Recent advances in remote sensing technologies and the cost reduction of surveying, along with the importance of natural resources management, present new opportunities for mapping land cover at a very high resolution over large areas. This paper proposes and applies a framework to update hyperspatial resolution (<1 m) land thematic mapping over large areas by handling multi-source and heterogeneous data. This framework deals with heterogeneity both from observation and the targeted features. First, observation diversity comes from the different platform and sensor types (25-cm passive optical and 1-m LiDAR) as well as the different instruments (three cameras and two LiDARs) used in heterogeneous observation conditions (date, time, and sun angle). Second, the local heterogeneity of the targeted features results from their within-type diversity and neighborhood effects. This framework is applied to surface water bodies in the southern part of Belgium (17,000 km²). This makes it possible to handle both observation and landscape contextual heterogeneity by mapping observation conditions, stratifying spatially and applying ad hoc classification procedures. The proposed framework detects 83% of the water bodies—if swimming pools are not taken into account—and more than 98% of those water bodies greater than 100 m², with an edge accuracy below 1 m over large areas. Full article

Accurate maps of surface water extent are of paramount importance for water management, satellite data processing and climate modeling. Several maps of water bodies based on remote sensing data have been released during the last decade. Nonetheless, none has a truly (90 ${}^{\circ }$ N/90 ${}^{\circ }$ S) global coverage while being thoroughly validated. This paper describes a global, spatially-complete (void-free) and accurate mask of inland/ocean water for the 2000–2012 period, built in the framework of the European Space Agency (ESA) Climate Change Initiative (CCI). This map results from the synergistic combination of multiple individual SAR and optical water body and auxiliary datasets. A key aspect of this work is the original and rigorous stratified random sampling designed for the quality assessment of binary classifications where one class is marginally distributed. Input and consolidated products were assessed qualitatively and quantitatively against a reference validation database of 2110 samples spread throughout the globe. Using all samples, overall accuracy was always very high among all products, between $98\%$ and $100\%$ . The CCI global map of open water bodies provided the best water class representation (F-score of $89\%$ ) compared to its constitutive inputs. When focusing on the challenging areas for water bodies’ mapping, such as shorelines, lakes and river banks, all products yielded substantially lower accuracy figures with overall accuracies ranging between $74\%$ and $89\%$ . The inland water area of the CCI global map of open water bodies was estimated to be 3.17 million km ${}^2$ ± 0.24 million km ${}^2$ . The dataset is freely available through the ESA CCI Land Cover viewer. Full article

Changes in the snow cover extent are both a cause and a consequence of climate change. Optical remote sensing with heliosynchronous satellites currently provides snow cover data at high spatial resolution with daily revisiting time. However, high latitude image acquisition is limited because reflective sensors of many satellites are switched off at high solar zenith angles (SZA) due to lower signal quality. In this study, the relevance and reliability of high SZA acquisition are objectively quantified in the purpose of high latitude snow cover detection, thanks to the PROBA-V (Project for On-Board Autonomy-Vegetation) satellite. A snow cover extent classification based on Normalized Difference Snow Index (NDSI) and Normalized Difference Vegetation Index (NDVI) has been performed for the northern hemisphere on latitudes between 55°N and 75°N during the 2015–2016 winter season. A stratified probabilistic sampling was used to estimate the classification accuracy. The latter has been evaluated among eight SZA intervals to determine the maximum usable angle. The global overall snow classification accuracy with PROBA-V, 82% ± 4%, was significantly larger than the MODIS (Moderate-resolution Imaging Spectroradiometer) snow cover extent product (75% ± 4%). User and producer accuracy of snow are above standards and overall accuracy is stable until 88.5° SZA. These results demonstrate that optical remote sensing data can still be used with large SZA. Considering the relevance of snow cover mapping for ecology and climatology, the data acquisition at high solar zenith angles should be continued by PROBA-V. Full article

