and producer’s accuracies of 88.5 % and 92.1 %, respectively. For crop type, a verification was performed against a newly collected street view dataset (overall agreement 82.5 %) and a limited number of publicly available in situ datasets (reaching minimum agreement of 80 %). Finally, global irrigated-area estimates were derived from available maps and statistical datasets, revealing the conservative nature of the WorldCereal irrigation product. The WorldCereal system provides a vital tool for policymakers, international organizations, and researchers to better understand global crop and irrigation patterns and to inform decision-making related to food security and sustainable agriculture. Our findings highlight the need for continued community efforts such as additional reference d

Managed grasslands cover about one third of the European utilized agricultural area. Appropriate grassland management is key for balancing trade-offs between provisioning and regulating ecosystem services. The timing and frequency of mowing events are major factors of grassland management. Recent studies have shown the feasibility of detecting mowing events using remote sensing time series from optical and radar satellites. In this study, we present a new method combining the regular observations of Sentinel-1 (S1) and the better accuracy of Sentinel-2 (S2) grassland mowing detection algorithms. This multi-source approach for grassland monitoring was assessed over large areas and in various contexts. The method was first validated in six European countries, based on Planet image interpretation. Its performances and sensitivity were then thoroughly assessed in an independent study area using a more precise and complete reference dataset based on an intensive field campaign. Results showed the robustness of the method across all study areas and different types of grasslands. The method reached a F1-score of 79% for detecting mowing events on hay meadows. Furthermore, the detection of mowing events along the growing season allows to classify mowing practices with an overall accuracy of 69%. This is promising for differentiating grasslands in terms of management intensity. The method could therefore be used for large-scale grassland monitoring to support agri-environmental schemes in Europe.

The convergence of new EO data flows, new methodological developments and cloud computing infrastructure calls for a paradigm shift in operational agriculture monitoring. The Copernicus Sentinel-2 mission providing a systematic 5-day revisit cycle and free data access opens a completely new avenue for near real-time crop specific monitoring at parcel level over large countries. This research investigated the feasibility to propose methods and to develop an open source system able to generate, at national scale, cloud-free composites, dynamic cropland masks, crop type maps and vegetation status indicators suitable for most cropping systems. The so-called Sen2-Agri system automatically ingests and processes Sentinel-2 and Landsat 8 time series in a seamless way to derive these four products, thanks to streamlined processes based on machine learning algorithms and quality controlled in situ data. It embeds a set of key principles proposed to address the new challenges arising from countrywide 10m resolution agriculture monitoring. The full-scale demonstration of this system for three entire countries (Ukraine, Mali, South Africa) and five local sites distributed across the world was a major challenge met successfully despite the availability of only one Sentinel-2 satellite in orbit. In situ data were collected for calibration and validation in a timely manner allowing the production of the four Sen2-Agri products over all the demonstration sites. The independent validation of the monthly cropland masks provided for most sites overall accuracy values higher than 90%, and already higher than 80% as early as the mid-season. The crop type maps depicting the 5 main crops for the considered study sites were also successfully validated: overall accuracy values higher than 80% and F1 Scores of the different crop type classes were most often higher than 0.65. These respective results pave the way for countrywide crop specific monitoring system at parcel level bridging the gap

The exploitation of new high revisit frequency satellite observations is an important opportunity for agricultural applications. The Sentinel-2 for Agriculture project S2Agri (http://www.esa-sen2agri.org/SitePages/Home.aspx) is designed to develop, demonstrate and facilitate the Sentinel-2 time series contribution to the satellite EO component of agriculture monitoring for many agricultural systems across the globe. In the framework of this project, this article studies the construction of a dynamic cropland mask. This mask consists of a binary “annual-cropland/no-annual-cropland” map produced several times during the season to serve as a mask for monitoring crop growing conditions over the growing season. The construction of the mask relies on two classical pattern recognition techniques: feature extraction and classification. One pixel- and two object-based strategies are proposed and compared. A set of 12 test sites are used to benchmark the methods and algorithms with regard to the diversity of the agro-ecological context, landscape patterns, agricultural practices and actual satellite observation conditions. The classification results yield promising accuracies of around 90% at the end of the agricultural season. Efforts will be made to transition this research into operational products once Sentinel-2 data become available.

Cropland mapping relies heavily on field data for algorithm calibration, making it, in many cases, applicable only at the field campaign scale. While the recently launched Sentinel-2 satellite will be able to deliver time series over large regions, it will not really be compatible with the current mapping approach or the available in situ data. This research introduces a generic methodology for mapping annual cropland along the season at high spatial resolution with the use of globally available baseline land cover and no need for field data. The methodology is based on cropland-specific temporal features, which are able to cope with the diversity of agricultural systems, prior information from which mislabeled pixels have been removed and a cost-effective classifier. Thanks to the JECAM network, eight sites across the world were selected for global cropland mapping benchmarking. Accurate cropland maps were produced at the end of the season, showing an overall accuracy of more than 85%. Early cropland maps were also obtained at three-month intervals after the beginning of the growing season, and these showed reasonable accuracy at the three-month stage (>70% overall accuracy) and progressive improvement along the season. The trimming-based method was found to be key for using spatially coarse baseline land cover information and, thus, avoiding costly field campaigns for prior information retrieval. The accuracy and timeliness of the proposed approach shows that it has substantial potential for operational agriculture monitoring programs.

