PurposeGrey modeling technique is an important element of grey system theory, and academic articles applied to agricultural science research have been published since 1985, proving the broad applicability and effectiveness of the technique from different aspects and providing a new means to solve agricultural science problems. The analysis of the connotation and trend of the application of grey modeling technique in agricultural science research contributes to the enrichment of grey technique and the development of agricultural science in multiple dimensions.Design/methodology/approachBased on the relevant literature selected from China National Knowledge Infrastructure, the Web of Science, SpiScholar and other databases in the past 37 years (1985–2021), this paper firstly applied the bibliometric method to quantitatively visualize and systematically analyze the trend of publication, productive author, productive institution, and highly cited literature. Then, the literature is combed by the application of different grey modeling techniques in agricultural science research, and the literature research progress is systematically analyzed.FindingsThe results show that grey model technology has broad prospects in the field of agricultural science research. Agricultural universities and research institutes are the main research forces in the application of grey model technology in agricultural science research, and have certain inheritance. The application of grey model technology in agricultural science research has wide applicability and precise practicability.Originality/valueBy analyzing and summarizing the application trend of grey model technology in agricultural science research, the research hotspot, research frontier and valuable research directions of grey model technology in agricultural science research can be more clearly grasped.

BP neural network (BPNN) is widely used due to its good generalization and robustness, but the model has the defect that it cannot automatically optimize the input variables. In response to this problem, this study uses the grey relational analysis method to rank the importance of input variables, obtains the key variables and the best BPNN model structure through multiple training and learning for the BPNN models, and proposes a variable optimization selection algorithm combining grey relational analysis and BP neural network. The predicted values from the metabolic GM (1, 1) model for key variables was used as input to the best BPNN model for prediction modeling, and a grey BP neural network model prediction model (GR-BPNN) was proposed. The long short-term memory neural network (LSTM), convolutional neural network (CNN), traditional BP neural network (BP), GM (1, N) model, and stepwise regression (SR) are also implemented as benchmark models to prove the superiority and applicability of the new model. Finally, the GR-BPNN forecasting model was applied to the grain yield forecast of the whole province and subregions for Henan Province. The forecasting results found that the growth rate of grain production in Henan Province slowed down and the center of gravity for grain production shifted northwards.

The stability of wheat production is closely related to national food security and agricultural sustainable development, and it has been a major policy concern for China. By analyzing the spatiotemporal factors and causes of wheat production, we can grasp the spatiotemporal distribution law of wheat production to rationally allocate agricultural resources. To this end, this study first conducted a quantitative analysis of the yield differentiation patterns in Huang-Huai-Hai (HHH) wheat based on the 2010–2020 wheat agricultural data, comprehensively using the Theil index and exploratory spatial data analysis. Second, to eliminate the spatial heterogeneity and multicollinearity of the modeling variables, a local model of SCA-GWR combining Spearman correlation analysis (SCA) and geographically weighted regression (GWR) was established. Compared with the traditional global regression model, the superiority and applicability of the SCA-GWR model are proved, and it is a simple and effective new method to detect spatial data nonstationarity. Finally, the factors influencing wheat production in the HHH region were detected based on the SCA-GWR local model, and relevant policy recommendations were put forward. The results show that: (1) The yield difference in different farming areas gradually narrowed, and the wheat production had a significant High-High aggregation trend. The center of gravity for wheat production lies in the southwest of the HHH region. (2) Wheat production still has a strong dependence on irrigation and fertilizer. Effective irrigated areas and temperature are the main driving forces for its production. The inhibitory effect of the proportion of nonagricultural employment on wheat production gradually weakened. Radiation and rainfall were only significantly positively correlated with wheat production in the central and southern HHH region. In response to the findings of the study, corresponding policy recommendations are made in terms of optimizing the allocation of resources, increasing investment in agricultural infrastructure, and vigorously researching and developing agricultural science and technology, and the results of the study can provide a basis for decision-making and management by relevant departments.

A sustainable growth of grain outputs mainly relies on improving output per unit area through scientific and technological innovation. From the perspective of scientific and technological innovation, taking the grain production process as the research object, a systems model of scientific and technological innovation in grain production is constructed based on the relevant data of Henan Province from 2010 to 2019. Firstly, the internal mechanism of grain production scientific and technological innovation is explored, and the feedback loop of grain production scientific and technological innovation is then established. Secondly, system dynamics and grey system theory are combined to construct table functions and logistic functions to establish the grain production scientific and technological innovation system model. Through testing the model, the stability and feasibility of the model are demonstrated, and the simulation and prediction of the innovation system of grain production scientific and technological in Henan Province are carried out. Thirdly, in order to explore the impact of feasible policy schemes on grain production, seven policy plans are designed to simulate grain production policy scenarios from the perspective of scientific and technological innovation. The results show that: (1) The adjustment of individual policies, especially the adjustment of the protection policy of scientific and technological innovation in grain production or the subsidy policy of agricultural materials, has a weak influence on the improvement of grain output. The progress of agricultural technology is the main support for improving the comprehensive grain production capacity. (2) The future grain growth potential of Henan Province should focus on increasing the yield per unit area, and the protection of cultivated land resources should not be ignored. (3) The combination of policies has mutually reinforcing effect, which leads to an ideal system simulation effect. Finally, from the perspective of the composition of scientific and technological innovation system in Henan Province, this study puts forward countermeasures and suggestions for the implementation of the strategy of “storing grain in technology” in Henan Province.