Soil fertility in smallholder farming areas is known to vary strongly on multiple scales. This study measures the sensitivity of the recorded satellite signal to on-farm soil fertility treatments applied to five crop types, and quantifies this fertilization effect with respect to within-field variation, between-field variation and field position in the catena. Plant growth was assessed in 5–6 plots per field in 48 fields located in the Sudano-Sahelian agro-ecological zone of southeastern Mali. A unique series of Very High Resolution (VHR) satellite and Unmanned Aerial Vehicle (UAV) images were used to calculate the Normalized Difference Vegetation Index (NDVI). In this experiment, for half of the fields at least 50% of the NDVI variance within a field was due to fertilization. Moreover, the sensitivity of NDVI to fertilizer application was crop-dependent and varied through the season, with optima at the end of August for peanut and cotton and early October for sorghum and maize. The influence of fertilizer on NDVI was comparatively small at the landscape scale (up to 35% of total variation), relative to the influence of other components of variation such as field management and catena position. The NDVI response could only partially be benchmarked against a fertilization reference within the field. We conclude that comparisons of the spatial and temporal responses of NDVI, with respect to fertilization and crop management, requires a stratification of soil catena-related crop growth conditions at the landscape scale. Full article

Land cover and land use maps derived from satellite remote sensing imagery are critical to support biodiversity and conservation, especially over large areas. With its 10 m to 20 m spatial resolution, Sentinel-2 is a promising sensor for the detection of a variety of landscape features of ecological relevance. However, many components of the ecological network are still smaller than the 10 m pixel, i.e., they are sub-pixel targets that stretch the sensor’s resolution to its limit. This paper proposes a framework to empirically estimate the minimum object size for an accurate detection of a set of structuring landscape foreground/background pairs. The developed method combines a spectral separability analysis and an empirical point spread function estimation for Sentinel-2. The same approach was also applied to Landsat-8 and SPOT-5 (Take 5), which can be considered as similar in terms of spectral definition and spatial resolution, respectively. Results show that Sentinel-2 performs consistently on both aspects. A large number of indices have been tested along with the individual spectral bands and target discrimination was possible in all but one case. Overall, results for Sentinel-2 highlight the critical importance of a good compromise between the spatial and spectral resolution. For instance, the Sentinel-2 roads detection limit was of 3 m and small water bodies are separable with a diameter larger than 11 m. In addition, the analysis of spectral mixtures draws attention to the uneven sensitivity of a variety of spectral indices. The proposed framework could be implemented to assess the fitness for purpose of future sensors within a large range of applications. Full article

Accurate and timely information on the global cropland extent is critical for food security monitoring, water management and earth system modeling. Principally, it allows for analyzing satellite image time-series to assess the crop conditions and permits isolation of the agricultural component to focus on food security and impacts of various climatic scenarios. However, despite its critical importance, accurate information on the spatial extent, cropland mapping with remote sensing imagery remains a major challenge. Following an exhaustive identification and collection of existing land cover maps, a multi-criteria analysis was designed at the country level to evaluate the fitness of a cropland map with regards to four dimensions: its timeliness, its legend, its resolution adequacy and its confidence level. As a result, a Unified Cropland Layer that combines the fittest products into a 250 m global cropland map was assembled. With an evaluated accuracy ranging from 82% to 95%, the Unified Cropland Layer successfully improved the accuracy compared to single global products. Full article

Early warning systems for food security require accurate and up-to-date information on the location of major crops in order to prevent hazards. A recent systematic analysis of existing cropland maps identified priority areas for cropland mapping and highlighted a major need for the Sahelian and Sudanian agrosystems. This paper proposes a knowledge-based approach to map cropland in the Sahelian and Sudanian agrosystems that benefits from the 100-m spatial resolution of the recent PROBA-V sensor. The methodology uses five temporal features characterizing crop development throughout the vegetative season to optimize cropland discrimination. A feature importance analysis validates the efficiency of using a diversity of temporal features. The fully-automated method offers the first cropland map at 100-m using the PROBA-V sensor with an overall accuracy of 84% and an F-score for the cropland class of 74%. The improvements observed compared to existing cropland products are related to the hectometric resolution, to the methodology and to the quality of the labeling layer from which reliable training samples were automatically extracted. Classification errors are mainly explained by data availability and landscape fragmentation. Further improvements are expected with the upcoming enhanced cloud screening of the PROBA-V sensor. Full article

