Satellite-based remote sensing technologies are utilized extensively to investigate urban thermal environment under rapid urban expansion. Current Moderate Resolution Imaging Spectroradiometer (MODIS) data are, however, unable to adequately represent the spatially detailed information because of its relatively coarser spatial resolution, while Landsat data cannot explore the temporally continued analysis due to the lower temporal resolution. Combining MODIS and Landsat data, “Landsat-like” data were generated by using the Flexible Spatiotemporal Data Fusion method (FSDAF) to measure land surface temperature (LST) variations, and Landsat-like data including Normalized Difference Vegetation Index (NDVI) and Normalized Difference Built Index (NDBI) were generated to analyze LST dynamic driving forces. Results show that (1) the estimated “Landsat-like” data are capable of measuring the LST variations; (2) with the urban expansion from 2013 to 2016, LST increases ranging from 1.80 °C to 3.92 °C were detected in areas where the impervious surface area (ISA) increased, while LST decreases ranging from −3.52 °C to −0.70 °C were detected in areas where ISA decreased; (3) LST has a significant negative correlation with the NDVI and a strong positive correlation with NDBI in summer. Our findings can provide information useful for mitigating undesirable thermal conditions and for long-term urban thermal environmental management.

Climate variation and underlying surface dynamics have caused a significant change in the trend of evapotranspiration (ET) in the Yellow River Basin (YRB) over the last two decades. Combined with the measured rainfall, runoff and gravity recovery and climate experiment (GRACE) product, five global ET products were firstly merged using a linear weighting method. Linear slope, “two-step” multiple regression, partial differential, and residual methods were then employed to explore the quantitative impacts of precipitation (PCPN), temperature (Temp), sunshine duration (SD), vapor pressure deficit (VPD), wind speed (WS), leaf area index (LAI), and the residual factors (e.g., microtopography changes, irrigation, etc.) on the ET trend in the YRB. The results show that: (1) The ET estimates were improved by merging five global ET products using the linear weighting method. The sensitivities of climatic factors and LAI on the ET trend can be separately calculated using proposed “two-step” statistical regression method; (2) the overall ET trend in the entire study area during 2000–2018 was 3.82 mm/yr, and the highest ET trend was observed in the Toudaoguai-Longmen subregion. ET trend was dominantly driven by vegetation greening, with an impact of 2.47 mm/yr and a relative impact rate of 51.16%. The results indicated that the relative impact rate of the residual factors (e.g., microtopography, irrigation, etc.) on the ET trend is up to 28.17%. The PCPN and VPD had increasing roles on the ET trend, with impacts of 0.45 mm/yr and 0.05 mm/yr, respectively, whereas the Temp, SD, and WS had decreasing impacts of –0.19 mm/yr, –0.15 mm/yr, and –0.17 mm/yr, respectively. (3) The spatial pattern of impact of specific influencing factor on the ET trend was determined by the spatial pattern of change trend slope of this factor and sensitivity of ET to this factor. ET trends of the source area and the Qingtongxia–Toudaoguai were dominated by the climatic factors, while the residual factors dominated the ET trend in the Tangnaihai–Qingtongxia area. The vegetation restoration was the dominant factor causing the increase in the ET in the middle reaches of the YRB, and the impact rates of the LAI were ranked as follows: Yanhe Rive > Wudinghe River > Fenhe River > Jinghe River > Beiluohe River > Qinhe River > Kuyehe River > Yiluohe River.

Accurate spatial information of cropland is crucial for precision agricultural management and ensuring national food security. High-resolution remote sensing imagery combined with deep learning algorithms provides a promising approach for extracting detailed cropland information. However, due to the diverse morphological characteristics of croplands across different agricultural landscapes, existing deep learning methods encounter challenges in precise boundary localization. The advancement of large-scale vision models has led to the emergence of the Segment Anything Model (SAM), which has demonstrated remarkable performance on natural images and attracted considerable attention in the field of remote sensing image segmentation. However, when applied to high-resolution cropland extraction, SAM faces limitations in semantic expressiveness and cross-domain adaptability. To address these issues, this study proposes a dual-branch framework integrating SAM and a semantically aware network (SAM-SANet) for high-resolution cropland extraction. Specifically, a semantically aware branch based on a semantic segmentation network is applied to identify cropland areas, complemented by a boundary-constrained SAM branch that directs the model’s attention to boundary information and enhances cropland extraction performance. Additionally, a boundary-aware feature fusion module and a prompt generation and selection module are incorporated into the SAM branch for precise cropland boundary localization. The former aggregates multi-scale edge information to enhance boundary representation, while the latter generates prompts with high relevance to the boundary. To evaluate the effectiveness of the proposed approach, we construct three cropland datasets named GID-CD, JY-CD and QX-CD. Experimental results on these datasets demonstrated that SAM-SANet achieved mIoU scores of 87.58%, 91.17% and 71.39%, along with mF1 scores of 93.54%, 95.35% and 82.21%, respectively. Comparative experiments with mainstream semantic segmentation models further confirmed the superior performance of SAM-SANet in high-resolution cropland extraction.