Frost forecasting via weakly-supervised semantic segmentation of satellite imagery

Recent research on frost forecasting has employed machine learning approaches to build prediction models tailored to specific locations. Although these models have proven effective, their applications are limited to areas where meteorological observations are available. Forecasting coverage can be e...

Full description

Saved in:
Bibliographic Details
Main Authors: Seokho Kang, Seon-Kyeong Seong, Eunha Sohn, Jiyoung Kim, Jaewoong Shim
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:GIScience & Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/15481603.2025.2496013
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849315494821101568
author Seokho Kang
Seon-Kyeong Seong
Eunha Sohn
Jiyoung Kim
Jaewoong Shim
author_facet Seokho Kang
Seon-Kyeong Seong
Eunha Sohn
Jiyoung Kim
Jaewoong Shim
author_sort Seokho Kang
collection DOAJ
description Recent research on frost forecasting has employed machine learning approaches to build prediction models tailored to specific locations. Although these models have proven effective, their applications are limited to areas where meteorological observations are available. Forecasting coverage can be extended by using meteorological satellite data as predictors, enabling frost forecasting over broader regions. This can be formulated as a semantic segmentation task of detecting areas where frost is likely to occur. Using satellite images and geographical information of the target region at the forecast time as inputs, the semantic segmentation model generates a frost probability map for the target time of forecast. However, an important challenge arises from the limited availability of pixel-wise labels, as frost occurrence information is only available for pixels corresponding to frost observatories. To address this issue, we propose a weakly-supervised learning method for training the semantic segmentation model using satellite imagery with incomplete supervision. The learning objective involves accurately classifying labeled pixels while suppressing the entire frost probability map to zero when no frost is observed at any observatory within the target region. Additionally, a metric-surrogate loss is incorporated to maximize the critical success index for labeled pixels. We demonstrate the effectiveness of the proposed method for frost forecasting with varying lead times across the South Korean region using Geo-KOMPSAT-2A satellite data.
format Article
id doaj-art-2e9be78d55c04a689c1d92c39f9d8437
institution Kabale University
issn 1548-1603
1943-7226
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series GIScience & Remote Sensing
spelling doaj-art-2e9be78d55c04a689c1d92c39f9d84372025-08-20T03:52:07ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262025-12-0162110.1080/15481603.2025.2496013Frost forecasting via weakly-supervised semantic segmentation of satellite imagerySeokho Kang0Seon-Kyeong Seong1Eunha Sohn2Jiyoung Kim3Jaewoong Shim4Department of Industrial Engineering, Sungkyunkwan University, Suwon, Republic of KoreaNational Meteorological Satellite Center, Korea Meteorological Administration, Jincheon, Republic of KoreaNational Meteorological Satellite Center, Korea Meteorological Administration, Jincheon, Republic of KoreaNational Meteorological Satellite Center, Korea Meteorological Administration, Jincheon, Republic of KoreaDepartment of Industrial Engineering, Seoul National University of Science and Technology, Seoul, Republic of KoreaRecent research on frost forecasting has employed machine learning approaches to build prediction models tailored to specific locations. Although these models have proven effective, their applications are limited to areas where meteorological observations are available. Forecasting coverage can be extended by using meteorological satellite data as predictors, enabling frost forecasting over broader regions. This can be formulated as a semantic segmentation task of detecting areas where frost is likely to occur. Using satellite images and geographical information of the target region at the forecast time as inputs, the semantic segmentation model generates a frost probability map for the target time of forecast. However, an important challenge arises from the limited availability of pixel-wise labels, as frost occurrence information is only available for pixels corresponding to frost observatories. To address this issue, we propose a weakly-supervised learning method for training the semantic segmentation model using satellite imagery with incomplete supervision. The learning objective involves accurately classifying labeled pixels while suppressing the entire frost probability map to zero when no frost is observed at any observatory within the target region. Additionally, a metric-surrogate loss is incorporated to maximize the critical success index for labeled pixels. We demonstrate the effectiveness of the proposed method for frost forecasting with varying lead times across the South Korean region using Geo-KOMPSAT-2A satellite data.https://www.tandfonline.com/doi/10.1080/15481603.2025.2496013Frost forecastingmeteorological satellitesemantic segmentationweakly-supervised learningconvolutional neural network
spellingShingle Seokho Kang
Seon-Kyeong Seong
Eunha Sohn
Jiyoung Kim
Jaewoong Shim
Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
GIScience & Remote Sensing
Frost forecasting
meteorological satellite
semantic segmentation
weakly-supervised learning
convolutional neural network
title Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
title_full Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
title_fullStr Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
title_full_unstemmed Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
title_short Frost forecasting via weakly-supervised semantic segmentation of satellite imagery
title_sort frost forecasting via weakly supervised semantic segmentation of satellite imagery
topic Frost forecasting
meteorological satellite
semantic segmentation
weakly-supervised learning
convolutional neural network
url https://www.tandfonline.com/doi/10.1080/15481603.2025.2496013
work_keys_str_mv AT seokhokang frostforecastingviaweaklysupervisedsemanticsegmentationofsatelliteimagery
AT seonkyeongseong frostforecastingviaweaklysupervisedsemanticsegmentationofsatelliteimagery
AT eunhasohn frostforecastingviaweaklysupervisedsemanticsegmentationofsatelliteimagery
AT jiyoungkim frostforecastingviaweaklysupervisedsemanticsegmentationofsatelliteimagery
AT jaewoongshim frostforecastingviaweaklysupervisedsemanticsegmentationofsatelliteimagery