Hydrological Applications Research Articles

Assessing the impact of distributed snow water equivalent calibration and assimilation of Copernicus snow water equivalent on modelled snow and streamflow performance

AbstractAccuracy of the Copernicus snow water equivalent (SWE) product and the impact of SWE calibration and assimilation on modelled SWE and streamflow was evaluated. Daily snowpack measurements were made at 12 locations from 2016 to 2019 across a 4104 km2 mixed‐forest basin in the Great Lakes region of central Ontario, Canada. Sub‐basin daily SWE calculated from these sites, observed discharge, and lake levels were used to calibrate a hydrologic model developed using the Raven modelling framework. Copernicus SWE was bias corrected during the melt period using mean bias subtraction and was compared to daily basin average SWE calculated from the measured data. Bias corrected Copernicus SWE was assimilated into the models using a range of parameters and the parameterizations from the model calibration. The bias corrected Copernicus product agreed well with measured data and provided a good estimate of mean basin SWE demonstrating that the product shows promise for hydrology applications within the study region. Calibration to spatially distributed SWE substantially improved the basin scale SWE estimate while only slightly degrading the flow simulation demonstrating the value of including SWE in a multi‐objective calibration formulation. The particle filter experiments yielded the best SWE estimation but moderately degraded the flow simulation. The particle filter experiments constrained by the calibrated snow parameters produced similar results to the experiments using the upper and lower bounds indicating that, in this study, model calibration prior to assimilation was not valuable. The calibrated models exhibited varying levels of skill in estimating SWE but demonstrated similar streamflow performance. This indicates that basin outlet streamflow can be accurately estimated using a model with a poor representation of distributed SWE. This may be sufficient for applications where estimating flow is the primary water management objective. However, in applications where understanding the physical processes of snow accumulation, melt and streamflow generation are important, such as assessing the impact of climate change on water resources, accurate representations of SWE are required and can be improved via multi‐objective calibration or data assimilation, as demonstrated in this study.

Improving the evapotranspiration estimation by coupling soil moisture and atmospheric variables in the relative evapotranspiration parameterization

Accurate monthly evapotranspiration (ET) estimation is essential for many forest, climate, and hydrological applications, as well as for some agricultural uses. In this study, the relationship between ET and relative evapotranspiration (F) using land surface, and atmospheric variables was assessed with 17 FLUXNET sites data in savanna, cropland, and forest land covers, distributed all over the world. A sigmoid (Fs) and a logarithmic (Fl) F expression were included in Walker et al.’s (2019a,b) equations to evaluate their impact on the accuracy of ET estimations. The new parameterizations of ET outperformed the original expression, showing root mean square errors lower than 24% of the mean observed ET. The results presented here suggest that atmospheric parameters, coupled with land explanatory variables included in F estimates, produce more precise ET estimations. In addition, Soil Moisture Active Passive (SMAP) products were used to obtain global maps of ET and compared with Global Landsurface Evaporation Amsterdam Methodology (GLEAM) and Terra Moderate Resolution Imaging Spectroradiometer (MODIS) MOD16 products, displaying the flexibility of these new parametrizations with different sources of data.

A framework for space–time modelling of rainfall events for hydrological applications of weather radar

High-resolution rainfall fields are a crucial tool for many hydrological and hydrodynamic applications, including flood forecasting and urban drainage design. The aim of this study is to explore and exploit the space–time properties of rainfall using Fast-Fourier transforms, to provide a new method for the generation of high-resolution synthetic rainfall grids. These fields have realistic spatio-temporal properties, parametrised using historical radar rainfall events, matching the resolution of weather radar data (1km, 5 min), for events with a duration of 0.5–6 h. Utilising spectral random field theory, simulated rainfall fields are generated with a prescribed correlation structure, anisotropy, advection and marginal rainfall rate proportions and distributions. A model for rainfall generation is demonstrated, with an enriched model parameter sampling architecture using meaningful event clustering, based on space–time event properties. This model framework performs well at recreating short-duration spatio-temporal rainfall events, both visually and statistically. The extension of a clustered rainfall model allows for larger-scale sampling of synthetic event parameters, with specific rainfall event types. There are numerous potential uses for this rainfall model, such as design storms or test cases for applications of radar rainfall estimates. These include but are not limited to nowcasting, numerical weather prediction, flash flood forecasting and machine learning model training data generation.

