Task assignment is a key issue in mobile crowdsensing (MCS). Previous task assignment methods were mainly static offline assignment. However, the MCS platform needs to process dynamically changing workers and tasks online in the actual assignment process. Hence, a reliable dynamic assignment strategy is crucial to improving the platform’s efficiency. This paper proposes an MCS dynamic task assignment framework to solve the task maximization assignment problem with spatiotemporal properties. First, a single worker is modeled for the Markov decision process, and a deep reinforcement learning algorithm (DDQN) is used to perform offline learning on historical task data. Then, in the dynamic assignment process, we consider the impact of current decisions on future decisions. Use the maximum flow model to maximize the number of tasks completed in each period while maximizing the expected value of all workers to achieve the optimal global assignment. Experiments show that the strategy proposed in this paper has good performance compared with the baseline strategy under different conditions.
Runoff pollution have become a serious issue in terms of water pollution in porous areas, especially in urban backfilled soil. The transport and distribution of runoff water and nutrients in the surface runoff and the subsurface runoff of backfilled soil runoff systems are determined using simulated rainfall and the results indicate that the flow patterns of runoff are different from those of surface runoff and subsurface runoff. The rate of surface runoff flow increases in the beginning and reaches a stable state with a delay of 10 min to rainfall, while the flow rate of subsurface runoff is consistent during the whole runoff period. Most of the pollutants (90% of total suspended solids, 88% of total phosphorus, and 78% of total nitrogen) are carried in the surface runoff, which directly results in polluting the surface‐receiving water. The results of the present study will provide information related to the management of runoff pollution in the backfilled soil runoff system.
This chapter focuses on the role of different soil fractions such as oxides, layer aluminosilicates, and organic matter in retaining some exogenous heavy metal elements was carried out with different solid soil fractions separated by a sequential extraction method from two soils different in both properties and mineral composition. Many studies on the selectivities and retention capacities of different oxides and minerals in the specific adsorption of heavy metal ions have been carried out with pure minerals. After treatments A, B, C, and D, that is, removal of soil manganese oxides and organic matter, more Copper (Cu) was retained by the red soil than by the original red soil, but the quantity of Cu retained by the black soil was the same as that by the original black soil. These results showed that the retention of Cu by the black soil and the red soil was mainly controlled by amorphous iron oxides.
Stormwater pollution in redeveloped soils mixed with construction wastes imposes a serious impact to receiving waters. The transport and distribution of rainfall water and nutrients in the surface-flow and subsurface-flow (including side-flow and down-flow) of bare redeveloped soil runoff system were determined. Results indicated that the flow patterns and pollutants transport of surface-flow were different from those in subsurface-flow. The flowrate of surface-flow increased at the beginning and reached to a stable state, and then disappeared immediately after the rainfall stopped. While the flow rate of subsurface-flow was persisted and decreased gradually artery the rainfall. Most of the pollutants were carried in the surface-flow, which directly results in polluting the surface-receiving waters. And the pollutants distribution percent in side-flow was higher than that in down-flow. Results obtained in this study will provide information for the management of stormwater pollution in the bare redeveloped soil mixed with construction wastes.
Using the Acoustic Doppler Current Profiler (ADCP), the authors try to measure the pollutant flux of key sections of the Qiantang River in the dry season by real time monitoring, to find its temporal and spatial distribution. Six monitoring sections along the Qiantang River were selected and located by GPS. Three water samples were taken from the surface to the bottom in each monitoring section. According to the flow data obtained with ADCP and the pollutant concentration data analysed, the pollutant fluxes of the six sections in the Qiantang River were calculated. The research showed that the maximum pollutant flux was in Yanlingwu, regardless of the magnitudes of COD Mn , NH 3 -N or TP, in the dry season of 2005. The minimum pollutant flux was observed in the Xin'an River factory section. Detailed analysis showed that the Lan River contributes considerably to the pollutants of the Yanlingwu section. Therefore, urgent effective measures are required to control the pollution in the Lan River estuary and Yanlingwu sections.
Technical framework for water environment simulation of contaminations is established based on visualization and a spatial environmental model is built. The main two contaminations, namely NH: -N and TP, are simulated on the platform of MapInfo and Delft3D in the Qiantang River at the low water period, to analyze its space-time diversity. For NH4+ -N, the measured values are 0.19 mg/L and 0.66 mg/L larger than simulated values at the Lanjiang River mouth and the Yanlingwu, 0.16 mg/L, 0.54 mg/L and 0.49 mg/L smaller at the Zhaixi, the Yushan and the Yuanpu. For TP, the measured values are 0.13 mg/L and 0.14 mg/L higher than simulated values at the Meicheng Water facility and Yanlingwu. However, the measure values are slightly lower than simulated ones at Zhaixi, Yushan, Puyang River mouth and Yuanpu, the trend of which accords with actual situation. The results indicate that the contaminations of the Qiantang Reach mostly come from the Lanjiang River, the Fuchun River and the Puyang River on the upstream, among which the Lanjiang River and the Puyang River have a very high concentration of polluted materials, which means bad water quality, and influence the water downstream. The Lanjiang River becomes the chief contaminative source in the Fuchun River. When the discharge from the Xin'an River Dam is small, the recirculation region may be formed and makes part of the Xin'an Reach contaminated. Otherwise, when the discharge is large, the water quality in the Fuchun River is apparently improved. And the Puyang River, which brings the contaminations from the upstream, along with the polluted water let into it from the industries along the reach, has significant impacts on the water quality in Qiantang Reach.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)