Kuolin Hsu

Artificial Neural Network Modeling of the Rainfall-Runoff Process

An artificial neural network (ANN) is a flexible mathematical structure which is capable of identifying complex nonlinear relationships between input and output data sets. ANN models have been found useful and efficient, particularly in problems for which the characteristics of the processes are difficult to describe using physical equations. This study presents a new procedure (entitled linear least squares simplex, or LLSSIM) for identifying the structure and parameters of three-layer feed forward ANN models and demonstrates the potential of such models for simulating the nonlinear hydrologic behavior of watersheds. The nonlinear ANN model approach is shown to provide a better representation of the rainfall-runoff relationship of the medium-size Leaf River basin near Collins, Mississippi, than the linear ARMAX (autoregressive moving average with exogenous inputs) time series approach or the conceptual SAC-SMA (Sacramento soil moisture accounting) model. Because the ANN approach presented here does not provide models that have physically realistic components and parameters, it is by no means a substitute for conceptual watershed modeling. However, the ANN approach does provide a viable and effective alternative to the ARMAX time series approach for developing input-output simulation and forecasting models in situations that do not require modeling of the internal structure of the watershed.

Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System

Abstract A satellite-based rainfall estimation algorithm, Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) Cloud Classification System (CCS), is described. This algorithm extracts local and regional cloud features from infrared (10.7 μm) geostationary satellite imagery in estimating finescale (0.04° × 0.04° every 30 min) rainfall distribution. This algorithm processes satellite cloud images into pixel rain rates by 1) separating cloud images into distinctive cloud patches; 2) extracting cloud features, including coldness, geometry, and texture; 3) clustering cloud patches into well-organized subgroups; and 4) calibrating cloud-top temperature and rainfall (Tb–R) relationships for the classified cloud groups using gauge-corrected radar hourly rainfall data. Several cloud-patch categories with unique cloud-patch features and Tb–R curves were identified and explained. Radar and gauge rainfall measurements were both used to evaluate the PERSIANN CCS rainfal...

Self-organizing linear output map (SOLO): an artificial neural network suitable for hydrologic modeling and analysis

Artificial neural networks (ANNs) can be useful in the prediction of hydrologic variables, such as streamflow, particularly when the underlying processes have complex nonlinear interrelationships. However, conventional ANN structures suffer from network training issues that significantly limit their widespread application. This paper presents a multivariate ANN procedure entitled self-organizing linear output map (SOLO), whose structure has been designed for rapid, precise, and inexpensive estimation of network structure/parameters and system outputs. More important, SOLO provides features that facilitate insight into the underlying processes, thereby extending its usefulness beyond forecast applications as a tool for scientific investigations. These characteristics are demonstrated using a classic rainfall-runoff forecasting problem. Various aspects of model performance are evaluated in comparison with other commonly used modeling approaches, including multilayer feedforward ANNs, linear time series modeling, and conceptual rainfall-runoff modeling.

PERSIANN-CDR: Daily Precipitation Climate Data Record from Multisatellite Observations for Hydrological and Climate Studies

AbstractA new retrospective satellite-based precipitation dataset is constructed as a climate data record for hydrological and climate studies. Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks–Climate Data Record (PERSIANN-CDR) provides daily and 0.25° rainfall estimates for the latitude band 60°S–60°N for the period of 1 January 1983 to 31 December 2012 (delayed present). PERSIANN-CDR is aimed at addressing the need for a consistent, long-term, high-resolution, and global precipitation dataset for studying the changes and trends in daily precipitation, especially extreme precipitation events, due to climate change and natural variability. PERSIANN-CDR is generated from the PERSIANN algorithm using GridSat-B1 infrared data. It is adjusted using the Global Precipitation Climatology Project (GPCP) monthly product to maintain consistency of the two datasets at 2.5° monthly scale throughout the entire record. Three case studies for testing the efficacy of the dataset ...

