Daily Rainfall Estimates Research Articles

High-Resolution Downscaling with Interpretable Relevant Vector Machine: Rainfall Prediction for Case Study in Selangor

Due to the discrepancy in resolution between existing global climate model output and the resolution required by decision-makers, there is a persistent need for climate downscaling. We conducted a study to determine the effectiveness of Relevant Vector Machine (RVM), one of the machine learning approaches, in outperforming existing statistical methods in downscaling historical rainfall data in the complex terrain of Selangor, Malaysia. While machine learning eliminates the requirement for manual feature selection when extracting significant information from predictor fields, considering multiple pivotal factors is essential. These factors include identifying relevant atmospheric features contributing to rainfall, addressing missing data, and developing a significant model to predict daily rainfall intensity using appropriate machine-learning techniques. The Principal Component Analysis (PCA) technique was employed to choose relevant environmental variables as input for the machine learning model, and various imputation methods were utilized to manage missing data, such as mean imputation and the KNN algorithm. To assess the performance of the RVM-based rainfall model, we collected a dataset from the Department of Irrigation and Drainage Malaysia. We used Nash-Sutcliffe Efficiency (NSE) and Root Mean Square Error (RMSE) as evaluation metrics. This study concluded that Relevance Vector Machine (RVM) models are suitable for forecasting future rainfall since they can support large rainfall extremes and generate reliable daily rainfall estimates based on rainfall extremes. In this study, the RVM model was employed to determine a predictive association between predictand variables and predictors.

Evaluation of ERA5 and CHIRPS rainfall estimates against observations across Ethiopia

Satellite-based precipitation estimates and global reanalysis products bear the promise of supporting the development of accurate and timely climate information for end users in sub-Sharan Africa. The accuracy of these global models, however, may be reduced in data-scarce regions and should be carefully evaluated. This study evaluates the performance of ERA5 reanalysis data and CHIRPS precipitation data against ground-based measurements from 167 rain gauges in Ethiopia, a region with complex topography and diverse climates. Focusing over a 38-year period (1981–2018), our study utilizes a point-to-pixel analysis to compare daily, monthly, seasonal, and annual precipitation data, conducting an evaluation based on continuous and categorical metrics. Our findings indicate that over Ethiopia CHIRPS generally outperforms ERA5, particularly in high-altitude areas, demonstrating a better capability in detecting high-intensity rainfall events. Both datasets, however, exhibit lower performance in Ethiopia's lowland regions, possibly the influence of sparse rain gauge networks informing gridded datasets. Notably, both CHIRPS and ERA5 were found to underestimate rainfall variability, with CHIRPS displaying a slight advantage in representing the erratic nature of Ethiopian rainfall. The study’s results highlight considerable performance differences between CHIRPS and ERA5 across varying Ethiopian landscapes and climatic conditions. CHIRPS’ effectiveness in high-altitude regions, especially for daily rainfall estimation, emphasizes its suitability in similar geographic contexts. Conversely, the lesser performance of ERA5 in these areas suggests a need for refined calibration and validation processes, particularly for complex terrains. These insights are essential for the application of satellite-based and reanalysis of rainfall data in meteorological, agricultural, and hydrological contexts, particularly in topographically and climatically diverse regions.

Do satellite-based products suffice for rainfall observations over data-sparse complex terrains? Evidence from the North-Western Himalayas

