Spectral-spatial Features Research Articles

Class incremental learning with analytic learning for hyperspectral image classification

Hyperspectral image classification (HSIC) is crucial for applications in agriculture and environmental monitoring. As ground objects evolve and remote sensing technology progresses, there is a growing need for HSIC models that can adapt to new data classes without requiring to be retrained from scratch. Throughout the continual learning procedure, the model is expected to not only effectively extract spatial–spectral features from the hyperspectral image but also alleviate the issue of catastrophic forgetting, i.e., the model forgets the learned classes’ knowledge when accessing novel classes during the training process. In this paper, for the HSIC task, we propose a class incremental learning method (HSI-CIL) that is based on analytic learning, a technique that converts network training into linear problems. Specifically, The HSI-CIL model consists of a lightweight feature extractor, a Feature Processing Module (FPM) and an Analytic Linear Classifier (ALC). This model does not need data storage for old and new classes and has only one epoch in the incremental learning stage, so it has lower consumption of resources and training time than several attempts have been proposed for addressing catastrophic forgetting. We perform abundant experiments with the proposed HSI-CIL on three publicly available hyperspectral datasets including Indian Pines, Pavia University, and Salinas. The experiments demonstrate that our HSI-CIL exceeds the state-of-the-art class incremental learning (CIL) techniques applied in HSIC with a certain gap.

AMHFN: Aggregation Multi-Hierarchical Feature Network for Hyperspectral Image Classification

Deep learning methods like convolution neural networks (CNNs) and transformers are successfully applied in hyperspectral image (HSI) classification due to their ability to extract local contextual features and explore global dependencies, respectively. However, CNNs struggle in modeling long-term dependencies, and transformers may miss subtle spatial-spectral features. To address these challenges, this paper proposes an innovative hybrid HSI classification method aggregating hierarchical spatial-spectral features from a CNN and long pixel dependencies from a transformer. The proposed aggregation multi-hierarchical feature network (AMHFN) is designed to capture various hierarchical features and long dependencies from HSI, improving classification accuracy and efficiency. The proposed AMHFN consists of three key modules: (a) a Local-Pixel Embedding module (LPEM) for capturing prominent spatial-spectral features; (b) a Multi-Scale Convolutional Extraction (MSCE) module to capture multi-scale local spatial-spectral features and aggregate hierarchical local features; (c) a Multi-Scale Global Extraction (MSGE) module to explore multi-scale global dependencies and integrate multi-scale hierarchical global dependencies. Rigorous experiments on three public hyperspectral image (HSI) datasets demonstrated the superior performance of the proposed AMHFN method.

ANN-Based Filtering of Drone LiDAR in Coastal Salt Marshes Using Spatial–Spectral Features

ANN-Based Filtering of Drone LiDAR in Coastal Salt Marshes Using Spatial–Spectral Features

STSNet: A cross-spatial resolution multi-modal remote sensing deep fusion network for high resolution land-cover segmentation

