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.

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.

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) Sentinel1 constellation provides synthetic aperture radar (SAR) images coverage with a 6 days revisit period at a high spatial resolution of pixel spacing 20 m. Sentinel-1 data are considerable useful, as they provide valuable information of the vegetation cover. The objective of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for rice height and dry biomass retrievals. To do this, we train Sentinel1 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 multi-temporal 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 an intensity radar data 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 R² = 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 R² = 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

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.