skip to main content

Explore Research Products in the NSF-PAR

  • NSF Public Access
  • Search Results
  • PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks
Title: PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks
Abstract

Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.

  more » « less
NSF-PAR ID:
10125614
Author(s) / Creator(s):
 ;  ;  ;  ;  ;  ;  
Publisher / Repository:
American Meteorological Society
Date Published:
Journal Name:
Journal of Hydrometeorology
Volume:
20
Issue:
12
ISSN:
1525-755X
Page Range / eLocation ID:
p. 2273-2289
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ( , Journal of Hydrometeorology)
    null (Ed.)
    Abstract This study presents the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Dynamic Infrared Rain Rate (PDIR-Now) near-real-time precipitation dataset. This dataset provides hourly, quasi-global, infrared-based precipitation estimates at 0.04° × 0.04° spatial resolution with a short latency (15–60 min). It is intended to supersede the PERSIANN–Cloud Classification System (PERSIANN-CCS) dataset previously produced as the near-real-time product of the PERSIANN family. We first provide a brief description of the algorithm’s fundamentals and the input data used for deriving precipitation estimates. Second, we provide an extensive evaluation of the PDIR-Now dataset over annual, monthly, daily, and subdaily scales. Last, the article presents information on the dissemination of the dataset through the Center for Hydrometeorology and Remote Sensing (CHRS) web-based interfaces. The evaluation, conducted over the period 2017–18, demonstrates the utility of PDIR-Now and its improvement over PERSIANN-CCS at all temporal scales. Specifically, PDIR-Now improves the estimation of rain/no-rain days as demonstrated by a critical success index (CSI) of 0.53 compared to 0.47 of PERSIANN-CCS. In addition, PDIR-Now improves the estimation of seasonal and diurnal cycles of precipitation as well as regional precipitation patterns erroneously estimated by PERSIANN-CCS. Finally, an evaluation is carried out to examine the performance of PDIR-Now in capturing two extreme events, Hurricane Harvey and a cluster of summer thunderstorms that occurred over the Netherlands, where it is shown that PDIR-Now adequately represents spatial precipitation patterns as well as subdaily precipitation rates with a correlation coefficient (CORR) of 0.64 for Hurricane Harvey and 0.76 for the Netherlands thunderstorms. 
    more » « less
  2. ; ; ; ( , International Journal of Climatology)

    Long‐term trends in equatorial African rainfall have proven difficult to determine because of a dearth in ground‐measured rainfall data. Multiple, satellite‐based products now provide daily rainfall estimates from 1983 to the present at relatively fine spatial resolutions, but in order to assess trends in rainfall, they must be validated alongside ground‐based measurements. The purpose of this paper is twofold: (a) to assess the accuracy of four rainfall products covering the past several decades in western Uganda; and (b) to ascertain recent, multi‐decadal trends in annual rainfall for the region. The four products are African Rainfall Climatology Version 2 (ARC2), Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks–Climate Data Record (PERSIANN‐CDR), and TAMSAT African Rainfall Climatology And Timeseries (TARCAT). The bias and accuracy of 10‐day, monthly, and seasonal rainfall totals of the four products were assessed using approximately 10 years of data from 10 rain gauges. The homogeneity of the products over multiple time periods was assessed using change‐point analysis. The accuracy of the four products increased with an increase in temporal scale, and CHIRPS was the only product that could be considered sufficiently accurate at estimating seasonal rainfall totals throughout most of the region. TARCAT tended to underestimate totals, and ARC2 and PERSIANN were in general the least accurate products. Only annual rainfall estimates from CHIRPS and TARCAT were significantly correlated with ground‐measured rainfall totals. TARCAT was the most homogeneous product, while ARC2, CHIRPS, and PERSIANN had significant negative change points that caused a drying bias over the 1983–2016 period. After adjusting the satellite‐based rainfall estimates based on the timing and magnitude of the change points, annual rainfall totals derived from all four products indicated that western Uganda experienced significantly increasing rainfall from 1983 to 2016.

