Heat exposure drives substantial global disease and mortality burdens, making spatially explicit heat health risk assessment essential for targeted adaptation. Existing studies apply diverse modeling approaches yet rarely evaluate them systematically because reliable epidemiological validation data remain scarce; conventional risk indices further depend on subjective indicator aggregation and expert weighting. Here we show an integrative geographically neural network weighted regression (GNNWR) framework validated against epidemiologically derived heat-attributable mortality fraction at the subdistrict level. The framework achieves stronger predictive performance and better generalization than ordinary least squares, multiplicative model, random forest, geographically weighted regression (GWR), multi-scale GWR, and other geographically weighted machine learning models, with consistent alignment between training and test sets and no evidence of overfitting. By learning spatial weights through a neural network, it simultaneously captures spatial non-stationarity and nonlinear relationships among meteorological, air pollution, demographic, socioeconomic, and built environment variables without requiring predefined index construction. It enables prediction in data-sparse areas and generates consistent high-resolution (100 m grid), subdistrict, and district-level risk maps, while identifying fine particulate matter (PM2.5) as the second strongest risk factor associated with heat-related mortality risk, after temperature. This validated, data-driven approach provides a transferable methodological foundation for identifying high-risk populations and informing precise public health interventions and urban climate adaptation strategies.

Global navigation satellite system (GNSS) timing modules from 5G base stations enable precipitable water vapor (PWV) retrieval, offering a promising approach to overcome the limitations of conventional meteorological stations in atmospheric monitoring. In this study, we retrieved PWV values (referred to as 5G-PWV) based on GNSS observations from 5G base stations in Zhoushan City, Zhejiang Province, China, using data from September to November 2024. The results were compared with ERA5 reanalysis data (ERA5-PWV) and observations from a dedicated GNSS station in Zhoushan (ZJZS-PWV). The 5G-PWV data showed consistent temporal variability with both ERA5-PWV and ZJZS-PWV. After applying a biweight quality control algorithm, comparisons against ERA5-PWV revealed a mean bias of -1.07 mm, a root-mean-square error of 8.03 mm, and a correlation coefficient of 0.828 for 5G-PWV. We further conducted assimilation and forecast experiments using the China Meteorological Administration Mesoscale Model coupled with its 3-D variational data assimilation system for two typhoon cases: Bebinca and Krathon. Validation of precipitation forecasts-with and without assimilation of 5G-PWV-showed that the assimilation of 5G-PWV improved the threat score. After assimilating 5G-PWV, both false alarms and missed alarms across different precipitation intensity thresholds were slightly reduced. The improved forecast performance is attributed to effective adjustments in the initial humidity field through the assimilation of 5G-PWV, as well as subsequent enhancements in the model's dynamic conditions via precipitation feedback. Our study demonstrates that GNSS-derived PWV from 5G base stations has clear potential to improve typhoon-related precipitation forecasting.

While green-blue spaces (GBSs) are known to mitigate heat-related health risks, the influence of their landscape configurations remains underexplored epidemiologically. This study quantifies how GBS exposure and its specific spatial configurations modify the association between heat and mortality. We conducted a case time series study across 1064 subdistricts in Zhejiang Province, China (2009-2020), using high-resolution data and a conditional Poisson regression with a distributed lag nonlinear model. We developed a green-blue space exposure index (GBSEI) and four landscape configuration indices: coupling (GBSCI), shape (GBSSI), fragmentation (GBSFI), and connectivity (GBSCOI). Higher GBS exposure (95th vs 5th percentile of GBSEI) was associated with significantly lower heat-related mortality risk (ratio of relative risk [RRR] = 1.13, 95% CI of 1.08-1.18). Specific landscape configurations were also crucial: higher coupling and connectivity, and less complex shapes, were associated with 7% (95% CI of 1%, 13%), 7% (95% CI of 1%, 13%), and 6% (95% CI of 2%, 10%) lower mortality risks, respectively. While GBS fragmentation showed no significant effect on all-cause mortality, it was linked to a lower risk of heat-related cardiovascular mortality. These protective effects were more pronounced at extreme heat levels and were stronger in females. Notably, while the protective effect of GBS quantity was universal, the benefits of optimized configurations were observed exclusively in high-income subdistricts. This study provides direct epidemiological evidence that not only GBS quantity but also its quality (specifically higher coupling, connectivity, and lower shape complexity) significantly protect against heat-related mortality, offering critical insights for evidence-based urban planning to design climate-resilient cities.

