Shifts in alpine tundra plant species have important consequences for biodiversity and ecosystem services. However, recent research on upward species shifts have focused mainly on polar and high-latitude regions and it therefore remains unclear whether such vegetation change trends also are applicable to the alpine tundra at the southern edges of alpine tundra species distribution. This study evaluated an alpine tundra region within the Changbai Mountains, China, that is part of the southernmost alpine tundra in eastern Eurasia. We investigated plant species shifts in alpine tundra within the Changbai Mountains over the last three decades (1984–2015) by comparing contemporary survey results with historical ones and evaluated potential changes in the distribution of dwarf shrub and herbaceous species over the next three decades (2016–2045) using a combination of observations and simulations. The results of this study revealed that the encroachment of herbaceous plants had altered tundra vegetation to a significant extent over the last three decades, especially within low and middle alpine tundra regions in Changbai Mountains, China. The herbaceous species would continue shifting upward and expanding while their dwarf shrub counterparts would continue shifting upward and shrinking over the next three decades under the RCP 4.5 and RCP 8.5 scenarios. The upward shifts of plant species would not keep up with the rate of climate warming under the RCP 8.5 scenarios. The dominant plant tundra species may transform from dwarf shrubs to herbaceous varieties. The results of this study provide a scientific basis for biodiversity protection under climate change and a reference data set for additional research on alpine vegetation dynamics.

The new development mode represented by the digital economy has provided new ideas for sustainable rural development. To comprehensively understand the status of digital rural development and propose scientific measures of rural revitalization in the Yellow River Basin (YRB), this study used counties as the research unit and data from 2020 to analyze the spatial differentiation characteristics and influencing factors by employing the Theil index, spatial autocorrelation analysis, and a geodetector model. The results showed that the digital rural development index in the YRB is slightly higher than it is in China overall, but the sub-index for the digital economy is lagging. The levels of digital rural development in the different reaches were lower reaches > middle reaches > upper reaches. Additionally, municipal districts and county-level cities have higher statuses than t general counties. Moreover, the decomposition of the Theil index shows that the intra-group differences in the upper reaches and general counties are the most important cause of the total differences. Moreover, the levels of digital rural development demonstrate spatial differences, with high and low levels in the east and west, respectively. An obvious reliable spatial correlation exists, and the spatial agglomeration featured with a similar level is significant. Finally, the influencing factors of spatial heterogeneity of digital rural development in the YRB and different reaches were different, with government expenditure being the main leading factor in the YRB and its upper reaches, while educational attainment and industrial structure are the leading factors in the middle reaches and lower reaches, respectively. The explanatory power of the interactions between the factors far exceeds that of a single factor, as shown through double-factor and nonlinear enhancement. This study provides a scientific reference for facilitating more targeted policy measures to achieving the goal of digital China and rural revitalization.

Soil salinization poses a severe threat to agricultural sustainability in the Yellow River Delta, where conventional spectral indices are limited by vegetation interference and seasonal dynamics in coastal saline-alkali landscapes. To address this, we developed an inversion framework integrating spectral indices and vegetation temporal features, combining multi-temporal Sentinel-2 optical data (January 2024–March 2025), Sentinel-1 SAR data, and terrain covariates. The framework employs Savitzky–Golay (SG) filtering to extract vegetation temporal indices—including NDVI temporal extremum and principal component features, capturing salt stress response mechanisms beyond single-temporal spectral indices. Based on 119 field samples and Variable Importance in Projection (VIP) feature selection, three ensemble models (XGBoost, CatBoost, LightGBM) were constructed under two strategies: single spectral features versus fused spectral and vegetation temporal features. The key results demonstrate the following: (1) The LightGBM model with fused features achieved optimal validation accuracy (R² = 0.77, RMSE = 0.26 g/kg), outperforming single-feature models by 13% in R². (2) SHAP analysis identified vegetation-related factors as key predictors, revealing a negative correlation between peak biomass and salinity accumulation, and the summer crop growth process affects soil salinization in the following spring. (3) The fused strategy reduced overestimation in low-salinity zones, enhanced model robustness, and significantly improved spatial gradient continuity. This study confirms that vegetation phenological features effectively mitigate agricultural interference (e.g., tillage-induced signal noise) and achieve high-resolution salinity mapping in areas where traditional spectral indices fail. The multi-temporal integration framework provides a replicable methodology for monitoring coastal salinization under complex land cover conditions.

Introduction: This paper proposes an improved detection framework, PLD-YOLO, to address the challenges of small object scale, strong background interference, and loss of shallow feature information during feature extraction in pest and disease detection under complex natural environments for intelligent plant protection. Methods: The proposed framework enhances small object representation by introducing a high-resolution feature branch. It further improves contextual modeling capability and suppresses complex background noise through multi-scale convolutions and an adaptive feature mechanism. In addition, a dynamic small object weighting strategy is introduced to improve small object learning under scale imbalance conditions. Results: This study systematically evaluates the proposed method on the Tomato-Village dataset constructed under natural environments and compares it with representative two-stage object detection methods, YOLO series models, and transformer-based detection models. Ablation studies, cross-dataset validation, and robustness evaluations under different field conditions further demonstrate the effectiveness and robustness of the proposed approach. The experimental results show that PLD-YOLO achieves excellent performance in terms of precision, recall, mAP@50, and mAP@50–95 while maintaining high inference efficiency. Discussion: The proposed method provides a potential technical solution for intelligent plant protection and contributes to the advancement of precision agriculture.