Globally, orchard soils are facing multiple severe health issues. However, different countries and regions have adopted their own soil classification standards, making many studies only useful for improving soil health in local orchards but not widely applicable to other regions. This fragmentation highlights the urgent need for internationally comparable approaches to orchard soil health assessment. Furthermore, there are currently no unified standards for screening orchard soil health indicators or establishing comprehensive evaluation indices. Many proposed orchard soil health assessment frameworks lack practical applicability. This review introduces and compares several soil health assessment methods, critically analyzes their limitations, and explores directions for improvement in their application to orchards. Additionally, it addresses the primary challenges, currently and in the future, facing orchard soil health—climate change and emerging contaminants. This review also evaluates current orchard soil health management practices, focusing on their advantages and limitations. Finally, this paper offers recommendations for data acquisition and analysis in future orchard soil health assessment frameworks and encourages the establishment of a Decision-Making Platform for Soil Health with Cross-Border Cooperation and Feedback, thereby promoting a more globally consistent perspective on orchard soil health.

For ultra-high-resolution (UHR) image semantic segmentation, striking a balance between computational efficiency and storage space is a crucial research direction. This paper proposes a Feature Fusion Network (EFFNet) to improve UHR image semantic segmentation performance. EFFNet designs a score map that can be embedded into the network for training purposes, enabling the selection of the most valuable features to reduce storage consumption, accelerate speed, and enhance accuracy. In the fusion stage, we improve upon previous redundant multiple feature fusion methods by utilizing a transformer structure for one-time fusion. Additionally, our combination of the transformer structure and multibranch structure allows it to be employed for feature fusion, significantly improving accuracy while ensuring calculations remain within an acceptable range. We evaluated EFFNet on the ISPRS two-dimensional semantic labeling Vaihingen and Potsdam datasets, demonstrating that its architecture offers an exceptionally effective solution with outstanding semantic segmentation precision and optimized inference speed. EFFNet substantially enhances critical performance metrics such as Intersection over Union (IoU), overall accuracy, and F1-score, highlighting its superiority as an architectural innovation in ultra-high-resolution remote sensing image semantic segmentation.