Understanding the evolution of regional water use structures and their underlying drivers is essential for optimizing water resource management and promoting sustainable development at the regional level. This study investigates the three major urban agglomerations in China-Beijing-Tianjin-Hebei (BTH), the Yangtze River Delta (YRD), and the Pearl River Delta (PRD)-and analyzes data from 2014 to 2023 using information entropy, Lorenz curves, Gini coefficients, and grey relational analysis to examine the evolution of water use structure and its driving factors. The findings reveal that: (1) total water use remained stable in BTH, fluctuated upward in YRD, and slightly declined in PRD; (2) unconventional water resources (UWR) expanded substantially across all three regions, contributing to structural optimization, with agricultural and industrial water shares declining while domestic and ecological shares increased; (3) the grey relational analysis identified distinct dominant drivers across sectors and regions. In agriculture, the effective irrigated area and sown area for grain crops were the most influential; for industrial water use, wastewater discharge was predominant in BTH, the number of enterprises in YRD, and the proportion of the secondary industry in PRD; for domestic water, urbanization was the primary driver in BTH, per capita usage in YRD, and population growth in PRD; finally, for ecological water, UWR and reclaimed water were significant in BTH and PRD, but less so in YRD. These findings highlight the role of UWR in alleviating water scarcity and underscore the need for region-specific policies, as well as a more refined quantification of policy intensity in the future.

Abstract Accurate wind speed forecasting is essential for daily activities and socio‐economic production. This study employs an explainable machine learning (ML) model to correct wind speed forecasts from a numerical weather prediction (NWP) model over weather stations across lead times of 1–24 hr in Zhejiang Province, China. Eleven meteorological variables derived from the NWP model are used as predictors. The results demonstrate that ML model substantially improves the original NWP forecasts, reducing the root mean square error of approximately 20%–40% at most stations and about 10% at certain coastal stations. The corrected forecasts also consistently achieve higher Kling‐Gupta Efficiency scores and Forecast Accuracy across all lead times. To enhance model interpretability, we apply Split Count and SHapley Additive exPlanation analyses. The results indicate that the friction velocity (UST) is the most influential predictor and reveal a threshold beyond which the ML model's correction performance improves markedly. The ML model performance slightly declines in coastal regions, likely due to the inconsistent representation of UST between the land and water surface in the NWP model. Monthly analysis further shows superior model performance in November and December, when UST values are higher. This study underscores the value of explainable ML models in improving NWP wind forecasts and provides insights for correcting meteorological variables in NWP models.

Accurate prediction of daily mortality is vital for effective early warning systems and the strategic allocation of medical resources, particularly given the rising public health challenges posed by climate change. This study presents a comparative analysis of epidemiological time series models and machine learning (ML) models for predicting daily all-cause mortality across 89 districts in Zhejiang Province, China (2009-2020), utilizing temperature and fine particulate matter (PM2.5) data. The study first evaluated the predictive performance of five temperature indices-Daily Mean Temperature (T), Apparent Temperature (AT), Humidex (HD), Discomfort Index (DI), and Heat Index (HI)-by applying a generalized additive mixed model (GAMM) with a distributed lag non-linear model (DLNM). The HD was identified as the optimal predictor, highlighting the critical role of moisture-driven heat stress in subtropical monsoon climates. Subsequently, the performance of the GAMM was compared with that of time series models (Autoregressive Integrated Moving Average [ARIMA], Prophet) and ML models (eXtreme Gradient Boosting [XGBoost], Random Forest [RF], Support Vector Machine [SVM], Multi-Layer Perceptron [MLP], and Long Short-Term Memory [LSTM]). While the RF model showed slightly higher accuracy (R2 = 0.672 full year; R2 = 0.674 cold season; R2 = 0.641 warm season) than the GAMM (R2 = 0.643 full year; R2 = 0.645 cold season; R2 = 0.626 warm season), this difference was negligible given the stochastic variability inherent in mortality time series data. Crucially, the GAMM provides essential mechanistic transparency in quantifying lagged exposure-response associations. Through explicit assessment of the mortality effects of environmental stressors, the GAMM serves as a superior tool for early warning systems and for guiding environmental health interventions and climate adaptation policies. These findings also provide crucial methodological guidance for selecting models that not only enable real-time mortality forecasting using weather and air pollution data, but also effectively support the early detection of abnormal mortality events in predictive health surveillance.