Intercomparison of Rain Gauge, Radar, and Satellite-Based Precipitation Estimates with Emphasis on Hydrologic Forecasting

Abstract This study compares mean areal precipitation (MAP) estimates derived from three sources: an operational rain gauge network (MAPG), a radar/gauge multisensor product (MAPX), and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) satellite-based system (MAPS) for the time period from March 2000 to November 2003. The study area includes seven operational basins of varying size and location in the southeastern United States. The analysis indicates that agreements between the datasets vary considerably from basin to basin and also temporally within the basins. The analysis also includes evaluation of MAPS in comparison with MAPG for use in flow forecasting with a lumped hydrologic model [Sacramento Soil Moisture Accounting Model (SAC-SMA)]. The latter evaluation investigates two different parameter sets, the first obtained using manual calibration on historical MAPG, and the second obtained using automatic calibration on both MAPS and MAPG, but ov...

Estimation of physical variables from multichannel remotely sensed imagery using a neural network: Application to rainfall estimation

Satellite-based remotely sensed data have the potential to provide hydrologically relevant information about spatially and temporally varying physical variables. A methodology for estimating such variables from multichannel remotely sensed data is presented; the approach is based on a modified counterpropagation neural network (MCPN) and is both effective and efficient at building complex nonlinear input-output function mappings from large amounts of data. An application to high-resolution estimation of the spatial and temporal variation of surface rainfall using geostationary satellite infrared and visible imagery is presented. Test results also indicate that spatially and temporally sparse ground-based observations can be assimilated via an adaptive implementation of the MCPN method, thereby allowing on-line improvement of the estimates.

Evaluation of satellite‐retrieved extreme precipitation rates across the central United States

JOURNAL OF GEOPHYSICAL RESEARCH, VOL. 116, D02115, doi:10.1029/2010JD014741, 2011 Evaluation of satellite‐retrieved extreme precipitation rates across the central United States A. AghaKouchak, 1 A. Behrangi, 2 S. Sorooshian, 1 K. Hsu, 1 and E. Amitai 3,4 Received 10 July 2010; revised 10 September 2010; accepted 27 October 2010; published 26 January 2011. [ 1 ] Water resources management, forecasting, and decision making require reliable estimates of precipitation. Extreme precipitation events are of particular importance because of their severe impact on the economy, the environment, and the society. In recent years, the emergence of various satellite‐retrieved precipitation products with high spatial resolutions and global coverage have resulted in new sources of uninterrupted precipitation estimates. However, satellite‐based estimates are not well integrated into operational and decision‐making applications because of a lack of information regarding the associated uncertainties and reliability of these products. In this study, four satellite‐ derived precipitation products (CMORPH, PERSIANN, TMPA‐RT, and TMPA‐V6) are evaluated with respect to their performance in capturing precipitation extremes. The Stage IV (radar‐based, gauge‐adjusted) precipitation estimates are used as reference data. The results show that with respect to the probability of detecting extremes and the volume of correctly identified precipitation, CMORPH and PERSIANN data sets lead to better estimates. However, their false alarm ratio and volume are higher than those of TMPA‐RT and TMPA‐V6. Overall, no single precipitation product can be considered ideal for detecting extreme events. In fact, all precipitation products tend to miss a significant volume of rainfall. With respect to verification metrics used in this study, the performance of all satellite products tended to worsen as the choice of extreme precipitation threshold increased. The analyses suggest that extensive efforts are necessary to develop algorithms that can capture extremes more reliably. Citation: AghaKouchak, A., A. Behrangi, S. Sorooshian, K. Hsu, and E. Amitai (2011), Evaluation of satellite‐retrieved extreme precipitation rates across the central United States, J. Geophys. Res., 116, D02115, doi:10.1029/2010JD014741. 1. Introduction [ 2 ] Precipitation plays a significant role in weather research, monitoring, and predictions. Improving our understanding of weather and climate, along with the development of reliable and uninterrupted measurements, are essential for proper assessment of weather conditions. Currently, in situ and radar‐based precipitation data are the major input for streamflow forecasts, flash flood warnings, and weather watches across the United States. While some regions have long‐term historical in situ precipitation measurements, poor spatial sampling makes the data inadequate to support monitoring, detection, and forecast studies. On the other hand, in most parts of the globe (except in a few developed countries), radar installations for precipitation measurements Department of Civil and Environmental Engineering, University of California, Irvine, California, USA. Jet Propulsion Laboratory, California Institute of Technology, Pasadena, California, USA. NASA Goddard Space Flight Center, Greenbelt, Maryland, USA. School of Earth and Environmental Sciences, Chapman University, Orange, California, USA. Copyright 2011 by the American Geophysical Union. 0148‐0227/11/2010JD014741 are not available. In the United States, with one of the most sophisticated radar measurement networks in the world, regions with extensive topographic relief (e.g., the western and southwestern United States) suffer from poor or non- existent radar coverage [Maddox et al., 2002]. In fact, Maddox et al. [2002] showed that at lower levels (e.g., 1000 m above ground level), which are closer estimates to ground‐level precipitation, the radar coverage area is sub- stantially smaller than at higher levels (e.g., 3000 m above ground level). [ 3 ] Clearly, the lack or absence of ground‐based precipi- tation networks hampers the development and use of flood and drought warning models, hydrological models, and extreme weather monitoring and decision‐making systems. Therefore, there exists the need to achieve alternative esti- mates of precipitation with sufficient sampling density, reliability, and accuracy to enable utilization of data for operational applications. Satellite‐derived precipitation esti- mates have the potential to improve precipitation observation at a global scale. In recent years, the National Aeronautics and Space Administration (NASA), National Oceanic and Atmospheric Administration (NOAA), and many other inter- national sponsored satellite missions have led to an increase in available precipitation data. These remotely sensed data have several advantages over in situ measurements, including D02115 1 of 11