Crop area extent estimates and crop type maps provide crucial information for agricultural monitoring and management. Remote sensing imagery in general and, more specifically, high temporal and high spatial resolution data as the ones which will be available with upcoming systems, such as Sentinel-2, constitute a major asset for this kind of application. The goal of this paper is to assess to what extent state-of-the-art supervised classification methods can be applied to high resolution multi-temporal optical imagery to produce accurate crop type maps at the global scale. Five concurrent strategies for automatic crop type map production have been selected and benchmarked using SPOT4 (Take5) and Landsat 8 data over 12 test sites spread all over the globe (four in Europe, four in Africa, two in America and two in Asia). This variety of tests sites allows one to draw conclusions applicable to a wide variety of landscapes and crop systems. The results show that a random forest classifier operating on linearly temporally gap-filled images can achieve overall accuracies above 80% for most sites. Only two sites showed low performances: Madagascar due to the presence of fields smaller than the pixel size and Burkina Faso due to a mix of trees and crops in the fields. The approach is based on supervised machine learning techniques, which need in situ data collection for the training step, but the map production is fully automatic.

Developing better agricultural monitoring capabilities based on Earth Observation data is critical for strengthening food production information and market transparency. The Sentinel-2 mission has the optimal capacity for regional to global agriculture monitoring in terms of resolution (10–20 meter), revisit frequency (five days) and coverage (global). In this context, the European Space Agency launched in 2014 the “Sentinel-2 for Agriculture” project, which aims to prepare the exploitation of Sentinel-2 data for agriculture monitoring through the development of open source processing chains for relevant products. The project generated an unprecedented data set, made of “Sentinel-2 like” time series and in situ data acquired in 2013 over 12 globally distributed sites. Earth Observation time series were mostly built on the SPOT4 (Take 5) data set, which was specifically designed to simulate Sentinel-2. They also included Landsat 8 and RapidEye imagery as complementary data sources. Images were pre-processed to Level 2A and the quality of the resulting time series was assessed. In situ data about cropland, crop type and biophysical variables were shared by site managers, most of them belonging to the “Joint Experiment for Crop Assessment and Monitoring” network. This data set allowed testing and comparing across sites the methodologies that will be at the core of the future “Sentinel-2 for Agriculture” system.

Developing better agricultural monitoring capabilities based on Earth Observation data is critical for strengthening food production information and market transparency. The Sentinel-2 mission has the optimal capacity for regional to global agriculture monitoring in terms of resolution (10–20 meter), revisit frequency (five days) and coverage (global). In this context, the European Space Agency launched in 2014 the “Sentinel¬2 for Agriculture” project, which aims to prepare the exploitation of Sentinel-2 data for agriculture monitoring through the development of open source processing chains for relevant products. The project generated an unprecedented data set, made of “Sentinel-2 like” time series and in situ data acquired in 2013 over 12 globally distributed sites. Earth Observation time series were mostly built on the SPOT4 (Take 5) data set, which was specifically designed to simulate Sentinel-2. They also included Landsat 8 and RapidEye imagery as complementary data sources. Images were pre-processed to Level 2A and the quality of the resulting time series was assessed. In situ data about cropland, crop type and biophysical variables were shared by site managers, most of them belonging to the “Joint Experiment for Crop Assessment and Monitoring” network. This data set allowed testing and comparing across sites the methodologies that will be at the core of the future “Sentinel¬2 for Agriculture” system.

The RAdiative transfer Model Intercomparison (RAMI) activity focuses on the benchmarking of canopy radiative transfer (RT) models. For the current fourth phase of RAMI, six highly realistic virtual plant environments were constructed on the basis of intensive field data collected from (both deciduous and coniferous) forest stands as well as test sites in Europe and South Africa. Twelve RT modelling groups provided simulations of canopy scale (directional and hemispherically integrated) radiative quantities, as well as a series of binary hemispherical photographs acquired from different locations within the virtual canopies. The simulation results showed much greater variance than those recently analysed for the abstract canopy scenarios of RAMI-IV. Canopy complexity is among the most likely drivers behind operator induced errors that gave rise to the discrepancies. Conformity testing was introduced to separate the simulation results into acceptable and non-acceptable contributions. More specifically, a shared risk approach is used to evaluate the compliance of RT model simulations on the basis of reference data generated with the weighted ensemble averaging technique from ISO-13528. However, using concepts from legal metrology, the uncertainty of this reference solution will be shown to prevent a confident assessment of model performance with respect to the selected tolerance intervals. As an alternative, guarded risk decision rules will be presented to account explicitly for the uncertainty associated with the reference and candidate methods. Both guarded acceptance and guarded rejection approaches are used to make confident statements about the acceptance and/or rejection of RT model simulations with respect to the predefined tolerance intervals.

The OLIVE (On Line Interactive Validation Exercise) platform is dedicated to the validation of global biophysical products such as LAI (Leaf Area Index) and FAPAR (Fraction of Absorbed Photosynthetically Active Radiation). It was developed under the framework of the CEOS (Committee on Earth Observation Satellites) Land Product Validation (LPV) sub-group. OLIVE has three main objectives: (i) to provide a consistent and centralized information on the definition of the biophysical variables, as well as a description of the main available products and their performances (ii) to provide transparency and traceability by an online validation procedure compliant with the CEOS LPV and QA4EO (Quality Assurance for Earth Observation) recommendations (iii) and finally, to provide a tool to benchmark new products, update product validation results and host new ground measurement sites for accuracy assessment. The functionalities and algorithms of OLIVE are described to provide full transparency of its procedures to the community. The validation process and typical results are illustrated for three FAPAR products: GEOV1 (VEGETATION sensor), MGVIo (MERIS sensor) and MODIS collection 5 FPAR. OLIVE is available on the European Space Agency CAL/VAL portal), including full documentation, validation exercise results, and product extracts.