无标签作物制图:利用5年Sentinel-2系列和机器学习研究作物分类模型的时空可转移性

Remote. Sens. Pub Date : 2023-07-05 DOI:10.3390/rs15133414
Tomáš Rusňák, T. Kasanický, Peter Malík, J. Mojžiš, J. Zelenka, M. Svicek, Dominik Abrahám, A. Halabuk
{"title":"无标签作物制图:利用5年Sentinel-2系列和机器学习研究作物分类模型的时空可转移性","authors":"Tomáš Rusňák, T. Kasanický, Peter Malík, J. Mojžiš, J. Zelenka, M. Svicek, Dominik Abrahám, A. Halabuk","doi":"10.3390/rs15133414","DOIUrl":null,"url":null,"abstract":"Multitemporal crop classification approaches have demonstrated high performance within a given season. However, cross-season and cross-region crop classification presents a unique transferability challenge. This study addresses this challenge by adopting a domain generalization approach, e.g., by training models on multiple seasons to improve generalization to new, unseen target years. We utilize a comprehensive five-year Sentinel-2 dataset over different agricultural regions in Slovakia and a diverse crop scheme (eight crop classes). We evaluate the performance of different machine learning classification algorithms, including random forests, support vector machines, quadratic discriminant analysis, and neural networks. Our main findings reveal that the transferability of models across years differs between regions, with the Danubian lowlands demonstrating better performance (overall accuracies ranging from 91.5% in 2022 to 94.3% in 2020) compared to eastern Slovakia (overall accuracies ranging from 85% in 2022 to 91.9% in 2020). Quadratic discriminant analysis, support vector machines, and neural networks consistently demonstrated high performance across diverse transferability scenarios. The random forest algorithm was less reliable in generalizing across different scenarios, particularly when there was a significant deviation in the distribution of unseen domains. This finding underscores the importance of employing a multi-classifier analysis. Rapeseed, grasslands, and sugar beet consistently show stable transferability across seasons. We observe that all periods play a crucial role in the classification process, with July being the most important and August the least important. Acceptable performance can be achieved as early as June, with only slight improvements towards the end of the season. Finally, employing a multi-classifier approach allows for parcel-level confidence determination, enhancing the reliability of crop distribution maps by assuming higher confidence when multiple classifiers yield similar results. To enhance spatiotemporal generalization, our study proposes a two-step approach: (1) determine the optimal spatial domain to accurately represent crop type distribution; and (2) apply interannual training to capture variability across years. This approach helps account for various factors, such as different crop rotation practices, diverse observational quality, and local climate-driven patterns, leading to more accurate and reliable crop classification models for nationwide agricultural monitoring.","PeriodicalId":20944,"journal":{"name":"Remote. Sens.","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Crop Mapping without Labels: Investigating Temporal and Spatial Transferability of Crop Classification Models Using a 5-Year Sentinel-2 Series and Machine Learning\",\"authors\":\"Tomáš Rusňák, T. Kasanický, Peter Malík, J. Mojžiš, J. Zelenka, M. Svicek, Dominik Abrahám, A. Halabuk\",\"doi\":\"10.3390/rs15133414\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multitemporal crop classification approaches have demonstrated high performance within a given season. However, cross-season and cross-region crop classification presents a unique transferability challenge. This study addresses this challenge by adopting a domain generalization approach, e.g., by training models on multiple seasons to improve generalization to new, unseen target years. We utilize a comprehensive five-year Sentinel-2 dataset over different agricultural regions in Slovakia and a diverse crop scheme (eight crop classes). We evaluate the performance of different machine learning classification algorithms, including random forests, support vector machines, quadratic discriminant analysis, and neural networks. Our main findings reveal that the transferability of models across years differs between regions, with the Danubian lowlands demonstrating better performance (overall accuracies ranging from 91.5% in 2022 to 94.3% in 2020) compared to eastern Slovakia (overall accuracies ranging from 85% in 2022 to 91.9% in 2020). Quadratic discriminant analysis, support vector machines, and neural networks consistently demonstrated high performance across diverse transferability scenarios. The random forest algorithm was less reliable in generalizing across different scenarios, particularly when there was a significant deviation in the distribution of unseen domains. This finding underscores the importance of employing a multi-classifier analysis. Rapeseed, grasslands, and sugar beet consistently show stable transferability across seasons. We observe that all periods play a crucial role in the classification process, with July being the most important and August the least important. Acceptable performance can be achieved as early as June, with only slight improvements towards the end of the season. Finally, employing a multi-classifier approach allows for parcel-level confidence determination, enhancing the reliability of crop distribution maps by assuming higher confidence when multiple classifiers yield similar results. To enhance spatiotemporal generalization, our study proposes a two-step approach: (1) determine the optimal spatial domain to accurately represent crop type distribution; and (2) apply interannual training to capture variability across years. This approach helps account for various factors, such as different crop rotation practices, diverse observational quality, and local climate-driven patterns, leading to more accurate and reliable crop classification models for nationwide agricultural monitoring.