scholarly journals Leveraging machine learning for quantitative precipitation estimation from Fengyun-4 geostationary observations and ground meteorological measurements

2021 ◽  
Vol 14 (11) ◽  
pp. 7007-7023
Author(s):  
Xinyan Li ◽  
Yuanjian Yang ◽  
Jiaqin Mi ◽  
Xueyan Bi ◽  
You Zhao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Rural Areas ◽  
Land Surface ◽  
Large Scale ◽  
Quantitative Estimation ◽  
Summer Precipitation ◽  
Bias Score ◽  
Surface Precipitation ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation

Abstract. Deriving large-scale and high-quality precipitation products from satellite remote-sensing spectral data is always challenging in quantitative precipitation estimation (QPE), and limited studies have been conducted even using China's latest Fengyun-4A (FY-4A) geostationary satellite. Taking three rainstorm events over South China as examples, a machine-learning-based regression model was established using the random forest (RF) method to derive QPE from FY-4A observations, in conjunction with cloud parameters and physical quantities. The cross-validation results indicate that both daytime (DQPE) and nighttime (NQPE) RF algorithms performed well in estimating QPE, with the bias score, correlation coefficient and root-mean-square error of DQPE (NQPE) of 2.17 (2.42), 0.79 (0.83) and 1.77 mm h−1 (2.31 mm h−1), respectively. Overall, the algorithm has a high accuracy in estimating precipitation under the heavy-rain level or below. Nevertheless, the positive bias still implies an overestimation of precipitation by the QPE algorithm, in addition to certain misjudgements from non-precipitation pixels to precipitation events. Also, the QPE algorithm tends to underestimate the precipitation at the rainstorm or even above levels. Compared to single-sensor algorithms, the developed QPE algorithm can better capture the spatial distribution of land-surface precipitation, especially the centre of strong precipitation. Marginal difference between the data accuracy over sites in urban and rural areas indicate that the model performs well over space and has no evident dependence on landscape. In general, our proposed FY-4A QPE algorithm has advantages for quantitative estimation of summer precipitation over East Asia.

scholarly journals Leveraging machine learning for quantitative precipitation estimation from Fengyun-4 geostationary observations and ground meteorological measurements

2021 ◽  
Author(s):  
Xinyan Li ◽  
Yuanjian Yang ◽  
Jiaqin Mi ◽  
Xueyan Bi ◽  
You Zhao ◽  
...  
Keyword(s):  
Rural Areas ◽  
Urban Areas ◽  
Large Scale ◽  
Predictive Ability ◽  
Summer Precipitation ◽  
Reanalysis Data ◽  
Probability Of Detection ◽  
Model Framework ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation

Abstract. Deriving large-scale and high-quality precipitation products from satellite remote sensing spectral data is always challenging in quantitative precipitation estimation (QPE), and limited studies have been conducted even using the China’s latest Fengyun-4A (FY-4A) geostationary satellite. Taking three rainstorm events over South China as examples, a Random Forest (RF) model framework for FY-4A QPE during daytime/nighttime is established by using FY-4A multi-band spectral information, cloud parameters, high-density precipitation observations, and physical quantities from reanalysis data. During daytime (nighttime), the probability of detection of the RF model for precipitation is 0.99 (0.99), while the correlation coefficient and root-mean-square error between the retrieved and observed precipitation are 0.77 (0.82) and 1.84 (2.32) mm/h, respectively, indicating that the RF model of FY-4A QPE has high precipitation retrieval accuracy. In particular, the RF model exhibits good spatiotemporal predictive ability for precipitation intensities within the range of 0.5–10 mm/h. For the retrieved accumulated precipitation, the precipitation intensity exhibits a greater impact on the predictive ability of the QPE algorithm than the precipitation duration. Due to the higher density of automatic stations in urban areas, the accuracy of FY-4A QPE over such areas is higher compared with rural areas. Both the accumulated precipitation and the distribution density of automatic stations are more important factors for the predictive ability of the RF model of FY-4A QPE. In general, our proposed FY-4A QPE algorithm has advantages for near-real-time monitoring of summer precipitation over East Asia.

scholarly journals Assessing the Applicability of Random Forest, Stochastic Gradient Boosted Model, and Extreme Learning Machine Methods to the Quantitative Precipitation Estimation of the Radar Data: A Case Study to Gwangdeoksan Radar, South Korea, in 2018