Intercomparison of High-Resolution Precipitation Products over Northwest Europe

AbstractSatellite-derived high-resolution precipitation products (HRPP) have been developed to address the needs of the user community and are now available with 0.25° × 0.25° (or less) subdaily resolutions. This paper evaluates a number of commonly available satellite-derived HRPPs covering northwest Europe over a 6-yr period. Precipitation products include the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA), the Climate Prediction Center (CPC) morphing (CMORPH) technique, the CPC merged microwave technique, the Naval Research Laboratory (NRL) blended technique, and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) technique. In addition, the Geosynchronous Operational Environmental Satellite (GOES) precipitation index (GPI) and the European Centre for Medium-Range Weather Forecasting (ECMWF) operational forecast model products are included for comparison. Surface reference data from the European radar network...

Diurnal Variability of Tropical Rainfall Retrieved from Combined GOES and TRMM Satellite Information

Abstract Recent progress in satellite remote-sensing techniques for precipitation estimation, along with more accurate tropical rainfall measurements from the Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI) and precipitation radar (PR) instruments, have made it possible to monitor tropical rainfall diurnal patterns and their intensities from satellite information. One year (August 1998–July 1999) of tropical rainfall estimates from the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) system were used to produce monthly means of rainfall diurnal cycles at hourly and 1° × 1° scales over a domain (30°S–30°N, 80°E–10°W) from the Americas across the Pacific Ocean to Australia and eastern Asia. The results demonstrate pronounced diurnal variability of tropical rainfall intensity at synoptic and regional scales. Seasonal signals of diurnal rainfall are presented over the large domain of the tropical Pacific Ocean, especially over the ITCZ and...

Evaluation of the PERSIANN-CDR Daily Rainfall Estimates in Capturing the Behavior of Extreme Precipitation Events over China

AbstractThis study evaluates the performance of a newly developed daily precipitation climate data record, called Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Climate Data Record (PERSIANN-CDR), in capturing the behavior of daily extreme precipitation events in China during the period of 1983–2006. Different extreme precipitation indices, in the three categories of percentile, absolute threshold, and maximum indices, are studied and compared with the same indices from the East Asia (EA) ground-based gridded daily precipitation dataset. The results show that PERSIANN-CDR depicts similar precipitation behavior as the ground-based EA product in terms of capturing the spatial and temporal patterns of daily precipitation extremes, particularly in the eastern China monsoon region, where the intensity and frequency of heavy rainfall events are very high. However, the agreement between the datasets in dry regions such as the Tibetan Plateau in the west and the Taklama...