Due to the phenomenon of holes and inferior seedlings in trays, it is necessary to remove and replenish unqualified seedlings. The traditional operation is labor-intensive, and the degree of mechanization is low. This paper took broccoli seedlings as the research object and developed an image recognition system suitable for seedling health recognition and pose judgement, researched and designed a plug-in end effector that reduces leaf damage, and conducted orthogonal tests to obtain a substrate parameter combination containing the moisture content, seedling age, and transplanting acceleration suitable for culling operations. A parallel robot kinematics and dynamics model was built. The fifth degree B-spline curve was used to construct the joint space motion curve for seven nodes, and the motor speed, torque, and end-effector acceleration were used to construct the joint space motion curves. The end-effector acceleration was the constraint condition to plan the optimal trajectory of the joint space in time, and the optimal time was obtained using the artificial fish swarm–particle swarm hybrid optimization algorithm. A single operation time was greatly reduced; the whole machine was systematically built; the average time of single-time seedling removal was measured; and the transplanting efficiency of the whole machine was high. In the seedling damage rate gap test, the leaf damage rate was low. This research provides a reference for the localized development of greenhouse high-speed and low-loss seedling removal equipment.

Multiple factors need to be considered when allocating water resources, among which water scarcity risk is often ignored. However, the unmet water demand of upstream sectors with high water dependency will exacerbate water scarcity, and lead to potential economic risk to the industrial chain. To solve it, we propose a method to quantify the intermediate virtual water scarcity risk transfer via the intermediate use matrix and Leontief inverse matrix, and apply it to virtual water trade in China in 2018. Meaningful conclusions are drawn as follows: (i) Although the water-use efficiency of all sectors in China increased steadily from 2007 to 2018, the overall input concentration of virtual water scarcity risk showed a rising trend, reflecting the gradual increase in the vulnerability of the industrial chain to water shortage. (ii) The virtual water scarcity risk in China mainly transferred through the secondary industry. The secondary industry accounted for 51.8% of the output and 71.8% of the input in the intermediate virtual water transfer, while 77.0% and 74.7%, respectively, in intermediate virtual water scarcity risk output and input. (iii) From 2007 to 2018, agriculture, chemical industry, metallurgy, electricity and heat supply always ranked as the top four of intermediate virtual water scarcity risk output sectors. As their downstream sectors, the construction industry, metallurgy, and other services are stable within the top four input sectors. (iv) The virtual water scarcity risk upstream transmitted is significantly dispersed after the intermediate inputs process, indicating that abundant import relationships are conducive to reduce the risk taken in. From the perspective of intermediate input, this paper argues that it is necessary to both ensure the water supply of the upstream source sectors and disperse the downstream import sources. Moreover, enriching industrial structures and closing production linkages between sectors is also beneficial for promoting sustainable economic development.

Water quality prediction is an important part of water pollution prevention and control. Using a long short-term memory (LSTM) neural network to predict water quality can solve the problem that comprehensive water quality models are too complex and difficult to apply. However, as water quality time series are generally multiperiod hybrid time series, which have strongly nonlinear and nonstationary characteristics, the prediction accuracy of LSTM for water quality is not high. The ensemble empirical mode decomposition (EEMD) method can decompose the multiperiod hybrid water quality time series into several simpler single-period components. To improve the accuracy of surface water quality prediction, a water quality prediction model based on EEMD-LSTM was proposed in this paper. The water quality time series was first decomposed into several intrinsic mode function components and one residual item, and then these components were used as the input of LSTM to predict water quality. The model was trained and validated using four water quality parameters (NH3N, pH, DO, CODMn) collected from the Xiaofu River and compared with the results of a single LSTM. During the validation period, the R2 values when using LSTM for NH3N, pH, DO and CODMn were 0.567, 0.657, 0.817 and 0.693, respectively, and the R2 values when using EEMD-LSTM for NH3N, pH, DO and CODMn were 0.924, 0.965, 0.961 and 0.936, respectively. The results show that the proposed model outperforms the single LSTM model in various evaluation indicators and greatly improves the model performance in terms of the hysteresis problem. The EEMD-LSTM model has high prediction accuracy and strong generalization ability, and further development may be valuable.

The impact of the Three Gorges Dam (TGD) on the discharge after its first operation in 2003 has drawn much attention. Most of the existing research focuses on the TGD’s impact after its initial operation in 2003. However, the water level first reached the TGD’s maximum water level, 175 m, in September 2009. In this paper, to quantify the TGD’s impact during flood season after its full operation in 2009, we created a hydrological model to reconstruct the daily discharge unregulated by the TGD from 2003 to 2018 at the five stations downstream from the TGD. The TGD had an impact on the maximum 1-day discharge and maximum 30-day runoff and the coefficient of variation of the daily discharge, but it had less impact on the flood season runoff and the coefficient of skewness of the daily discharge. Additionally, the TGD was only responsible for 18.3% of the change in the maximum 1-day discharge at the Datong station, which is 1123 km downstream from the TGD. Moreover, the TGD had limited impact on the discharge after its initial operation in 2003, but the impact of the TGD on discharge increased after its full operation in 2009. This study helps to show the TGD’s impact on the discharge of the Yangtze River from the Yichang station (43 km downstream from the TGD) to the Datong station.

Water quality prediction is an important part of water pollution prevention and control. Using a long short-term memory (LSTM) neural network to predict water quality can solve the problem that comprehensive water quality models are too complex and difficult to apply. However, as water quality time series are generally multiperiod hybrid time series, which have strongly nonlinear and nonstationary characteristics, the prediction accuracy of LSTM for water quality is not high. The ensemble empirical mode decomposition (EEMD) method can decompose the multiperiod hybrid water quality time series into several simpler single-period components. To improve the accuracy of surface water quality prediction, a water quality prediction model based on EEMD–LSTM was developed in this paper. The water quality time series was first decomposed into several intrinsic mode function components and one residual item, and then these components were used as the input of LSTM to predict water quality. The model was trained and validated using four water quality parameters (NH3-N, pH, DO, CODMn) collected from the Xiaofu River and compared with the results of a single LSTM. During the validation period, the R2 values when using LSTM for NH3-N, pH, DO and CODMn were 0.567, 0.657, 0.817 and 0.693, respectively, and the R2 values when using EEMD–LSTM for NH3-N, pH, DO and CODMn were 0.924, 0.965, 0.961 and 0.936, respectively. The results show that the developed model outperforms the single LSTM model in various evaluation indicators and greatly improves the model performance in terms of the hysteresis problem. The EEMD–LSTM model has high prediction accuracy and strong generalization ability, and further development may be valuable.