2019 ◽  
Vol 2019 ◽  
pp. 1-17
Author(s):  
Ju-Young Shin ◽  
Yonghun Ro ◽  
Joo-Wan Cha ◽  
Kyu-Rang Kim ◽  
Jong-Chul Ha
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
South Korea ◽  
Extreme Learning Machine ◽  
Radar Data ◽  
Machine Learning Algorithms ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation ◽  
Learning Machine ◽  
Estimation Models

Machine learning algorithms should be tested for use in quantitative precipitation estimation models of rain radar data in South Korea because such an application can provide a more accurate estimate of rainfall than the conventional ZR relationship-based model. The applicability of random forest, stochastic gradient boosted model, and extreme learning machine methods to quantitative precipitation estimation models was investigated using case studies with polarization radar data from Gwangdeoksan radar station. Various combinations of input variable sets were tested, and results showed that machine learning algorithms can be applied to build the quantitative precipitation estimation model of the polarization radar data in South Korea. The machine learning-based quantitative precipitation estimation models led to better performances than ZR relationship-based models, particularly for heavy rainfall events. The extreme learning machine is considered the best of the algorithms used based on evaluation criteria.

scholarly journals Responding to Large-Scale Forest Damage in an Alpine Environment with Remote Sensing, Machine Learning, and Web-GIS

2021 ◽  
Vol 13 (8) ◽  
pp. 1541
Author(s):  
Marco Piragnolo ◽  
Francesco Pirotti ◽  
Carlo Zanrosso ◽  
Emanuele Lingua ◽  
Stefano Grigolato
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Land Surface ◽  
Large Scale ◽  
Learning Algorithm ◽  
Web Gis ◽  
Forest Damage ◽  
Strong Negative Correlation ◽  
Ground Truth Data ◽  
Severity Prediction

This paper reports a semi-automated workflow for detection and quantification of forest damage from windthrow in an Alpine region, in particular from the Vaia storm in October 2018. A web-GIS platform allows to select the damaged area by drawing polygons; several vegetation indices (VIs) are automatically calculated using remote sensing data (Sentinel-2A) and tested to identify the more suitable ones for quantifying forest damage using cross-validation with ground-truth data. Results show that the mean value of NDVI and NDMI decreased in the damaged areas, and have a strong negative correlation with severity. RGI has an opposite behavior in contrast with NDVI and NDMI, as it highlights the red component of the land surface. In all cases, variance of the VI increases after the event between 0.03 and 0.15. Understorey not damaged from the windthrow, if consisting of 40% or more of the total cover in the area, undermines significantly the sensibility of the VIs to detecting and predicting severity. Using aggregational statistics (average and standard deviation) of VIs over polygons as input to a machine learning algorithm, i.e., Random Forest, results in severity prediction with regression reaching a root mean square error (RMSE) of 9.96, on a severity scale of 0–100, using an ensemble of area averages and standard deviations of NDVI, NDMI, and RGI indices. The results show that combining more than one VI can significantly improve the estimation of severity, and web-GIS tools can support decisions with selected VIs. The reported results prove that Sentinel-2 imagery can be deployed and analysed via web-tools to estimate forest damage severity and that VIs can be used via machine learning for predicting severity of damage, with careful evaluation of the effect of understorey in each situation.

scholarly journals Evaluation and Improvement of FY-4A AGRI Quantitative Precipitation Estimation for Summer Precipitation over Complex Topography of Western China

2021 ◽  
Vol 13 (21) ◽  
pp. 4366
Author(s):  
Jing Ren ◽  
Guirong Xu ◽  
Wengang Zhang ◽  
Liang Leng ◽  
Yanjiao Xiao ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Mean Squared Error ◽  
Time Integration ◽  
Summer Precipitation ◽  
Western China ◽  
Complex Topography ◽  
Brightness Temperatures ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation ◽  
Dynamic Time