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. Full article

In order to monitor crop growth along the season with synthetic aperture radar (SAR) images, radiative transfer models were developed to retrieve key biophysical parameters, such as the Leaf Area Index (LAI). The semi-empirical water cloud model (WCM) can be used to estimate LAI values from SAR data and surface soil moisture information. Nevertheless, instability problems can occur during the model calibration, which subsequently reduce its transferability in both time and space. To avoid these ill-posed cases, three calibration methodologies are benchmarked in the present study. The accuracy of the retrieved LAI values for each methodology was analyzed, as well as the sensitivity of the signal to LAI for different soil moisture values. The sensitivity of the cross-polarization was highlighted especially for high LAI. The VV polarization was found sensitive for LAI values inferior to 2 m 2 /m 2 . Given the differential sensitivity of the C-band backscatter to maize canopies in each polarization, a Bayesian fusion of the LAI estimates in linear polarizations was developed. This fusion gives lower weights to estimates with a high uncertainty. This method systematically reduces the error and its associated variance. When considering all polarizations, the RMSE on LAI estimation decreased by 0.32 m 2 /m 2 , i.e., one fourth of the error value, as compared to the best estimation from a single polarization, and the associated uncertainty was reduced by a factor of two. Focusing on the two most sensitive polarizations to maize canopies (VV-HV), the error diminished by a third. This fusion framework shows thus a great potential to improve the accuracy and reliability of LAI retrieval of C-band quad-polarized data, as well as dual-polarized data, such as Sentinel-1. Full article

The leaf area index (LAI) and the fraction of photosynthetically active radiation absorbed by green vegetation (FAPAR) are essential climatic variables in surface process models. FCOVER is also important to separate vegetation and soil for energy balance processes. Currently, several LAI, FAPAR and FCOVER satellite products are derived moderate to coarse spatial resolution. The launch of Sentinel-2 in 2015 will provide data at decametric resolution with a high revisit frequency to allow quantifying the canopy functioning at the local to regional scales. The aim of this study is thus to evaluate the performances of a neural network based algorithm to derive LAI, FAPAR and FCOVER products at decametric spatial resolution and high temporal sampling. The algorithm is generic, i.e., it is applied without any knowledge of the landcover. A time series of high spatial resolution SPOT4_HRVIR (16 scenes) and Landsat 8 (18 scenes) images acquired in 2013 over the France southwestern site were used to generate the LAI, FAPAR and FCOVER products. For each sensor and each biophysical variable, a neural network was first trained over PROSPECT+SAIL radiative transfer model simulations of top of canopy reflectance data for green, red, near-infra red and short wave infra-red bands. Our results show a good spatial and temporal consistency between the variables derived from both sensors: almost half the pixels show an absolute difference between SPOT and LANDSAT estimates of lower that 0.5 unit for LAI, and 0.05 unit for FAPAR and FCOVER. Finally, downward-looking digital hemispherical cameras were completed over the main land cover types to validate the accuracy of the products. Results show that the derived products are strongly correlated with the field measurements (R² > 0.79), corresponding to a RMSE = 0.49 for LAI, RMSE = 0.10 (RMSE = 0.12) for black-sky (white sky) FAPAR and RMSE = 0.15 for FCOVER. It is concluded that the proposed generic algorithm provides a good basis to monitor the seasonal variation of the vegetation biophysical variables for important crops at decametric resolution. Full article

Illegal occupation of argan forest parcels by local households is a new phenomenon in South West Morocco. This is primarily due to the weakening of traditional common control systems and to the boom of the argan oil price. The scope of this work is to develop a decision support system based on dynamic spatial modelling, allowing to anticipate the land tenure dynamics and their impact on forest stand degradation under different policy scenarios. The model simulates the change of land possession by locals and the forest stand degradation levels. The methodological approach combines a Markov chain analysis (MCA) with stakeholders’ preferences for land tenure. First, parcels’ transition probabilities are computed using the MCA. Second, the acquiring suitability map is derived from multi-criteria evaluation procedure (AHP) using biophysical and socio-economic data. Finally, uncertainty is introduced in the simulation based on probabilistic analysis for supporting socio-economic diversity and non-mechanistic human behavior. The modelling approach was successfully used to compare three scenarios: business as usual (continuation of illegal acquiring), total disengagement of the population and private/public partnership with incentives for restoring argan parcel. The model yields geographic information about (i) the magnitude of the on-going process; (ii) the potential occurrence of land use conflicts induced by new policies; and (iii) the location of land conservation or degradation hot-spots. The outcomes of the “business as usual” and of the “total disengagement” models were similar over a 30-year simulation period: in both cases, the proportion of “highly degraded” parcels was doubled and the number of “quite degraded” parcels was increased by 50%. On the other hand, should the private/public partnership effectively work, about 40% of the parcels could be restored to a sustainable level. Full article