Remotely sensed observations are crucial for conducting meteorological studies, particularly over complex mountainous terrains such as, the North-Western Himalayas (NWH), which are characterized by a very sparse and uneven distribution of ground observatories. These complex terrains are subject to huge inter-basin climatic and topographic heterogeneity, which often induces large inconsistencies in the form of varying rainfall estimations and observations among the satellite-based gridded precipitation products (GPPs). This underpins the need for a detailed sub-regional validation of GPPs and attribution of the observed discrepancies over such complex terrains. This study provides a comprehensive validation analysis of four major high-resolution GPPs (TMPA-3B42V7, CHIRPS-V2.0, CMORPH-CDR, and PERSIANN-CDR) against the in-situ gridded observations provided by IMD, across the six sub-basins of NWH. Utilizing various descriptive, statistical, and categorical metrics, we evaluated the daily, seasonal, and annual rainfall climatology for each dataset and also extracted their longitudinal and latitudinal error profiles and detection capabilities as a function of elevation and local relief. High inconsistencies were observed among the datasets, with each dataset performing differently over different sub-basins. All the datasets underperformed IMD over higher elevations, while TMPA-3B42V7 performed better even over the Upper Indus sub-basin. CHIRPS-V2.0 performed well over Jhelum, and Chenab sub-basins, whereas the CDR version of CMORPH, performed well over the flatter terrains of Ravi, Beas, and Satluj sub-basins, particularly during the summer monsoons. The IR-based PERSIANN-CDR, on the other hand, failed to capture the daily rainfall estimates and underperformed IMD throughout NWH. The findings further highlight low detection capability of datasets at higher rainfall thresholds, indicating underestimation of extreme rainfall. With respect to the relationship between GPPs performance and topographic components, the results showed that the occurrence frequency of rain detection in GPPs decreases, while the occurrence frequency of over-detection increases with increase in elevation and local relief. Although, the performance of GPPs co-varies with both topographic components, local relief governed by the multi-step topographic gradients comprising valleys, orographic fronts, and orographic interiors was observed to have a more profound effect on error profiles. Lastly, the study identifies and discusses the probable regional (e.g., rainfall structure, orographic influence, biophysical, data scarcity, spatial resolution), and product-specific (e.g., source of generation, remote sensing instrumentation, satellite algorithms, data assimilation techniques) factors attributing to the inconsistencies observed among the datasets. The findings from the present research offer insights to the algorithm developers for improving product accuracy and hydro-meteorologist for utilizing appropriate GPP over respective sub-basin.

Bias correction and spatial disaggregation of satellite-based data for the detection of rainfall seasonality indices

Like many other African countries, Ghana's rain gauge networks are rapidly deteriorating, making it challenging to obtain real-time rainfall estimates. In recent years, significant progress has been made in the development and availability of real-time satellite precipitation products (SPPs). SPPs may complement or substitute gauge data, enabling better real-time forecasting of stream flows, among other things. However, SPPs still have significant biases that must be corrected before the rainfall estimates can be used for any hydrologic application, such as real-time or seasonal forecasting. The daily satellite-based rainfall estimate (CHIRPS-v2) data were bias-corrected using the Bias Correction and Spatial Disaggregation (BSCD) approach. The study further investigated how bias correction of daily satellite-based rainfall estimates affects the identification of seasonality and extreme rainfall indices in Ghana. The results revealed that the seasonal and annual rainfall patterns in the region were better represented after the bias correction of the CHIRPS-v2 data. We observed that, before bias correction, the cessation dates in the country's southwest and upper middle regions were slightly different. However, they matched those of the gauge well after bias correction. The novelty of this study is that, in addition to improving rainfall using CHIRPS data, it also enhances the identification of seasonality indices. The paper suggests the BCSD approach for correcting rainfall estimates from other algorithms using long-term historical records indicative of the rainfall variability area under consideration.

Estimation of daily design rainfall in Argentina from satellite-derived data

Se presentan los resultados de la estimación de las precipitaciones diarias de diseño en Argentina para el 97 % del territorio nacional continental. Este análisis se basó en el procesamiento de los datos de precipitación derivados de satélite (DPDS) del producto CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data), con una resolución espacial de 5 km y una cobertura temporal de 37 años. La extracción de los mapas de precipitación diaria máxima anual (pdMa) se efectuó por medio de códigos ad hoc desarrollados a través de la plataforma Google Earth Engine. Se compararon las series de pdMa provenientes de CHIRPS con las obtenidas a partir de 64 estaciones pluviométricas provistas por el Servicio Meteorológico Nacional (SMN), determinando las pendientes de la regresión lineal. Estos parámetros de la regresión fueron interpolados al territorio bajo estudio para corregir los mapas de pdMa. Los mapas corregidos se procesaron a través de códigos desarrollados en Python para asociar probabilidades empíricas de no excedencia y ajustar la distribución teórica óptima de probabilidades a cada uno de los 106 778 pixeles considerados. A partir de estos resultados se generaron mapas de precipitaciones diarias de diseño para periodos de retorno comprendidos entre 2 y 100 años. Los resultados se validaron contra 30 estaciones provenientes del Sistema Nacional de Información Hídrica, obteniéndose un acuerdo aceptable. Se considera que los resultados obtenidos serán de utilidad en tareas de diseño hidrológico, en especial en las regiones que carecen de registros pluviométricos adecuados para un análisis estadístico tradicional.

