TRMM-era neural networks for GPM-era satellite quantitative precipitation estimation (QPE)

• Published in: Atmospheric research Vol. 315; p. 107879
• Main Authors: Leganés, Livia J., Navarro, Andrés, Lee, Gyuwon, Martín, Raúl, Kidd, Chris, Tapiador, Francisco J.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2025
• Subjects: algorithms; FORTRAN; GPM; GPROF; hydrologic cycle; hydrometeorology; Neural network; PYTHON; Quantitative precipitation estimates; radar; rain; Remote sensing; satellites; Quantitative precipitation estimates; GPM; FORTRAN; Neural network; PYTHON; Remote sensing; GPROF
• ISSN: 0169-8095
• DOI: 10.1016/j.atmosres.2024.107879

Quantitative Precipitation Estimates (QPE) obtained from satellite data are essential for accurately assessing the hydrological cycle in both land and ocean. Early artificial Neural Networks (NN) methods were used previously either to merge infrared and microwave data or to derive better precipitation products from radar and radiometer measurements. Over the last 25 years, machine learning technology has advanced significantly, accompanied by the initiation of new satellites, such as the Global Precipitation Measurement Mission Core Observatory (GPM-CO). In addition, computing power has increased exponentially since the beginning of the 21st century. This paper compares the performance of a pure NN FORTRAN, originally designed to expedite the 2A12 TRMM (Tropical Rainfall Measuring Mission) algorithm, with a contemporary state-of-the-art NN in Python using the TensorFlow library (NN PYTHON). The performance of FORTRAN and Python approaches to QPE using GPM-CO data are compared with the goal of achieving a minimum NN architecture that at least matches the outcome of the Goddard Profiling Algorithm (GPROF) algorithm. Another conclusion is that the new NN PYTHON does not present significant advantages over the old FORTRAN code. The latter does not require dependencies, which has many practical advantages in operational use and therefore have an edge over more complex approaches in hydrometeorology. •A Neural Network method for QPE from PMW radiometer data is presented.•A simple FORTRAN NN compares well with a PYTHON TENSORFLOW NN.•GPROF can be simulated with a simple FORTRAN NNs/ PYTHON NN.