The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience, a few avenues for improvements have been identified regarding data size, head diversity, and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and complemented by adding 1722 images from 5 additional countries, allowing for 81,553 additional wheat heads. We now release in 2021 a new version of the Global Wheat Head Detection dataset, which is bigger, more diverse, and less noisy than the GWHD_2020 version.

Yield prediction is of great significance in agricultural production. Remote sensing technology based on unmanned aerial vehicles (UAVs) offers the capacity of non-intrusive crop yield prediction with low cost and high throughput. In this study, a winter wheat field experiment with three levels of irrigation (T1 = 240 mm, T2 = 190 mm, T3 = 145 mm) was conducted in Henan province. Multispectral vegetation indices (VIs) and canopy water stress indices (CWSI) were obtained using an UAV equipped with multispectral and thermal infrared cameras. A framework combining a long short-term memory neural network and random forest (LSTM-RF) was proposed for predicting wheat yield using VIs and CWSI from multi-growth stages as predictors. Validation results showed that the R² of 0.61 and the RMSE value of 878.98 kg/ha was achieved in predicting grain yield using LSTM. LSTM-RF model obtained better prediction results compared to the LSTM with n R² of 0.78 and RMSE of 684.1 kg/ha, which is equivalent to a 22% reduction in RMSE. The results showed that LSTM-RF considered both the time-series characteristics of the winter wheat growth process and the non-linear characteristics between remote sensing data and crop yield data, providing an alternative for accurate yield prediction in modern agricultural management.

Soil microstructure is an important feature that controls soil behaviour at the macroscale. This microstructure depends on the sample preparation method and evolves during saturation and loading. This paper investigates the effects of compaction water content, drying techniques adopted prior to performing porosimetry, saturation and loading on the evolution of the microstructure of a silty soil. Mercury intrusion porosimetry is used to obtain the pore-size distribution at different states of soil presenting single and double porosity. It is observed that in presence of aggregates (obtained from a compaction on the dry side of optimum), the bimodal pore-size distribution is not significantly affected by the saturation process at zero stress. This feature of behaviour is quite specific to low plasticity silty soil. Conversely, loading under saturated conditions has a more significant effect on the pore-size distribution. This bimodal distribution converges into a single mode of pore size when the stress is significantly greater than the apparent preconsolidation pressure. The observed experimental results are interpreted in the light of pore-size distribution evolution during saturation and loading.