A dynamic snow depth retrieval model based on time-series clustering optimization for GPS-IR DOI Creative Commons
Tianyu Wang, Rui Zhang, Yunjie Yang

et al.

Advances in Space Research, Journal Year: 2024, Volume and Issue: 74(7), P. 2831 - 2845

Published: July 6, 2024

Due to the influence of environmental factors (i.e., terrain and surface coverage) around GPS receivers, snow depth retrieval results obtained by existing global positioning system interferometric reflection (GPS-IR) method show significant variability. The resulting loss reliability accuracy limits broad application this technology. Therefore, paper proposes a dynamic model based on time-series clustering optimization for GPS-IR fully leverage multi-source satellite observation data automatic high-precision retrieval. employs Dynamic Time Warping distance measurement combined with K-Medoids algorithm categorize frequency sequences from various trajectories, facilitating effective integration multi-constellation acquisition optimal datasets. Additionally, Long Short-Term Memory networks are integrated capture process long-term dependencies in data, enhancing model's adaptability handling data. Validated against SNOTEL measured standard machine learning algorithms (such as BP Neural Networks, RBF, SVM), capability is confirmed. For P351 AB39 sites, correlation coefficients L1 band were both 0.996, RMSEs 0.051 0.018 m, respectively. experiment that proposed demonstrates superior precision robustness compared previous method. Then, we analyze caused sudden snowfall events. methodology offer new insights into in-depth study monitoring.

Language: Английский

Prediction of Historical, Current, and Future Configuration of Tibetan Medicinal Herb Gymnadenia orchidis Based on the Optimized MaxEnt in the Qinghai–Tibet Plateau DOI Creative Commons
Ming Li, Yi Zhang, Yongsheng Yang

et al.

Plants, Journal Year: 2024, Volume and Issue: 13(5), P. 645 - 645

Published: Feb. 26, 2024

Climate change plays a pivotal role in shaping the shifting patterns of plant distribution, and gaining insights into how medicinal plants plateau region adapt to climate will be instrumental safeguarding rich biodiversity highlands. Gymnosia orchidis Lindl. (G. orchidis) is valuable Tibetan resource with significant medicinal, ecological, economic value. However, growth G. severely constrained by stringent natural conditions, leading drastic decline its resources. Therefore, it crucial study suitable habitat areas facilitate future artificial cultivation maintain ecological balance. In this study, we investigated zones based on 79 occurrence points Qinghai–Tibet Plateau (QTP) 23 major environmental variables, including climate, topography, soil type. We employed Maximum Entropy model (MaxEnt) simulate predict spatial distribution configuration changes during different time periods, last interglacial (LIG), Last Glacial (LGM), Mid-Holocene (MH), present, scenarios (2041–2060 2061–2080) under three (SSP126, SSP370, SSP585). Our results indicated that annual precipitation (Bio12, 613–2466 mm) mean temperature coldest quarter (Bio11, −5.8–8.5 °C) were primary factors influencing orchidis, cumulative contribution 78.5%. The driest season had most overall impact. Under current covered approximately 63.72 × 104/km2, encompassing Yunnan, Gansu, Sichuan, parts Xizang provinces, highest suitability observed Hengduan, Yunlin, Himalayan mountain regions. past, area experienced Mid-Holocene, variations total centroid migration direction. scenarios, projected expand significantly SSP370 (30.33–46.19%), followed SSP585 (1.41–22.3%), while contraction expected SSP126. Moreover, centroids exhibited multidirectional movement, extensive displacement (100.38 km2). This provides theoretical foundation for conservation endangered QTP.

Language: Английский

Citations

9
High-resolution snow depth retrieval by passive microwave based on linear unmixing and machine learning stacking technique DOI

Yanan Bai,

Zhen Li,

Ping Zhang

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 138, P. 104467 - 104467

Published: March 13, 2025

Language: Английский

Citations

0
Snow depth inversion and mapping at 500 m resolution from 1980 to 2020 in Northeast China using radiative transfer model and machine learning DOI
Yanlin Wei, Xiaofeng Li, Lingjia Gu

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 139, P. 104533 - 104533

Published: April 14, 2025

Language: Английский

Citations

0
Inequalities of population exposure and mortality due to heatwaves in China DOI
Peng Tian, F Zhang, Yanyun Yan

et al.