Satellite quantitative precipitation estimation (QPE) can make up for the insufficiency of ground observations for monitoring precipitation. Using an Advanced Geosynchronous Radiation Imager (AGRI) on the FengYun-4A (FY-4A) satellite and rain gauges (RGs) for observations in the summer of 2020. The existing QPE of the FY-4A was evaluated and found to present poor accuracy over the complex topography of Western China. Therefore, to improve the existing QPE, first, cloud classification thresholds for the FY-4A were established with the dynamic clustering method to identify convective clouds. These thresholds consist of the brightness temperatures (TBs) of FY-4A water vapor and infrared channels, and their TB difference. Then, quantitative cloud growth rate correction factors were introduced to improve the QPE of the convective-stratiform technique. This was achieved using TB hourly variation rates of long-wave infrared channel 12, which is able to characterize the evolution of clouds. Finally, the dynamic time integration method was designed to solve the inconsistent time matching between the FY-4A and RGs. Consequently, the QPE accuracy of the FY-4A was improved. Compared with the existing QPE of the FY-4A, the correlation coefficient between the improved QPE of the FY-4A and the RG hourly precipitation increased from 0.208 to 0.492, with the mean relative error and root mean squared error decreasing from −47.4% and 13.78 mm to 8.3% and 10.04 mm, respectively. However, the correlation coefficient is not sufficiently high; thus, the algorithm needs to be further studied and improved.

scholarly journals The Quantile-Matching Approach to Improving Radar Quantitative Precipitation Estimation in South China

2021 ◽  
Vol 13 (23) ◽  
pp. 4956
Author(s):  
Linye Song ◽  
Shangfeng Chen ◽  
Yun Li ◽  
Duo Qi ◽  
Jiankun Wu ◽  
...  
Keyword(s):  
South China ◽  
Weather Radar ◽  
Absolute Error ◽  
Rain Gauge ◽  
Observation Data ◽  
Matching Method ◽  
Study Region ◽  
Surface Precipitation ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation

Weather radar provides regional rainfall information with a very high spatial and temporal resolution. Because the radar data suffer from errors from various sources, an accurate quantitative precipitation estimation (QPE) from a weather radar system is crucial for meteorological forecasts and hydrological applications. In the South China region, multiple weather radar networks are widely used, but the accuracy of radar QPE products remains to be analyzed and improved. Based on hourly radar QPE and rain gauge observation data, this study first analyzed the QPE error in South China and then applied the Quantile Matching (Q-matching) method to improve the radar QPE accuracy. The results show that the rainfall intensity of the radar QPE is generally larger than that determined from rain gauge observations but that it usually underestimates the intensity of the observed heavy rainfall. After the Q-matching method was applied to correct the QPE, the accuracy improved by a significant amount and was in good agreement with the rain gauge observations. Specifically, the Q-matching method was able to reduce the QPE error from 39–44%, demonstrating performance that is much better than that of the traditional climatological scaling method, which was shown to be able to reduce the QPE error from 3–15% in South China. Moreover, after the Q-matching correction, the QPE values were closer to the rainfall values that were observed from the automatic weather stations in terms of having a smaller mean absolute error and a higher correlation coefficient. Therefore, the Q-matching method can improve the QPE accuracy as well as estimate the surface precipitation better. This method provides a promising prospect for radar QPE in the study region.

scholarly journals Relative Roles of Large-Scale Orography and Land Surface Processes in the Global Hydroclimate. Part II: Impacts on Hydroclimate over Eurasia

2006 ◽  
Vol 7 (4) ◽  
pp. 642-659 ◽  
Author(s):  
Kazuyuki Saito ◽  
Tetsuzo Yasunari ◽  
Kumiko Takata
Keyword(s):  
Land Surface ◽  
Large Scale ◽  
Warm Season ◽  
Summer Precipitation ◽  
Winter Precipitation ◽  
Bare Rock ◽  
Surface Scheme ◽  
Water Holding ◽  
East West ◽  
Higher Sensitivity

Abstract A series of simplistic simulations from an AGCM coupled to a simple land surface scheme and water vapor tracers was performed to explore the relative roles of basic factors in land surface conditions, with regard to the seasonal evolution of the hydroclimate over Eurasia. Large-scale orography in Asia and vegetation (further decomposed to soil and vegetation skin) were evaluated, with orography represented in the model by surface altitude, soil represented by water-holding capacity, and vegetation skin represented by surface albedo and roughness. The percentage of global annual precipitation over land (occupying 25.6% of the total surface) was 14.8%, 15.0%, and 21.7% for the mountainless “bare rock” (i.e., vegetationless) surface, and the bare-rock and vegetated surface, respectively. The result for evaporation was 8.9%, 9.0%, and 16.2%, respectively, showing higher sensitivity to the land surface changes than precipitation. The orography and vegetation (i.e., soil and vegetation skin) showed different impacts on Eurasian hydroclimate on the seasonal and regional scales. Thermodynamical forcings to the atmosphere increased over the continent with the inclusion of both. Large-scale orography in Asia exerted east–west contrast in the surface energy exchange in summer in eastern Eurasia. An increase in extratropical winter precipitation with mountains was also noticed because of the atmospheric vapor transport changes. Impact of soil and vegetation skin was clearly found in the warm season in the extratropics; soil impacts extratropical summer precipitation due to enhanced recycling of water and the resultant increased water supply.

