When using the Cobb-Douglas (C-D) production function to measure the contribution rate of agricultural technological progress (ATP), it is necessary to estimate the output elasticity coefficient (OEC) of each input factor in C-D production function. For this purpose, it is usually necessary to take logarithm at both sides of C-D production function and convert it into a linear function, and then use regression analysis method to estimate the OECs of input factors. However, there are some problems in this method remains unsolved: first, the OECs estimated by taking logarithm of C-D production function are not the optimal estimation of the original C-D production function; second, the regression results sometimes fail to pass statistical test; third, some OECs cannot be guaranteed to be non-negative. Aiming at resolving these problems, a method for estimating OECs in C-D production function based on the Hybrid Improved Bat Optimization Algorithm (HIBA) was proposed. This method solves the problems existing in the OEC estimation methods in the existing literatures. To verify the effectiveness of the proposed method in this study, the OECs of input factors in China’ Sichuan Province from 1996 to 2018 was estimated. The estimation results show that, compared with other estimation methods in the existing literatures, the proposed method can not only guarantee that it is the optimal estimation of the OECs in the original C-D production function, but also ensure that the OECs are non-negative and with high precision and good fitting effect. Finally, based on the estimation results, this study measured and analyzed the contribution rate of agricultural input factors and ATP of Sichuan Province and puts forward corresponding suggestions for the agricultural development in this region.
Metro passenger flow prediction is a crucial and challenging task in the intelligent transportation system of subways. It serves as the foundation for achieving intelligent transportation in subway systems and holds significant importance in practical applications. Although much progress has been made, accurate traffic flow prediction still faces challenges. To address this, we propose the Spatio-Temporal Fusion Graph Convolutional Network (STFGCN) for predicting metro passenger flow. Specifically, we employ Discrete Cosine Transform (DCT) to replace the Fourier Transform used in traditional models, which avoids the Gibbs phenomenon associated with the Fourier Transform. We combine DCT with channel attention to form periodic trend-enhancing attention, thereby enhancing the expressive power of the model. Furthermore, we introduce trend similarity-aware attention to capture the evolutionary trends of time series and adopt a dynamic correlation graph convolutional network to dynamically adjust spatial correlation strengths based on changes in different time periods. Experimental results on the Hangzhou Metro’s inbound and outbound passenger flow datasets demonstrate that the STFGCN model exhibits significant superiority over baseline models and shows excellent performance in metro passenger flow prediction. Compared to the CorrSTN model, STFGCN achieves improvements of 22.15%, 16.9%, and 0.6% in MAE, RMSE, and MAPE, respectively.
Scientifically evaluating China’s black soil protection policy and exploring its evolution characteristics are crucial for promoting high-quality and efficient black soil protection projects worldwide. Utilizing the Policy Modeling Consistency (PMC) index model, the effectiveness of China’s black soil protection policy system is assessed. Building upon this evaluation, the research delves into the evolution process of the black soil protection policy system, examining its dynamic characteristics across different government levels. Through the application of text mining technology and visual analysis techniques, the study explores four dimensions: keyword co-occurrence, vertical synergy calculation, policy theme identification, and policy tool analysis. The results show the following: (1) The PMC index showed a phased growth trend, and various indicators gradually improved and tended to be stable. (2) Government policies at the same level exhibit progressive evolution patterns in terms of policy keywords and themes. (3) Across different levels of government, there are hierarchical lag evolution rules observed in policy keywords and provincial policy tools. Additionally, policy keywords display vertical synergy evolution patterns. In conclusion, future black soil conservation policies need to reduce hierarchical delays, enhance the coverage and comprehensiveness of policy content, and establish a sound policy feedback mechanism. The conclusions of the study are significant for improving management approaches throughout the black soil zones of the world.
Pork supply prediction is a challenging task of significant importance for pig producers and administrators, as it aids decision-making and maintains the pork supply–demand balance. Previous studies failed to consider impact factors like the month-age transfer principle of pigs, epidemic factors, and the simultaneous import and export volumes of pork, leading to the absence of a quantitative prediction model for pork supply. In this background, we proposed a novel quantitative prediction model of pork supply that incorporates pork production and pork import/export volumes. First, a prediction model for pork production that takes into account the month-age transfer principle of pigs and epidemic factors was presented, along with a recursive model of the pig-herd system. A novel method based on a modified self-organizing migrating algorithm (MSOMA) was proposed for calculating the quantity of monthly newly retained sows (NRS). Furthermore, the pork-production prediction model considered the epidemic factor as a random disturbance term (RDT), and a prediction method based on MSOMA and a back-propagation neural network (MSOMA-BPNN) was introduced to predict such disturbance terms. Second, the proposed MSOMA-BPNN was employed to predict pork import and export volumes. The pork supply was subsequently determined based on the predicted pork production, as well as the pork import and export volumes. The proposed pork supply prediction model was applied to forecast China’s pork supply from 2010 to 2023. The results validate the high effectiveness and reliability of the proposed model, providing valuable insights for decision makers. The empirical results demonstrate that the proposed model is a promising and effective tool for predicting the pork supply. To our knowledge, this is a novel tool for pork supply prediction, considering the pig-herd system and pork import and export volumes from a systemic perspective. These features allow for consideration of the scientific formulation of a pig production plan, the establishment of early warning mechanisms to deal with epidemic situations and emergencies, and the regulation of pork supply and demand balance.