Growth and nitrogen productivity of drip-irrigated winter wheat under different nitrogen fertigation strategies in the North China Plain

Excessive application of nitrogen (N) fertilizer is the main cause of N loss and poor use efficiency in winter wheat (Triticum aestivum L.) production in the North China Plain (NCP).Drip fertigation is considered to be an effective method for improving N use efficiency and reducing losses,while the performance of drip fertigation in winter wheat is limited by poor N scheduling.A two-year field experiment was conducted to evaluate the growth,development and yield of drip-fertigated winter wheat under different split urea (46%N,240 kg ha^(-1)) applications.The six treatments consisted of five fertigation N application scheduling programs and one slow-release fertilizer (SRF) application.The five N scheduling treatments were N0–100 (0%at sowing and 100%at jointing/booting),N25–75 (25%at sowing and 75%at jointing and booting),N50–50(50%at sowing and 50%at jointing/booting),N75–25 (75%at sowing and 25 at jointing/booting),and N100–0 (100%at sowing and 0%at jointing/booting).The SRF (43%N,240 kg ha^(-1)) was only used as fertilizer at sowing.Split N application significantly (P<0.05) affected wheat grain yield,yield components,aboveground biomass (ABM),water use efficiency(WUE) and nitrogen partial factor productivity (NPFP).The N50–50 and SRF treatments respectively had the highest yield(8.84 and 8.85 t ha^(-1)),ABM (20.67 and 20.83 t ha^(-1)),WUE (2.28 and 2.17 kg m^(-3)) and NPFP (36.82 and 36.88 kg kg^(-1)).This work provided substantial evidence that urea-N applied in equal splits between basal and topdressing doses compete economically with the highly expensive SRF for fertilization of winter wheat crops.Although the single-dose SRF could reduce labor costs involved with the traditional method of manual spreading,the drip fertigation system used in this study with the N50–50 treatment provides an option for farmers to maintain wheat production in the NCP.

Skeleton Split Strategies for Spatial Temporal Graph Convolution Networks

Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the data during critical events.A skeleton representation of the human body has been proven to be effective for this task.The skeletons are presented in graphs form-like.However,the topology of a graph is not structured like Euclideanbased data.Therefore,a new set of methods to perform the convolution operation upon the skeleton graph is proposed.Our proposal is based on the Spatial Temporal-Graph Convolutional Network(ST-GCN)framework.In this study,we proposed an improved set of label mapping methods for the ST-GCN framework.We introduce three split techniques(full distance split,connection split,and index split)as an alternative approach for the convolution operation.The experiments presented in this study have been trained using two benchmark datasets:NTU-RGB+D and Kinetics to evaluate the performance.Our results indicate that our split techniques outperform the previous partition strategies and aremore stable during training without using the edge importance weighting additional training parameter.Therefore,our proposal can provide a more realistic solution for real-time applications centred on daily living recognition systems activities for indoor environments.