CloudSense: A model for cloud type identification using machine learning from radar data

The knowledge of type of precipitating cloud is crucial for radar based quantitative estimates of precipitation. We propose a novel model called CloudSense which uses machine learning to accurately identify the type of precipitating clouds over the complex terrain locations in the Western Ghats (WG)...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehzooz Nizar, Jha K. Ambuj, Manmeet Singh, S.B. Vaisakh, G. Pandithurai
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Applied Computing and Geosciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590197424000569
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065508429201408
author Mehzooz Nizar
Jha K. Ambuj
Manmeet Singh
S.B. Vaisakh
G. Pandithurai
author_facet Mehzooz Nizar
Jha K. Ambuj
Manmeet Singh
S.B. Vaisakh
G. Pandithurai
author_sort Mehzooz Nizar
collection DOAJ
description The knowledge of type of precipitating cloud is crucial for radar based quantitative estimates of precipitation. We propose a novel model called CloudSense which uses machine learning to accurately identify the type of precipitating clouds over the complex terrain locations in the Western Ghats (WG) of India. CloudSense uses vertical reflectivity profiles collected during July–August 2018 from an X-band radar to classify clouds into four categories namely stratiform, mixed stratiform-convective, convective and shallow clouds. The machine learning (ML) model used in CloudSense was trained using a dataset balanced by Synthetic Minority Oversampling Technique (SMOTE), with features selected based on physical characteristics relevant to different cloud types. Among various ML models evaluated Light Gradient Boosting Machine (LightGBM) demonstrate superior performance in classifying cloud types with a BAC (Balanced Accuracy) of 0.79 and F1-Score of 0.8. CloudSense generated results are also compared against conventional radar algorithms and we find that CloudSense performs better than radar algorithms. For 200 samples tested, the radar algorithm achieved a BAC of 0.69 and F1-Score of 0.68, whereas CloudSense achieved a BAC of 0.8 and F1-Score of 0.79. Our results show that ML based approach can provide more accurate cloud detection and classification which would be useful to improve precipitation estimates over the complex terrain of the WG.
format Article
id doaj-art-1586e06bed624a9baa7976dc332bce8b
institution DOAJ
issn 2590-1974
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Applied Computing and Geosciences
spelling doaj-art-1586e06bed624a9baa7976dc332bce8b2025-08-20T02:48:58ZengElsevierApplied Computing and Geosciences2590-19742024-12-012410020910.1016/j.acags.2024.100209CloudSense: A model for cloud type identification using machine learning from radar dataMehzooz Nizar0Jha K. Ambuj1Manmeet Singh2S.B. Vaisakh3G. Pandithurai4Cochin University of Science and Technology, Kochi, India; Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India; Corresponding author. Cochin University of Science and Technology, Kochi, India.Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, IndiaIndian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India; The University of Texas at Austin, Austin, TX, USAIndian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, IndiaIndian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, IndiaThe knowledge of type of precipitating cloud is crucial for radar based quantitative estimates of precipitation. We propose a novel model called CloudSense which uses machine learning to accurately identify the type of precipitating clouds over the complex terrain locations in the Western Ghats (WG) of India. CloudSense uses vertical reflectivity profiles collected during July–August 2018 from an X-band radar to classify clouds into four categories namely stratiform, mixed stratiform-convective, convective and shallow clouds. The machine learning (ML) model used in CloudSense was trained using a dataset balanced by Synthetic Minority Oversampling Technique (SMOTE), with features selected based on physical characteristics relevant to different cloud types. Among various ML models evaluated Light Gradient Boosting Machine (LightGBM) demonstrate superior performance in classifying cloud types with a BAC (Balanced Accuracy) of 0.79 and F1-Score of 0.8. CloudSense generated results are also compared against conventional radar algorithms and we find that CloudSense performs better than radar algorithms. For 200 samples tested, the radar algorithm achieved a BAC of 0.69 and F1-Score of 0.68, whereas CloudSense achieved a BAC of 0.8 and F1-Score of 0.79. Our results show that ML based approach can provide more accurate cloud detection and classification which would be useful to improve precipitation estimates over the complex terrain of the WG.http://www.sciencedirect.com/science/article/pii/S2590197424000569Machine learningPrecipitating cloudsDoppler weather radarWestern ghatsLightGBM
spellingShingle Mehzooz Nizar
Jha K. Ambuj
Manmeet Singh
S.B. Vaisakh
G. Pandithurai
CloudSense: A model for cloud type identification using machine learning from radar data
Applied Computing and Geosciences
Machine learning
Precipitating clouds
Doppler weather radar
Western ghats
LightGBM
title CloudSense: A model for cloud type identification using machine learning from radar data
title_full CloudSense: A model for cloud type identification using machine learning from radar data
title_fullStr CloudSense: A model for cloud type identification using machine learning from radar data
title_full_unstemmed CloudSense: A model for cloud type identification using machine learning from radar data
title_short CloudSense: A model for cloud type identification using machine learning from radar data
title_sort cloudsense a model for cloud type identification using machine learning from radar data
topic Machine learning
Precipitating clouds
Doppler weather radar
Western ghats
LightGBM
url http://www.sciencedirect.com/science/article/pii/S2590197424000569
work_keys_str_mv AT mehzooznizar cloudsenseamodelforcloudtypeidentificationusingmachinelearningfromradardata
AT jhakambuj cloudsenseamodelforcloudtypeidentificationusingmachinelearningfromradardata
AT manmeetsingh cloudsenseamodelforcloudtypeidentificationusingmachinelearningfromradardata
AT sbvaisakh cloudsenseamodelforcloudtypeidentificationusingmachinelearningfromradardata
AT gpandithurai cloudsenseamodelforcloudtypeidentificationusingmachinelearningfromradardata