Daily maximum rainfall estimation by best-fit probability distribution in the source region of Indus River

Daily maximum rainfall estimation by best-fit probability distribution in the source region of Indus River

Estimation of Daily Design Rainfall in Argentina from Satellite-Derived Data

Estimation of Daily Design Rainfall in Argentina from Satellite-Derived Data

Evaluation and Bias correction of Tropical Applications of Meteorology using SATellite (TAMSAT) daily rainfall estimates over the data-scarce region of Southern Ethiopia

Precipitation data is an intrinsic parameter of rainfall-runoff simulation. since it is strongly hooked into the accuracy of the spatial and temporal representation of the precipitation. In regions where rainfall stations are scarce, additional data sources could also be needed. Satellite platforms have provided a satisfactory alternative because of their global coverage. Tropical Applications of Meteorology using SATellite (TAMSAT) is one such data source provided by the research group of the University of Reading, UK. This dataset provides rainfall estimates across Africa which captures the rainfall pattern in GenaleDawa River basin (southern Ethiopia) but with a magnitude bias of over-estimation and under-estimations. In this study, magnitude bias correction of the TAMSAT dataset with a linear scaling technique resulted in a rainfall grid of the area with ~4 km spatial resolution of a 35 year (1983–2017) daily rainfall dataset. Intercomparison between Satellite rainfall product and observed data were done using point to grid method selecting nine representative metrological stations.The average correlation R is 0.45 and the average NS is 0.028 and the Categorical index POD, FAR, FB and HSS, values were 0.49,0.4,0.84, and 0.4) before bias correction. After bias correction, these values were improved to the average value of R=0.87 and NS =0.764 and POD, FAR, FB, and HSS of (0.71,0.22, 0.92, and 0.66 respectively

Effect of temporal sampling mismatches between satellite rainfall estimates and rain gauge observations on modelling extreme rainfall in the Upper Awash Basin, Ethiopia

Matching the temporal sampling of Satellite Rainfall Estimates (SREs) with rain gauge data is a prerequisite for evaluating the accuracy of SREs. However, some of the previous studies have evaluated the performance of SREs without considering the timing of the daily rain gauge observations. Such uncertainties may affect the application of SREs for studying the statistics of rainfall extremes. Therefore, this study aims to assess the effect of temporal sampling mismatch on the frequency analysis of daily rainfall extremes over a mountainous region in Ethiopia, the Upper Awash basin. For this purpose, we consider the 0-hr, 1-hr, 3-hr, 5-hr, and 6-hr temporal mismatches between SREs and gauges, which emerge from the use of different definitions of daily precipitation in these data sources. To represent those mismatches, the sub-daily TRMM 3B42v7 and sub-hourly IMERG v06B SREs are aggregated for different time windows, and their impacts on the estimation of the Metastastical Extreme Value Distribution (MEVD) parameters, and high-quantile extremes are then quantified using the relative error metrics. Results show that the 1-hr and 3-hr temporal discrepancies between SREs and gauges produce a comparable result in reproducing the observed MEVD parameters and high quantiles of daily rainfall. However, we found different results when the temporal mismatch between SREs and gauges increases from 3-hr to 6-hr. For all temporal mismatches, IMERG v06B outperforms TRMM 3B42v7 for estimating the MEVD parameters and high quantiles of daily rainfall. Both SREs provide the best estimation of high-quantile extremes for shorter return periods than the longer ones. Additionally, the uncertainty of the MEVD parameters is substantial in the lowland (Elevation < 2000 m) than in the highland (Elevation > 2000 m) regions of the basin. Overall, the temporal discrepancy between SREs and gauges leads to discrepancies in rainfall statistics. Therefore, more caution is necessary when applying the daily rainfall estimates of the remotely sensed datasets that have different temporal sampling compared to the daily rain gauge observations.

