Downscaling Groundwater Storage Data in China to a 1-km Resolution Using Machine Learning Methods
نویسندگان
چکیده
High-resolution and continuous hydrological products have tremendous importance for the prediction of water-related trends enhancing capability sustainable water resources management under climate change human impacts. In this study, we used random forest (RF) extreme gradient boosting (XGBoost) methods to downscale groundwater storage (GWS) from 1° (~110 km) 1 km by downscaling Gravity Recovery Climate Experiment (GRACE) Global Land Data Assimilation System (GLDAS) data 0.25° (~25 respectively, China. Three evaluation metrics were employed testing dataset 2004−2016: The R2 ranged 0.77−0.89 XGBoost (0.74−0.86 RF), correlation coefficient (CC) 0.88−0.94 (0.88−0.93 RF) root-mean-square error (RMSE) 0.37−2.3 (0.4−2.53 RF). models GLDAS was 0.64−0.82 (0.63−0.82 CC 0.80−0.91 (0.80−0.90 RMSE 0.63−1.75 (0.63−1.77 downscaled GWS derived GRACE validated using in situ measurements comparing time series variations maintained accuracy original data. interannual changes within 9 river basins between pre- post-downscaling consistent, emphasizing reliability products. Ultimately, annual TWS, provided 2004 2016, providing a solid foundation studying local changes, conducting finer-scale studies adapting policy formulation condition.
منابع مشابه
Downscaling GRACE Remote Sensing Datasets to High-Resolution Groundwater Storage Change Maps of California's Central Valley
NASA’s Gravity Recovery and Climate Experiment (GRACE) has already proven to be a powerful data source for regional groundwater assessments in many areas around the world. However, the applicability of GRACE data products to more localized studies and their utility to water management authorities have been constrained by their limited spatial resolution (~200,000 km2). Researchers have begun to...
متن کاملUWashington: Negation Resolution using Machine Learning Methods
This paper reports on a simple system for resolving the scope of negation in the closed track of the *SEM 2012 Shared Task. Cue detection is performed using regular expression rules extracted from the training data. Both scope tokens and negated event tokens are resolved using a Conditional Random Field (CRF) sequence tagger – namely the SimpleTagger library in the MALLET machine learning toolk...
متن کاملAnalyzing the performance of different machine learning methods in determining the transportation mode using trajectory data
With the widespread advent of the smart phones equipping with Global Positioning System (GPS), a huge volume of users’ trajectory data was generated. To facilitate urban management and present appropriate services to users, studying these data was raised as a widespread research filed and has been developing since then. In this research, the transportation mode of users’ trajectories was identi...
متن کاملScaling information from ENVISAT ASAR data for downscaling of scatterometer derived soil moisture estimates to 1 km resolution
Soil moisture information is an important factor in the fields of hydrology, meteorology and climatology. For hydrological applications, soil moisture data with a spatial resolution of 1 km is often requested. Current remote sensing methods are limited to a spacial resolution of 25–50 km. This study was motivated by the need to improve the resolution of soil moisture information. The aim was to...
متن کاملStatistical downscaling of GRACE gravity satellite-derived groundwater level data
With the continued threat from climate change, population growth and followed by increasing water demand, the need for hydrological data with high spatial resolution and proper time coverage to be felt more than ago. Therefore, having data such as terrestrial water storage changes and groundwater level changes with high resolution spatial helps to plan and make decisions for water resource mana...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2021
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs13030523