Improving rainfall-runoff modeling in the Mekong river basin using bias-corrected satellite precipitation products by convolutional neural networks

Accurate rainfall-runoff (RR) modeling is crucial for effective Mekong River Basin (MRB) water resource management. Satellite precipitation products (SPPs) can offer valuable data for such modeling; however, these products often exhibit biases that may adversely affect hydrological simulations. This study aimed to improve RR modeling using bias-corrected SPPs and the Soil and Water Assessment Tool (SWAT) model for MRB. A convolutional neural network-based deep learning framework was employed to correct biases in four SPPs (TRMM, PERSIANN-CDR, CHIRPS, and CMORPH), resulting in four respective bias-corrected SPPs (ADJ_TRMM, ADJ_CDR, ADJ_CHIR, and ADJ_CMOR). The bias-corrected products were compared against a gauge-based dataset in terms of rainfall analysis, and their performance within the SWAT model was assessed over calibration (2004–2013) and validation (2014–2015). Bias-corrected products demonstrated superior performance in rainfall analysis, with ADJ_TRMM outperforming other products. The SWAT model calibration results showed satisfactory performance across all stations, with a Nash-Sutcliffe Efficiency (NSE) ranging from [0.76–0.87]. Integrating bias-corrected SPPs into the SWAT model significantly increased the RR simulations in the MRB, indicated by higher NSE values [0.72–0.85] compared to uncorrected SPPs [-0.37 to 0.85] at the Kratie station. Besides, the inconsistent performance of bias-corrected products between rainfall analysis and RR modeling was observed, with ADJ_CDR outperforming ADJ_TRMM in the SWAT model. These results highlight the significance of using bias-corrected SPPs in hydrological modeling applications, especially in areas with limited ground-based precipitation data, and highlight the need for further research to refine bias correction methods and address the limitations of the SWAT model.

Corn, soybeans and winter wheat water requirements over the contiguous United States between 2013 and 2021: The application of the SEBALIGEE v2 global model

The open-source fully-automated Surface Energy Balance Algorithm for Land-Improved (SEBALI) Google Earth Engine (SEBALIGEE) estimates 30-m actual evapotranspiration (ET) at a monthly rate, a much needed parameter in many hydrological and agricultural applications. An improved version of the basin-based SEBALIGEE v1 is proposed in this paper. The improvement of SEBALIGEE v1, designated as v2, focuses primarily on incorporating advanced machine learning approaches which have enabled for the first time to implement SEBALIGEE over any scale application and enhance its overall performance. More particularly, an evaluation of the monthly ET estimated from the new algorithm across several fluxnet sites in the US, China, Italy, Belgium, Germany, and France, yielded a Mean Absolute Error (MAE) of 12.22 mm/month versus 14.54 mm/month in the original SEBALIGEE v1. Furthermore, we applied the new any-scale capability of SEBALIGEE v2 over the contiguous United States (CONUS) while emphasizing on the three main crops, including corn, soybeans and winter wheat. Our analysis indicated that all three crops presented two similar ET seasonal cycles with peaks occurring in late spring to the summer (May-Aug) and between October and January, corresponding well to the key stages of crop life cycle. Moreover, corn and soybeans exhibited similar magnitudes of ET (36 ∼ 168 mm/month) and higher than winter wheat (33 ∼ 122 mm/month), with large standard deviations observed in the ET estimates amogst all the crops. On interannual comparisons, the corn and soybeans ET and aKc showed higher values than winter wheat, with the highest and lowest years identified and discussed. Following an exploratory analysis against some of the most common interfering variables such as air temperature, dewpoint temperature, surface net solar radiation, wind speed, SPEI drought index calculated on 14 days and 30-days, it was noted that the surface net solar radiation had the most influencing factor on ET in corn and soybeans plantations with R2 values of ∼0.72. The SPEI-30 stands out for winter wheat, showing a water scarcity tolerance up to a month in most of its developing stages. Different management practices are then recommended in each of these two crops’ categories (corn and soybeans vs. winter wheat).

Validation of downscaled 1‐km SMOS and SMAP soil moisture data in 2010–2021

AbstractSoil moisture (SM) is an important component for many applications in agriculture, hydrology, meteorology, and ecology. In past decades, passive/active microwave sensors onboard Earth observation satellites are utilized to obtain SM estimates from radiometer or radar observations. In this study, the Soil Moisture and Ocean Salinity (SMOS) Level 3 daily SM retrievals at 25‐km spatial resolution between 2010 and 2021 were downscaled through an apparent thermal inertia principle‐based algorithm. The 1‐km downscaled SMOS SM retrievals were validated by in situ measurements from 635 sites of 19 SM networks in the world, which were acquired from the International Soil Moisture Network and Texas Soil Observation Network. Additionally, the validation results of the SMOS SM products were compared with those of the Soil Moisture Active Passive (SMAP) global Level 2 enhanced SM products at 1‐km downscaled and original 9‐km resolution in 2015–2021. It shows that the downscaled SMOS SM data have an overall improved accuracy and outperform the coarse‐resolution 25‐km data, with a lower unbiased Root Mean Squared Error of 0.114 m3/m3 on average.

