Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations
The retrieval of accurate profiles of temperature and water vapour is important for the study of atmospheric convection. Recent development in computational techniques motivated us to use adaptive techniques in the retrieval algorithms. In this work, we have used an adaptive neuro-fuzzy inference sy...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2015-01-01
|
| Series: | Atmospheric Measurement Techniques |
| Online Access: | http://www.atmos-meas-tech.net/8/369/2015/amt-8-369-2015.pdf |
| _version_ | 1819242029892239360 |
|---|---|
| author | K. Ramesh A. P. Kesarkar J. Bhate M. Venkat Ratnam A. Jayaraman |
| author_facet | K. Ramesh A. P. Kesarkar J. Bhate M. Venkat Ratnam A. Jayaraman |
| author_sort | K. Ramesh |
| collection | DOAJ |
| description | The retrieval of accurate profiles of temperature and water vapour is important
for the study of atmospheric convection. Recent development in computational
techniques motivated us to use adaptive techniques in the retrieval algorithms.
In this work, we have used an adaptive neuro-fuzzy inference system (ANFIS) to
retrieve profiles of temperature and humidity up to 10 km over the tropical
station Gadanki (13.5° N, 79.2° E), India. ANFIS is
trained by using observations of temperature and humidity measurements by
co-located Meisei GPS radiosonde (henceforth referred to as radiosonde) and
microwave brightness temperatures observed by radiometrics multichannel
microwave radiometer MP3000 (MWR). ANFIS is trained by considering these
observations during rainy and non-rainy days (ANFIS(RD + NRD)) and during non-rainy days only (ANFIS(NRD)). The comparison of ANFIS(RD + NRD) and
ANFIS(NRD) profiles with independent radiosonde observations and profiles
retrieved using multivariate linear regression (MVLR: RD + NRD and NRD)
and artificial neural network (ANN) indicated that the errors in the
ANFIS(RD + NRD) are less compared to other retrieval methods.
<br><br>
The Pearson product movement correlation coefficient (<i>r</i>) between retrieved
and observed profiles is more than 92% for temperature profiles for all
techniques and more than 99% for the ANFIS(RD + NRD) technique
Therefore this new techniques is relatively better for the retrieval of
temperature profiles. The comparison of bias, mean absolute error (MAE), RMSE and symmetric mean absolute percentage error
(SMAPE) of retrieved temperature and relative humidity (RH) profiles using ANN and ANFIS also
indicated that profiles retrieved using ANFIS(RD + NRD) are significantly
better compared to the ANN technique. The analysis of profiles concludes that
retrieved profiles using ANFIS techniques have improved the temperature
retrievals substantially; however, the retrieval of RH by all techniques
considered in this paper (ANN, MVLR and ANFIS) has limited success. |
| first_indexed | 2024-12-23T14:33:19Z |
| format | Article |
| id | doaj.art-a3fea63b6e17436c9fed60fd8eaf635b |
| institution | Directory Open Access Journal |
| issn | 1867-1381 1867-8548 |
| language | English |
| last_indexed | 2024-12-23T14:33:19Z |
| publishDate | 2015-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Measurement Techniques |
| spelling | doaj.art-a3fea63b6e17436c9fed60fd8eaf635b2022-12-21T17:43:25ZengCopernicus PublicationsAtmospheric Measurement Techniques1867-13811867-85482015-01-018136938410.5194/amt-8-369-2015Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observationsK. Ramesh0A. P. Kesarkar1J. Bhate2M. Venkat Ratnam3A. Jayaraman4Department of Computer Applications, Anna University, Regional Center, Tirunelveli, Tamil Nadu 627 005, IndiaNational Atmospheric Research Laboratory, Gadanki 517 112, Chittoor District, Andhra Pradesh, IndiaNational Atmospheric Research Laboratory, Gadanki 517 112, Chittoor District, Andhra Pradesh, IndiaNational Atmospheric Research Laboratory, Gadanki 517 112, Chittoor District, Andhra Pradesh, IndiaNational Atmospheric Research Laboratory, Gadanki 517 112, Chittoor District, Andhra Pradesh, IndiaThe retrieval of accurate profiles of temperature and water vapour is important for the study of atmospheric convection. Recent development in computational techniques motivated us to use adaptive techniques in the retrieval algorithms. In this work, we have used an adaptive neuro-fuzzy inference system (ANFIS) to retrieve profiles of temperature and humidity up to 10 km over the tropical station Gadanki (13.5° N, 79.2° E), India. ANFIS is trained by using observations of temperature and humidity measurements by co-located Meisei GPS radiosonde (henceforth referred to as radiosonde) and microwave brightness temperatures observed by radiometrics multichannel microwave radiometer MP3000 (MWR). ANFIS is trained by considering these observations during rainy and non-rainy days (ANFIS(RD + NRD)) and during non-rainy days only (ANFIS(NRD)). The comparison of ANFIS(RD + NRD) and ANFIS(NRD) profiles with independent radiosonde observations and profiles retrieved using multivariate linear regression (MVLR: RD + NRD and NRD) and artificial neural network (ANN) indicated that the errors in the ANFIS(RD + NRD) are less compared to other retrieval methods. <br><br> The Pearson product movement correlation coefficient (<i>r</i>) between retrieved and observed profiles is more than 92% for temperature profiles for all techniques and more than 99% for the ANFIS(RD + NRD) technique Therefore this new techniques is relatively better for the retrieval of temperature profiles. The comparison of bias, mean absolute error (MAE), RMSE and symmetric mean absolute percentage error (SMAPE) of retrieved temperature and relative humidity (RH) profiles using ANN and ANFIS also indicated that profiles retrieved using ANFIS(RD + NRD) are significantly better compared to the ANN technique. The analysis of profiles concludes that retrieved profiles using ANFIS techniques have improved the temperature retrievals substantially; however, the retrieval of RH by all techniques considered in this paper (ANN, MVLR and ANFIS) has limited success.http://www.atmos-meas-tech.net/8/369/2015/amt-8-369-2015.pdf |
| spellingShingle | K. Ramesh A. P. Kesarkar J. Bhate M. Venkat Ratnam A. Jayaraman Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations Atmospheric Measurement Techniques |
| title | Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| title_full | Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| title_fullStr | Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| title_full_unstemmed | Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| title_short | Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| title_sort | adaptive neuro fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations |
| url | http://www.atmos-meas-tech.net/8/369/2015/amt-8-369-2015.pdf |
| work_keys_str_mv | AT kramesh adaptiveneurofuzzyinferencesystemfortemperatureandhumidityprofileretrievalfrommicrowaveradiometerobservations AT apkesarkar adaptiveneurofuzzyinferencesystemfortemperatureandhumidityprofileretrievalfrommicrowaveradiometerobservations AT jbhate adaptiveneurofuzzyinferencesystemfortemperatureandhumidityprofileretrievalfrommicrowaveradiometerobservations AT mvenkatratnam adaptiveneurofuzzyinferencesystemfortemperatureandhumidityprofileretrievalfrommicrowaveradiometerobservations AT ajayaraman adaptiveneurofuzzyinferencesystemfortemperatureandhumidityprofileretrievalfrommicrowaveradiometerobservations |