Improving near real-time precipitation estimation using a U-Net convolutional neural network and geographical information

Abstract Reliable near real-time precipitation estimates are essential for monitoring and managing of natural disasters such as floods. Quality of inputs and capability of the retrieval algorithm are two important aspects for developing satellite-based precipitation datasets. Most retrieval algorithms utilize infrared (IR) information as their input due to its fine spatiotemporal resolution and near-instantaneous availability. However, their sole reliance on IR information limits their capability to learn different mechanisms of precipitation during training, resulting in less accurate estimates. Moreover, recent advances in the field of machine learning offer attractive opportunities to improve the precipitation retrieval algorithms. This study investigates the effectiveness of adding geographical information (i.e. latitude and longitude) to IR information and the application of a U-Net-based convolutional neural network for improving the accuracy of retrieval algorithms. This research suggests that applying an appropriate CNN architecture on geographical and IR information provides an opportunity to improve the satellite-based precipitation products.

[1]  C. C. Pain,et al.  Rapid spatio-temporal flood prediction and uncertainty quantification using a deep learning method , 2019, Journal of Hydrology.

[2]  P. Xie,et al.  Global Precipitation: A 17-Year Monthly Analysis Based on Gauge Observations, Satellite Estimates, and Numerical Model Outputs , 1997 .

[3]  Ashish Sharma,et al.  Merging radar and gauge information within a dynamical model combination framework for precipitation estimation in cold climates , 2019, Environmental Modelling & Software.

[4]  Y. Hong,et al.  Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System , 2004 .

[5]  Jonathan L. Goodall,et al.  Deep learning Using Physically-Informed Input Data for Wetland Identification , 2020, Environ. Model. Softw..

[6]  Robert F. Adler,et al.  A Satellite Infrared Technique to Estimate Tropical Convective and Stratiform Rainfall , 1988 .

[7]  A. Hou,et al.  The Global Precipitation Measurement Mission , 2014 .

[8]  Florian Pappenberger,et al.  Daily evaluation of 26 precipitation datasets using Stage-IV gauge-radar data for the CONUS , 2018, Hydrology and Earth System Sciences.

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  Richard K. G. Do,et al.  Convolutional neural networks: an overview and application in radiology , 2018, Insights into Imaging.

[11]  Charless C. Fowlkes,et al.  Conditional Generative Adversarial Networks (cGANs) for Near Real-Time Precipitation Estimation from Multispectral GOES-16 Satellite Imageries - PERSIANN-cGAN , 2019, Remote. Sens..

[12]  Yudong Tian,et al.  Evaluation of the High-Resolution CMORPH Satellite Rainfall Product Using Dense Rain Gauge Observations and Radar-Based Estimates , 2012 .

[13]  Katie Price,et al.  Comparison of radar and gauge precipitation data in watershed models across varying spatial and temporal scales , 2014 .

[14]  Jia Guo,et al.  Construction of a drought monitoring model using deep learning based on multi-source remote sensing data , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[15]  K. Trenberth,et al.  The changing character of precipitation , 2003 .

[16]  A. Ihler,et al.  A Deep Neural Network Modeling Framework to Reduce Bias in Satellite Precipitation Products , 2016 .

[17]  Tristan L'Ecuyer,et al.  A Comparison of Precipitation Occurrence from the NCEP Stage IV QPE Product and theCloudSatCloud Profiling Radar , 2014 .

[18]  Kuolin Hsu,et al.  Global Precipitation Trends across Spatial Scales Using Satellite Observations , 2017 .

[19]  Chris Kidd,et al.  Rainfall Estimation from a Combination of TRMM Precipitation Radar and GOES Multispectral Satellite Imagery through the Use of an Artificial Neural Network , 2000 .

[20]  T. Lohse,et al.  Application of deep learning methods to analysis of imaging atmospheric Cherenkov telescopes data , 2018, Astroparticle Physics.

[21]  P. Xie,et al.  Kalman Filter–Based CMORPH , 2011 .

[22]  Frank S. Marzano,et al.  Investigating a SSM/I microwave algorithm to calibrate Meteosat infrared instantaneous rainrate estimates , 2007 .

[23]  Soroosh Sorooshian,et al.  Short‐Term Precipitation Forecast Based on the PERSIANN System and LSTM Recurrent Neural Networks , 2018, Journal of Geophysical Research: Atmospheres.

[24]  Annamária R. Várkonyi-Kóczy,et al.  Deep Learning and Machine Learning in Hydrological Processes Climate Change and Earth Systems a Systematic Review , 2019 .

[25]  Kuolin Hsu,et al.  Flood Forecasting and Inundation Mapping Using HiResFlood-UCI and Near-Real-Time Satellite Precipitation Data: The 2008 Iowa Flood , 2015 .

[26]  Frank S. Marzano,et al.  Multivariate statistical integration of Satellite infrared and microwave radiometric measurements for rainfall retrieval at the geostationary scale , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[27]  B. N. Meisner,et al.  The Relationship between Large-Scale Convective Rainfall and Cold Cloud over the Western Hemisphere during 1982-84 , 1987 .

[28]  Kuolin Hsu,et al.  PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks , 2019, Journal of Hydrometeorology.

[29]  R. Moore,et al.  Rainfall and sampling uncertainties: A rain gauge perspective , 2008 .

[30]  Brian A. Colle,et al.  The Limitations of the WSR-88D Radar Network for Quantitative Precipitation Measurement over the Coastal Western United States , 1999 .

[31]  Chuli Hu,et al.  A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data , 2019, Environ. Model. Softw..

