Temperature is a crucial indicator for studying climate, as well as the social and economic changes in a region. Temperature reanalysis products, such as ERA5-Land, have been widely used in studying temperature change. However, global-scale temperature reanalysis products have errors because they overlook the influence of multiple factors on temperature, and this issue is more obvious in smaller areas. During the cold months (January, February, March, November, and December) in the Yellow River Basin, ERA5-Land products exhibit significant errors compared to temperatures observed by meteorological stations, typically underestimating the temperature. This study proposes improving temperature reanalysis products using deep learning and multi-source remote sensing and geographic data fusion. Specifically, convolutional neural networks (CNN) and bidirectional long short-term memory networks (BiLSTM) capture the spatial and temporal relationships between temperature, DEM, land cover, and population density. A deep spatiotemporal model is established to enhance temperature reanalysis products, resulting in higher resolution and more accurate temperature data. A comparison with the measured temperatures at meteorological stations indicates that the accuracy of the improved ERA5-Land product has been significantly enhanced, with the mean absolute error (MAE) reduced by 28.7% and the root mean square error (RMSE) reduced by 25.8%. This method obtained a high-precision daily temperature dataset with a 0.05° resolution for cold months in the Yellow River Basin from 2015 to 2019. Based on this dataset, the annual trend of average temperature changes during the cold months in the Yellow River Basin was analyzed. This study provides a scientific basis for improving ERA5-Land temperature reanalysis products in the Yellow River Basin and offers theoretical support for climate change research in the region.

Understanding the spatiotemporal dynamics of land-use and cover change (LUCC) and ecosystem service (ES) responses is essential for assessing ecological functions in regional landscapes. However, conventional LUCC simulations often rely on historical trends and inadequately represent the spatially heterogeneous effects of top-down policy constraints. Taking the Henan section of the Yellow River Basin (HYRB) as a case study, we developed a policy-to-rule framework that translated ecological redlines, urban development boundaries, and restoration requirements into explicit spatial constraints and land-use transition rules in the PLUS model. A policy-constrained High-Quality Development Scenario (HQDS) was established, with the Natural Growth Scenario (NGS) as a reference. Five ESs were assessed using InVEST from 1985 to 2050, and the results were integrated with the Minimum Cumulative Resistance (MCR) model and circuit theory to construct an ecological security pattern (ESP). Historical reconstruction of the 2022 land-use pattern achieved an overall accuracy of 90.18% and a Kappa coefficient of 86.39%. The five ESs remained relatively stable overall: water yield, soil conservation, and the sediment-related indicator increased, whereas habitat quality and carbon storage declined slightly. Ecological source areas expanded from 7140.54 km² in 1985 to 12,039.17 km² under the HQDS in 2050, a 68.6% increase. Compared with the NGS, the HQDS increased source areas by 562.42 km² (4.9%), reduced ecological corridors from 26 to 24, and increased their total length from 1068.89 to 1099.61 km. These differences represent the projected, scenario-conditioned consequences of the specified policy constraints and provide quantitative decision support for future ecological management.