MiRTaW: An Algorithm for Atmospheric Temperature and Water Vapor Profile Estimation from ATMS Measurements Using a Random Forests Technique

Francesco Di Paola,Saverio Nilo,Angela Cersosimo,Domenico Cimini,Elisabetta Ricciardelli,Sabrina Gentile,Paolo Sanò,Salvatore Larosa,Mariassunta Viggiano,Arianna Di Paola,Edoardo Geraldi,Donatello Gallucci,Ermann Ripepi,Filomena Romano

doi:10.3390/rs10091398

Abstract

A new algorithm for the estimation of atmospheric temperature (T) and water vapor (WV) vertical profiles in nonprecipitating conditions is presented. The microwave random forest temperature and water vapor (MiRTaW) profiling algorithm is based on the random forest (RF) technique and it uses microwave (MW) sounding from the Advanced Technology Microwave Sounder (ATMS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite. Three different data sources were chosen for both training and validation purposes, namely, the ERA-Interim from the European Centre for Medium-Range Weather Forecasts (ECMWF), the Infrared Atmospheric Sounding Interferometer Atmospheric Temperature Water Vapour and Surface Skin Temperature (IASI L2 v6) from the Meteorological Operational satellites of the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT), and the radiosonde observations from the Integrated Global Radiosonde Archive (IGRA). The period from 2012 to 2016 was considered in the training dataset; particular attention was paid to the instance selection procedure, in order to reduce the full training dataset with negligible information loss. The out-of-bag (OOB) error was computed and used to select the optimal RF parameters. Different RFs were trained, one for each vertical level: 32 levels for T (within 10–1000 hPa) and 23 levels for WV (200–1000 hPa). The validation of the MiRTaW profiling algorithm was conducted on a dataset from 2017. The mean bias error (MBE) of T vertical profiles ranges within about (−0.4–0.4) K, while for the WV mixing ratio, the MBE starts at ~0.5 g/kg near the surface and decreases to ~0 g/kg at 200 hPa level, in line with the expectations.

Highlights

The Advanced Technology Microwave Sounder (ATMS) is a cross-track scanning microwave (MW) radiometer currently flying onboard the Suomi National Polar-orbiting Partnership (SNPP) and the National Oceanic and Atmospheric Administration NOAA-20 satellite missions
We propose a new algorithm, based on a random forests (RF) regression technique [30,31] and ATMS brightness temperature (BT) observations; it exploits the relatively small data dimensions of MW soundings and their ability to penetrate the cloud cover to provide T and water vapor (WV) vertical profiles in reasonable time and nearly-all-weather conditions
This paper presents a random forest approach to profiling atmospheric temperature and water vapor by MW passive observations

Summary

Introduction

The Advanced Technology Microwave Sounder (ATMS) is a cross-track scanning microwave (MW) radiometer currently flying onboard the Suomi National Polar-orbiting Partnership (SNPP) and the National Oceanic and Atmospheric Administration NOAA-20 satellite missions. ATMS provides MW passive observations, useful to retrieve temperature (T) and water vapor (WV) atmospheric vertical profiles [1,2], among other products. These profiles play an important role in atmosphere monitoring and they are routinely used for climate applications and operational weather prediction [3,4]. The first algorithms developed in the 1980s were based on statistical multivariate regression methods and were applied to simulated data [14,15]. Optimal estimation methods were proposed, which estimate the vertical profiles with an iterative scheme starting from an a priori state of the atmosphere and varying it at each iteration, until convergence between observed brightness temperature (BT) and forward model simulations is reached [20,21,22,23]

Methods

Findings

Discussion

Conclusion