Ten deep learning techniques to address small data problems with remote sensing

Safonova, Anastasiia; Ghazaryan, Gohar; Stiller, Stefan; Main-Knorn, Magdalena; Nendel, Claas; Ryo, Masahiro

doi:10.1016/j.jag.2023.103569

Cited by 14 publications

(2 citation statements)

References 200 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach aimed to compensate for the shortcomings of existing methods and provide a reliable outcome for effectively estimating AGB. [61][62][63]. As an extended version of long short-term memory (LSTM), BiLSTM consists of both forward and backward LSTM layers.…”

Section: Setting Of Feature Combination Scenariosmentioning

confidence: 99%

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

Zhang,

Zhou,

Zhang

et al. 2024

Forests

View full text Add to dashboard Cite

The estimation of forest above-ground biomass (AGB) can be significantly improved by leveraging remote sensing (RS) and deep learning (DL) techniques. In this process, it is crucial to obtain appropriate RS features and develop a suitable model. However, traditional methods such as random forest (RF) feature selection often fail to adequately consider the complex relationships within high-dimensional RS feature spaces. Moreover, challenges related to parameter selection and overfitting inherent in DL models may compromise the accuracy of AGB estimation. Therefore, this study proposes a novel framework based on freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 optical data. Firstly, we designed new indices through the formula analogous with vegetation index calculation to integrate multidimensional spectral and structural information. Then, leveraging the simplicity of computational principles, a pigeon-inspired optimization algorithm (PIO) was introduced into a bi-directional long short-term memory neural network (PIO-BiLSTM), which achieved the set objective function through repeated iteration and validation to obtain the optimal model parameters. Finally, to verify the framework’s effect, we conducted experiments in two different tree species and compared another seven classical optimization algorithms and machine learning models. The results indicated that the new indices significantly improved the inversion accuracy of all models in both categories, and the PIO-BiLSTM model achieved the highest accuracy (Category-1: R2 = 0.8055, MAE = 8.8475 Mg·ha−1, RMSE = 12.2876 Mg·ha−1, relative RMSE = 18.1715%; Category-2: R2 = 0.7956, MAE = 1.7103 Mg·ha−1, RMSE = 2.2887 Mg·ha−1, relative RMSE = 9.3000%). Compared with existing methods, the proposed framework greatly reduced the labor costs in parameter selection, and its potential uncertainty also decreased by up to 9.0%. Furthermore, the proposed method has a strong generalization ability and is independent of tree species, indicating its great potential for future forest AGB inversion in wider regions with diverse forest types.

show abstract

Section: Setting Of Feature Combination Scenariosmentioning

confidence: 99%

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

Zhang,

Zhou,

Zhang

et al. 2024

Forests

View full text Add to dashboard Cite

show abstract

“…Compared to commonly used computer vision datasets, remote sensing datasets are considered small datasets, especially those focused on the collocation observation of SAR and scatterometer. Therefore, some complex deep networks may not be suitable for the OSWS super-resolution mapping [19]. Additionally, this research aims to enable the scatterometer OSWS to learn local historical spatial information from SAR OSWS while preserving the OSWS inversion accuracy of the scatterometer itself.…”

Section: Introductionmentioning

confidence: 99%

Super Resolution Mapping of Scatterometer Ocean Surface Wind Speed Using Generative Adversarial Network: Experiments in the Southern China Sea

Wan,

Liu,

Guo

et al. 2024

JMSE

View full text Add to dashboard Cite

This paper designed a Generative Adversarial Network (GAN)-based super-resolution framework for scatterometer ocean surface wind speed (OSWS) mapping. An improved GAN, WSGAN, was well-trained to generate high-resolution OSWS (~1/64 km) from low-resolution OSWS (~12.5 km) retrieved from scatterometer observations. The generator of GAN incorporated Synthetic Aperture Radar (SAR) information in the training phase. Therefore, the pre-trained model could reconstruct high-resolution OSWS with historical local spatial and texture information. The training experiments were executed in the South China Sea using the OSWS generated from the Advanced SCATterometer (ASCAT) scatterometer and Sentinel-1 SAR OSWS set. Several GAN-based methods were compared, and WSGAN performed the best in most sea states, enabling more detail mining with fewer checkerboard artifacts at a scale factor of eight. The model reaches an overall root mean square error (RMSE) of 0.81 m/s and an overall mean absolute error (MAE) of 0.68 m/s in the collocation region of ASCAT and Sentinel-1. The model also exhibits excellent generalization capability in another scatterometer with an overall RMSE of 1.11 m/s. This study benefits high-resolution OSWS users when no SAR observation is available.

show abstract

Deep learning and satellite remote sensing for biodiversity monitoring and conservation

Pettorelli,

Williams,

Schulte to Bühne

et al. 2024

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

In the context of the current nature crisis, being able to reliably and cost‐effectively track subtle changes in the biosphere across adequate spatial and temporal extents and resolutions is crucial. Deep learning represents a group of versatile approaches to image processing tasks that are increasingly combined with satellite remote sensing imagery to monitor biodiversity and inform ecology and conservation, yet an overview of the opportunities and challenges associated with this development has so far been lacking. Here, we provide an interdisciplinary perspective on current research and technological developments associated with satellite remote sensing and deep learning that have the potential to make a difference in biodiversity monitoring and wildlife conservation; highlight challenges to the broader adoption of these approaches by experts operating at the interface between satellite remote sensing and ecology and conservation; and discuss how these can be overcome. By enabling the leveraging of big data and by providing new ways to learn about biodiversity and its dynamics, deep learning approaches promise to become a powerful tool to help address current monitoring needs and knowledge gaps. In certain situations, deep learning approaches may moreover substantially reduce the time and resources required to analyse satellite imagery. However, issues relating to capacity building, reference data access, environmental costs as well as model interpretability, robustness and alignment need to be addressed to successfully capitalize on these opportunities.

show abstract

Ten deep learning techniques to address small data problems with remote sensing

Cited by 14 publications

References 200 publications

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

A Novel Framework for Forest Above-Ground Biomass Inversion Using Multi-Source Remote Sensing and Deep Learning

Super Resolution Mapping of Scatterometer Ocean Surface Wind Speed Using Generative Adversarial Network: Experiments in the Southern China Sea

Deep learning and satellite remote sensing for biodiversity monitoring and conservation

Contact Info

Product

Resources

About