Sea surface reflectance is a key underlying-surface parameter for remote sensing retrievals of sea fog, sea wind, and marine aerosols, and it exhibits significant variability across different times and ocean-current-controlled regions, with maximum variations of up to approximately 15

Urban greenness is celebrated for its environmental and health benefits, yet its association with ozone (O-3)-related health risk via biogenic volatile organic compound (BVOC) emissions remains underexplored. Integrating WRF-CMAQ model simulations and population-based epidemiological analyses using a case time-series study design, we examined the paradoxical link between greenness and O-3 formation and associated mortality risk in Zhejiang, China, from 2013 to 2020. The association between per IQR increase in O-3 and all-cause mortality risk was significantly stronger in subdistricts with a high greenness exposure level (mortality increase in 4.8%, 95% CI: 3.8-5.7) compared to subdistricts with a low greenness exposure level (1.0%, 95% CI: 0.2-1.7; P for difference < 0.001). This observational association is supported by the WRF-CMAQ model simulations, which estimated a median greenness contribution to O-3 formation of 13.76% (IQR: 5.68%) in summer and 1.16% (0.85%) in winter. Similar difference in mortality risk was also observed for cardiovascular mortality and respiratory mortality. This effect modification was consistent across age and sex subgroups and more pronounced during the cold season and in rural areas. By highlighting the counterintuitive role of greenness in O-3-related health risks, our study offers critical insights for urban greening, emphasizing the need to balance ecological ambitions with public health imperatives for a sustainable environment.

This study employs an ensemble modeling approach to systematically assess the impacts of human activities and climate change on suitable habitats of five Taxus species in China (T. wallichiana var. mairei, T. cuspidata, T. chinensis, T. wallichiana, and T. yunnanensis). The research integrates ten statistical and machine learning algorithms alongside eight CMIP6 climate models, analyzing habitat changes through 2100 under four emission scenarios (SSP1-2.6 to SSP5-8.5). Results reveal that human activities are associated with reductions in habitat suitability across all species, though vulnerabilities differ markedly. T. wallichiana var. mairei, distributed in densely populated mid-lower Yangtze River mountains, experiences the highest and most rapidly increasing anthropogenic pressure (Human Footprint Index rising from 11 in 1993 to 13 in 2009), with highly suitable habitat contracting from 14 & times; 1011 m2 to 11 & times; 1011 m2. T. cuspidata, constrained by its narrow distribution range, shows the strongest negative association between human footprint and habitat suitability among the five taxa, with modeled suitable habitat area declining from 3.6 & times; 1011 m2 under the climate-only model to 2.75 & times; 1011 m2 under the HF2009 model. Climate change poses more severe long-term threats. Under extreme warming (SSP5-8.5), model projections suggest T. cuspidata suitable habitat could decline to approximately 2.4 & times; 1011 m2 by 2081-2100, though this estimate is subject to greater uncertainty given the limited occurrence records available for this species (n =14). All species exhibit consistent northwestward migration toward higher elevations, but geographic barriers-particularly the absence of suitable mountainous terrain north of the Yangtze River-will prevent northward tracking, resulting in inevitable habitat loss. The study emphasizes urgent needs for adaptive conservation strategies including high-elevation protected area networks, assisted migration, and comprehensive monitoring systems.

Accurate crowd counting under uneven illumination at nighttime is critical for real-world applications. However, existing methods struggle with complex illumination variations. In this work, we present the first approach specifically designed for nighttime crowd counting, based on the insight that effective features should be both semantically rich and context-aware to handle uneven illumination conditions. Our method includes three key innovations: a Stable Diffusion backbone that extracts robust multi-scale visual features to improve illumination invariance; textual cues that explicitly describe scene type, illumination condition, and crowd density, providing high-level semantic guidance; and an image-text fusion module that enables deep interaction between visual and textual modalities, enhancing the model’s ability to distinguish people from complex backgrounds. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in nighttime crowd counting under uneven illumination, offering both practical value and technical innovation for real-world deployment.

