{"id":9742,"date":"2024-10-23T11:45:58","date_gmt":"2024-10-23T09:45:58","guid":{"rendered":"https:\/\/www.uni.lu\/research-en\/?post_type=events&p=9742"},"modified":"2024-11-28T08:45:01","modified_gmt":"2024-11-28T07:45:01","slug":"doctoral-defence-yiqun-wang-2","status":"publish","type":"events","link":"https:\/\/www.uni.lu\/research-en\/events\/doctoral-defence-yiqun-wang-2\/","title":{"rendered":"Doctoral Defence: Yiqun WANG"},"content":{"rendered":"\n
\n

The Doctoral School in Science and Engineering<\/a> is happy to invite you to Yiqun WANG\u2019s defence entitled<\/p>\n\n\n\n

\nCross Domain Early Crop Mapping based on Time-series Remote Sensing Data<\/h5>\n\n\n\n

Supervisor: Prof. Radu STATE<\/a><\/p>\n\n\n\n

This dissertation presents a comprehensive study of advanced remote sensing methodologies for early crop mapping, employing innovative machine learning techniques to address significant challenges in agricultural monitoring. The research encapsulates three main studies: ECMDCM (Early Crop Mapping using Dynamic Clustering Method), CropSTGAN (Crop Spectral-temporal Generative Adversarial Neural Network), and MultiCropGAN (Multiple Crop Mapping Generative Adversarial Neural Network), each contributing uniquely to the field of precision agriculture.<\/p>\n\n\n\n

The ECMDCM introduces a novel dynamic clustering approach using time-series NDVI and EVI data to enhance the accuracy of early crop mapping across the continental United States. By optimizing ecoregion delineations through the elbow and silhouette methods and employing Kmeans++ for clustering, this method demonstrates significant improvements over traditional static clustering techniques, offering a more dynamic and precise mapping of crop types.<\/p>\n\n\n\n

The CropSTGAN framework addresses the challenges of cross-domain variability in remote sensing-based crop mapping. It incorporates a domain mapper that effectively aligns temporal and spectral features across different geographic and temporal scales, facilitating robust model performance even in the presence of significant data distribution discrepancies. This framework has been validated across diverse regions and years, showcasing superior accuracy and adaptability in comparison to conventional approaches.<\/p>\n\n\n\n

Lastly, the MultiCropGAN framework is developed to tackle domain shift and label space discrepancies, which are prevalent in global agricultural settings. By incorporating identity losses into the generator\u2019s loss function, MultiCropGAN ensures the preservation of essential characteristics in the data, enhancing the authenticity and accuracy of crop type classification. Extensive testing across various North American regions highlights its effectiveness, particularly in handling divergent label spaces, thereby improving the reliability and applicability of crop mapping techniques.<\/p>\n\n\n\n

Together, these studies not only demonstrate the potential of generative adversarial networks and dynamic clustering in remote sensing but also pave the way for future innovations in agricultural monitoring. This thesis aims to contribute to the enhancement of global food security strategies through improved crop monitoring and management, underlining the critical role of advanced remote sensing technologies in the future of agriculture.<\/p>\n\n\n\n