Client-side web-based model coupling using basic model interface for hydrology and water resources

Abstract A recent trend in hydroinformatics has been the growing number of data, models, and cyber tools, which are web accessible, each aiming to improve common research tasks in hydrology through web technologies. Coupling web-based models and tools holds great promise for an integrated environment that can facilitate community participation, collaboration, and scientific replication. There are many examples of server-side, hydroinformatics resource coupling, where a common standard serves as an interface. Yet, there are few, if any, examples of client-side resource coupling, particularly cases where a common specification is employed. Toward this end, we implemented the basic model interface (BMI) specification in the JavaScript programing language, the most widely used programing language on the web. By using BMI, we coupled two client-side hydrological applications (HydroLang and HLM-Web) to perform rainfall–runoff simulations of historical events with rainfall data and a client-side hydrological model as a case study demonstration. Through this process, we present how a common and often tedious task – the coupling of two independent web resources – can be made easier through the adoption of a common standard. Furthermore, applying the standard has facilitated a step toward the possibility of client-side ‘Model as a Service’ for hydrological models.

Generalized logistic model for r largest order statistics, with hydrological application

Generalized logistic model for r largest order statistics, with hydrological application

Evaluation of GSMaP Version 8 Precipitation Products on an Hourly Timescale over Mainland China

A thorough evaluation of the recently released Global Satellite Mapping of Precipitation (GSMaP) is critical for both end-users and algorithm developers. In this study, six products from three versions of GSMaP version 8, including real time (NOW-R and NOW-C), near real time (NRT-R and NRT-C), and post-real time (MVK-R and MVK-C), are systematically and quantitatively evaluated based on time-by-time observations from 2167 stations in mainland China. Among each version, both products with and without gauge correction are adopted to detect the gauge correction effect. Error quantification is carried out on an hourly timescale. Three common statistical indices (i.e., correlation coefficient (CC), relative bias (RB), and root mean square error (RMSE)) and three event detection capability indices (i.e., probability of detection (POD), false alarm ratio (FAR), and critical success index (CSI)) were adopted to analyze the inversion errors in precipitation amount and precipitation event frequency across the various products. Additionally, in this study, we examine the dependence of GSMaP errors on rainfall intensity and elevation. The following main results can be concluded: (1) MVK-C exhibits the best ability to retrieve rainfall on the hourly timescale, with higher CC values (0.31 in XJ to 0.47 in SC), smaller RMSE values (0.14 mm/h in XJ to 0.99 mm/h in SC), and lower RB values (−4.78% in XJ to 16.03% in NC). (2) Among these three versions, the gauge correction procedure plays a crucial role in reducing errors, especially in the post-real-time version. After being corrected, MVK-C demonstrates an obvious CC value improvement (>0.3 on the hourly timescale) in various sub-regions, increasing the percentage of sites with CC values above 0.5 from 0.03% (MVK-R) to 28.47% (MVK-C). (3) GSMaP products generally exhibit error dependencies on precipitation intensity and elevation, particularly in areas with drastic elevation changes (such as 1200–1500 m and 3000–3300 m), where the accuracy of satellite precipitation estimates is significantly affected. (4) CC values decreased with an increasing rainfall intensity; RB and RMSE values increased with an increasing rainfall intensity. The results of this study may be helpful for algorithm developers and end-users and provide a scientific reference for different hydrological applications and disaster risk reduction.

