Advanced Machine Learning and Deep Learning Approaches for Remote Sensing

doi:10.3390/books978-3-0365-7947-4

Reprint

Download Flyer

Advanced Machine Learning and Deep Learning Approaches for Remote Sensing

Edited by

June 2023

362 pages

ISBN978-3-0365-7946-7 (Hardback)
ISBN978-3-0365-7947-4 (PDF)

https://doi.org/10.3390/books978-3-0365-7947-4

Free download (PDF)

This book is a reprint of the Special Issue Advanced Machine Learning and Deep Learning Approaches for Remote Sensing that was published in

Engineering

Environmental & Earth Sciences

Summary

This reprint provides research on how technologies such as artificial intelligence-based machine learning and deep learning can be applied to remote sensing. Through this, we can see the process of solving the existing problems of image and image signal processing for remote sensing. These techniques are computationally intensive and require the help of high-performance computing devices. With the development of devices such as GPUs, remote sensing technology, and aerial sensing technology, it is possible to monitor the Earth with high-resolution images and to obtain vast amounts of Earth observation data. The papers published in this reprint describe recent advances in big data processing and artificial intelligence-based technologies for remote sensing technology.

Format

Hardback

License

Keywords

live fuel moisture content; deep learning; ensemble learning; multi-source remote sensing; spatiotemporal fusion; dilated convolution; improved transformer encoder; global correlation information; semantic segmentation; attention mechanism; robust deep learning; remote sensing; data fusion; low-light image enhancement; retinex theory; deep learning; remote-sensing; orbital angular momentum; mode detection; fine-grained image classification; attention pyramid; atmospheric turbulence; sea surface temperature; mutual information; LSTM; self-attention; interdimensional attention; noise suppression deblurring; curriculum learning; image reconstruction; turbulence degradation; depthwise separable convolutional neural networks; spectrogram augmentation; sound detection; vehicle detection; image super-resolution; deep learning; remote sensing; model design; evaluation methods; maritime communication; evaporation duct; deep learning; multi-dimensional prediction model; digital surface model; multimodal; multi-scale supervision; feature separation; reconstruction refinement; significant wave height; deep learning; autoencoder; principal component analysis; SAR; altimeter; Gaussian process regression; convolutional neural network; deep learning; computer vision; solar farm; solar panel; capacity estimation; photovoltaics; remote sensing; optical remote sensing; peri-urban forests; lightweight convolutional neural network; FlexibleNet; carbon sequestration; remote sensing; semi-supervised learning; few-shot learning; SAR target recognition; discriminative representation learning; remote image; deep learning; semantic segmentation; CNN; multiscale feature fusion; Transformer; improved Tversky loss; two-step convolution model; cloud detection; cloud matting; cloud removal; n/a