A Novel Framework of Detecting Convective Initiation Combining Automated Sampling, Machine Learning, and Repeated Model Tuning from Geostationary Satellite Data

• Published in: Remote sensing (Basel, Switzerland) Vol. 11; no. 12; p. 1454
• Main Authors: Han, Daehyeon, Lee, Juhyun, Im, Jungho, Sim, Seongmun, Lee, Sanggyun, Han, Hyangsun
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2019
• Subjects: Algorithms; Artificial intelligence; Atmospheric models; automated sampling; Automation; Clouds; convective initiation (CI); Datasets; False alarms; Himawari-8; Lead time; Learning algorithms; Machine learning; Meteorological satellites; Principal components analysis; Rain; random forest; repeated model tuning; Sampling; Sensors; Synchronous satellites; Training; Tuning; East Asia; Japan; Korean Peninsula
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs11121454

This paper proposes a complete framework of a machine learning-based model that detects convective initiation (CI) from geostationary meteorological satellite data. The suggested framework consists of three main processes: (1) An automated sampling tool; (2) machine learning-based CI detection modelling; (3) repeated model tuning through validation. In this study, the automated sampling tool was able to track the CI objects iteratively, even without ancillary data such as an atmospheric motion vector (AMV). The collected samples were used to train the machine learning model for CI detection. Random forest (RF) was used to classify the CI and non-CI. To enhance the advantages of the machine learning approach, we adopted model tuning to iteratively update the training dataset from each validation result by adding hits and misses to the CI samples, and false alarms and correct negatives to the non-CI samples. Using 12 interest fields from the Himawari-8 Advanced Himawari Imager (AHI) over the Korean Peninsula, this simple and intuitive tuning process increased the overall probability of detection (POD) from 0.79 to 0.82 and decreased the overall false alarm rate (FAR) from 0.46 to 0.37 with around 40 min of the lead-time. Amongst the 12 interest fields, T b (11.2) µm was identified as the most significant predictor in the RF model, followed by T b (8.6—11.2) µm, and T b (6.2–7.3) µm. The effect of model tuning on the CI detection performance was also analyzed using spatiotemporal validation maps. By automatically collecting and updating the machine learning training dataset, the suggested framework is expected to help the maintenance of the CI detection model from an operational perspective.