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.

Many cities worldwide have large amounts of industrial vacant land (IVL) due to development and transformation, posing a growing problem. However, the large-scale identification of IVL is hindered by obstacles such as high cost, high variability, and closed-source data. Moreover, it is difficult to distinguish industrial vacant land from operational industrial land based solely upon image features. To address these issues, we propose a method for the large-scale automatic identification of IVL. The framework uses deep learning to train remote-sensing images of potential industrial vacant land to generate a semantic segmentation model and further use population density and surface temperature data to filter model predictions. The feasibility of the proposed methodology was validated through a case study in Tangshan City, Hebei Province, China. The study indicates two major conclusions: (1) The proposed IVL identification framework can efficiently generate industrial vacant land mapping. (2) HRNet exhibits the highest accuracy and strongest robustness after training compared with other semantic segmentation backbone networks, ensuring high-quality performance and stability, as evidenced by a model accuracy of 97.84%. Based on the above advantages, the identification framework provides a reference method for various countries and regions to identify industrial vacant land on a large scale, which is of great significance for advancing the research and transformation of industrial vacant land worldwide.

Accurate information on the location of dominant tree species is essential for scientific forest management. However, factors like changes in forest phenology, stand conditions, and mixed understory backgrounds introduce uncertainties in remote sensing-based species mapping. To address these challenges, this study maps dominant tree species using time series Sentinel-2 data combined with environmental context data. To quantify the impact of understory background on mapping accuracy, this study applied a random forest inversion model to estimate the canopy cover across the study area. Binary contour plots and Pearson’s correlation coefficient were used to quantify the relationship between canopy cover and classification uncertainty at both the grid and pixels. A 10 m resolution map of dominant tree species in Yunnan Province, featuring eight species, was produced with an overall accuracy of 83.52% and a Kappa coefficient of 0.8115. The R² value between the predicted and actual tree area proportions was greater than 0.93, with RMSEs consistently below 2.6. In addition, we observed strong negative correlations between different canopy cover classes. The correlations were −0.67 for low-cover areas, −0.40 for medium-cover areas, and −0.73 for high-cover areas. Our mapping framework enables the accurate identification of regional dominant species, and the established relationship between understory context and classification uncertainty provides valuable insights for analyzing potential mapping errors.