Recently, deep learning models have found extensive application in high-resolution land-cover segmentation research. However, the most current research still suffers from issues such as insufficient utilization of multi-modal information, which limits further improvement in high-resolution land-cover segmentation accuracy. Moreover, differences in the size and spatial resolution of multi-modal datasets collectively pose challenges to multi-modal land-cover segmentation. Therefore, we propose a high-resolution land-cover segmentation network (STSNet) with cross-spatial resolution spatio-temporal-spectral deep fusion. This network effectively utilizes spatio-temporal-spectral features to achieve information complementary among multi-modal data. Specifically, STSNet consists of four components: (1) A high resolution and multi-scale spatial-spectral encoder to jointly extract subtle spatial-spectral features in hyperspectral and high spatial resolution images. (2) A long-term spatio-temporal encoder formulated by spectral convolution and spatio-temporal transformer block to simultaneously delineates the spatial, temporal and spectral information in dense time series Sentinel-2 imagery. (3) A cross-resolution fusion module to alleviate the spatial resolution differences between multi-modal data and effectively leverages complementary spatio-temporal-spectral information. (4) A multi-scale decoder integrates multi-scale information from multi-modal data. We utilized airborne hyperspectral remote sensing imagery from the Shenyang region of China in 2020, with a spatial resolution of 1authors declare that they have no known competm, a spectral number of 249, and a spectral resolution ≤ 5 nm, and its Sentinel dense time-series images acquired in the same period with a spatial resolution of 10 m, a spectral number of 10, and a time-series number of 31. These datasets were combined to generate a multi-modal dataset called WHU-H2SR-MT, which is the first open accessed large-scale high spatio-temporal-spectral satellite remote sensing dataset (i.e., with >2500 image pairs sized 300 m × 300 m for each). Additionally, we employed two open-source datasets to validate the effectiveness of the proposed modules. Extensive experiments show that our multi-scale spatial-spectral encoder, spatio-temporal encoder, and cross-resolution fusion module outperform existing state-of-the-art (SOTA) algorithms in terms of overall performance on high-resolution land-cover segmentation. The new multi-modal dataset will be made available at http://irsip.whu.edu.cn/resources/resources_en_v2.php, along with the corresponding code for accessing and utilizing the dataset at https://github.com/RS-Mage/STSNet.

Domain adaptation hyperspectral image fusion based on spatial-spectral domain separation

ABSTRACT Hyperspectral datasets captured by airborne are one of the important data sources in the field of hyperspectral image fusion. However, the limited number of data samples often hinders the optimal performance of deep learning-based methods on these datasets. Domain adaptation is expected to alleviate the issue of data scarcity. However, there are two issues that need to be addressed in applying domain adaptation to hyperspectral image fusion, which are the heterogeneity and spatial degradation diversity of hyperspectral data. In this paper, we propose a domain adaptation hyperspectral image fusion network based on spatial-spectral domain separation. The model, constructed with three-dimensional convolutional layers, effectively addresses the challenge of hyperspectral data heterogeneity. Compared with 2D convolution, 3D convolution is able to consider both spatial and spectral dimensions and extract spatial-spectral features efficiently. Based on this, we design a domain-separation architecture to extract domain-invariant and domain-private features in the spatial-spectral domain. The architecture achieves domain adaptation by extracting domain-invariant features from both datasets to obtain the prior knowledge in the source dataset and apply it to the target dataset. Additionally, the spatial degradation of different datasets varies due to distinct shooting conditions during the acquisition. Therefore, the fusion algorithms should be robust to various degradation scenarios. To tackle this challenge, we design the Observation Module to predict degradation information and the Degradation Information Modulation Module to apply it to the input, thereby enhancing the network’s robustness. Experiments on various datasets demonstrate that our method is qualitatively and quantitatively superior to state-of-the-art methods.

Early detection of N, P, K deficiency in Choy Sum using hyperspectral imaging-based spatial spectral feature mining

Leafy vegetables are widely consumed around the world for their rich nutritional qualities. To ensure a reliable and cost-effective supply of leafy vegetables in the future, advancements in their production are essential. Deficiencies of nitrogen (N), phosphorus (P), and potassium (K) impair growth of leafy vegetables and the ensuing visual symptoms make the plants unmarketable. We studied the use of non-contact large area hyperspectral imaging (HSI) for early detection of N, P and K deficiencies in the leafy vegetable, Choy Sum, before the appearance of visual symptoms. The wide spectral data of 500–900 nm extracted from the plants were subjected to advanced feature mining, facilitating the creation of novel spectral indices tailored to each vital nutrient by leveraging the Pearson’s correlations of 0.85 for N, 0.64 for P, and 0.68 for K with gold standard elemental concentration data. Early detection of deficiencies and timely replenishment of macronutrient(s) can prevent the development of obvious symptoms and thus maintain the visual quality of Choy Sum. These newly created spectral indices hold the potential to provide non-destructive estimation of nutrient content in plants, offering a promising avenue for future advancements in precision agriculture and resource-efficient crop management.