Solar power is expected to play a key role in achieving global carbon neutrality by the mid‐to‐late 21st century. However, photovoltaic (PV) plant constructions may affect regional climates by altering surface properties and the energy balance. This study applies an advanced “space‐and‐time” method combined with high‐quality satellite products to comprehensively assess the impacts of 57 PV plants for different land cover types in China. The results indicate an overall surface albedo decrease (−0.025; −10.9%) due to PV constructions, with the largest decrease in barren lands (−0.03; −12.2%) and more pronounced variation in winter. Moreover, the decreases in direct and diffuse albedo caused by PV installations are comparable. PV‐induced surface broadband emissivity (BBE) changes vary in sign, with plants in barren lands exhibiting a relatively consistent pattern (1.7 × 10 −3 ; 0.2%). The combined effect of PV‐induced surface albedo and BBE changes contribute to surface land surface temperature (LST) variations. Daytime LST decreases more markedly (–0.36 K) with greater seasonal variation than nighttime LST (−0.07 K), dominating the daily mean LST changes (−0.23 K). Correlation analysis indicates that PV plants exhibit different cooling mechanisms during the day and night. Changes in surface ET caused by PV constructions reflect variations in vegetation, with croplands experiencing the strongest reduction (−2.13 mm/year; −1.0%), particularly in summer. This study offers valuable insights into the local climate impacts of PV plants and their interactions with soil and vegetation, providing a more comprehensive and reliable basis for simulating the climate effects of PV plants.

More than half of the global population now resides in urban areas, and that number is expected to increase to 60% by 2030 and 70% by 2050. Under the warming climate, extreme precipitation, short-term extreme precipitation in particular, tends to increase, leading to a higher risk of flood disasters in urban areas and posing greater challenges to urban construction and social emergency management. Cities themselves can affect the dynamic and thermodynamic structure of the atmosphere through, e.g., the urban heat island effect, increased surface friction, and anthropogenic aerosol emissions, which then influence the evolution of convection and the associated precipitation. The related nonlinear physical processes are very complex. This five-part talk will mainly present our recent studies on the relationship between urbanization and extreme precipitation in China. First, a background on changes of urban extreme precipitation worldwide. Second, the physical processes producing extreme hourly precipitation in the two major coastal urban agglomerations in China (i.e., the Pearl River Delta and the Yangtze River Delta), focusing on the collective roles played by multiple cities, coastlines and topography. Third, the possible impact of urbanization on the disastrous extreme rainfall event in Zhengzhou, the capital city of Henan Province in central China on July 20, 2022. Fourth, the high uncertainty of modeling urban extreme precipitation at monsoon coast (South China) using an advanced regional earth system model at convection-permitting resolutions. Finally, concluding remarks.

Gaoyang Low Uplift, situated in Jizhong Depression's central region, is a key geothermal zone in the North China Plain yet remains under-researched regarding its geothermal characteristics. This study selects it as a model area, probing into the ground heat flow and lithospheric thermal structure of its southern and northern parts via geothermal logging and rock-sample tests. By integrating regional tectonic evolution and stratigraphic and structural distribution, the study highlights the significance of various parameters in understanding the lithospheric thermal structure for geothermal resource development in the area. The advantageous geothermal conditions in the northern region stem from several factors: higher mantle heat flow and higher deep temperatures, a thinner lithosphere, shallowly buried carbonate geothermal reservoirs, and extensive extensional water-conducting faults within the Cenozoic strata. Here, mantle heat flow is the key driver of geothermal resources formation. By influencing the strength of geological activity, it in turn affects the other factors.

Early identification of Schizophrenia Spectrum Disorder (SSD) is crucial for effective intervention and prognosis improvement. Previous neuroimaging-based classifications have primarily focused on chronic, medicated SSD cohorts. However, the question remains whether brain metrics identified in these populations can serve as trait biomarkers for early-stage SSD. This study investigates whether functional connectivity features identified in chronic, medicated SSD patients could be generalized to early-stage SSD. Data were collected from 502 SSD patients and 575 healthy controls (HCs) across four medical institutions. Resting-state functional connectivity (FC) features were used to train a Support Vector Machine (SVM) classifier on individuals with medicated chronic SSD and HCs from three sites. The remaining site, comprising both chronic medicated and first-episode unmedicated SSD patients, was used for independent validation. A univariable analysis examined the association between medication dosage or illness duration and FC. The classifier achieved 69

Deep learning has shown significant advantages in object detection, particularly with the You Only Look Once (YOLO) model. YOLO adopted an end-to-end training and detection method that balances speed and accuracy, making it an effective way for synthetic aperture radar (SAR) ship detection. This paper mainly compared several mainstream YOLO series, focusing on detection accuracy and efficiency in SAR ship detection. The experiment results with SAR Ship Detection Dataset indicated that YOLOv6 outperformed other YOLO series models in terms of accuracy and efficiency, achieving a mAP of 0.742 with FPS being 200.00. However, it has a larger parameter size (of 16.30M). Meanwhile, both YOLOv5 and YOLOv8 showed good overall performance with fewer parameters compared against YOLOv6, while their mAP and FPS were relatively lower. This comprehensive analysis highlighted the advancements of different YOLO series, providing valuable insights for further investigation on improving object detection (e.g., SAR ship detection).

