In recent years, crop yield prediction has become a research hotspot in the field of agricultural science, playing a decisive role in the economic development of every country. Therefore, accurate and timely prediction of crop yields is of great significance for the national formulation of relevant economic policies and provides a reasonable basis for agricultural decision-making. The results obtained through prediction can selectively observe the impact of factors such as crop growth cycles, soil changes, and rainfall distribution on crop yields, which is crucial for predicting crop yields. Although traditional machine learning methods can obtain an estimated crop yield value and to some extent reflect the current growth status of crops, their prediction accuracy is relatively low, with significant deviations from actual yields, and they fail to achieve satisfactory results. To address these issues, after in-depth research on the development and current status of crop yield prediction, and a comparative analysis of the advantages and problems of domestic and foreign yield prediction algorithms, this paper summarizes the methods of crop yield prediction based on deep learning. This includes analyzing and summarizing existing major prediction models, analyzing prediction methods for different crops, and finally providing relevant views and suggestions on the future development direction of applying deep learning to crop yield prediction research.

Under the background of the global “carbon neutrality” goal, it is of great significance to study the environmental effect of FDI in rapid economic development. This paper proposes an original framework to determine the relative influence of five factors on the Belt and Road countries with a strong FDI-CO₂ association. Based on the panel smooth transition regression (PSTR) model, we establish country-specific and time-specific FDI-CO₂ coefficients for 59 Belt and Road countries during 2003–2018. These coefficients are assumed to change smoothly as a function of five threshold variables, considered the most important in the literature devoted to the FDI-CO₂ correlations. The results show that the degree of GDP per capita, industrialization, openness, and total factor productivity significantly influences the FDI-CO₂ relationship. However, they showed obvious heterogeneity. The coefficient of elasticity of the environmental effects of FDI smoothly transitions between the different intervals, the relationship between GDP per capita and FDI-CO₂ coefficient shows a bell-shaped change, the relationship between degree of trade openness and FDI-CO₂ coefficient also shows a bell-shaped change, the relationship between industrialization level and FDI-CO₂ coefficient shows an inverted N-shaped change, the change of a country’s technological level shows a bell-shaped relationship with the FDI-CO₂ coefficient. The results indicate that PSTR model can be used to study the threshold effect on FDI’s influence on carbon dioxide emissions and the individual and time differences in coefficients of elasticity, to provide a new research perspective and new conclusions on the environmental effect of FDI in rapid economic development.

According to the status of agricultural information, this paper analyzed the advantages, opportunities and challenges of developing wisdom agriculture in Chengdu. By analyzed the local characteristics of Chengdu agriculture, the construction program of Chengdu wisdom agriculture was designed, which was based on the existing agricultural informatization. The positioning and development theme of Chengdu agriculture is leisure agriculture, urban agriculture and quality agriculture.

A new condition monitoring method of vegetable growth was proposed, which was based on internet of things. It was combined remote environmental monitoring, video surveillance, intelligently decision-making and two-way video consultation together organically.