scholarly journals Drought Recurrence and Seasonal Rainfall Prediction in the Río Yaqui Basin, Mexico

2008 ◽  
Vol 47 (4) ◽  
pp. 991-1005 ◽  
Author(s):  
Robert E. Nicholas ◽  
David S. Battisti
Keyword(s):  
Land Surface ◽  
Large Scale ◽  
Meteorological Drought ◽  
Strong Relationship ◽  
Statistical Prediction ◽  
Climate Indices ◽  
Strongly Correlated ◽  
Surface Precipitation ◽  
Rainfall Prediction ◽  
Forecast Models

Abstract A statistical approach is used to explore the variability of precipitation and meteorological drought in Mexico’s Río Yaqui basin on seasonal-to-decadal time scales. For this purpose, a number of custom datasets have been developed, including a monthly 1900–2004 precipitation index for the Yaqui basin created by merging two gridded land surface precipitation products, a 349-yr tree-ring-based proxy for Yaqui wintertime rainfall, and a variety of large-scale climate indices derived from gridded SST records. Although significantly more rain falls during the summer (June–September) than during the winter (November–April), wintertime rainfall is over 3 times as variable relative to the climatological mean. Summertime rainfall appears to be unrelated to any large-scale patterns of variability, but a strong relationship between ENSO and Yaqui rainfall during the winter months offers the possibility of meaningful statistical prediction for this season’s precipitation. Analysis of both historical and reconstructed rainfall data suggests that meteorological droughts as severe as the 1994–2002 Yaqui drought occur about 2 times per century, droughts of even greater severity have occurred in the past, and such droughts are generally associated with wintertime anomalies. Whereas summertime reservoir inflow is larger in the Yaqui basin, wintertime inflow is more variable (in both relative and absolute terms) and is much more strongly correlated with same-season rainfall. Using the identified wintertime ENSO–rainfall relationship, two simple empirical forecast models for possible use by irrigation planners are demonstrated.

scholarly journals CAFE60v1: A 60-year large ensemble climate reanalysis. Part II: Evaluation

2021 ◽  
pp. 1-62
Author(s):  
Terence J. OߣKane ◽  
Paul A. Sandery ◽  
Vassili Kitsios ◽  
Pavel Sakov ◽  
Matthew A. Chamberlain ◽  
...  
Keyword(s):  
Sea Ice ◽  
Retrospective Analysis ◽  
Land Surface ◽  
Large Scale ◽  
Climate Model ◽  
Global Climate ◽  
Sea Ice Extent ◽  
Data Resource ◽  
Surface Precipitation ◽  
Recent Climate

AbstractThe CSIRO Climate retrospective Analysis and Forecast Ensemble system: version 1 (CAFE60v1) provides a large (96 member) ensemble retrospective analysis of the global climate system from 1960 to present with sufficiently many realizations and at spatio-temporal resolutions suitable to enable probabilistic climate studies. Using a variant of the ensemble Kalman filter, 96 climate state estimates are generated over the most recent six decades. These state estimates are constrained by monthly mean ocean, atmosphere and sea ice observations such that their trajectories track the observed state while enabling estimation of the uncertainties in the approximations to the retrospective mean climate over recent decades. For the atmosphere, we evaluate CAFE60v1 in comparison to empirical indices of the major climate teleconnections and blocking with various reanalysis products. Estimates of the large scale ocean structure, transports and biogeochemistry are compared to those derived from gridded observational products and climate model projections (CMIP). Sea ice (extent, concentration and variability) and land surface (precipitation and surface air temperatures) are also compared to a variety of model and observational products. Our results show that CAFE60v1 is a useful, comprehensive and unique data resource for studying internal climate variability and predictability, including the recent climate response to anthropogenic forcing on multi-year to decadal time scales.

Sign in / Sign up

Export Citation Format

Share Document