Global long term daily 1 km surface soil moisture dataset with physics informed machine learning.

Although soil moisture is a key factor of hydrologic and climate applications, global continuous high resolution soil moisture datasets are still limited. Here we use physics-informed machine learning to generate a global, long-term, spatially continuous high resolution dataset of surface soil moisture, using International Soil Moisture Network (ISMN), remote sensing and meteorological data, guided with the knowledge of physical processes impacting soil moisture dynamics. Global Surface Soil Moisture (GSSM1 km) provides surface soil moisture (0-5 cm) at 1 km spatial and daily temporal resolution over the period 2000-2020. The performance of the GSSM1 km dataset is evaluated with testing and validation datasets, and via inter-comparisons with existing soil moisture products. The root mean square error of GSSM1 km in testing set is 0.05 cm3/cm3, and correlation coefficient is 0.9. In terms of the feature importance, Antecedent Precipitation Evaporation Index (APEI) is the most important significant predictor among 18 predictors, followed by evaporation and longitude. GSSM1 km product can support the investigation of large-scale climate extremes and long-term trend analysis.

Rain Area Detection in South-Western Kenya by Using Multispectral Satellite Data from Meteosat Second Generation.

This study presents a rain area detection scheme that uses a gradient based adaptive technique for daytime and nighttime rain area detection and correction from reflectance and infrared (IR) brightness temperatures data of the Meteosat Second Generation (MSG) satellite. First, multiple parametric rain detection models developed from MSG's reflectance and IR data were calibrated and validated with rainfall data from a dense network of rain gauge stations and investigated to determine the best model parameters. The models were based on a conceptual assumption that clouds characterised by the top properties, e.g., high optical thickness and effective radius, have high rain probabilities and intensities. Next, a gradient based adaptive correction technique that relies on rain area-specific parameters was developed to reduce the number and sizes of the detected rain areas. The daytime detection with optical (VIS0.6) and near IR (NIR1.6) reflectance data achieved the best detection skill. For nighttime, detection with thermal IR brightness temperature differences of IR3.9-IR10.8, IR3.9-WV73 and IR108-WV62 showed the best detection skill based on general categorical statistics. Compared to the Global Precipitation Measurement (GPM) Integrated Mult-isatellitE Retrievals for GPM (IMERG) and the gauge station data from the southwest of Kenya, the model showed good agreement in the spatial dynamics of the detected rain area and rain rate.