Integration of Satellite-Derived and Ground-Based Soil Moisture Observations for a Precipitation Product over the Upper Heihe River Basin, China

Abstract

Precipitation monitoring is important for earth system modeling and environmental management. Low spatial representativeness limits gauge measurements of rainfall and low spatial resolution limits satellite-derived rainfall. SM2RAIN-based products, which exploit the inversion of the water balance equation to derive rainfall from soil moisture (SM) observations, can be an alternative. However, the quality of SM data limits the accuracy of rainfall. The goal of this work was to improve the accuracy of rainfall estimation through merging multiple soil moisture (SM) datasets. This study proposed an integration framework, which consists of multiple machine learning methods, to use satellite and ground-based soil moisture observations to derive a precipitation product. First, three machine learning (ML) methods (random forest (RF), long short-term memory (LSTM), and convolutional neural network (CNN)) were used, respectively to generate three SM datasets (RF-SM, LSTM-SM, and CNN-SM) by merging satellite (SMOS, SMAP, and ASCAT) and ground-based SM observations. Then, these SM datasets were merged using the Bayesian model averaging method and validated by wireless sensor network (WSN) observations. Finally, the merged SM data were used to produce a rainfall dataset (SM2R) using SM2RAIN. The SM2R dataset was validated using automatic meteorological station (AMS) rainfall observations recorded throughout the Upper Heihe River Basin (China) during 2014–2015 and compared with other rainfall datasets. Our results revealed that the quality of the SM2R data outperforms that of GPM-SM2RAIN, Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), ERA5-Land (ERA5) and multi-source weighted-ensemble Precipitation (MSWEP). Triple-collocation analysis revealed that SM2R outperformed China Meteorological Data and the China Meteorological Forcing Dataset. Ultimately, the SM2R rainfall product was considered successful with acceptably low spatiotemporal errors (RMSE = 3.5 mm, R = 0.59, and bias = −1.6 mm).

Assessing rainfall and extreme weather variability for climate resilient agricultural production systems in Nigeria

“…Monitoring such inconsistencies of rainfall in a geographic region and over long-term periods could present a significant challenge, especially with inadequate data (Dinku, 2019;Dieulin et al, 2019) for spatiotemporal variability analysis. The lack of widespread ancillary rainfall data from ground meteorological stations on a scale of regular time intervals would significantly hinder meaningful spatiotemporal rainfall analysis (Le et al, 2020;Adane et al, 2021;Zhang et al, 2022). However, the proliferation of satellite-based sensors in recent years and the advent of geographic Information Systems (GIS) have resolved this bottleneck (Singh et al, 2022;Gosset et al, 2023).…”

Evaluation of Geospatial Interpolation Techniques for Enhancing Spatiotemporal Rainfall Distribution and Filling Data Gaps in Asir Region, Saudi Arabia

“…The selection of an interpolation method, whether deterministic or geostatistical, depends on the trade-off between accuracy and computational efficiency. Deterministic techniques are more straightforward and faster but do not account for the uncertainty associated with the estimation process [34], while geostatistical techniques provide a comprehensive view of the uncertainty associated with the estimation process but are computationally more intensive [35,36]. As a result, several spatial interpolation techniques have been developed that are appropriate for the rapid estimation process [20,[37][38][39][40][41].…”