Explore the vast range of titles available.

The development and improvement of methods to map agricultural land cover are currently major challenges, especially for radar images. This is due to the speckle noise nature of radar, leading to a less intensive use of radar rather than optical images. The European Space Agency Sentinel-1 constellation, which recently became operational, is a satellite system providing global coverage of Synthetic Aperture Radar (SAR) with a 6-days revisit period at a high spatial resolution of about 20 m. These data are valuable, as they provide spatial information on agricultural crops. The aim of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques. The analysis is carried out on multitemporal Sentinel-1 data over an area in Camargue, France. The data set was processed in order to produce an intensity radar data stack from May 2017 to September 2017. We improved this radar time series dataset by exploiting temporal filtering to reduce noise, while retaining as much as possible the fine structures present in the images. We revealed that even with classical machine learning approaches (K nearest neighbors, random forest, and support vector machines), good performance classification could be achieved with F-measure/Accuracy greater than 86% and Kappa coefficient better than 0.82. We found that the results of the two deep recurrent neural network (RNN)-based classifiers clearly outperformed the classical approaches. Finally, our analyses of the Camargue area results show that the same performance was obtained with two different RNN-based classifiers on the Rice class, which is the most dominant crop of this region, with a F-measure metric of 96%. These results thus highlight that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series.

This study proposes an effective method to map rice crops using the Sentinel-1 SAR (Synthetic Aperture Radar) time series over the Camargue region, Southern France. First, the temporal behavior of the SAR backscattering coefficient over 832 plots containing different crop types was analyzed. Through this analysis, the rice cultivation was identified using metrics derived from the Gaussian profile of the VV/VH time series (3 metrics), the variance of the VV/VH time series (one metric), and the slope of the linear regression of the VH time series (one metric). Using the derived metrics, rice plots were mapped through two different approaches: decision tree and Random Forest (RF). To validate the accuracy of each approach, the classified rice map was compared to the available national data. Similar high overall accuracy was obtained using both approaches. The overall accuracy obtained using a simple decision tree reached 96.3%, whereas an overall accuracy of 96.6% was obtained using the RF classifier. The approach, therefore, provides a simple yet precise and powerful tool to map paddy rice areas.

This study aimed to propose an accurate and cost-effective analytical approach for the delineation of fruit trees in orchards, vineyards, and olive groves in Southern France, considering two locations. A classification based on phenology metrics (PM) derived from the Sentinel-2 time series was developed to perform the classification. The PM were computed by fitting a double logistic model on temporal profiles of vegetation indices to delineate orchard and vineyard classes. The generated PM were introduced into a random forest (RF) algorithm for classification. The method was tested on different vegetation indices, with the best results obtained with the leaf area index. To delineate the olive class, the temporal features of the green chlorophyll vegetation index were found to be the most appropriate. Obtained overall accuracies ranged from 89–96% and a Kappa of 0.86–0.95 (2016–2021), respectively. These accuracies are much better than applying the RF algorithm to the LAI time series, which led to a Kappa ranging between 0.3 and 0.52 and demonstrates the interest in using phenological traits rather than the raw time series of the remote sensing data. The method can be well reproduced from one year to another. This is an interesting feature to reduce the burden of collecting ground-truth information. If the method is generic, it needs to be calibrated in given areas as soon as a phenology shift is expected.

This study aimed to develop an approach using Sentinel-1 synthetic aperture radar (SAR) data and the Optirrig crop growth and irrigation model to detect irrigation dates and amounts for maize crops in the Occitanie region, Southern France. The surface soil moisture (SSM) derived from SAR data was analyzed for changes indicating irrigation events at the plot scale in four reference plots located in Montpellier (P1) and Tarbes (P2, P3, and P4). As rain most likely covers several square kilometers, while irrigation is decided at the plot scale, a difference between SSM signals at the grid scale (10 km × 10 km) and plot scale is a clear indication of a recent irrigation event. Its date and amount are then sought by forcing irrigation dates and amounts in Optirrig, selecting the most relevant (date, amount) combination from an appropriate criterion. As the observed SSM values hold for a depth of a few centimeters, while the modeled SSM values hold for exactly 10 cm, the best irrigation combination is the one that gives similar relative changes in SSM values rather than similar SSM values. The irrigation dates were detected with an overall accuracy (recall) of 86.2% and a precision of 85.7%, and thus, with relatively low numbers of missed or false irrigation detections, respectively. The performance of the method in detecting seasonal irrigation amounts varied with climatic conditions. For the P1 plot in the semi-arid climate of Montpellier, the mean absolute error percentage (MAE%) was 16.4%, showing a higher efficiency when compared with the humid climate of Tarbes (P2, P3, and P4 plots), where a higher MAE% of 50% was recorded, indicating a larger discrepancy between the detected and actual irrigation amounts. The limitations of the proposed method can be attributed to the characteristics of the Sentinel-1 constellation, including its 6-day revisit time and signal penetration challenges in dense maize cover, as well as the mismatch between the parameterization of Optirrig for SSM simulations and the actual irrigation practices followed by farmers. Despite these weaknesses, the results demonstrated the relevance of combining Optirrig and S1 SAR-derived SSM data for field-scale detection of irrigation dates and, potentially, irrigation amounts.