Inter-comparison and assessment of digital elevation models for hydrological applications in the Upper Mahi River Basin

Inter-comparison and assessment of digital elevation models for hydrological applications in the Upper Mahi River Basin

SWAT model applications in hydrology: A systematic review

SWAT model applications in hydrology: A systematic review

Beyond Exact Repeat Missions: Embracing Geodetic Altimetry for Inland Water Monitoring and Modeling

Satellite radar altimetry has become an essential tool for hydrological research over the past 2 decades. Unlike imagery that quantifies the water dynamics from the horizontal dimension, altimetry observations deliver vertical information, which is crucial for hydrological research. Geodetic mission (GM) altimetry data, characterized by long repeat periods compared to exact repeat missions, have been underutilized in hydrology. This paper aims to advocate for integrating geodetic altimetry data into inland water research and bring awareness to its potential applications. We demonstrated the values of GM data from CryoSat-2, Saral/AltiKa, Jason-1, and Jason-2 through 3 applications: (a) large-scale lake monitoring for improved understanding of regional and global hydrological cycles, (b) retrieval of local geoid undulations over large lakes to enhance the precision of individual water level observations, and (c) mapping river longitudinal profiles and construction of time series of river levels. We believe that the findings of this study will pave the way for more comprehensive utilization of geodetic altimetry data in diverse hydrological applications, ultimately advancing inland water altimetry.

Enhancing short-term streamflow forecasting of extreme events: A wavelet-artificial neural network hybrid approach

Accurate short-term streamflow forecasting models are crucial for effective water resource management, enabling timely responses to extreme flood or drought events and mitigating potential socioeconomic damage. This study proposes robust hybrid Wavelet Artificial Neural Network (WANN) models for real-world hydrological applications. Two WANN variants, WANNone and WANNmulti, are proposed for short-term streamflow forecasting of extreme (high and low) flows at eight gauging stations within Brazil's Paraíba do Sul River basin. WANNone directly feeds both the original streamflow data and the decomposed components obtained through an À Trous wavelet transform into the ANN architecture. Conversely, WANNmulti utilizes separate ANNs for the original data, with the final streamflow estimate reconstructed via the inverse wavelet transform of the individual ANN outputs. The performance of these WANN models is then compared against conventional ANN models. In both approaches, Bayesian optimization is employed to fine-tune the hyperparameters within the ANN architecture. The WANN models achieved superior performance for 7-day streamflow forecasts compared to conventional ANN models. WANN models yielded high R2 values (>0.9) and low MAPE (4.8%–14.7%) within the expected RMSE range, demonstrating statistically significant improvements over ANN models (71% and 75% reduction in RMSE and MAPE, respectively, and 69% increase in R2). Further analysis revealed that WANNmulti models generally exhibited superior performance for low extreme flow predictions, while WANNone models achieved the highest accuracy for high extreme flows at most stations. WANN models' strong performance suggests their value for real-time flood warnings, enabling improved decision-making in areas like flood/drought mitigation and urban water planning.

IMPLEMENTATION OF GABELLA METHOD AND RANDOM FOREST FOR GROUND CLUTTER DETECTION IN PADANG WEATHER RADAR DATA

Weather radar is an active remote sensing instrument for various hydrological and meteorological applications. One advantage of weather radar is its ability to detect rainfall in space and time with high spatial resolution. However, one of the issues that contaminate radar observations is ground clutter. Ground clutter is a signal or echo from non-meteorological objects on the earth’s surface that are stationary in the time domain. Detecting and mitigating clutter effects is crucial to achieve precise weather measurements. This research aims to implement the Gabella and random forest methods to detect ground clutter in Padang weather radar data and determine the optimal method between the two. The implementation of the Gabella method for detecting ground clutter in Padang weather radar data was suboptimal. This was due to the most duplicated data at the same point being only 15.97% of the total data. Meanwhile the random forest method obtained a kappa value of 92.03%. This indicates that the random forest model created using 2000 trees as the parameter performs well. Based on these results, the random forest method identified as the most optimal approach for detecting ground clutter in Padang weather radar data.

Proposal for Real-time Quality Control Method to Enhance Hydrological Application of Radar Rainfall

The primary aim of a rain radar is to observe ground-level rainfall accurately. Effective quality control of rain radar data is necessary to ensure accuracy. In the field of hydrology, various methods have been employed to improve the quality of radar rainfall by correcting or synthesizing it with gauge rainfall. However, it is more important to enhance the quality of radar polarimetric variables in order to improve the quality of radar rainfall. Rain radar systems generate various polarimetric variables through complex radar hardware systems and signal processing algorithms. Measurement errors may arise from equipment abnormalities, inappropriate operating settings, and obstructions in observation during signal processing algorithms and production process of polarimetric variables. Because rain radar is an observation device operating in real time, it entails more frequent and continuous quality control compared to flowmeters that intermittently measure streamflow. This study introduces a series of real-time quality control methods tailored for rain radar, including inspection of radar rainfall accuracy, quality analysis of polarimetric variables (ρ<sub>HV</sub>, Z<sub>DR</sub>, Φ<sub>DP</sub>), error estimation of polarimetric variables, and long-term variability of errors.