Hyperspectral image classification with spectral-spatial feature integration and ensemble learning

<p>Hyperspectral imaging (HSI) has emerged as a robust remote sensing and medical imaging tool. However, HSI classification remains a challenging problem due to the high-dimensional data and the need for efficient feature selection and enhancement techniques. The proposed work addresses the problem of spatial feature extraction in spectral-spatial HSI classification tasks. This paper introduces an innovative model addressing the intricacies of spatial feature extraction in spectral-spatial HSI classification tasks, employing a fusion of spectral and spatial features through an adaptive kernel-based Gaussian filtering mechanism to elevate the quality of HSI data and augment classification performance. The classification is executed using three distinct classifiers, whose decisions are harmoniously integrated within an ensemble learning framework to optimize outcomes. The effectiveness of the proposed system is meticulously evaluated across three diverse datasets, Indian Pine, Pavia, and Salinas. This study also compares the model's efficiency against the existing similar work presented in the literature. The results show that the proposed work outperforms existing methods with constantly showing 99% accuracy and kappa score for each dataset, demonstrating its potential applications in various domains such as remote sensing and medical imaging.</p>

A Global Spatial-Spectral Feature Fused Autoencoder for Nonlinear Hyperspectral Unmixing

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach.

Noise-Disruption-Inspired Neural Architecture Search with Spatial–Spectral Attention for Hyperspectral Image Classification

In view of the complexity and diversity of hyperspectral images (HSIs), the classification task has been a major challenge in the field of remote sensing image processing. Hyperspectral classification (HSIC) methods based on neural architecture search (NAS) is a current attractive frontier that not only automatically searches for neural network architectures best suited to the characteristics of HSI data, but also avoids the possible limitations of manual design of neural networks when dealing with new classification tasks. However, the existing NAS-based HSIC methods have the following limitations: (1) the search space lacks efficient convolution operators that can fully extract discriminative spatial–spectral features, and (2) NAS based on traditional differentiable architecture search (DARTS) has performance collapse caused by unfair competition. To overcome these limitations, we proposed a neural architecture search method with receptive field spatial–spectral attention (RFSS-NAS), which is specifically designed to automatically search the optimal architecture for HSIC. Considering the core needs of the model in extracting more discriminative spatial–spectral features, we designed a novel and efficient attention search space. The core component of this innovative space is the receptive field spatial–spectral attention convolution operator, which is capable of precisely focusing on the critical information in the image, thus greatly enhancing the quality of feature extraction. Meanwhile, for the purpose of solving the unfair competition issue in the traditional differentiable architecture search (DARTS) strategy, we skillfully introduce the Noisy-DARTS strategy. The strategy ensures the fairness and efficiency of the search process and effectively avoids the risk of performance crash. In addition, to further improve the robustness of the model and ability to recognize difficult-to-classify samples, we proposed a fusion loss function by combining the advantages of the label smoothing loss and the polynomial expansion perspective loss function, which not only smooths the label distribution and reduces the risk of overfitting, but also effectively handles those difficult-to-classify samples, thus improving the overall classification accuracy. Experiments on three public datasets fully validate the superior performance of RFSS-NAS.

Spatial-spectral feature extraction for in-field chlorophyll content estimation using hyperspectral imaging

In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained RP2 of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (RP2 = 0.85) compared to RF bands (RP2 = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with RP2 of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved RP2 above 0.93 in individual years (RP2 = 0.96 in 2021, RP2 = 0.94 in 2021) and RP2 in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.

