A long-term daily gridded snow depth dataset for the Northern Hemisphere from 1980 to 2019 based on machine learning
A long-term daily gridded snow depth dataset for the Northern Hemisphere from 1980 to 2019 based on machine learning
复制标题
DOI：
10.1080/20964471.2023.2177435
复制
发表时间：
2023-03
期刊：
影响因子：
4
通讯作者：
Yanxing Hu;T. Che;L. Dai;Yu Zhu;Lin Xiao;Jie Deng;Xin Li
中科院分区：
文献类型：
--
作者：
Yanxing Hu;T. Che;L. Dai;Yu Zhu;Lin Xiao;Jie Deng;Xin Li
高质量的雪深产品对于冰冻圈科学及其相关学科的研究具有重要意义。目前覆盖北方半球的长时间序列雪深产品可分为遥感雪深产品和再分析雪深产品两大类。然而，现有的网格化雪深产品存在一些缺点。遥感雪深产品在时间和空间上是不连续的，往往低估了雪深，而再分析雪深产品具有粗糙的空间分辨率和很大的不确定性。为了克服这些问题，在我们以前的工作中，我们提出了一种新的基于随机森林回归的数据融合框架，该框架对来自地球观测系统的高级微波扫描辐射计（AMSR-E）、高级微波扫描辐射计-2（AMSR-2）、全球气候研究积雪监测（Global Snow Monitoring for Climate Research（GlobSnow）、北方半球积雪深度（NHSD）、ERA中期和现代研究和应用回顾分析，第2版（MERRA-2），结合地理位置（纬度和经度）和地形数据（海拔），这些数据被用作输入自变量。使用超过30，000个地面观测点作为因变量，在不同时间段训练和验证模型。这种融合框架产生了空间分辨率为0.25°的北方半球连续日积雪深度产品的长时间序列。在这里，我们用13，272个观测点比较了融合雪深和原始网格雪深产品，显示了我们产品的精度提高。融合（最佳原始）数据集的评价指数产生的决定系数R2为0.81（0.23），均方根误差（RMSE）为7.69（15.86）cm，平均绝对误差（MAE）为2.74（6.14）cm。融合雪深和现场观测值之间的大部分偏差（88.31%）在-5 cm到5 cm之间。对Sodankylä（SOD）、Old白杨（OAS）、Old Black Spruce（OBS）和Old Jack Pine（OJP）等独立积雪观测点的准确性评估表明，融合后的雪深数据集对于雪深小于100 cm且周围环境相对均匀的情况具有较高的精度。随机选点和独立现场验证的结果表明，在深积雪区和地形复杂区，融合雪深产品的精度没有明显提高。在海拔100 ~ 2000 m范围内，融合雪深精度较高，R2在0.73 ~ 0.86之间。时空分析和Mann-Kendall趋势检验表明，积雪深度呈减小趋势。这种融合的积雪深度产品为了解积雪的时空特征及其与气候变化、水文和水循环、水资源管理、生态环境、雪灾和灾害预防的关系提供了基础。
ABSTRACT A high-quality snow depth product is very import for cryospheric science and its related disciplines. Current long time-series snow depth products covering the Northern Hemisphere can be divided into two categories: remote sensing snow depth products and reanalysis snow depth products. However, existing gridded snow depth products have some shortcomings. Remote sensing-derived snow depth products are temporally and spatially discontinuous and tend to underestimate snow depth, while reanalysis snow depth products have coarse spatial resolutions and great uncertainties. To overcome these problems, in our previous work we proposed a novel data fusion framework based on Random Forest Regression of snow products from Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E), Advanced Microwave Scanning Radiometer-2 (AMSR2), Global Snow Monitoring for Climate Research (GlobSnow), the Northern Hemisphere Snow Depth (NHSD), ERA-Interim, and Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2), incorporating geolocation (latitude and longitude), and topographic data (elevation), which were used as input independent variables. More than 30,000 ground observation sites were used as the dependent variable to train and validate the model in different time periods. This fusion framework resulted in a long time series of continuous daily snow depth product over the Northern Hemisphere with a spatial resolution of 0.25°. Here, we compared the fused snow depth and the original gridded snow depth products with 13,272 observation sites, showing an improved precision of our product. The evaluation indices of the fused (best original) dataset yielded a coefficient of determination R2 of 0.81 (0.23), Root Mean Squared Error (RMSE) of 7.69 (15.86) cm, and Mean Absolute Error (MAE) of 2.74 (6.14) cm. Most of the bias (88.31%) between the fused snow depth and in situ observations was in the range of −5 cm to 5 cm. The accuracy assessment of independent snow observation sites – Sodankylä (SOD), Old Aspen (OAS), Old Black Spruce (OBS), and Old Jack Pine (OJP) – showed that the fused snow depth dataset had high precision for snow depths of less than 100 cm with a relatively homogeneous surrounding environment. The results of random point selection and independent in situ site validation show that the accuracy of the fused snow depth product is not significantly improved in deep snow areas and areas with complex terrain. In the altitude range of 100 m to 2000 m, the fused snow depth had a higher precision, with R2 varying from 0.73 to 0.86. The fused snow depth had a decreasing trend based on the spatiotemporal analysis and Mann-Kendall trend test method. This fused snow depth product provides the basis for understanding the temporal and spatial characteristics of snow cover and their relation to climate change, hydrological and water cycle, water resource management, ecological environment, snow disaster and hazard prevention.