Desert locust swarms intermittently damage crops and pastures in sixty countries from Africa to western Asia, threatening the food security of 10% of the world’s population. During the 20th century, desert locust control operations began organizing, and nowadays, they are coordinated by the Food and Agriculture Organization (FAO), which promotes a preventative strategy based on early warning and rapid response. This strategy implies a constant monitoring of the populations and of the ecological conditions favorable to their development. Satellite remote sensing can provide a near real-time monitoring of these conditions at the continental scale. Thus, the desert locust control community needs a reliable detection of green vegetation in arid and semi-arid areas as an indicator of potential desert locust habitat. To meet this need, a colorimetric transformation has been developed on both SPOT-VEGETATION and MODIS data to produce dynamic greenness maps. After their integration in the daily locust control activities, this research aimed at assessing those dynamic greenness maps from the producers’ and the users’ points of view. Eight confusion matrices and Pareto boundaries were derived from high resolution reference maps representative of the temporal and spatial diversity of Mauritanian habitats. The dynamic greenness maps were found to be accurate in summer breeding areas (F-score = 0.64–0.87), but accuracy dropped in winter breeding areas (F-score = 0.28–0.40). Accuracy is related to landscape fragmentation (R2 = 0.9): the current spatial resolution remains too coarse to resolve complex fragmented patterns and accounts for a substantial (60%) part of the error. The exploitation of PROBA-V 100-m images at the finest resolution (100-m) would enhance by 20% the vegetation detection in fragmented habitat. A survey revealed that end-users are satisfied with the product and find it fit for monitoring, thanks to an intuitive interpretation, leading to more efficiency. Full article

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. Full article

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. Full article

With the ever-increasing number of satellites and the availability of data free of charge, the integration of multi-sensor images in coherent time series offers new opportunities for land cover and crop type classification. This article investigates the potential of structural biophysical variables as common parameters to consistently combine multi-sensor time series and to exploit them for land/crop cover classification. Artificial neural networks were trained based on a radiative transfer model in order to retrieve high resolution LAI, FAPAR and FCOVER from Landsat-8 and SPOT-4. The correlation coefficients between field measurements and the retrieved biophysical variables were 0.83, 0.85 and 0.79 for LAI, FAPAR and FCOVER, respectively. The retrieved biophysical variables’ time series displayed consistent average temporal trajectories, even though the class variability and signal-to-noise ratio increased compared to NDVI. Six random forest classifiers were trained and applied along the season with different inputs: spectral bands, NDVI, as well as FAPAR, LAI and FCOVER, separately and jointly. Classifications with structural biophysical variables reached end-of-season overall accuracies ranging from 73%–76% when used alone and 77% when used jointly. This corresponds to 90% and 95% of the accuracy level achieved with the spectral bands and NDVI. FCOVER appears to be the most promising biophysical variable for classification. When assuming that the cropland extent is known, crop type classification reaches 89% with spectral information, 87% with the NDVI and 81%–84% with biophysical variables. Full article