A Multi-Scale Mask Convolution-Based Blind-Spot Network for Hyperspectral Anomaly Detection

Existing methods of hyperspectral anomaly detection still face several challenges: (1) Due to the limitations of self-supervision, avoiding the identity mapping of anomalies remains difficult; (2) the ineffective interaction between spatial and spectral features leads to the insufficient utilization of spatial information; and (3) current methods are not adaptable to the detection of multi-scale anomaly targets. To address the aforementioned challenges, we proposed a blind-spot network based on multi-scale blind-spot convolution for HAD. The multi-scale mask convolution module is employed to adapt to diverse scales of anomaly targets, while the dynamic fusion module is introduced to integrate the advantages of mask convolutions at different scales. The proposed approach includes a spatial–spectral joint module and a background feature attention mechanism to enhance the interaction between spatial–spectral features, with a specific emphasis on highlighting the significance of background features within the network. Furthermore, we propose a preprocessing technique that combines pixel shuffle down-sampling (PD) with spatial spectral joint screening. This approach addresses anomalous identity mapping and enables finite-scale mask convolution for better detection of targets at various scales. The proposed approach was assessed on four real hyperspectral datasets comprising anomaly targets of different scales. The experimental results demonstrate the effectiveness and superior performance of the proposed methodology compared with nine state-of-the-art methods.

MSSFNet: A Multiscale Spatial-Spectral Fusion Network for Extracting Offshore Floating Raft Aquaculture Areas in Multispectral Remote Sensing Images.

Accurately extracting large-scale offshore floating raft aquaculture (FRA) areas is crucial for supporting scientific planning and precise aquaculture management. While remote sensing technology offers advantages such as wide coverage, rapid imaging, and multispectral capabilities for FRA monitoring, the current methods face challenges in terms of establishing spatial-spectral correlations and extracting multiscale features, thereby limiting their accuracy. To address these issues, we propose an innovative multiscale spatial-spectral fusion network (MSSFNet) designed specifically for extracting offshore FRA areas from multispectral remote sensing imagery. MSSFNet effectively integrates spectral and spatial information through a spatial-spectral feature extraction block (SSFEB), significantly enhancing the accuracy of FRA area identification. Additionally, a multiscale spatial attention block (MSAB) captures contextual information across different scales, improving the ability to detect FRA areas of varying sizes and shapes while minimizing edge artifacts. We created the CHN-YE7-FRA dataset using Sentinel-2 multispectral remote sensing imagery and conducted extensive evaluations. The results showed that MSSFNet achieved impressive metrics: an F1 score of 90.76%, an intersection over union (IoU) of 83.08%, and a kappa coefficient of 89.75%, surpassing those of state-of-the-art methods. The ablation results confirmed that the SSFEB and MSAB modules effectively enhanced the FRA extraction accuracy. Furthermore, the successful practical applications of MSSFNet validated its generalizability and robustness across diverse marine environments. These findings highlight the performance of MSSFNet in both experimental and real-world scenarios, providing reliable, precise FRA area monitoring. This capability provides crucial data for scientific planning and environmental protection purposes in coastal aquaculture zones.

Multi-dimensional attention-aided transposed ConvBiLSTM network for hyperspectral image super-resolution

Hyperspectral (HS) image always suffers from the deficiency of low spatial resolution, compared with conventional optical image types, which has limited its further applications in remote sensing areas. Therefore, HS image super-resolution (SR) techniques are broadly employed in order to observe finer spatial structures while preserving the spectra of ground covers. In this paper, a novel multi-dimensional attention-aided transposed convolutional long-short term memory (LSTM) network is proposed for single HS image super-resolution task. The proposed network employs the convolutional bi-directional LSTM for the purpose of local and non-local spatial–spectral feature explorations, and transposed convolution for the purpose of image amplification and reconstruction. Moreover, a multi-dimensional attention module is proposed, aiming to capture the salient features on spectral, channel, and spatial dimensions, simultaneously, to further improve the learning abilities of network. Experiments on four commonly-used HS images demonstrate the effectiveness of this approach, compared with several state-of-the-art deep learning-based SR methods.