[32]  Daisuke Matsuoka,et al.  Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model , 2018, Progress in Earth and Planetary Science.

[33]  Feng Ding,et al.  Radar and Multisensor Precipitation Estimation Techniques in National Weather Service Hydrologic Operations , 2013 .

[34]  Amir AghaKouchak,et al.  Capabilities of satellite precipitation datasets to estimate heavy precipitation rates at different temporal accumulations , 2014 .

[35]  X. Zeng.  The Relationship among Precipitation, Cloud-Top Temperature, and Precipitable Water over the Tropics , 1999 .

[36]  Chaopeng Shen,et al.  A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists , 2017, Water Resources Research.

[37]  S. Sorooshian,et al.  Evaluation of satellite-retrieved extreme precipitation rates across the central United States , 2011 .

[38]  S. Sorooshian,et al.  Intercomparison of rain gauge, radar, and satellite-based precipitation estimates with emphasis on hydrologic forecasting , 2005 .

[39]  Jonathan M. Harbor,et al.  CSTAT+: A GPU-accelerated spatial pattern analysis algorithm for high-resolution 2D/3D hydrologic connectivity using array vectorization and convolutional neural network operators , 2019, Environ. Model. Softw..

[40]  Long Ye,et al.  Projecting Australia's forest cover dynamics and exploring influential factors using deep learning , 2019, Environ. Model. Softw..

[41]  Soroosh Sorooshian,et al.  Evaluation of PERSIANN-CDR Constructed Using GPCP V2.2 and V2.3 and A Comparison with TRMM 3B42 V7 and CPC Unified Gauge-Based Analysis in Global Scale , 2019, Remote. Sens..

[42]  S. Sorooshian,et al.  Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks , 1997 .

[43]  R. Scofield,et al.  Status and Outlook of Operational Satellite Precipitation Algorithms for Extreme-Precipitation Events , 2003 .

[44]  V. Levizzani,et al.  Status of satellite precipitation retrievals , 2009 .

[45]  J. Awange,et al.  The newly merged satellite remotely sensed, gauge and reanalysis-based Multi-Source Weighted-Ensemble Precipitation: Evaluation over Australia and Africa (1981-2016). , 2019, The Science of the total environment.

[46]  Soroosh Sorooshian,et al.  The PERSIANN family of global satellite precipitation data: a review and evaluation of products , 2018, Hydrology and Earth System Sciences.

[47]  Fuzhong Weng,et al.  Advanced microwave sounding unit cloud and precipitation algorithms , 2003 .

[48]  S. Sorooshian,et al.  Evaluation of PERSIANN system satellite-based estimates of tropical rainfall , 2000 .

[49]  E. Anagnostou,et al.  Precipitation: Measurement, remote sensing, climatology and modeling , 2009 .

[50]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[51]  Xuan Zhu,et al.  Automatic land cover classification of geo-tagged field photos by deep learning , 2017, Environ. Model. Softw..

[52]  J. Janowiak,et al.  GPCP Pentad Precipitation analyses: An experimental dataset based on gauge observations and satellite estimates , 2003 .

[53]  B. Nelson,et al.  Evaluation of precipitation estimates over CONUS derived from satellite, radar, and rain gauge data sets at daily to annual scales (2002–2012) , 2015 .

[54]  Hui Lu,et al.  Ground validation of GPM IMERG and TRMM 3B42V7 rainfall products over southern Tibetan Plateau based on a high‐density rain gauge network , 2017 .

[55]  Viviana Maggioni,et al.  A Review of Merged High-Resolution Satellite Precipitation Product Accuracy during the Tropical Rainfall Measuring Mission (TRMM) Era , 2016 .

[56]  J. Janowiak,et al.  CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal Resolution , 2004 .

[57]  Kuolin Hsu,et al.  PERSIANN-MSA: A Precipitation Estimation Method from Satellite-Based Multispectral Analysis , 2009 .

[58]  Soroosh Sorooshian,et al.  Evaluation of PERSIANN-CCS rainfall measurement using the NAME event rain gauge network , 2007 .

[59]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[60]  S. Sorooshian,et al.  A Review of Global Precipitation Data Sets: Data Sources, Estimation, and Intercomparisons , 2018 .

[61]  Christian D. Kummerow,et al.  A method for combining passive microwave and infrared rainfall observations , 1995 .

[62]  S. Kanae,et al.  Global Hydrological Cycles and World Water Resources , 2006, Science.

[63]  Kuolin Hsu,et al.  The CHRS Data Portal, an easily accessible public repository for PERSIANN global satellite precipitation data , 2019, Scientific Data.

[64]  Yang Hong,et al.  Evaluation of the successive V6 and V7 TRMM multisatellite precipitation analysis over the Continental United States , 2013 .

[65]  P. A. Arkin,et al.  A combined microwave/infrared rain rate algorithm , 2001 .

[66]  J. Janowiak,et al.  A Real–Time Global Half–Hourly Pixel–Resolution Infrared Dataset and Its Applications , 2001 .

[67]  A. Okuyama,et al.  An Introduction to Himawari-8/9— Japan’s New-Generation Geostationary Meteorological Satellites , 2016 .

[68]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[69]  Pijush Samui,et al.  A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area. , 2019, The Science of the total environment.

[70]  Kuolin Hsu,et al.  Bias adjustment of infrared‐based rainfall estimation using Passive Microwave satellite rainfall data , 2017 .

[71]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[72]  Congcong Wen,et al.  A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. , 2019, The Science of the total environment.

[73]  R. Moore,et al.  Accuracy of rainfall measurement for scales of hydrological interest , 2000 .