Zheng Mandi, Liu Zhong, Li Jiahui, Xu Zhaohui, Sun Junling
College of Land Science and Technology, China Agricultural University, Beijing 100193, China; Key Laboratory of Arable Land Conservation in North China, Ministry of Agriculture and Rural Affairs, Beijing 100193, China; Institute of Agriculture Resources and Environment Sciences, Tianjin Academy of Agricultural Sciences, Tianjin 300100, China.
College of Land Science and Technology, China Agricultural University, Beijing 100193, China; Key Laboratory of Arable Land Conservation in North China, Ministry of Agriculture and Rural Affairs, Beijing 100193, China.
Sci Total Environ. 2024 Nov 10;950:175260. doi: 10.1016/j.scitotenv.2024.175260. Epub 2024 Aug 8.
Soil moisture plays an important role in the water and heat exchanges between the land surface and atmosphere, and it has great importance for agricultural production, ecological planning, and water resources management. Although microwave remote sensing has been widely used in large-scale soil moisture monitoring, the accuracy of the downscaled retrieval results cannot be guaranteed for regions with high vegetation coverage and high soil heterogeneity. To address these challenges, this study built soil moisture indice set based on MODIS and elevation data by calculating the Pearson correlation coefficient (R) and Maximum Information Coefficient (MIC), then constructed decision tree models (Gradient Boosting Decision Tree and Random Forest) about the indice set and low-resolution Soil Moisture Active Passive (SMAP) by using two ensemble learning methods (Bagging and Boosting). The models were applied to the high-resolution soil moisture indices in Jilin Province for the years 2017 to 2020 to generate 1 km-resolution products. In the validation process, Triple Collocation Analysis (TCA), comparison of soil moisture maps with coarse and fine resolution, and in-situ measurements in Lishu County, Tongyu County, and Jilin City were used to evaluate the differences between downscaling soil moisture results and ground observations at network, seasonal and point scales. The results were as follows: (1) The correlation coefficient (R) calculated by the TCA method was 0.733 (GBDT_36km) > 0.649 (RF_36km), and the error variance was 0.0004 (GBDT_36km) < 0.00058 (RF_36km). (2) R at network scale was 0.798 (GBDT_SM) > 0.662 (RF_SM), RMSE was 0.040 (GBDT_SM) < 0.044 (RF_SM), the point scale R was 0.864 (GBDT_SM) > 0.833 (RF_SM), RMSE was 0.029 (GBDT_SM) < 0.039 (RF_SM). The R in four stages of the growth period was GBDT_SM > RF_SM, RMSE was GBDT_SM < RF_SM. In conclusion, the GBDT and RF models can reliably downscale soil moisture in Jilin Province, and the Boosting ensemble learning method represented by GBDT had a better estimation performance.
土壤湿度在陆地表面与大气之间的水热交换中起着重要作用，对农业生产、生态规划和水资源管理具有重要意义。尽管微波遥感已广泛应用于大规模土壤湿度监测，但对于植被覆盖度高和土壤异质性高的区域，降尺度反演结果的准确性无法得到保证。为应对这些挑战，本研究通过计算皮尔逊相关系数（R）和最大信息系数（MIC），基于MODIS和高程数据构建土壤湿度指数集，然后利用两种集成学习方法（Bagging和Boosting）构建关于该指数集和低分辨率土壤湿度主动被动遥感（SMAP）的决策树模型（梯度提升决策树和随机森林）。将这些模型应用于吉林省2017年至2020年的高分辨率土壤湿度指数，以生成1公里分辨率的产品。在验证过程中，采用三重配置分析（TCA）、粗分辨率和细分辨率土壤湿度图比较以及梨树县、通榆县和吉林市的实地测量，在网络、季节和点尺度上评估土壤湿度降尺度结果与地面观测之间的差异。结果如下：（1）通过TCA方法计算的相关系数（R）为0.733（GBDT_36km）>0.649（RF_36km），误差方差为0.0004（GBDT_36km）<0.00058（RF_36km）。（2）网络尺度上的R为0.798（GBDT_SM）>0.662（RF_SM），均方根误差（RMSE）为0.040（GBDT_SM）<0.044（RF_SM），点尺度上的R为0.864（GBDT_SM）>0.833（RF_SM），RMSE为0.029（GBDT_SM）<0.039（RF_SM）。生长周期四个阶段的R为GBDT_SM>RF_SM，RMSE为GBDT_SM<RF_SM。总之，GBDT和RF模型能够可靠地对吉林省土壤湿度进行降尺度处理，以GBDT为代表的Boosting集成学习方法具有更好的估计性能。
Zotero 插件