Timely and accurate information on the global cropland extent is critical for applications in the fields of food security, agricultural monitoring, water management, land-use change modeling and Earth system modeling. On the one hand, it gives detailed location information on where to analyze satellite image time series to assess crop condition. On the other hand, it isolates the agriculture component to focus food security monitoring on agriculture and to assess the potential impacts of climate change on agricultural lands. The cropland class is often poorly captured in global land cover products due to its dynamic nature and the large variety of agro-systems. The overall objective was to evaluate the current availability of cropland datasets in order to propose a strategic planning and effort distribution for future cropland mapping activities and, therefore, to maximize their impact. Following a very comprehensive identification and collection of national to global land cover maps, a multi-criteria analysis was designed at the country level to identify the priority areas for cropland mapping. As a result, the analysis highlighted priority regions, such as Western Africa, Ethiopia, Madagascar and Southeast Asia, for the remote sensing community to focus its efforts. A Unified Cropland Layer at 250 m for the year 2014 was produced combining the fittest products. It was assessed using global validation datasets and yields an overall accuracy ranging from 82%–94%. Masking cropland areas with a global forest map reduced the commission errors from 46% down to 26%. Compared to the GLC-Share and the International Institute for Applied Systems Analysis-International Food Policy Research Institute (IIASA-IFPRI) cropland maps, significant spatial disagreements were found, which might be attributed to discrepancies in the cropland definition. This advocates for a shared definition of cropland, as well as global validation datasets relevant for the agriculture class in order to systematically assess existing and future cropland maps. Full article

Desert locusts (Schistocerca gregaria) represent a major threat for agro-pastoral resources and food security over almost 30 million km2 from northern Africa to the Arabian peninsula and India. Given the differential food preferences of this insect pest and the extent and remoteness of the their distribution area, near-real-time remotely-sensed information on potential habitats support control operations by narrowing down field surveys to areas favorable for their development and prone to gregarization and outbreaks. The development of dynamic greenness maps, which detect the onset of photosynthetic vegetation, allowed national control centers to identify potential habitats to survey, as locusts prefer green and fresh vegetation. Their successful integration into the daily control operations led to a new need: the near-real-time identification of the onset of dryness, a synonym for the loss of habitat attractiveness, likely to be abandoned by locusts. The timely availability of this information would enable control centers to focus their surveys on areas more prone to gregarization, leading to more efficiency in the allocation of resources and in decision making. In this context, this work developed an original method to detect in near-real-time the onset of vegetation senescence. The design of the detection relies on the temporal behavior of two indices: the Normalized Difference Vegetation Index, depending on the green vegetation, and the Normalized Difference Tillage Index, sensitive to both green and dry vegetation. The method is demonstrated in Mauritania, an ever-affected country, with 10-day MODIS mean composites for the years 2010 and 2011. The discrimination performance of three classes (“growth”, “density reduction” and “drying”) were analyzed for three classification methods: maximum likelihood (61.4% of overall accuracy), decision tree (71.5%) and support vector machine (72.3%). The classification accuracy is heterogeneous in both time and space and is affected by several factors, such as vegetation density, the north-south climatic gradient and the relief. Smoothing the vegetation time series resulted in an increase of the overall accuracy of about 5% at the expense of a loss in timeliness of ten days. To simulate near-real-time monitoring conditions, the decision tree was applied to the decade of 2010. Overall, the seasonal vegetation cycle appeared clear and consistent. The results obtained pave the way for an operational implementation of the senescence dynamic mapping and, consequently, to further strengthen the capacity of the locust control management. Full article

Land cover is one of the essential climate variables of the ESA Climate Change Initiative (CCI). In this context, the Land Cover CCI (LC CCI) project aims at building global land cover maps suitable for climate modeling based on Earth observation by satellite sensors. The challenge is to generate a set of successive maps that are both accurate and consistent over time. To do so, operational methods for the automated classification of optical images are investigated. The proposed approach consists of a locally trained classification using an automated selection of training samples from existing, but outdated land cover information. Combinations of local extraction (based on spatial criteria) and self-cleaning of training samples (based on spectral criteria) are quantitatively assessed. Two large study areas, one in Eurasia and the other in South America, are considered. The proposed morphological cleaning of the training samples leads to higher accuracies than the statistical outlier removal in the spectral domain. An optimal neighborhood has been identified for the local sample extraction. The results are coherent for the two test areas, showing an improvement of the overall accuracy compared with the original reference datasets and a significant reduction of macroscopic errors. More importantly, the proposed method partly controls the reliability of existing land cover maps as sources of training samples for supervised classification. Full article