Impact of land use/land cover changes on evapotranspiration and model accuracy using Google Earth engine and classification and regression tree modeling

This research uses a Classification and Regression Tree (CART) model with Google Earth Engine (GEE) to assess the winter season’s land cover and change detection mapping impact on the evapotranspiration (crop water requirement) parameters. Winter seasons, crucial for agricultural planning, and irrigation water requirement challenges in accurately mapping land cover and detecting changes due to the dynamic nature of farming practices during this period. In this study, Landsat-8 OLI images have been combined to map Land use and Land cover (LULC) and other change detection mapping in Akola Block, Maharashtra, India, during the 2018–2022 winter season. As an discoverer researcher that found detailed information of LULC classes during last 2018 to 2022 winter seasons, the use of the CART model in combination with a cloud-computing GEE demonstrates to be a practical approach for accurate land cover classification and change detection maps to create a pixel-based winter seasons information of study area. The novelty of this study lies in its innovative use of GEE, a powerful platform for remote sensing and geospatial analysis, to create LULC maps with remarkable accuracy. Achieving a 100% training accuracy across the four years under consideration is an exceptional feat, highlighting the reliability and stability of the methodology. Furthermore, the validation accuracy values, ranging from 89 to 94% for the winter seasons of 2018 to 2022, underscore the robustness of this approach. Such consistently high accuracy in mapping LULC over time is a groundbreaking achievement and offers a new dimension to the field of hydrology. For the hydrological community, the implications of this study are profound. Accurate LULC mapping and change detection provide critical data for modeling and analyzing the effects of land use changes on water resources, watershed management, and water quality. The User, Kappa, and Producer accuracy metrics used in this research highlight the model’s performance and its suitability for hydrological applications. These accurate LULC maps can aid in the development of hydrological models, forecasting, and decision-making processes, ultimately contributing to more effective water resource management and environmental conservation. In summary, this study’s innovative use of GEE, its remarkable accuracy in LULC mapping, and its relevance to the hydrological community demonstrate the potential for advanced remote sensing and geospatial tools to significantly improve our understanding of land use changes and their implications for water resources and environmental management.

Mass-change And Geosciences International Constellation (MAGIC) expected impact on science and applications

SUMMARY The joint ESA/NASA Mass-change And Geosciences International Constellation (MAGIC) has the objective to extend time-series from previous gravity missions, including an improvement of accuracy and spatio-temporal resolution. The long-term monitoring of Earth’s gravity field carries information on mass change induced by water cycle, climate change and mass transport processes between atmosphere, cryosphere, oceans and solid Earth. MAGIC will be composed of two satellite pairs flying in different orbit planes. The NASA/DLR-led first pair (P1) is expected to be in a near-polar orbit around 500 km of altitude; while the second ESA-led pair (P2) is expected to be in an inclined orbit of 65°–70° at approximately 400 km altitude. The ESA-led pair P2 Next Generation Gravity Mission shall be launched after P1 in a staggered manner to form the MAGIC constellation. The addition of an inclined pair shall lead to reduction of temporal aliasing effects and consequently of reliance on de-aliasing models and post-processing. The main novelty of the MAGIC constellation is the delivery of mass-change products at higher spatial resolution, temporal (i.e. subweekly) resolution, shorter latency and higher accuracy than the Gravity Recovery and Climate Experiment (GRACE) and Gravity Recovery and Climate Experiment Follow-On (GRACE-FO). This will pave the way to new science applications and operational services. In this paper, an overview of various fields of science and service applications for hydrology, cryosphere, oceanography, solid Earth, climate change and geodesy is provided. These thematic fields and newly enabled applications and services were analysed in the frame of the initial ESA Science Support activities for MAGIC. The analyses of MAGIC scenarios for different application areas in the field of geosciences confirmed that the double-pair configuration will significantly enlarge the number of observable mass-change phenomena by resolving smaller spatial scales with an uncertainty that satisfies evolved user requirements expressed by international bodies such as IUGG. The required uncertainty levels of dedicated thematic fields met by MAGIC unfiltered Level-2 products will benefit hydrological applications by recovering more than 90 per cent of the major river basins worldwide at 260 km spatial resolution, cryosphere applications by enabling mass change signal separation in the interior of Greenland from those in the coastal zones and by resolving small-scale mass variability in challenging regions such as the Antarctic Peninsula, oceanography applications by monitoring meridional overturning circulation changes on timescales of years and decades, climate applications by detecting amplitude and phase changes of Terrestrial Water Storage after 30 yr in 64 and 56 per cent of the global land areas and solid Earth applications by lowering the Earthquake detection threshold from magnitude 8.8 to magnitude 7.4 with spatial resolution increased to 333 km.