Rainfall prediction using Extreme Gradient Boosting

Rainfall greatly affects human life in various sectors including agriculture, transportation, etc. and also can affect natural disasters such as drought, floods, and landslides. This situation prompts us to build an accurate rainfall prediction model so that prescriptive measures can be made. Previous research on rainfall prediction uses models that have their limitations and thus produce poor performance. This study aims to build a multivariate rainfall prediction model using the best performing technique to date namely the Extreme Gradient Boosting. This model is built based on 7 years of historical weather data collected by the weather station. The result had demonstrated that the model is capable of producing accurate predictions for daily rainfall estimates with training RMSE of 2.7 mm and the testing MAE of 8.8 mm.

Comparison of two bias correction methods for TRMM 3B42 satellite daily rainfall estimates over Northern Tunisia

The overall objective of this study is to evaluate and correct the Tropical Rainfall Measuring Mission (TRMM) 3B42 algorithm for Northern Tunisia focusing on heavy rainfall events. Two types of correction methods are tested. The first is the combined scheme (CoSch) which was applied in two different ways. CoSch (1) combines satellite data with interpolated in situ data. However, CoSch (2) combines satellite data with a not interpolated in situ map where the pixel value is randomly selected from the rainfall stations belonging this pixel. The second type of correction is the best linear unbiased estimator. The study period is from January 2007 to August 2009. The in situ database is composed of an average of 318 rain gauges. Heavy events are defined as those daily events exceeding 50 mm/day for at least one station. A total of 77 heavy rainfall events result from this selection criterion; 35 events were recorded during the dry period (May to October) and 42 during the wet season (November to April). We first investigate the boxplots of the various evaluation indicators for raw TRMM. The best achievement is for moderate events. The worst performance is for very light and light events. Moreover, we noticed that raw TRMM estimates perform better during wet season. The error decomposition underlined that the highest underestimated values are localized in orographic areas in Le Kef, also in Cap Bon. However, the rainfall overestimation appeared in the central part of the study area (Bizerte and Zaghouan). About the bias correction method comparison, CoSch (1) performance showed a stronger correction than the unbiased estimator which outperforms CoSch (2). As for raw TRMM, CoSch (1) reports better correlation during wet season. The correction of probability of detection (POD) is more important for the wet season reaching 0.9 by the CoSch (1) and unbiased estimator methods. The threat score (TS) coefficients are found not sensitive to the season whatever the correction method.

Spatiotemporal patterns of synchronous heavy rainfall events in East Asia during the Baiu season

Abstract. Investigating the synchrony and interdependency of heavy rainfall occurrences is crucial to understand the underlying physical mechanisms and reduce physical and economic damages by improved forecasting strategies. In this context, studies utilizing functional network representations have recently contributed to significant advances in the understanding and prediction of extreme weather events. To thoroughly expand on previous works employing the latter framework to the East Asian summer monsoon (EASM) system, we focus here on changes in the spatial organization of synchronous heavy precipitation events across the monsoon season (April to August) by studying the temporal evolution of corresponding network characteristics in terms of a sliding window approach. Specifically, we utilize functional climate networks together with event coincidence analysis for identifying and characterizing synchronous activity from daily rainfall estimates between 1998 and 2018. Our results demonstrate that the formation of the Baiu front as a main feature of the EASM is reflected by a double-band structure of synchronous heavy rainfall with two centers north and south of the front. Although the two separated bands are strongly related to either low- or high-level winds, which are commonly assumed to be independent, we provide evidence that it is rather their mutual interconnectivity that changes during the different phases of the EASM season in a characteristic way. Our findings shed some new light on the interplay between tropical and extratropical factors controlling the EASM intraseasonal evolution, which could potentially help to improve future forecasts of the Baiu onset in different regions of East Asia.

