Mapping Fine Spatial Resolution Precipitation from TRMM Precipitation Datasets Using an Ensemble Learning Method and MODIS Optical Products in China

Zhao, Xiaodan; Jing, Wenlong; Zhang, Pengyan

doi:10.3390/su9101912

Cited by 15 publications

(5 citation statements)

References 47 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, there are still some shortcomings in the RF-based NMRI map, e.g., the blocky effect in Figure 9a,d, which affects the continuity of the whole picture. Such blocky effects have also been found in other regression studies using RF models [53,54]. This phenomenon is mainly due to the characteristics of the RF model.…”

Section: Point-surface Fusion Results Of Nmrisupporting

confidence: 70%

Monitoring the Variation of Vegetation Water Content with Machine Learning Methods: Point–Surface Fusion of MODIS Products and GNSS-IR Observations

Yuan

Yue

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Vegetation water content (VWC) is recognized as an important parameter in vegetation growth studies, natural disasters such as forest fires, and drought prediction. Recently, the Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) has emerged as an important technique for monitoring vegetation information. The normalized microwave reflection index (NMRI) was developed to reflect the change of VWC based on this fact. However, NMRI uses local site-based data, and the sparse distribution hinders the application of NMRI. In this study, we obtained a 500 m spatially continuous NMRI product by integrating GNSS-IR site data with other VWC-related products using the point–surface fusion technique. The auxiliary data in the fusion process include the normalized difference vegetation index (NDVI), gross primary productivity (GPP), and precipitation. Meanwhile, the fusion performance of three machine learning methods, i.e., the back-propagation neural network (BPNN), generalized regression neural network (GRNN), and random forest (RF) are compared and analyzed. The machine learning methods achieve satisfactory results, with cross-validation R values of 0.71–0.83 and RMSEs of 0.025–0.037. The results show a clear improvement over the traditional multiple linear regression method, which achieves R (RMSE) values of only about 0.4 (0.045). It indicates that the machine learning methods can better learn the complex nonlinear relationship between NMRI and the input VWC-related index. Among the machine learning methods, the RF model obtained the best results. Long time-series NMRI images with a 500 m spatial resolution in the western part of the continental U.S. were then obtained. The results show that the spatial distribution of the NMRI product is consistent with a drought situation from 2012 to 2014 in the U.S., which verifies the feasibility of analyzing and predicting drought times and distribution ranges by using the 500 m fusion product.

show abstract

Section: Point-surface Fusion Results Of Nmrisupporting

confidence: 70%

Monitoring the Variation of Vegetation Water Content with Machine Learning Methods: Point–Surface Fusion of MODIS Products and GNSS-IR Observations

Yuan

Yue

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Rainfall is a critical component of the global water cycle [1,2] and is crucial for a wide range of applications such as crop modeling, hydrometeorology, water resources management, flood and drought monitoring, and climatological applications [3][4][5][6]. Rainfall data from ground stations have been conventionally used to provide local estimates of rainfall amounts [7,8], but their limited spatial representativeness, inhomogeneous distribution and high maintenance costs constrain their applicability at the global scale [3,[9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…1 Derived from the LC-CCI product shown in Figure1b;2,3 Calculation based on the ground-based gridded rainfall dataset developed by[59] (period: 1980-2015). * for instance, 4094 is equivalent to 4,094,000 km 2 ; ** a.s.l.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of the Performance of SM2RAIN-Derived Rainfall Products over Brazil

