The pollution control problem of discarded lead-acid batteries has become increasingly prominent in China. An extended producer responsibility system must be implemented to solve the problem of recycling and utilization of waste lead batteries. Suppose the producer assumes responsibility for the entire life cycle of lead batteries. In that case, it will effectively reduce environmental pollution caused by non-compliant disposal of waste lead batteries, reduce environmental pollution, and achieve the sustainable development of lead resources. Based on the operating mechanism of the extended responsibility system for lead-acid battery producers in China, this article considers three recycling channel structures: recycling only by manufacturers (mode M), recycling by the union (mode R), and third-party recycling (mode C). This article comprehensively compares the differences between the three recycling channels. The research results show that: (1) under the EPR system, the choice of production companies is affected by the recovery rate and profit rate. (2) By comparing different recycling channel models, we found that the recovery rate of independent recycling by the manufacturer is the largest. Still, the profit rate of the manufacturer that entrusts the alliance (M) to recycle is the highest. The manufacturer can entrust to alliance or independent recycling of waste lead batteries according to the different profit rates and recovery rates. (3) From the perspective of the supply chain, independent recycling (M) by production companies or recycling (R) by the commissioned union may be the best. The choice of recycling channels for producers depends on independent recycling and commissioning alliance’ recycling costs and reuse costs.

Urban road networks have complex spatial and temporal correlations, driving a surge of research interest in spatial-temporal traffic flow prediction. However, prior approaches often overlook the temporal-scale differentiation of spatial-temporal features, limiting their ability to extract complex structural information. In this work, we design the multibranch adaptive fusion graph convolutional network (MBAF-GCN) that explicitly exploits the prior spatial-temporal characteristics at different temporal scales, and each branch is responsible for extracting spatial-temporal features at a specific scale. Besides, we design the spatial-temporal feature fusion (STFF) module to refine the prediction results. Based on the multibranch complementary features, the module adopts a coarse-to-fine fusion strategy, incorporating different spatial-temporal scale features to obtain recalibrated prediction results. Finally, we evaluate the MBAF-GCN using two real-world traffic datasets. Experimentally, the newly designed multibranch can efficaciously utilize the prior information of different temporal scales. Our MBAF-GCN achieved better performance in the comparative model, indicating its potential and validity.

No abstract