Daily Rainfall Estimate by Emissivity Temporal Variation from 10 Satellites

AbstractRainfall retrieval algorithms for passive microwave radiometers often exploit the brightness temperature depression due to ice scattering at high-frequency channels (≥85 GHz) over land. This study presents an alternate method to estimate the daily rainfall amount using the emissivity temporal variation (i.e., Δe) under rain-free conditions at low-frequency channels (19, 24, and 37 GHz). Emissivity is derived from 10 passive microwave radiometers, including the Global Precipitation Measurement (GPM) Microwave Imager (GMI), the Advanced Microwave Scanning Radiometer 2 (AMSR2), three Special Sensor Microwave Imager/Sounders (SSMIS), the Advanced Technology Microwave Sounder (ATMS), and four Advanced Microwave Sounding Units-A (AMSU-A). Four different satellite combination schemes are used to derive the Δe for daily rainfall estimates. They are all 10 satellites, 5 imagers, 6 satellites with very different equator crossing times, and GMI only. Results show that Δe from all 10 satellites has the best performance with a correlation of 0.60 and RMSE of 6.52 mm, compared with the Integrated Multisatellite Retrievals for GPM (IMERG) Final run product. The 6-satellites scheme has comparable performance with the all-10-satellites scheme. The 5-imagers scheme performs noticeably worse with a correlation of 0.49 and RMSE of 7.28 mm, while the GMI-only scheme performs the worst with a correlation of 0.25 and RMSE of 11.36 mm. The inferior performance from the 5-imagers and GMI-only schemes can be explained by the much longer revisit time, which cannot accurately capture the emissivity temporal variation.

Daily rainfall estimates considering seasonality from a MODWT-ANN hybrid model

Abstract Analyses based on precipitation data may be limited by the quality of the data, the size of the available historical series and the efficiency of the adopted methodologies; these factors are especially limiting when conducting analyses at the daily scale. Thus, methodologies are sought to overcome these barriers. The objective of this work is to develop a hybrid model through the maximum overlap discrete wavelet transform (MODWT) to estimate daily rainfall in homogeneous regions of the Tocantins-Araguaia Hydrographic Region (TAHR) in the Amazon (Brazil). Data series from the Climate Prediction Center morphing (CMORPH) satellite products and rainfall data from the National Water Agency (ANA) were divided into seasonal periods (dry and rainy), which were adopted to train the model and for model forecasting. The results show that the hybrid model had a good performance when forecasting daily rainfall using both databases, indicated by the Nash–Sutcliffe efficiency coefficients (0.81–0.95), thus, the hybrid model is considered to be potentially useful for modelling daily rainfall.

Assessment of Near-Real-Time Satellite Precipitation Products from GSMaP in Monitoring Rainfall Variations over Taiwan

This study assessed four near-real-time satellite precipitation products (NRT SPPs) of Global Satellite Mapping of Precipitation (GSMaP)—NRT v6 (hereafter NRT6), NRT v7 (hereafter NRT7), Gauge-NRT v6 (hereafter GNRT6), and Gauge-NRT v7 (hereafter GNRT7)— in representing the daily and monthly rainfall variations over Taiwan, an island with complex terrain. The GNRT products are the gauge-adjusted version of NRT products. Evaluations for warm (May–October) and cold months (November–April) were conducted from May 2017 to April 2020. By using observations from more than 400 surface gauges in Taiwan as a reference, our evaluations showed that GNRT products had a greater error than NRT products in underestimating the monthly mean rainfall, especially during the warm months. Among SPPs, NRT7 performed best in quantitative monthly mean rainfall estimation; however, when examining the daily scale, GNRT6 and GNRT7 were superior, particularly for monitoring stronger (i.e., more intense) rainfall events during warm and cold months, respectively. Spatially, the major improvement from NRT6 to GNRT6 (from NRT7 to GNRT7) in monitoring stronger rainfall events over southwestern Taiwan was revealed during warm (cold) months. From NRT6 to NRT7, the improvement in daily rainfall estimation primarily occurred over southwestern and northwestern Taiwan during the warm and cold months, respectively. Possible explanations for the differences between the ability of SPPs are attributed to the algorithms used in SPPs. These findings highlight that different NRT SPPs of GSMaP should be used for studying or monitoring the rainfall variations over Taiwan for different purposes (e.g., warning of floods in different seasons, studying monthly or daily precipitation features in different seasons, etc.).