Comparing three machine learning algorithms with existing methods for natural streamflow estimation

ABSTRACT Natural streamflow data is required in many hydrological applications. However, many basins are located in data-scarce regions or are impacted by human construction and activities. In this paper, we explore three machine learning algorithms, namely artificial neural networks, random forest and light gradient boosting machine, to simultaneously estimate all the parameters of the coupled modèle du Génie Rural à 4 paramètres Journaliers (GR4J) and snow accounting routine called CemaNeige model. A database of 675 basins in the USA and Quebec is used to train and test ensembles. After using the estimated parameters in GR4J, the resulting naturalized streamflow series are compared with those obtained by the established drainage area ratio and spatial proximity transfer methods in 11 test basins. The results indicate that the machine learning algorithms outperform the drainage area ratio and spatial proximity transfer methods. Among machine learning algorithms, random forests obtain lower (better) continuous ranked probability scores than the other methods for 10 out of 11 test basins.

Error modeling and hierarchical Bayesian fusion for spaceborne and ground radar rainfall data

The optimal fusion of multisource rainfall data can improve the accuracy and resolution of a posteriori estimates, which is beneficial for hydrological and meteorological applications. In this study, the errors of ground-based dual-polarization radar (GR) and dual-frequency precipitation radar (DPR) on global precipitation measurement (GPM) satellite rainfall estimation were modeled, and a hierarchical Bayesian (HB) framework was developed for GR and DPR rainfall data fusion. According to the matched optimal estimated GR rainfall and rain gauge data, the GR rainfall error was analyzed, and the error variance varying with rain type and intensity was described and modeled. The rain types were classified based on disdrometer and dual-polarization radar data. By comparing the DPR rainfall product with GR rainfall, the DPR rainfall error was divided into systematic and random errors. The systematic error was linearly fitted, and the probability distributions for the random error and the variable error parameters were analyzed and modeled. Because the parameters for GR and DPR rainfall errors varied with rain type and intensity, we developed a HB fusion approach considering the varying parameters in rainfall error modeling. The performance of the fusion algorithm was evaluated using matched GR and DPR cases, which showed that the HB fusion can effectively improve the consistency between the original DPR rainfall product and rain gauge data, reducing the relative bias by an average of 30% and improving the correlation by an average of 20%. Compared with the conventional Bayesian (CB) fusion algorithm, which is based on overall error modeling, the HB fusion results can improve the root mean square error by an average of 24% and relative bias by 14%.

COMPARISON AND EVALUATION OF MACHINE-LEARNING-BASED SPATIAL DOWNSCALING APPROACHES ON SATELLITE-DERIVED PRECIPITATION DATA

Abstract. Precipitation estimation with high accuracy and resolution is crucial for hydrological and meteorological applications, particularly in ungauged river basins and regions with scarce water resources. Many machine learning (ML) algorithms have been employed in the downscaling of precipitation, however, it remains unclear which algorithm can outperform others. To address this issue, this study evaluates the performance of four ML based downscaling methods to generate high-resolution precipitation estimates at an annual scale. The satellite-derived precipitation data, environmental variables, such as, latitude, longitude, normalized difference vegetation index (NDVI), digital elevation model (DEM), and land surface temperature (LST), as well as the observations from rainfall gauges were used to constructed the regression models. The performance of the four ML algorithms including the Support Vector Regression (SVR), Random Forest (RF), Spatial Random Forest (SRF), and Extreme Gradient Boosting (XGBoost) algorithms was compared with three conventional methods: Multiple Linear Regression (MLR), geographically weighted regression (GWR) and Kriging interpolation model. Results showed that ML-based method generally outperformed traditional interpolation methods in precipitation downscaling, as they had higher accuracy and were better at reproducing the spatial distribution of rainfall. Out of ML approaches, XGBoost received the best performance, followed by SRF, RF and SVR, indicating its robustness of capturing nonlinear relationships. After the XGBoost, better performance of SRF than RF and SVR was found. This might be because the SRF just introduced the spatial autocorrelation into the RF models, which illustrated the importance of capturing spatial variations in ML algorithms. These findings regarding the comparison and assessment provided a novel downscaling method for generating high-resolution precipitation data, which could benefit regional flood forecasting, drought monitoring, and irrigation planning.