ADVANCING AIRBORNE HYPERSPECTRAL DATA PROCESSING AND APPLICATIONS FOR SUSTAINABLE AGRICULTURE USING RTM-BASED MACHINE LEARNING

被引:4
作者
Zhou, Qu [1 ,2 ]
Wang, Sheng [1 ,2 ]
Guan, Kaiyu [1 ,2 ,3 ]
机构
[1] Univ Illinois, Inst Sustainabil Energy & Environm, Agroecosyst Sustainabil Ctr, Champaign, IL 61820 USA
[2] Univ Illinois, Coll Agr Consumer & Environm Sci, Champaign, IL 61820 USA
[3] Univ Illinois, Natl Ctr Supercomp Applicat, Champaign, IL 61820 USA
来源
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年
关键词
airborne hyperspectral remote sensing; sustainable agriculture; radiative transfer modeling; machine learning; atmospheric correction; retrieving applications;
D O I
10.1109/IGARSS52108.2023.10283455
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Airborne hyperspectral remote sensing data can provide rich spatial and spectral information at very high resolutions (spatial: <1 m; spectral: <5 nm) to accurately monitor diverse agroecosystem variables such as crop traits, soil properties, and agricultural practices. This high-resolution information is beneficial to agricultural stakeholders for decision-making, timely management, and precision evaluations, which can further advance sustainable agriculture. However, it is challenging to process large-volume airborne hyperspectral data and fulfill the potential of airborne hyperspectral information for sustainable agriculture. To overcome these challenges, we developed an operational framework to process and utilize airborne hyperspectral images using Radiative Transfer Modeling (RTM)-based Machine Learning (RTM-ML) approaches. The framework can accurately and efficiently conduct atmospheric correction of and retrieve agroecosystem variables such as crop nitrogen, cover crop aboveground biomass, and crop residue from airborne hyperspectral data. Extensive validation against ground truth data indicated that the framework can efficiently derive surface reflectance from airborne raw data with mean absolute errors<0.03 and cosine similarities>0.99; and reliably quantify crop nitrogen, cover crop aboveground biomass, and crop residue with an R-2 of 0.85, 0.72, and 0.82, respectively. Our framework demonstrated strong capabilities in processing and utilizing airborne hyperspectral data for sustainable agriculture.
引用
收藏
页码:1269 / 1272
页数:4
相关论文
共 50 条
[41]   Applications of machine learning algorithms in lithological mapping of Saint Katherine Neoproterozoic rocks in the South Sinai of Egypt using hyperspectral PRISMA data [J].
Ali-Bik, Mohamed W. ;
Zafar, Tehseen ;
Hassan, Safaa M. ;
Sadek, Mohamed F. ;
Abo Khashaba, Saif M. .
SCIENTIFIC REPORTS, 2025, 15 (01)
[42]   Enhancing prediction of crop yield and soil health assessment for sustainable agriculture using machine learning approach [J].
Vhatkar, Kapil Netaji ;
Koparde, Shweta Ashish ;
Kothari, Sonali ;
Sarwade, Jayesh ;
Sakur, Kishor .
METHODSX, 2025, 14
[43]   Machine learning-based modeling in food processing applications: State of the art [J].
Khan, Md. Imran H. ;
Sablani, Shyam S. ;
Nayak, Richi ;
Gu, Yuantong .
COMPREHENSIVE REVIEWS IN FOOD SCIENCE AND FOOD SAFETY, 2022, 21 (02) :1409-1438
[44]   Providing Cooperative Data Analytics for Real Applications Using Machine Learning [J].
Iyengar, Arun ;
Kalagnanam, Jayant ;
Patel, Dhaval ;
Reddy, Chandra ;
Shrivastava, Shrey .
2019 39TH IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2019), 2019, :1878-1890
[45]   MACHINE LEARNING IN EARTH SYSTEM SCIENCE APPLICATIONS USING SATELLITE DATA [J].
Haupt, Sue Ellen .
IGARSS 2024-2024 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, IGARSS 2024, 2024, :1284-1287
[46]   Handling imbalanced data in supervised machine learning for lithological mapping using remote sensing and airborne geophysical data [J].
Nugroho, Hary ;
Wikantika, Ketut ;
Bijaksana, Satria ;
Saepuloh, Asep .
OPEN GEOSCIENCES, 2023, 15 (01)
[47]   Advancing algal biofuel production through data-driven insights: A comprehensive review of machine learning applications [J].
Omole, Olakunle Ayodeji ;
Ogbaga, Chukwuma C. ;
Okolie, Jude A. ;
Akande, Olugbenga ;
Kimera, Richard ;
Dayil, Joseph Lepnaan .
COMPUTERS & CHEMICAL ENGINEERING, 2025, 196
[48]   Towards sustainable energy efficiency: Data-driven optimization in large-scale plants using machine learning applications [J].
Ha, Byeongmin ;
Lee, Hyeonjeong ;
Hwangbo, Soonho .
ENERGY, 2025, 331
[49]   Machine learning applications for sustainable manufacturing: a bibliometric-based review for future research [J].
Jamwal, Anbesh ;
Agrawal, Rajeev ;
Sharma, Monica ;
Kumar, Anil ;
Kumar, Vikas ;
Garza-Reyes, Jose Arturo Arturo .
JOURNAL OF ENTERPRISE INFORMATION MANAGEMENT, 2022, 35 (02) :566-596
[50]   Predictions of Spartina alterniflora leaf functional traits based on hyperspectral data and machine learning models [J].
Li, Wei ;
Zuo, Xueyan ;
Liu, Zhijun ;
Nie, Leichao ;
Li, Huazhe ;
Wang, Junjie ;
Dou, Zhiguo ;
Cai, Yang ;
Zhai, Xiajie ;
Cui, Lijuan .
EUROPEAN JOURNAL OF REMOTE SENSING, 2024, 57 (01)