\",\"PeriodicalId\":20944,\"journal\":{\"name\":\"Remote. Sens.\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Remote. Sens.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/rs15133414\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Remote. Sens.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/rs15133414","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

多时间作物分类方法在给定季节内表现优异。然而,跨季节和跨地区的作物分类提出了一个独特的可转移性挑战。本研究通过采用领域泛化方法解决了这一挑战,例如,通过在多个季节上训练模型来提高对新的、看不见的目标年的泛化。我们利用斯洛伐克不同农业区的全面五年Sentinel-2数据集和多样化的作物方案(八种作物类别)。我们评估了不同机器学习分类算法的性能,包括随机森林、支持向量机、二次判别分析和神经网络。我们的主要发现表明,不同地区之间模型的可转移性不同,多瑙河低地与斯洛伐克东部相比表现更好(总体精度从2022年的91.5%到2020年的94.3%)(总体精度从2022年的85%到2020年的91.9%)。二次判别分析、支持向量机和神经网络在不同的可转移性场景中始终表现出高性能。随机森林算法在不同情况下的泛化可靠性较差,特别是当不可见域的分布存在显著偏差时。这一发现强调了采用多分类器分析的重要性。油菜籽、草地和甜菜始终表现出稳定的跨季节可转移性。我们观察到,所有时期在分类过程中都起着至关重要的作用,其中7月最重要,8月最不重要。可以接受的表现最早可以在6月实现,只有轻微的改进接近赛季结束。最后,采用多分类器方法允许包裹级置信度确定,当多个分类器产生相似结果时,通过假设更高的置信度来增强作物分布图的可靠性。为了提高时空概化能力,本研究提出了两步方法:(1)确定最优空间域以准确表征作物类型分布;(2)采用年际培训来捕捉不同年份的变化。这种方法有助于考虑各种因素,例如不同的作物轮作做法、不同的观测质量以及当地气候驱动的模式,从而为全国农业监测提供更准确和可靠的作物分类模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Crop Mapping without Labels: Investigating Temporal and Spatial Transferability of Crop Classification Models Using a 5-Year Sentinel-2 Series and Machine Learning
Multitemporal crop classification approaches have demonstrated high performance within a given season. However, cross-season and cross-region crop classification presents a unique transferability challenge. This study addresses this challenge by adopting a domain generalization approach, e.g., by training models on multiple seasons to improve generalization to new, unseen target years. We utilize a comprehensive five-year Sentinel-2 dataset over different agricultural regions in Slovakia and a diverse crop scheme (eight crop classes). We evaluate the performance of different machine learning classification algorithms, including random forests, support vector machines, quadratic discriminant analysis, and neural networks. Our main findings reveal that the transferability of models across years differs between regions, with the Danubian lowlands demonstrating better performance (overall accuracies ranging from 91.5% in 2022 to 94.3% in 2020) compared to eastern Slovakia (overall accuracies ranging from 85% in 2022 to 91.9% in 2020). Quadratic discriminant analysis, support vector machines, and neural networks consistently demonstrated high performance across diverse transferability scenarios. The random forest algorithm was less reliable in generalizing across different scenarios, particularly when there was a significant deviation in the distribution of unseen domains. This finding underscores the importance of employing a multi-classifier analysis. Rapeseed, grasslands, and sugar beet consistently show stable transferability across seasons. We observe that all periods play a crucial role in the classification process, with July being the most important and August the least important. Acceptable performance can be achieved as early as June, with only slight improvements towards the end of the season. Finally, employing a multi-classifier approach allows for parcel-level confidence determination, enhancing the reliability of crop distribution maps by assuming higher confidence when multiple classifiers yield similar results. To enhance spatiotemporal generalization, our study proposes a two-step approach: (1) determine the optimal spatial domain to accurately represent crop type distribution; and (2) apply interannual training to capture variability across years. This approach helps account for various factors, such as different crop rotation practices, diverse observational quality, and local climate-driven patterns, leading to more accurate and reliable crop classification models for nationwide agricultural monitoring.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Influences of Different Factors on Gravity Wave Activity in the Lower Stratosphere of the Indian Region Estimating Sugarcane Aboveground Biomass and Carbon Stock Using the Combined Time Series of Sentinel Data with Machine Learning Algorithms Dynamic Screening Strategy Based on Feature Graphs for UAV Object and Group Re-Identification The Expanding of Proglacial Lake Amplified the Frontal Ablation of Jiongpu Co Glacier since 1985 Investigation of Light-Scattering Properties of Non-Spherical Sea Salt Aerosol Particles at Varying Levels of Relative Humidity
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1