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: unknown, P. 145626 - 145626

Published: May 1, 2025

Language: Английский

Citations

0
A Downscaling Algorithm for Snow Cover Extent over the Tibetan Plateau Based on a Similar Conditional Probability and Otsu’s Method DOI

Yanlong Shen,

Xiaoyan Wang,

Ruixiang Zhu

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2025, Volume and Issue: 63, P. 1 - 14

Published: Jan. 1, 2025

Language: Английский

Citations

0
Rapid degradation of frozen soil environments in thermokarst-affected alpine grasslands on the Qinghai-Tibet Plateau under climate change DOI
Yuanhong Deng, Xiaoyan Li, Chao Yang

et al.

CATENA, Journal Year: 2025, Volume and Issue: 254, P. 108936 - 108936

Published: March 19, 2025

Language: Английский

Citations

0
Power Spectra’s Perspective on Meteorological Drivers of Snow Depth Multiscale Behavior over the Tibetan Plateau DOI Creative Commons
Yueqian Cao, Lingmei Jiang

Land, Journal Year: 2025, Volume and Issue: 14(4), P. 790 - 790

Published: April 7, 2025

The meteorology-driven multiscale behavior of snow depth over the Tibetan Plateau was investigated via analyzing spatio-temporal variability 28 intraseasonal continuous cover regions. By employing power spectra and Kullback–Leibler (K-L) distance, spectral similarities between meteorological factors were examined at scales 5 km, 10 20 50 km across seasons from 2008 to 2014. Results reveal distinct seasonal scale-dependent dynamics: in spring winter, exhibits lower variance with scale breaks around emphasizing critical roles precipitation, atmospheric moisture, temperature, K-L distances smaller scales. Summer shows highest spatial variance, primarily influenced by wind radiation, as indicated 15–45 km. Autumn demonstrates lowest heterogeneity, windspeed driving redistribution finer alignment maps implies that data can be effectively downscaled or upscaled without significant loss information. These findings are essential for improving modeling forecasting, particularly context climate change, well effective water resource management adaptation strategies this strategically vital plateau.

Language: Английский

Citations

0
Efficient estimation of plant species diversity in desert regions using UAV-based quadrats and advanced machine learning techniques DOI
Hangshu Xin, Renping Zhang, Liangliang Zhang

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 385, P. 125614 - 125614

Published: May 6, 2025

Language: Английский

Citations

0
Challenges of earth remote sensing data during geological exploration DOI
Andrey Samsonov,

Yu. A. Churikov,

A. R. Ibragimov

et al.

International Journal of Environmental Science and Technology, Journal Year: 2025, Volume and Issue: unknown

Published: May 10, 2025

Language: Английский

Citations

0
Improved snow depth estimation on the Tibetan Plateau using AMSR2 and ensemble learning models DOI Creative Commons

Qingyu Gu,

Jiahui Xu, Jingwen Ni

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 133, P. 104102 - 104102

Published: Aug. 19, 2024

Snow depth (SD) is essential for studying climate change and hydrological cycle on the Tibetan Plateau (TP). Despite effectiveness of passive microwave remote sensing large-scale SD measurement, its low spatial resolution scanning gaps limit application, particularly in TP region where terrain complex snow distribution exhibits obvious heterogeneity. This study developed Advanced Microwave Scanning Radiometer 2 (AMSR2) downscaling models using ensemble learning methods AMSR2 brightness temperature data from October 1, 2012, to April 30, 2021. We employed five methods—AdaBoost, GBDT, XGBoost, LightGBM, Random Forest—with LightGBM achieving highest accuracy (RMSE=2.66 cm). Recursive feature elimination (RFE) was applied model, optimizing factor selection maintaining high accuracy. The excelled estimating shallow areas (SD<5 cm) with an RMSE 1.60 cm. SHapley Additive exPlanations (SHAP) values were used quantify global local contributions each modeling process. Key factors included cover days, meteorological influences, (BT) at 89 GHz horizontal polarization, although their varied significantly across due environmental gradients. resulting 500 m estimates offer detailed accurate information mountainous regions. Our results help improve water resource management analysis TP.

Language: Английский

Citations

2