Papers

61,005 results
|
Article Tier 2

A new band selection framework for hyperspectral remote sensing image classification

Researchers developed a new framework for reducing data complexity in hyperspectral satellite images by combining dual band selection with a convolutional neural network, achieving over 97% classification accuracy across three benchmark datasets. This approach could improve remote sensing applications like land cover mapping and environmental monitoring.

2024 Scientific Reports 15 citations
Article Tier 2

Multiscale Dense Cross-Attention Mechanism with Covariance Pooling for Hyperspectral Image Scene Classification

Researchers developed a multiscale dense cross-attention mechanism with covariance pooling for hyperspectral image scene classification, addressing challenges of high dimensionality and feature redundancy in deep convolutional frameworks to improve classification accuracy.

2021 Mobile Information Systems 45 citations
Article Tier 2

From Local to Global: Efficient Dual Attention Mechanism for Single Image Super-Resolution

Researchers developed a dual attention mechanism for deep learning neural networks to improve single image super-resolution. This type of image enhancement technology could have applications in improving the detection and classification of microplastic particles in environmental images.

2021 IEEE Access 8 citations
Article Tier 2

Applications of Deep Learning-Based Super-Resolution Networks for AMSR2 Arctic Sea Ice Images

Researchers applied deep learning-based super-resolution networks to enhance the spatial resolution of AMSR2 passive microwave satellite images of Arctic sea ice, addressing the coarse native resolution that limits detailed analysis of sea ice extent and dynamics. The approach improved image quality and enabled more precise monitoring of Arctic sea ice changes with implications for understanding climate impacts on polar ecosystems.

2023 Remote Sensing 4 citations
Article Tier 2

3D Fourier-based Global Feature Extraction for Hyperspectral Image Classification

Researchers proposed HGFNet, a hybrid deep learning architecture combining 3D convolutional local feature extraction with three complementary Fourier transform strategies for hyperspectral image classification, achieving efficient long-range spectral-spatial modeling and improved discrimination of underrepresented classes via an adaptive focal loss mechanism.

2026 ArXiv.org
Article Tier 2

Enhancing the Detection of Coastal Marine Debris in Very High-Resolution Satellite Imagery via Unsupervised Domain Adaptation

Researchers proposed a satellite-based marine debris detection model using unsupervised domain adaptation to overcome limitations of applying high-resolution trained models to lower-resolution imagery. The approach improves practical applicability for monitoring coastal debris distributions across diverse satellite data sources.

2024 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8 citations
Article Tier 2

Enhancing Structural Crack Detection through a Multiscale Multilevel Mask Deep Convolutional Neural Network and Line Similarity Index

Researchers developed a multiscale multilevel mask deep convolutional neural network (MSML Mask DCNN) combined with a line similarity index (LSI) for automated structural crack detection in infrastructure. Field tests in a building and underground power tunnel demonstrated the system outperformed existing neural networks by accurately identifying linear and curvilinear crack features using only publicly available training images.

2023 International Journal of Intelligent Systems 3 citations
Article Tier 2

Flux to Flow: a Clearer View of Earth’s Water Cycle Via Neural Networks and Satellite Data

This dissertation developed neural network methods to enhance the spatial resolution of satellite measurements of Earth's water cycle, enabling finer-scale monitoring of hydrological processes such as precipitation, evaporation, and runoff across diverse environments.

2023
Article Tier 2

A Hybrid Deep Learning Model for Wind and Solar Power Forecasting in Smart Grids

Researchers developed a hybrid deep learning model combining multiple neural network architectures to improve wind and solar power forecasting in smart grids, addressing limitations of traditional models in handling the complex, non-linear, and time-varying nature of renewable energy output.

2025 Preprints.org
Article Tier 2

Hyperspectral detection of soil microplastics via multimodal feature fusion and a dual-path attention residual convolutional network

A hyperspectral imaging approach combined with multimodal deep learning was developed to detect microplastics in soil, achieving high accuracy in identifying plastic particles against complex soil backgrounds. The method offers a faster, less destructive alternative to traditional chemical extraction and spectroscopy for soil monitoring.

2025 Talanta 1 citations
Article Tier 2

Development of representative convolutional neural network based models for microplastic spectral identification

Researchers developed more representative convolutional neural network (CNN) models for microplastic spectral identification by training on expanded spectral databases that include greater diversity of plastic types, aging stages, secondary additives, pigments, and environmental contamination, outperforming library-search methods in classification accuracy and speed.

2024 Zenodo (CERN European Organization for Nuclear Research)
Article Tier 2

Landslide Mapping Using Two Main Deep-Learning Convolution Neural Network Streams Combined by the Dempster–Shafer Model

Researchers evaluated deep-learning convolutional neural network approaches combined using the Dempster-Shafer model for mapping earthquake-induced landslides from PlanetScope optical and ALOS topographic data, finding that fusing two CNN streams improved mapping accuracy over single-stream approaches for post-earthquake landslide inventory generation.