Interactive Siamese spatial-Spectral cross-layer fusion transformer for hyperspectral image change detection

ABSTRACT Recently, methods based on Transformer have been widely used in the research field of hyperspectral image (HSI) change detection (CD). However, existing transformer-based CD research does not sufficiently utilize the spatial-spectral features of HSIs. In this article, we propose an interactive Siamese spatial-spectral cross-layer fusion Transformer (IS2CF-Former) network to improve the accuracy of HSI-CD. The proposed Siamese interactive module integrates the Siamese network with the Transformer structure, enhancing communication between bi-temporal images. We have made improvements to the cross-layer adaptive fusion (CAF) Transformer, where the cross-layer fusion module enhances the interaction between layers and the ability to capture local contextual features, concurrently reducing the model’s parameter count to mitigate the risk of overfitting. The CAF Transformer is applied to extract spatial and spectral features. Evaluating the detection performance of the proposed model on three bi-temporal HSIs through extensive experiments demonstrates superior accuracy compared to seven excellent CD methods.

An Analysis on Intelligent Systems for Remote Sensing Satellite Image Processing and Classification

The integration of intelligent systems to the remote sensing satellite image processing and classification has greatly changed. This paper offers a synthesis of the subject, with respect to intelligent systems’ contribution to the improvement of these processes’ accuracy and speed. Accuracy of different methods such as machine learning algorithms, artificial neural networks, and deep learning techniques in the extraction of information from satellite image comprehension is considered a research interest. The presented problems and open issues are data complexity, feature extraction, and classification accuracy over the data, along with new methods in enhancing the intelligent systems to minimize those problems. It expands knowledge of intelligent systems’ contribution to remote sensing applications by outlining how these advancements have influenced the progression of image analysis for the given research goals. This research work gives the summary of our research by outlining the techniques used in the study, the problems solved, and the general outcomes of incorporating intelligent systems in the area of remote sensing and satellite image analysis. Accuracy analysis results for the SVM based methodology with spatial-spectral features include 90% of accuracy, 88% of the precision, and 90% of the F1-score, which in turn makes it easy to make sound decisions when using satellite imagery in different fields like agriculture, urban development, and environment.

Deep hierarchical spectral-spatial feature fusion for hyperspectral image classification based on convolutional neural network

Joint spectral-spatial feature extraction has been proven to be the most effective part of hyperspectral image (HSI) classification. But, due to the mixing of informative and noisy bands in HSI, joint spectral-spatial feature extraction using convolutional neural network (CNN) may lead to information loss and high computational cost. More specifically, joint spectral-spatial feature extraction from excessive bands may cause loss of spectral information due to the involvement of convolution operation on non-informative spectral bands. Therefore, we propose a simple yet effective deep learning model, named deep hierarchical spectral-spatial feature fusion (DHSSFF), where spectral-spatial features are exploited separately to reduce the information loss and fuse the deep features to learn the semantic information. It makes use of abundant spectral bands and few informative bands of HSI for spectral and spatial feature extraction, respectively. The spectral and spatial features are extracted through 1D CNN and 3D CNN, respectively. To validate the effectiveness of our model, the experiments have been performed on five well-known HSI datasets. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods and achieved 99.17%, 98.84%, 98.70%, 99.18%, and 99.24% overall accuracy on Kennedy Space Center, Botswana, Indian Pines, University of Pavia, and Salinas datasets, respectively.

LCFE-X: Pluggable Local Channel Feature Extraction model enhancement method for hyperspectral image classification

Spectral information of hyperspectral images offers high-dimensional features for downstream tasks. Local spectral signatures in different wavelength ranges are critical for material identification and pixel classification. In line with conventional vision methods, recent studies have focused on bolstering the spatial modelling capabilities of transformers. However, the focus remains predominantly global when the channel dimension is considered. Current research on enhancing local channel feature extraction is primarily model specific and lacks generalisable methods that can be applied to various models. Therefore, this study introduces a Local Channel Feature Extraction (LCFE) module. It extracts spectral-spatial features and key features within each band group and then integrates the features to obtain local channel features. Subsequently, a pluggable LCFE-X model enhancement method is proposed. This involves performing LCFE at the front end of the model and fusing the extracted features with the original features. Three enhanced hyperspectral image classification models, namely, LCFE-ViT, LCFE-SF, and LCFE-MF, are constructed based on recently proposed models. Extensive experiments demonstrate that the LCFE module effectively extracts local spectral signatures, and the proposed method enhances the performance of the various basic models. The code is available at https://github.com/YiSu1997/LCFE-X.