This study utilizes the Weather Research and Forecasting model coupled with an atmospheric chemistry model, a multi-layer urban canopy model (UCM), and a building energy model to simulate the extreme rainfall event influencing the Guangzhou city in South China on 7 May 2017. By employing small variations in the longwave emissivity of buildings within the UCM, 11 convective-permitting experiments are conducted. The maximal 18-hr and hourly rainfall accumulation vary from a 2-year return period to as high as a 20 or 40-year return period with notable spatial differences. Comparisons between the more accurate group (GOOD) and less accurate group (POOR) simulations highlight that some minor differences in the near-surface air thermodynamic conditions in urban area could lead to substantial differences in local convection and its impacts on subsequent convective systems. With persistent transportation of warm, moist airflows from the northern South China Sea, formation of a slow-moving mesoscale outflow boundary to the north of the urban agglomeration leads to the development of a quasi-stationary, compactly structured meso-gamma-scale rainstorm in the GOOD simulations. The stronger low-level to near-surface convergence and mid-level cyclonic shear within this system substantially enhance low-level updrafts, leading to increased microphysical production and stronger horizontal advection of rainwater within the system. These findings offer some process-based understanding about the uncertainties in simulating urban extreme rainfall and underscore the need to develop ensemble forecasting methods for convection-permitting numerical models that incorporate increasingly complicated representations of anthropogenic influences. Precise forecasting of extreme precipitation in cities is an urgent need for hazards mitigation, but very challenging. It is unclear how well the state-of-the-art numerical models with the most advanced representations of natural and anthropogenic physical processes can simulate urban extreme precipitation. Therefore, we conduct 11 experiments with small variations in a physical parameter of buildings to simulate an extreme rainfall influencing Guangzhou city using a state-of-the-art coupled model with very high resolutions to resolve the initiation and propagation of extreme rainfall-producing convection. We find the small changes in the setting led to substantial differences in the location and intensity of rainfall, for example, the simulated rainfall accumulations vary from once every 2 to 40 years. By comparing those experiments with good and poor results, we illustrate why the simulated rainfall differ so much in the new perspective of convection evolution. The small differences in near-surface air conditions over cities can lead to huge bifurcation in convection development. Whether the continuous lifting of warm onshore airflows can be reproduced dictates whether a well-organized rainstorm can subsequently form. The dynamical structure of the rainstorm can substantially modulate the microphysical production and transportation of rainwater and thus the maximal hourly rain rates. The simulated rainfall shows high uncertainties in 11 experiments with only minor changes in an urban canopy parameter Small differences in the urban near-surface air conditions lead to huge variations in local convection and subsequent rainstorms The uncertainties in simulating mesoscale and convective-scale processes lead to the uncertainties in predicting extreme rainfall

The unique geographical and climatic conditions in the Three-River Headwaters Region gave birth to distinctive plant species and vegetation types. To reveal the spatial distribution of plant communities and soil habitats along the riparian zone of the Sanjiangyuan Region and their influencing mechanisms, 14 survey plots were set up （ten from the Yangtze River source, two from the Lancang River source, and two from the Yellow River source）, and the effects of soil nutrient characteristics （especially soil phosphorus morphology）, climate factors, and river topography on plant community characteristics were quantitatively analyzed. The results showed that the plant community composition in the riparian zone of the source of the three rivers was dominated by perennial herbs （72.2%）, followed by annual herbs （20.4%） and shrubs （7.4%）. The dominant plants were Stipa purpurea, Polygonum orbiculatum, Carex parvula, Potentilla anserina, and Gentiana straminea. The average plant coverage, Shannon-Wiener index, and Pielou index were （64.4% ±23.6%）, （1.31 ±0.42）, and （0.84 ±0.08）, respectively. The plant community diversity index was the highest in the Yangtze River source, followed by that in the Lancang River source, and the lowest in the Yellow River source. The soil pH of the riparian zone of the Yangtze River source was significantly higher than that of the Lancang River source, whereas the mean contents of organic matter, total nitrogen, and Fe-Al combined phosphorus were significantly lower than those of the Lancang River source. The calcium and magnesium-combined phosphorus was the main form of phosphorus in riparian soil （63.89%）. Temperature, soil organic phosphorus content, and pH had significant effects on plant composition in the riparian zone of the Three-River Headwaters Region, whereas soil calcium and magnesium-combined phosphorus content had significant effects on plant community diversities. These results may deepen the scientific understanding of the evolution trend and genetic mechanism of plant communities in the riparian zone of the Three-River Headwaters Region.

