Understanding crop phenology is crucial for predicting crop yields and identifying potential risks to food security. The objective was to investigate the effectiveness of satellite sensor data, compared to field observations and proximal sensing, in detecting crop phenological stages. Time series data from 122 winter wheat, 99 silage maize, and 77 late potato fields were analyzed during 2015–2017. The spectral signals derived from Digital Hemispherical Photographs (DHP), Disaster Monitoring Constellation (DMC), and Sentinel-2 (S2) were crop-specific and sensor-independent. Models fitted to sensor-derived fAPAR (fraction of absorbed photosynthetically active radiation) demonstrated a higher goodness of fit as compared to fCover (fraction of vegetation cover), with the best model fits obtained for maize, followed by wheat and potato. S2-derived fAPAR showed decreasing variability as the growing season progressed. The use of a double sigmoid model fit allowed defining inflection points corresponding to stem elongation (upward sigmoid) and senescence (downward sigmoid), while the upward endpoint corresponded to canopy closure and the maximum values to flowering and fruit development. Furthermore, increasing the frequency of sensor revisits is beneficial for detecting short-duration crop phenological stages. The results have implications for data assimilation to improve crop yield forecasting and agri-environmental modeling.

In this upcoming Common Agricultural Policy (CAP) reform, the use of satellite imagery is taking an increasing role for improving the Integrated Administration and Control System (IACS). Considering the operational aspect of the CAP monitoring process, the use of Sentinel-1 SAR (Synthetic Aperture Radar) images is highly relevant, especially in regions with a frequent cloud cover, such as Belgium. Indeed, SAR imagery does not depend on sunlight and is barely affected by the presence of clouds. Moreover, the SAR signal is particularly sensitive to the geometry and the water content of the target. Crop identification is often a pre-requisite to monitor agriculture at parcel level (ploughing, harvest, grassland mowing, intercropping, etc.) The main goal of this study is to assess the performances and constraints of a SAR-based crop classification in an operational large-scale application. The Random Forest object-oriented classification model is built on Sentinel-1 time series from January to August 2020 only. It can identify crops in the Walloon Region (south part of Belgium) with high performance: 93.4% of well-classified area, representing 88.4% of the parcels. Among the 48 crop groups, the six most represented ones get a F1-score higher or equal to 84%. Additionally, this research documents how the classification performance is affected by different parameters: the SAR orbit, the size of the training dataset, the use of different internal buffers on parcel polygons before signal extraction, the set of explanatory variables, and the period of the time series. In an operational context, this allows to choose the right balance between classification accuracy and model complexity. A key result is that using a training dataset containing only 3.2% of the total number of parcels allows to correctly classify 91.7% of the agricultural area. The impact of rain and snow is also discussed. Finally, this research analyses how the classification accuracy depends on some characteristics of the parcels like their shape or size. This allows to assess the relevance of the classification depending on those characteristics, as well as to identify a subset of parcels for which the global accuracy is higher.

Intra-field heterogeneity of soil properties, such as soil organic carbon (SOC), nitrogen (N), phosphorous (P), exchangeable cations, pH, or soil texture, is a function of complex interactions between biological factors, physical factors, and historic agricultural management. Mapping the crop growth and final yield heterogeneity and quantifying their link with soil properties can contribute to an optimization of amendment/fertilizer application and crop yield in a management variable zones (MVZ) approach. To this end, we studied a field of 17 ha consisting of four former fields that were merged in early 2017 and cropped with winter wheat in 2018. Historical management practices data were collected. The topsoil characteristics were analyzed by grid-based sampling and kriged to create maps. We tested the capacity of a multispectral MicaSense^® RedEdge-M^TM camera sensor embedded on an unmanned aerial vehicle (UAV) to map in-season growth of winter wheat. Relating several vegetation indices (VIs) to the plant area index (PAI) measured in the field highlighted the red-edge NDVI (RENDVI) as the most suitable to follow the crop growth throughout the growing season. The georeferenced final grain yield of the winter wheat was measured by a combine harvester. The spatial patterns in RENDVI at three phenological stages were mapped and analyzed together with the yield map. For each of these images a conditional inference forest (CI-forest) algorithm was used to identify the soil properties significantly influencing these spatial patterns. Historical management practices of the four former fields have induced significant heterogeneity in soil properties and crop growth. The spatial patterns of RENDVI are rather constant over time and their Spearman rank correlation with yield is similar along the growing season (r ≃ 0.7). Soil properties explain between 87% (mid-March) to 78% (mid-May) of the variance in RENDVI throughout the growing season, as well as 66% of the variance in yield. The pH and exchangeable K are the most significant factors explaining from 15 to 26% of the variance in crop growth. The methodology proposed in this paper to quantify the importance of soil parameters based on the CI-forest algorithm can contribute to a better management of amendment/fertilizer inputs by stressing the most important parameters to take into consideration for site-specific management. We also showed that heterogeneity induced by the soil properties can be described by a crop map early in the season and that this crop map can be used to optimize soil sampling and thus amendment/fertilizer management.

The orange wheat blossom midge, Sitodiplosis mosellana, and the yellow wheat blossom midge, Contarinia tritici, are major pests of wheat crops. In this context, it is essential to assess the susceptibility of wheat varieties to these pests and to identify tolerance or resistance mechanisms. This is commonly done by counting larvae collected from infested wheat heads, but manual counting is labor-intensive and prone to errors. This study presents a deep learning–based method for the automatic detection and counting of Sitodiplosis mosellana and Contarinia tritici larvae in RGB images acquired with smartphones. A dataset of 254 images containing 48,920 annotated larvae was generated under diverse acquisition conditions. Several YOLO-based object detection architectures were evaluated to identify the most effective configuration. The best-performing model (YOLOv26m, input size 1280 × 1280) achieved high detection performance on the test set, with an F1-score of 0.972 and an mAP50 of 0.982. Counting performance was satisfying, with a mean absolute error (MAE) of 3.000 larvae per image and a relative counting error (CE) of 1.828%. The model successfully distinguished between the two visually similar species, although slightly better performance was observed for S. mosellana (CE of 2.579% against 3.306% for C.tritici), likely due to class imbalance in the training data. This study demonstrates the effectiveness of recent YOLO architectures for detecting small, numerous, and clustered objects in complex environments. The trained model, code, and labeled dataset are made publicly available to facilitate reproducibility and support the development of automated counting methods for other insect species.