2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 64 citations
Article Tier 2

Detection of Vegetation Spectral Signatures in Hyperspectral Images using Artificial Neural Networks

This study developed a computer program that can identify plants and vegetation in detailed satellite images by analyzing how they reflect different colors of light. The technology successfully detected about 42% of an area as vegetation in a test neighborhood, which was more accurate than older methods. This could help scientists better monitor environmental changes like deforestation or urban green spaces that affect air quality and human health.

2026 International Journal of Computers Communications & Control
Article Tier 2

Enhancing marine debris identification with convolutional neural networks

A deep learning model was developed to identify and classify marine debris components captured by underwater remotely operated vehicle imagery, addressing the challenge of widely distributed ocean waste including microplastics. The convolutional neural network demonstrated improved accuracy for debris detection and classification compared to conventional image analysis methods.

2024 Journal of Emerging Investigators 1 citations
Article Tier 2

Enhanced Microplastic Aggregation Prediction via Deep Learning and Spectral Analysis of Marine Snow Composition

Researchers developed a deep learning framework called the Spectral-Enhanced Aggregation Prediction Network that integrates spectral analysis of marine snow to improve prediction of microplastic aggregation rates in the ocean, addressing limitations of current models that struggle with the complex interplay of biological, chemical, and physical factors.

2025 Zenodo (CERN European Organization for Nuclear Research)
Article Tier 2

Extraction the Spatial Distribution of Mangroves in the Same Month Based on Images Reconstructed with the FSDAF Model

Researchers applied the FSDAF spatiotemporal fusion model to reconstruct cloud-free satellite images for the same target month, enabling accurate extraction of mangrove spatial distributions in coastal wetlands despite the persistent cloud cover that limits image availability in mangrove-growing regions. The approach demonstrated improved accuracy in mapping mangrove extent compared to methods relying on mosaicked images spanning several months.

2023 Forests 5 citations
Article Tier 2

Enhanced Microplastic Aggregation Prediction via Deep Learning and Spectral Analysis of Marine Snow Composition

Researchers developed a deep learning framework called the Spectral-Enhanced Aggregation Prediction Network that integrates spectral analysis of marine snow to improve prediction of microplastic aggregation rates in the ocean, addressing limitations of current models that struggle with the complex interplay of biological, chemical, and physical factors.

2025 Zenodo (CERN European Organization for Nuclear Research)
Article Tier 2

An Attention-Based 3D Convolutional Autoencoder for Few-Shot Hyperspectral Unmixing and Classification

Researchers developed a semi-supervised deep learning pipeline for hyperspectral image classification that uses a 3D convolutional autoencoder with attention mechanisms to extract spectral-spatial features, achieving better classification accuracy than supervised CNN methods when only small amounts of labeled data are available.

2023 Remote Sensing 12 citations
Article Tier 2

Sanxingdui Cultural Relics Recognition Algorithm Based on Hyperspectral Multi-Network Fusion

A hyperspectral multi-network recognition algorithm was developed to identify ancient Sanxingdui cultural relics non-destructively, improving accuracy over conventional methods that risk damaging irreplaceable artifacts. The approach demonstrates how spectroscopic imaging and machine learning can support cultural heritage conservation.

2023 Computers, materials & continua/Computers, materials & continua (Print) 4 citations
Article Tier 2

Automatic Identification and Classification of Marine Microplastic Pollution Based on Deep Learning and Spectral Imaging Technology

Researchers developed an AI system combining deep learning with multispectral imaging to automatically identify and classify marine microplastics, using a feature-selection method called ReliefF to reduce noise in complex ocean samples. The approach achieved high accuracy and offers a scalable solution for large-scale ocean microplastic monitoring that outperforms traditional manual inspection.

2025 Traitement du signal
Article Tier 2

Depth-Wise Separable Convolution Attention Module for Garbage Image Classification

Researchers developed a depth-wise separable convolution attention module for classifying garbage images using deep learning. The study proposed an improved convolutional neural network architecture that enhances classification accuracy while reducing computational complexity. The findings suggest that automated image-based waste sorting using AI could improve efficiency over manual garbage classification methods.

2022 Sustainability 49 citations
Article Tier 2

A Novel Multi-Branch Channel Expansion Network for Garbage Image Classification

Researchers developed a novel multi-branch channel expansion deep learning network for garbage image classification, finding that conventional deep network architectures with skip connections performed poorly on the TrashNet dataset and that their optimized structure better addressed data scarcity in this domain.

2020 IEEE Access 61 citations
Article Tier 2

Slim Deep Learning Approach for Microplastics Image Classification in the Marine Environment

Researchers developed a lightweight convolutional neural network called the Slim-DL-Model for classifying microplastics in marine environment images, designed to overcome the computational demands of existing architectures like VGG16 and ResNet for real-time field applications. The model achieves competitive classification accuracy while significantly reducing computational requirements, enabling deployable microplastic monitoring systems.

2025 Cognizance Journal of Multidisciplinary Studies
Article Tier 2

Detection of Trash in Sea Using Deep Learning

Researchers developed a deep learning convolutional neural network (CNN) model to detect and classify trash in marine and aquatic environments from underwater images, aiming to overcome the limitations of manual debris detection for objects that may be submerged or partially obscured.

2022 YMER Digital