2019

View full text Add to dashboard Cite

Microwave-based satellite soil moisture products enable an innovative way of estimating rainfall using soil moisture observations with a bottom-up approach based on the inversion of the soil water balance Equation (SM2RAIN). In this work, the SM2RAIN-CCI (SM2RAIN-ASCAT) rainfall data obtained from the inversion of the microwave-based satellite soil moisture (SM) observations derived from the European Space Agency (ESA) Climate Change Initiative (CCI) (from the Advanced SCATterometer (ASCAT) soil moisture data) were evaluated against in situ rainfall observations under different bioclimatic conditions in Brazil. The research V7 version of the Tropical Rainfall Measurement Mission Multi-satellite Precipitation Analysis (TRMM TMPA) was also used as a state-of-the-art rainfall product with an up-bottom approach. Comparisons were made at daily and 0.25° scales, during the time-span of 2007–2015. The SM2RAIN-CCI, SM2RAIN-ASCAT, and TRMM TMPA products showed relatively good Pearson correlation values (R) with the gauge-based observations, mainly in the Caatinga (CAAT) and Cerrado (CER) biomes (R median > 0.55). SM2RAIN-ASCAT largely underestimated rainfall across the country, particularly over the CAAT and CER biomes (bias median < −16.05%), while SM2RAIN-CCI is characterized by providing rainfall estimates with only a slight bias (bias median: −0.20%), and TRMM TMPA tended to overestimate the amount of rainfall (bias median: 7.82%). All products exhibited the highest values of unbiased root mean square error (ubRMSE) in winter (DJF) when heavy rainfall events tend to occur more frequently, whereas the lowest values are observed in summer (JJA) with light rainfall events. The SM2RAIN-based products showed larger contribution of systematic error components than random error components, while the opposite was observed for TRMM TMPA. In general, both SM2RAIN-based rainfall products can be effectively used for some operational purposes on a daily scale, such as water resources management and agriculture, whether the bias is previously adjusted.

show abstract

“…The hyper-parameter of machine learning algorithms plays a pivotal role in its performance. In this framework, the scikit-learn GridSearchCV algorithm with cross-validation (GSCV) splitting strategy [59] is used to identify the best hyper-parameter values of each machine learning-vegetation index [12,35,70,71]. The total number of pixels at 25 km were divided into two groups.…”

Section: Hyper-parameter Optimizationmentioning

confidence: 99%

Downscaling TRMM Monthly Precipitation Using Google Earth Engine and Google Cloud Computing

Elnashar

Zeng

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Accurate precipitation data at high spatiotemporal resolution are critical for land and water management at the basin scale. We proposed a downscaling framework for Tropical Rainfall Measuring Mission (TRMM) precipitation products through integrating Google Earth Engine (GEE) and Google Colaboratory (Colab). Three machine learning methods, including Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), and Artificial Neural Network (ANN) were compared in the framework. Three vegetation indices (Normalized Difference Vegetation Index, NDVI; Enhanced Vegetation Index, EVI; Leaf Area Index, LAI), topography, and geolocation are selected as geospatial predictors to perform the downscaling. This framework can automatically optimize the models’ parameters, estimate features’ importance, and downscale the TRMM product to 1 km. The spatial downscaling of TRMM from 25 km to 1 km was achieved by using the relationships between annual precipitations and annually-averaged vegetation index. The monthly precipitation maps derived from the annual downscaled precipitation by disaggregation. According to validation in the Great Mekong upstream region, the ANN yielded the best performance when simulating the annual TRMM precipitation. The most sensitive vegetation index for downscaling TRMM was LAI, followed by EVI. Compared with existing downscaling methods, the proposed framework for downscaling TRMM can be performed online for any given region using a wide range of machine learning tools and environmental variables to generate a precipitation product with high spatiotemporal resolution.

show abstract

Mapping Fine Spatial Resolution Precipitation from TRMM Precipitation Datasets Using an Ensemble Learning Method and MODIS Optical Products in China

Cited by 15 publications

References 47 publications

Monitoring the Variation of Vegetation Water Content with Machine Learning Methods: Point–Surface Fusion of MODIS Products and GNSS-IR Observations

Monitoring the Variation of Vegetation Water Content with Machine Learning Methods: Point–Surface Fusion of MODIS Products and GNSS-IR Observations

Evaluation of the Performance of SM2RAIN-Derived Rainfall Products over Brazil

Downscaling TRMM Monthly Precipitation Using Google Earth Engine and Google Cloud Computing

Contact Info

Product

Resources

About