A Deep Learning-Based Multitasking Model for Hyperspectral Image Analysis using Novel TAIGA Dataset

• Published in: IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium
• Main Authors: Chhapariya, Koushikey, Benoit, Alexandre, Buddhiraju, Krishna Mohan, Kumar, Anil
• Other Authors: Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, India, Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry ), Indian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2024
• Subjects: MESH: deep learning; MESH: hyperspectral imaging; MESH: machine learning; MESH: multitask; MESH: classification; MESH: regression; [STAT]Statistics [stat]; [INFO]Computer Science [cs]; [SDE]Environmental Sciences; taiga
• Online Access: https://hal.science/hal-04697949; https://doi.org/10.1109/IGARSS53475.2024.10641762

International audience Hyperspectral imaging is essential for the detailed and accurate identification of materials and features across various applications, including environmental monitoring and agricultural assessment. However, processing large-scale hyperspectral images is time-consuming and requires huge computational resources attributed to their volume. Additionally, classification methods lacking spatial information and focusing only on spectral information are inadequate with the feature complexity of the dataset. Hence, to overcome the above-mentioned challenges, there is a dire need for advanced algorithms capable of efficiently processing large-scale hyperspectral data. This paper highlights the motivation and need for multitask learning models for hyperspectral datasets. A large-scale hyperspectral dataset called TAIGA, which comprises both categorical and continuous forest variables, is considered. The proposed deep learning model addresses data imbalance and loss function concerns by incorporating spectral as well as spatial information to develop a multitask model. This work emphasizes the importance of accounting for correlations between data and tasks when designing a relevant model. As a result, the study leads to more efficient model training, reduced data requirements, and potentially improved overall predictive capabilities. We achieved overall accuracy for categorical variables as high as 98.25% and mean absolute error as low as 0.019 for continuous variables.