A Joint Network of Edge-Aware and Spectral-Spatial Feature Learning for Hyperspectral Image Classification.

Hyperspectral image (HSI) classification is a vital part of the HSI application field. Since HSIs contain rich spectral information, it is a major challenge to effectively extract deep representation features. In existing methods, although edge data augmentation is used to strengthen the edge representation, a large amount of high-frequency noise is also introduced at the edges. In addition, the importance of different spectra for classification decisions has not been emphasized. Responding to the above challenges, we propose an edge-aware and spectral-spatial feature learning network (ESSN). ESSN contains an edge feature augment block and a spectral-spatial feature extraction block. Firstly, in the edge feature augment block, the edges of the image are sensed, and the edge features of different spectral bands are adaptively strengthened. Then, in the spectral-spatial feature extraction block, the weights of different spectra are adaptively adjusted, and more comprehensive depth representation features are extracted on this basis. Extensive experiments on three publicly available hyperspectral datasets have been conducted, and the experimental results indicate that the proposed method has higher accuracy and immunity to interference compared to state-of-the-art (SOTA) method.

An improved 3D-SwinT-CNN network to evaluate the fermentation degree of black tea

Fermentation is a key process in forming the flavor quality of black tea. Evaluating the degree of fermentation during black tea processing is difficult. This paper proposes an improved 3D-SwinT-CNN network for the end-to-end processing of black tea's hyperspectral images to evaluate the degree of fermentation. The model incorporates dilated convolution and a shifted window self-attention mechanism, expanding the network's receptive field and capturing both local spatial-spectral and global features of black tea hyperspectral images. The accuracy is 98.13% on the test set. Compared to manual feature extraction methods, the accuracy improved by 3.45%. Compared to baseline 3D-CNNs, 3D-SwinT-CNN demonstrates superior spatial-spectral feature extraction, achieving an average accuracy improvement of 10.17%. Ablation experiments were conducted to further verify the effectiveness of the introduced modules. The proposed 3D-SwinT-CNN aims to establish a research foundation for online evaluation of black tea's fermentation degree.

Enhanced detection of Aspergillus flavus in peanut kernels using a multi-scale attention transformer (MSAT): Advancements in food safety and contamination analysis

In this study, a multi-scale attention transformer (MSAT) was coupled with hyperspectral imaging for classifying peanut kernels contaminated with diverse Aspergillus flavus fungi. The results underscored that the MSAT significantly outperformed classic deep learning models, due to its sophisticated multi-scale attention mechanism which enhanced its classification capabilities. The multi-scale attention mechanism was utilized by employing several multi-head attention layers to focus on both fine-scale and broad-scale features. It also integrated a series of scale processing layers to capture features at different resolutions and incorporated a self-attention mechanism to integrate information across different levels. The MSAT model achieved outstanding performance in different classification tasks, particularly in distinguishing healthy peanut kernels from those contaminated with aflatoxigenic fungi, with test accuracy achieving 98.42±0.22%. However, it faced challenges in differentiating peanut kernels contaminated with aflatoxigenic fungi from those with non-aflatoxigenic contamination. Visualization of attention weights explicitly revealed that the MSAT model's multi-scale attention mechanism progressively refined its focus from broad spatial-spectral features to more specialized signatures. Overall, the MSAT model's advanced processing capabilities marked a notable advancement in the field of food quality safety, offering a robust and reliable tool for the rapid and accurate detection of Aspergillus flavus contaminations in food.