With the advancement of remote sensing technology, the acquisition of ultra-high-resolution remote sensing imagery has become a reality, opening up new possibilities for detailed research and applications of Earth’s surface. These ultra-high-resolution images, with spatial resolutions at the meter or sub-meter level and pixel counts exceeding 4 million, contain rich geometric and attribute details of surface objects. Their use significantly improves the accuracy of surface feature analysis. However, this also increases the computational resource demands of deep learning-driven semantic segmentation tasks. Therefore, we propose the Transform Dual-Branch Attention Net (TDBAN), which effectively integrates global and local information through a dual-branch design, enhancing image segmentation performance and reducing memory consumption. TDBAN leverages a cross-collaborative module (CCM) based on the Transform mechanism and a data-related learnable fusion module (DRLF) to achieve adaptive content processing. Experimental results show that TDBAN achieves mean intersection over union (mIoU) of 73.6% and 72.7% on DeepGlobe and Inria Aerial datasets, respectively, and surpasses existing models in memory efficiency, highlighting its superiority in handling ultra-high-resolution remote sensing images. This study not only advances the development of ultra-high-resolution remote sensing image segmentation technology, but also lays a solid foundation for further research in this field.

We used tree-ring width data of Larix gmelinii and Pinus sylvestris var. mongolica from the northern region of the Daxing’an Mountains, China; normalized difference vegetation index (NDVI) data; and microtopographic information (elevation, slope direction, slope gradient, and topographic location index) to assess spatiotemporal dynamics in the growth of the boreal forest and topographic patterns of forest decline under the background of climate warming. Forest growth trends were determined based on tree growth decline indicators and NDVI time series trends, and topographic patterns of forest decline were analyzed using the C5.0 decision tree model. More climatic information was present in the radial growth of the trees at higher elevations, and P. sylvestris var. mongolica was influenced strongly by climatic factors of the previous year. Since 1759, tree radial growth trends in the study area have experienced two recessions during 1878–1893 and 1935–1943, which were characterized by persistent narrow whorls of tree rings of below-average growth. Changes in NDVI and tree-ring information were similar, and they together indicate a high risk of declining forest growth in the northern Daxing’an Mountains after 2010, especially at higher elevations. The NDVI time series showed that the high temperatures in 2003 negatively affected forest growth in the study area, which was confirmed by the tree-ring data. The decision tree terrain model results had an accuracy of 0.861, and elevation was the most important terrain factor affecting forest decline. The relative importance of elevation, topographic position index, aspect, and slope was 58.41%, 17.70%, 16.81%, and 7.08%, respectively. Classification rule-based decision tree models can be used to quantify the effects of terrain factors on tree growth. This research methodology can aid the management of regional forestry resources and the conservation of forest resources under the background of climate change, which increases the risk of forest decline.

In northeastern China, simultaneous reconstruction of temperature and precipitation changes in the same region using tree ring data has not yet been reported, limiting our understanding of the historical climate. Using tree ring samples from the Greater Khingan Mountains, it was established that there are five standardized tree ring width chronologies of Pinus sylvestris var. mongolica at five elevations. Correlation analyses revealed significant relationships between the tree ring chronologies and climate data for multiple months. Specifically, the correlation coefficient between the average minimum temperature from May to July and the composite chronologies of mid–high and mid-elevations was 0.726, whereas that between the total precipitation from August to July and the low-elevation chronology was 0.648 (p < 0.01). Based on these findings, we reconstructed two series: the average minimum temperature from May to July over the past 211 years and the total precipitation from August to July over the past 214 years. The reconstructed sequences revealed changes in the average minimum temperature from 1812 to 2022 and precipitation from 1809 to 2022 in the northern part of the Greater Khingan Mountains. The variances explained by the reconstruction equations were 0.528 and 0.421 (adjusted R-squared: 0.520 and 0.411), with F-test values of 65.896 and 42.850, respectively, exceeding the significance level of 0.01. The reliability of the reconstructed sequences was validated by historical records of meteorological disasters and the reconstruction results in the surrounding area. The reconstructed temperature and precipitation sequences exhibited distinct patterns of temperature fluctuations, dry–wet changes, and periodic oscillations. The region experienced two warm periods (1896–1909 and 2006–2020), two cold periods (1882–1888 and 1961–1987), a wet period (1928–1938), a drought period (1912–1914), and a period prone to severe drought events (1893–1919) during the past 210 years. The temperature series showed periodicities of 2–2.5 years, 3.9 years, 5.2 years, and 68 years, while the precipitation series exhibited periodicities of 2.1 years, 2.5 years, and 2.8 years, possibly related to El Niño–Southern Oscillation (ENSO) events, quasi-biennial oscillation, and Pacific Decadal Oscillation (PDO). Spatial correlation analysis indicated that the reconstructed temperature and precipitation sequences accurately represented the hydrothermal changes in the study area.

We developed a tree ring width chronology from 1797 to 2020 (224 years) for the northwestern foothills of the Greater Khingan Mountains (GKMs) in northeastern China using 51 tree ring sample cores from 24 Pinus sylvestris var. mongolica (PSM). Pearson’s correlation analysis was used to analyze the relationship between tree ring width and regional climate factors. The standardized chronology was positively associated with the minimum temperature (T_min) in the previous May (r = 0.721, p < 0.01), indicating that this parameter was the main climatic factor limiting PSM growth in the region. We established a secure reconstruction equation for the May T_min from 1797 to 2020. There were 31 warm and 43 cold years in the 224-year reconstructed temperature series, accounting for 13.8% and 19.2% of the total years, respectively. Warm periods were observed in 1820–1829, 1877–1898, 1947–1958, and 1991–2020, whereas cold periods occurred in 1820, 1829–1870, 1899–1927, 1934–1947, and 1960–1988. The observed temperature sequence was highly consistent with the reconstructed sequence from the tree rings, which verified the reliability of the reconstructed results. The spatial correlation analysis indicated that the reconstructed temperature sequence accurately represented the temperature changes in the northwestern foothills of the GKM and surrounding areas. Multi-window spectral analysis and wavelet analysis revealed significant periodic fluctuations from 2 to 6 years, 21.2 years, 48.5 years, and 102.2 years. These periodic variations may be related to the El Niño–Southern Oscillation (ENSO), the Atlantic Multi-Year Intergenerational Oscillation (AMO), the Pacific Decadal Oscillation (PDO), and solar activity. This study expands the existing climate records in the region and provides valuable data support for understanding climate change patterns in the GKM and the scientific predictions of future climate changes.

To study the radial growth of Mongolian pine (Pinus sylvestris var. mongholica, MP) trees in response to climatic factors against the global warming background in the northeast part of the Greater Khingan Mountains (GKM), 101 tree cores were collected at contrasting altitudes (1100 and 650 m) in the Mordoga area, a tree-ring width chronology of MP was established for that region at both altitudes, and the relation between climatic factors and ring width trends at different time scales was investigated. The results revealed four major findings. (1) The ring width chronology of MP in the low-altitude area has better quality. (2) The growth of MP at high (low) altitude was mainly influenced by temperature (precipitation) factors. (3) Before a sudden change in temperature, there was a decreasing trend in the annual indices of MPs at higher altitudes. The chronological coefficients of MPs at both altitudes showed a significant upward trend after the increase in temperature. (4) The sliding analysis results showed that the stability of the relationship between MP growth and its response to climatic factors at both altitudes was also mostly similar. MP growth is relatively stable and sensitive and to climatic factors as temperatures increase.