Suitability of different data sources in rainfall pattern characterization in the tropical central highlands of Kenya

Uncertainty in rainfall pattern has put rain-fed agriculture in jeopardy, even for the regions considered high rainfall potential like the Central Highlands of Kenya (CHK). The rainfall pattern in the CHK is spatially and temporally variable in terms of onset and cessation dates, frequency and occurrence of dry spells, and seasonal distribution. Appraisal of the variability is further confounded by the lack of sufficient observational data that can enable accurate characterisation of the rainfall pattern in the region. We, therefore, explored the utilisation of satellite daily rainfall estimates from the National Aeronautics and Space Administration (NASA) for rainfall pattern characterisation in the CHK. Observed daily rainfall data sourced from Kenya meteorological department were used as a reference point. The observation period was from 1997 to 2015. Rainfall in the CHK was highly variable, fairly distributed and with low intensity in all the seasons. Onset dates ranged between mid-February to mid-March and mid-August to mid-October for long rains (LR) and short rains (SR) seasons, respectively. Cessation dates ranged from late May to mid-June and mid-December to late December for the LR and SR, respectively. There was a high probability (93%) of dry spell occurrence. More research needs to be done on efficient use of the available soil moisture and on drought tolerant crop varieties to reduce the impact of drought on crop productivity. Comparison between satellite and observed rain gauge data showed close agreement at monthly scale than at daily scale, with general agreement between the two datasets. Hence, we concluded that, given the availability, accessibility, frequency of estimation and spatial resolution, satellite estimates can complement observed rain gauge data. Stakeholders in the fields of agriculture, natural resource management, environment among others, can utilise the findings of this study in planning to reduce rainfall-related risks and enhance food security.

Space-time variogram for daily rainfall estimates using rain gauges and satellite data in mountainous tropical Island of Bali, Indonesia (Preliminary Study)

High spatio-temporal variability of daily rainfall in Bali Island can create the absence of structure in the daily variogram in certain days. This research proposes a new technique applying space–time variogram for 3-successive daily rainfall to detect structure in variogram estimation by merging rain gauges and satellite data applying ordinary kriging (OK), regression kriging with CMORPH (CM), regression kriging with TRMM (TR), and blended monthly rainfall (MONT) to obtain daily blended gridded rainfall estimates. Original retrieval of CMORPH (CM_OR) and TRMM (TR_OR) also used as control points to assess the proposed method. Uncertainty and sensitivity analysis including cross validation were carried out to validate the proposed method.The result shows that a new technique, adapted from CMORPH specific character, can be applied to detect the existence of structure in variogram. Blended gridded daily rainfall estimates of CM has highest probability detection of rainy events, while OK the lowest. Generally, the four interpolation methods (OK, CM, MONT, TR) have low accuracy at leeward and in a coastal area. All of them have almost similar performance indicated by no clear distinction of RMSE value from cross validation. CM, MONT, and TR have a good sensitivity with maximum and minimum temperature, indicating that satellite data can improve the gridded rainfall estimates. However, it is required an improvement of daily gridded rainfall estimates since there are large RMSE values and low coefficient correlation in certain days because of strong and erratic behavior of rainy events in a mountainous tropical island of Bali.