This study investigates the characteristics of tropical cyclones (TCs) that cause extreme hourly precipitation (EXHP) in Zhejiang, China, using datasets from 67 national stations (Con-ST) and 1551 surface stations (All-ST), spanning 1973-2020 and 2011-2020, respectively. Our analysis revealed notable variations in the EXHP caused by individual TCs. The top 10 % of TCs contributed 37.2-38 % of the total TC-induced EXHP amount, while the bottom 50 % only accounted for 5.8-22.7 %. Using sparse stations may overestimate the impact of TCs causing EXHP in the lower to middle rankings. Long-term trend analysis suggested a consistent increase in TC-induced EXHP despite a decreasing trend in the number of TCs affecting Zhejiang. High-value EXHP centers tended to be concentrated in mountainous areas within 0-50 km from the coastline, where Con-ST stations are sparse and can significantly underestimate EXHP. The maximum amount of EXHP per TC increased logarithmically with the number of observation stations. In Zhejiang, EXHP predominantly occurred northeast of the TC centers (50.4-61.7 %) and within 500 km from the TC center (69.5-81.5 %). High-frequency EXHP centers exhibited a clockwise rotation with increasing distance from the TC center-a pattern resembling a "spiral rainband." A key area where most EXHP in Zhejiang occurred when TC centers remained within this area was identified. The TC intensity within the key area was a key factor influencing EXHP occurrence in Zhejiang, whereas the duration of TC center residence within the key area and the distance of its movement were crucial predictors of significant EXHP occurrence. The analysis of large-scale environmental fields revealed that high-EXHP TCs are characterized by strong upper-level divergence, intense upward motion, and an expanded subtropical high. The southeasterly steering airflow drives these TCs northwestward, prolonging their impact on Zhejiang and resulting in significant moisture accumulation and EXHP.

Simulation of multispectral broadband data from hyperspectral profiles is applicable for many purposes, mainly including sensor assessment and cross-calibration. For the simulation process, several aggregation methods have been proposed. In this paper, three aggregation methods were implemented, to investigate the impacts associated with method on the simulation of multispectral broadband. Comparative analyses were conducted in terms of channel reflectance and several derived vegetation indices, while mainly taking the wide field of view (WFV) sensor onboard Gaofen-6 for case study. Furthermore, impacts on the between-sensor comparability with the Landsat 8 Operational Land Imager (OLI) were discussed. Differences among aggregation methods in reflectance of the Gaofen-6 WFV varied along with channels, and obvious differences were observed in channels over near-infrared (770–890 nm) and red-edge (690–730 nm). Between-sensor difference relative to the Landsat 8 OLI was observed mainly over near-infrared, while the variations among aggregation methods were about 0.4%-2.0%.

Benefited from the increased satellite observations with medium spatial resolution, land use/cover mapping at local to global scales has provided important supports for society and academy community. For specific purposes (e.g., disaster assessment, detecting surface abrupt change), it is needed to increase the observation frequency, through combining different satellite sensors (i.e. as virtual constellation). However, many factors challenge this combination in practice, in which the comparability issue in sensor settings should be considered among various payload platforms. In this study, from the perspective of practical application, a comparative analysis of land use/cover mapping was investigated, with focusing on three observations by the Gaofen-1 (GF-1) wide field of view (WFV), Sentinel-2A Multi-Spectral Instrument (MSI), and Landsat-8 Operational Land Imager (OLI) respectively. Four methods were implemented in classification experiments. Preliminary results showed that the Sentinal-2A MSI outperformed the GF-1 WFV and the Landsat-8 OLI in classification, no matter which classifier was considered. Meanwhile, the higher spatial resolution of the GF-1 WFV certainly compensated its lack of spectral channels compared against the Landsat-8 OLI. The choice of methods affected classification for a specific observation, while the more suitable classifier varied among sensors. This study underlines the compatibility issue in land use/cover mapping with different observations.