The research and improvement of methods to be used for crop monitoring are currently major challenges, especially for radar images due to their speckle noise nature. The European Space Agency’s (ESA) Sentinel-1 constellation provides synthetic aperture radar (SAR) images coverage with a 6-day revisit period at a high spatial resolution of pixel spacing of 20 m. Sentinel-1 data are considerably useful, as they provide valuable information of the vegetation cover. The objective of this work is to study the capabilities of multitemporal radar images for rice height and dry biomass retrievals using Sentinel-1 data. To do this, we train Sentinel-1 data against ground measurements with classical machine learning techniques (Multiple Linear Regression (MLR), Support Vector Regression (SVR) and Random Forest (RF)) to estimate rice height and dry biomass. The study is carried out on a multitemporal Sentinel-1 dataset acquired from May 2017 to September 2017 over the Camargue region, southern France. The ground in-situ measurements were made in the same period to collect rice height and dry biomass over 11 rice fields. The images were processed in order to produce a radar stack in C-band including dual-polarization VV (Vertical receive and Vertical transmit) and VH (Vertical receive and Horizontal transmit) data. We found that non-parametric methods (SVR and RF) had a better performance over the parametric MLR method for rice biophysical parameter retrievals. The accuracy of rice height estimation showed that rice height retrieval was strongly correlated to the in-situ rice height from dual-polarization, in which Random Forest yielded the best performance with correlation coefficient R 2 = 0.92 and the root mean square error (RMSE) 16% (7.9 cm). In addition, we demonstrated that the correlation of Sentinel-1 signal to the biomass was also very high in VH polarization with R 2 = 0.9 and RMSE = 18% (162 g·m − 2 ) (with Random Forest method). Such results indicate that the highly qualified Sentinel-1 radar data could be well exploited for rice biomass and height retrieval and they could be used for operational tasks.

The assessment of rice yield at territory level is important for strategic economic decisions. Assessing spatial and temporal yield variability at regional scale is difficult because of the numerous factors involved, including agricultural practices, phenological calendars, and environmental contexts. New remote sensing data acquired at decametric resolution (Sentinel missions) can provide information on this spatial variability. The study objective was thus to evaluate the potential of Sentinel-2 images for monitoring rice cropping systems and yield from farm to region scales. The approach considered both observations and modeling. In-depth farmers surveys were carried out in the Camargue region, Southeastern France. The novelty was to use operational tools (BVNET and PHENOTB) to compute leaf area index, to daily interpolate this biophysical variable from 44 images acquired in 2016 and 2017 for each rice field, and to derive key phenological parameters from the analysis of the temporal profiles. The STICS crop model was spatially used, considering the biophysical variables derived from remote sensing. We tested four simulation strategies, differing in the integration intensity of remote sensing information into the model. Results have shown that (1) Sentinel-2 data allowed distinguishing early and late rice varieties. (2) The phenological stages mapped at the regional level allowed to better understand the agricultural practices of farmers. (3) The assimilation of remote sensing data to the STICS crop model significantly improved yield estimation and provided useful information on the spatial variability observed at regional scale. It was the first time that Sentinel-2 data are used with STICS crop model to assess rice yield at both farm and regional scale in the Camargue area. The proposed method is based on free open data and free access model, easily reproducible in other environmental contexts.

Conventional methods of crop mapping need ground truth information to train the classifier. Thanks to the frequent acquisition allowed by recent satellite missions (Sentinel 2), we can identify temporal patterns that depend on both phenology and crop management. Some of these patterns are specific to a given crop and thus can be used to map it. Thus, we can substitute ground truth information used in conventional methods with agronomic knowledge. This approach was applied to identify irrigated permanent grasslands (IPG) in the Crau area (Southern France), which play a crucial role in groundwater recharge. The grassland is managed by making three mows during the May–October period, which leads to a specific temporal pattern of leaf area index (LAI). The mowing detection algorithm was designed using the temporal LAI signal derived from Sentinel 2 observations. The algorithm includes some filtering to remove noise in the signal that might lead to false mowing detection. A pixel is considered a grassland if the number of detected mows is greater than 1. A data set covering five years (2016–2020) was used. The detection mowing number was conducted at the pixel level, and then the results were aggregated at the plot level. An evaluation data set including 780 plots was used to assess the performances of the classification. We obtained a Kappa index ranging between 0.94 and 0.99 according to the year. These results were better than other supervised classification methods that include training data sets. The analysis of land-use changes shows that misclassified plots concern grasslands managed less intensively with strong intra-parcel heterogeneity due to irrigation defects or year-round grazing. Time series analysis, therefore, allows us to understand different management practices. Real land-use change in use can be observed, but long time series are needed to confirm the change and remove ambiguities with heterogeneous grasslands.