     
    more » « less
  3. ; ; ; ; ; ; ; ( , Bulletin of the American Meteorological Society)
    Abstract Precipitation measurements with high spatiotemporal resolution are a vital input for hydrometeorological and water resources studies; decision-making in disaster management; and weather, climate, and hydrological forecasting. Moreover, real-time precipitation estimation with high precision is pivotal for the monitoring and managing of catastrophic hydroclimate disasters such as flash floods, which frequently transpire after extreme rainfall. While algorithms that exclusively use satellite infrared data as input are attractive owing to their rich spatiotemporal resolution and near-instantaneous availability, their sole reliance on cloud-top brightness temperature (Tb) readings causes underestimates in wet regions and overestimates in dry regions—this is especially evident over the western contiguous United States (CONUS). We introduce an algorithm, the Precipitation Estimations from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN) Dynamic Infrared–Rain rate model (PDIR), which utilizes climatological data to construct a dynamic (i.e., laterally shifting) Tb–rain rate relationship that has several notable advantages over other quantitative precipitation-estimation algorithms and noteworthy skill over the western CONUS. Validation of PDIR over the western CONUS shows a promising degree of skill, notably at the annual scale, where it performs well in comparison to other satellite-based products. Analysis of two extreme landfalling atmospheric rivers show that solely IR-based PDIR performs reasonably well compared to other IR- and PMW-based satellite rainfall products, marking its potential to be effective in real-time monitoring of extreme storms. This research suggests that IR-based algorithms that contain the spatiotemporal richness and near-instantaneous availability needed for rapid natural hazards response may soon contain the skill needed for hydrologic and water resource applications. 
    more » « less
  4. ; ; ; ; ( , Geocarto International)
    In this study, a comparative analysis of three satellite precipitation products including Tropical Rainfall Measuring Mission (TRMM-3B43 V7), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR), and Climate Hazards Group InfraRed Precipitation with Station (CHIRPS V2) with ground-measured Indian Meteorological Department (IMD) precipitation data were performed to estimate the meteorological drought in the Bundelkhand region of Central India. The high-resolution CHIRPS data showed the closest agreement with the IMD precipitation and well captured the drought characteristics. The Standardized Precipitation Index (SPI) identified seven major droughts events during the period of 1981 to 2016. Appropriate calibration and validation were performed for drought forecasting using the Auto-Regressive Integrated Moving Average (ARIMA) model. The forecasting result showed a reasonably good agreement with the observed datasets with the one-month lead time. The outcomes of this study have policy level implications for drought monitoring and preparedness in this region. 
    more » « less
  5. ; ; ; ( , The 1st Electronic Conference on Hydrological Cycle (CHyCle-2017))
    A recently funded US National Science Foundation project seeks to investigate monsoon variability within the Ganges-Brahmaputra-Meghna (GBM) river basin as a potential predictor for annual shoreline erosion rates in the lower coastal delta region. Many previous studies have examined the interannual variability of South Asian precipitation either within political boundaries or across large spans of latitudes and longitudes, but few have taken a more hydrologic approach by analyzing the atmospheric-oceanic forcings that lead to precipitation falling only within the GBM basin. The temporal climate patterns would likely be different from previous studies and are hypothesized to have a more direct effect on outlet discharge and erosion rates. In the present study, mean monsoon precipitation (June-July-August-September) for the 2,309 0.25° grid boxes of the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) was extracted using geospatial methods. A Principal Component (PC) analysis was performed over the period 1983 to 2015. The first PC explains 88.7% of the variance and resembles climatology with the center of action over Bangladesh. The eigenvector shows a downward trend consistent with studies reporting a recent decline in monsoon rainfall. The second PC explains 2.9% of the variance and concentrates rainfall in the western portion of the basin. The 2nd component has greater temporal variability than the 1st component and an apparent decadal cycle. An analysis of global precipitation indicates that the rainfall patterns obtained within the GBM are localized. Surface and upper-air atmospheric height fields suggest the 2nd PC pattern is forced by a Rossby wave train stemming from the North Atlantic. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email