Nine-Year Systematic Evaluation of the GPM and TRMM Precipitation Products in the Shuaishui River Basin in East-Central China

Owing to their advantages of wide coverage and high spatiotemporal resolution, satellite precipitation products (SPPs) have been increasingly used as surrogates for traditional ground observations. In this study, we have evaluated the accuracy of the latest five GPM IMERG V6 and TRMM 3B42 V7 precipitation products across the monthly, daily, and hourly scale in the hilly Shuaishui River Basin in East-Central China. For evaluation, a total of four continuous and three categorical metrics have been calculated based on SPP estimates and historical rainfall records at 13 stations over a period of 9 years from 2009 to 2017. One-way analysis of variance (ANOVA) and multiple posterior comparison tests are used to assess the significance of the difference in SPP rainfall estimates. Our evaluation results have revealed a wide-ranging performance among the SPPs in estimating rainfall at different time scales. Firstly, two post-time SPPs (IMERG_F and 3B42) perform considerably better in estimating monthly rainfall. Secondly, with IMERG_F performing the best, the GPM products generally produce better daily rainfall estimates than the TRMM products. Thirdly, with their correlation coefficients all falling below 0.6, neither GPM nor TRMM products could estimate hourly rainfall satisfactorily. In addition, topography tends to impose similar impact on the performance of SPPs across different time scales, with more estimation deviations at high altitude. In general, the post-time IMERG_F product may be considered as a reliable data source of monthly or daily rainfall in the study region. Effective bias-correction algorithms incorporating ground rainfall observations, however, are needed to further improve the hourly rainfall estimates of the SPPs to ensure the validity of their usage in real-world applications.

A multilayer perceptron and multiclass support vector machine based high accuracy technique for daily rainfall estimation from MSG SEVIRI data

The current paper introduces a new multilayer perceptron (MLP) and support vector machine (SVM) based approach to improve daily rainfall estimation from the Meteosat Second Generation (MSG) data. In this study, the precipitation is first detected and classified into convective and stratiform rain by two MLP models, and then four multi-class SVM algorithms were used for daily rainfall estimation. Relevant spectral and textural input features of the developed algorithms were derived from the spectral MSG SEVIRI radiometer channels. The models were trained using radar rainfall data set colected over north Algeria. Validation of the proposed daily rainfall estimation technique was performed by rain gauge network data set recorded over north Algeria. Thus, several statistical scores were calculated, such as correlation coefficient (r), root mean square error (RMSE), mean error (Bias), and mean absolute error (MAE). The findings given by: (r = 0.97, bias = 0.31 mm, RMSE = 2.20 mm and MAE = 1.07 mm), showed a quite satisfactory relationship between the estimation and the respective observed daily precipitation. Moreover, the comparison of the results with those of two advanced techniques based on random forests (RF) and weighted ‘k’ nearest neighbor (WkNN) showed higher accuracy obtained by the proposed model.

Evaluation of Satellite-Based Rainfall Estimates in the Lower Mekong River Basin (Southeast Asia)

Satellite-based precipitation is an essential tool for regional water resource applications that requires frequent observations of meteorological forcing, particularly in areas that have sparse rain gauge networks. To fully realize the utility of remotely sensed precipitation products in watershed modeling and decision-making, a thorough evaluation of the accuracy of satellite-based rainfall and regional gauge network estimates is needed. In this study, Tropical Rainfall Measuring Mission (TRMM) Multi-Satellite Precipitation Analysis (TMPA) 3B42 v.7 and Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) daily rainfall estimates were compared with daily rain gauge observations from 2000 to 2014 in the Lower Mekong River Basin (LMRB) in Southeast Asia. Monthly, seasonal, and annual comparisons were performed, which included the calculations of correlation coefficient, coefficient of determination, bias, root mean square error (RMSE), and mean absolute error (MAE). Our validation test showed TMPA to correctly detect precipitation or no-precipitation 64.9% of all days and CHIRPS 66.8% of all days, compared to daily in-situ rainfall measurements. The accuracy of the satellite-based products varied greatly between the wet and dry seasons. Both TMPA and CHIRPS showed higher correlation with in-situ data during the wet season (June–September) as compared to the dry season (November–January). Additionally, both performed better on a monthly than an annual time-scale when compared to in-situ data. The satellite-based products showed wet biases during months that received higher cumulative precipitation. Based on a spatial correlation analysis, the average r-value of CHIRPS was much higher than TMPA across the basin. CHIRPS correlated better than TMPA at lower elevations and for monthly rainfall accumulation less than 500 mm. While both satellite-based products performed well, as compared to rain gauge measurements, the present research shows that CHIRPS might be better at representing precipitation over the LMRB than TMPA.