A range of remote sensing platforms provide high spatial and temporal resolution insights which are useful for monitoring vegetation growth. Very few studies have focused on fruit orchards, largely due to the inherent complexity of their structure. Fruit trees are mixed with inter-rows that can be grassed or non-grassed, and there are no standard protocols for ground measurements suitable for the range of crops. The assessment of biophysical variables (BVs) for fruit orchards from optical satellites remains a significant challenge. The objectives of this study are as follows: (1) to address the challenges of extracting and better interpreting biophysical variables from optical data by proposing new ground measurements protocols tailored to various orchards with differing inter-row management practices, (2) to quantify the impact of the inter-row at the Sentinel pixel scale, and (3) to evaluate the potential of Sentinel 2 data on BVs for orchard development monitoring and the detection of key phenological stages, such as the flowering and fruit set stages. Several orchards in two pedo-climatic zones in southeast France were monitored for three years: four apricot and nectarine orchards under different management systems and nine cherry orchards with differing tree densities and inter-row surfaces. We provide the first comparison of three established ground-based methods of assessing BVs in orchards: (1) hemispherical photographs, (2) a ceptometer, and (3) the Viticanopy smartphone app. The major phenological stages, from budburst to fruit growth, were also determined by in situ annotations on the same fields monitored using Viticanopy. In parallel, Sentinel 2 images from the two study sites were processed using a Biophysical Variable Neural Network (BVNET) model to extract the main BVs, including the leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fraction of green vegetation cover (FCOVER). The temporal dynamics of the normalised FAPAR were analysed, enabling the detection of the fruit set stage. A new aggregative model was applied to data from hemispherical photographs taken under trees and within inter-rows, enabling us to quantify the impact of the inter-row at the Sentinel 2 pixel scale. The resulting value compared to BVs computed from Sentinel 2 gave statistically significant correlations (0.57 for FCOVER and 0.45 for FAPAR, with respective RMSE values of 0.12 and 0.11). Viticanopy appears promising for assessing the PAI (plant area index) and FCOVER for orchards with grassed inter-rows, showing significant correlations with the Sentinel 2 LAI (R2 of 0.72, RMSE 0.41) and FCOVER (R2 0.66 and RMSE 0.08). Overall, our results suggest that Sentinel 2 imagery can support orchard monitoring via indicators of development and inter-row management, offering data that are useful to quantify production and enhance resource management.

The objective of this study was to analyze the sensitivity of radar signals in the X-band in irrigated grassland conditions. The backscattered radar signals were analyzed according to soil moisture and vegetation parameters using linear regression models. A time series of radar (TerraSAR-X and COSMO-SkyMed) and optical (SPOT and LANDSAT) images was acquired at a high temporal frequency in 2013 over a small agricultural region in southeastern France. Ground measurements were conducted simultaneously with the satellite data acquisitions during several grassland growing cycles to monitor the evolution of the soil and vegetation characteristics. The comparison between the Normalized Difference Vegetation Index (NDVI) computed from optical images and the in situ Leaf Area Index (LAI) showed a logarithmic relationship with a greater scattering for the dates corresponding to vegetation well developed before the harvest. The correlation between the NDVI and the vegetation parameters (LAI, vegetation height, biomass, and vegetation water content) was high at the beginning of the growth cycle. This correlation became insensitive at a certain threshold corresponding to high vegetation (LAI ~2.5 m2/m2). Results showed that the radar signal depends on variations in soil moisture, with a higher sensitivity to soil moisture for biomass lower than 1 kg/m². HH and HV polarizations had approximately similar sensitivities to soil moisture. The penetration depth of the radar wave in the X-band was high, even for dense and high vegetation; flooded areas were visible in the images with higher detection potential in HH polarization than in HV polarization, even for vegetation heights reaching 1 m. Lower sensitivity was observed at the X-band between the radar signal and the vegetation parameters with very limited potential of the X-band to monitor grassland growth. These results showed that it is possible to track gravity irrigation and soil moisture variations from SAR X-band images acquired at high spatial resolution (an incidence angle near 30°).

A wide range of environmental applications require the monitoring of land surface temperature (LST) at frequent intervals and fine spatial resolutions, but these conditions are not offered nowadays by the available space sensors. To overcome these shortcomings, LST downscaling methods have been developed to derive higher resolution LST from the available satellite data. This research concerns the application of a data assimilation (DA) downscaling approach, the genetic particle smoother (GPS), to disaggregate Meteosat 8 LST time series (3 km × 5 km) at finer spatial resolutions. The methodology was applied over the Crau-Camargue region in Southeastern France for seven months in 2009. The evaluation of the downscaled LSTs has been performed at a moderate resolution using a set of coincident clear-sky MODIS LST images from Aqua and Terra platforms (1 km × 1 km) and at a higher resolution using Landsat 7 data (60 m × 60 m). The performance of the downscaling has been assessed in terms of reduction of the biases and the root mean square errors (RMSE) compared to prior model-simulated LSTs. The results showed that GPS allows downscaling the Meteosat LST product from 3 × 5 km2 to 1 × 1 km2 scales with a RMSE less than 2.7 K. Finer scale downscaling at Landsat 7 resolution showed larger errors (RMSE around 5 K) explained by land cover errors and inter-calibration issues between sensors. Further methodology improvements are finally suggested.