Intercropping has emerged as a pivotal strategy in modern ecological agriculture, significantly contributing to biodiversity enhancement, ecological system services and soil quality improvement. In light of global food security challenges and the scarcity of arable land, intercropping is anticipated to become increasingly important for enhancing farmland quality and ensuring food security in China. Current research primarily highlights the benefits of intercropping in improving farmland quality and crop productivity, with some attention also given to its role in promoting biodiversity and ecological system services. However, the mechanisms by which intercropping specifically enhances soil physical, chemical and biological properties to sustain long-term soil health and improve farmland quality require further investigation. This review examines the concept of sugarcane intercropping and its role in promoting soil health and enhancing ecological system services. It systematically synthesizes recent research findings on the effects of sugarcane intercropping on soil physical, chemical and biological properties in southern China. Additionally, this review outlines future research directions and priorities for developing intercropping systems that prioritize farmland quality improvement, aiming to provide insights into the broader value that intercropping in China’s strategies for farmland quality enhancement.

In the face of rising food demand and declining wheat acreage, improving wheat yield and resource use efficiency will be key to sustainable wheat production. To address the challenge, this study proposed a framework for wheat green production, quantified the benefits of key technologies and technology models based on the framework in wheat yield and nitrogen use efficiency (NUE), and developed a new model for the promotion of technology. The framework included soil, root layer and canopy systems, where the adoption of single technologies based on the framework could increase wheat yield and NUE by improving soil fertility, managing soil nutrient supply and building high-yielding systems. Through combining specific single technologies, a year-round plastic film mulching model in dryland cropping, and an efficient nutrient and water management technique model for irrigated cropping were established, providing benefits in wheat yield and NUE. A multi-subject joint innovation technology model was also developed to serve as a bridge to transform agricultural technology into agricultural productivity. In the future, a sustainable increase in wheat production in China will require innovation in key technologies and technology models, the development of new technology promotion models, and the combined efforts of the whole community.

With the development of smart agriculture, accurately identifying crop diseases through visual recognition techniques instead of by eye has been a significant challenge. This study focused on apple leaf disease, which is closely related to the final yield of apples. A multiscale fusion dense network combined with an efficient multiscale attention (EMA) mechanism called Incept_EMA_DenseNet was developed to better identify eight complex apple leaf disease images. Incept_EMA_DenseNet consists of three crucial parts: the inception module, which substituted the convolution layer with multiscale fusion methods in the shallow feature extraction layer; the EMA mechanism, which is used for obtaining appropriate weights of different dense blocks; and the improved DenseNet based on DenseNet_121. Specifically, to find appropriate multiscale fusion methods, the residual module and inception module were compared to determine the performance of each technique, and Incept_EMA_DenseNet achieved an accuracy of 95.38%. Second, this work used three attention mechanisms, and the efficient multiscale attention mechanism obtained the best performance. Third, the convolution layers and bottlenecks were modified without performance degradation, reducing half of the computational load compared with the original models. Incept_EMA_DenseNet, as proposed in this paper, has an accuracy of 96.76%, being 2.93%, 3.44%, and 4.16% better than Resnet50, DenseNet_121 and GoogLeNet, respectively, proved to be reliable and beneficial, and can effectively and conveniently assist apple growers with leaf disease identification in the field.