Multi-scale Image Research Articles

Multi-scale object detection in UAV images based on adaptive feature fusion.

With the widespread use of UAVs, UAV aerial image target detection technology can be used for practical applications in the military, traffic planning, personnel search and rescue and other fields. In this paper, we propose a multi-scale UAV aerial image detection method based on adaptive feature fusion for solving the problem of detecting small target objects in UAV aerial images. This method automatically adjusts the convolution kernel receptive field and reduces the redundant background of the image by adding an adaptive feature extraction module (AFEM) to the backbone network. This enables it to obtain more accurately and effectively small target feature information. In addition, we design an adaptive feature weighted fusion network (SBiFPN) to effectively enhance the representation of shallow feature information of small targets. Finally, we add an additional small target detection scale to the original network to expand the receptive field of the network and strengthen the detection of small target objects. The training and testing are carried out on the VisDrone public dataset. The experimental results show that the proposed method can achieve 38.5% mAP, which is 2.0% higher than the baseline network YOLOv5s, and can still detect the UAV aerial image well in complex scenes.

Multiscale image denoising algorithm based on UNet3+

Multiscale image denoising algorithm based on UNet3+

The value of a neural network based on multi-scale feature fusion to ultrasound images for the differentiation in thyroid follicular neoplasms

ObjectiveThe objective of this research was to create a deep learning network that utilizes multiscale images for the classification of follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) through preoperative US.MethodsThis retrospective study involved the collection of ultrasound images from 279 patients at two tertiary level hospitals. To address the issue of false positives caused by small nodules, we introduced a multi-rescale fusion network (MRF-Net). Four different deep learning models, namely MobileNet V3, ResNet50, DenseNet121 and MRF-Net, were studied based on the feature information extracted from ultrasound images. The performance of each model was evaluated using various metrics, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, F1 value, receiver operating curve (ROC), area under the curve (AUC), decision curve analysis (DCA), and confusion matrix.ResultsOut of the total nodules examined, 193 were identified as FTA and 86 were confirmed as FTC. Among the deep learning models evaluated, MRF-Net exhibited the highest accuracy and area under the curve (AUC) with values of 85.3% and 84.8%, respectively. Additionally, MRF-Net demonstrated superior sensitivity and specificity compared to other models. Notably, MRF-Net achieved an impressive F1 value of 83.08%. The curve of DCA revealed that MRF-Net consistently outperformed the other models, yielding higher net benefits across various decision thresholds.ConclusionThe utilization of MRF-Net enables more precise discrimination between benign and malignant thyroid follicular tumors utilizing preoperative US.

PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions

Due to its insensitivity to light intensity and the capability to capture multidimensional information, polarimetric imaging technology has been proven to have advantages over traditional intensity-based imaging techniques for object detection tasks in adverse environmental conditions, particularly in road traffic scenarios. Recently, with the rapid development of artificial intelligence technology, deep learning (DL)-powered object detection techniques can further enhance recognition accuracy and algorithm robustness. This improvement is made possible by the ability of DL technology to leverage large datasets and extract deeper levels of target-specific features. However, constructing large-scale polarimetric datasets poses challenges as obtaining polarimetric information requires multiple captures of intensity images. In other words, the workload is several times higher compared to traditional imaging techniques. To address the current scarcity of polarimetric datasets and evaluate the practical performance of various algorithms on polarimetric datasets, this paper proposes a Polarimetric Object Detection Benchmark (PODB) dataset. The PODB provides an integrated quality evaluation framework for DL-based object detection algorithms in complex road scenes by incorporating polarimetric imaging. Besides, we conducted extensive object detection experiments using the PODB, which allowed for a comprehensive validation and performance evaluation of effective benchmark algorithms. Furthermore, a physics-based multi-scale image fusion cascaded object detection neural network model is proposed. By combining the multidimensional information provided by polarized images with an adaptive learning multi-decision object detection neural network model, the recognition accuracy of complex road scenes in adverse weather conditions has been improved by approximately 10%. Additionally, we anticipate that PODB will serve as an effective platform for evaluating and comparing the performance of object detection algorithms, as well as providing researchers with a baseline for future studies in developing new DL-based methods.

Abstract 76: Correlated multi-scale 3D optical microscopy of tumor tissues

Abstract Three-dimensional (3D) optical microscopy in combination with advanced tissue clearing methods permits the interrogation of intact large-sized tumor tissues. There are many optical microscopy methods (e.g. light-sheet and confocal microscopy) offering 3D tumor images at varying levels of spatial resolution (e.g. organ, tissue, cell, and molecule level). However, it is a challenge to correlatively integrate various resolution 3D images obtained by different optical microscopy of tumor tissue. In this project, we developed a correlated multi-scale 3D optical microscopy method that enables the acquisition of macroscopic to microscopic spatial information from a single tumor tissue in 3D. Firstly, we used light sheet microscopy to image a whole large-sized, cleared tumor tissue and analyzed the results to identify regions of interests (ROIs). After defining ROIs in the 3D whole tumor image, we added a UV-activatable visible dye, spiropyran, in the agarose gel surrounding the cleared tumor and exposed the sample to a UV light sheet horizontally at the height (z-axis) of the tumor where the ROIs present. The activated dye showed ‘purple’ colored lines in the agarose gel and we physically marked the gel along the visible colored lines. We further sectioned the tumor at the ROI positions using a vibratome after reversing tissue clearing process. After immunofluorescence staining and aqueous-based tissue clearing, confocal microscopy allowed the localization of various cell types in the ROIs of tumor macrosections. To validate the method for multi-scale evaluation of cancer immunotherapy, we tested it with control and DMXAA-treated mouse mammary tumor tissues. We successfully acquired the 3D images of whole tumors by capturing autofluorescence signals with a 633 nm excitation laser and its matched emission filter. Based on the autofluorescence tumor images, we defined two ROIs for each control and treated tumor and performed optical marking and physical sectioning of the tumors as described above. Next, we stained the macrosections (400 µm thick) with DAPI, CK8-DL488, CD45-DL550, and ER-TR7-DL680 to visualize cancer, immune, and stromal cells in the ROIs at cellular resolution. We quantitatively analyzed the correlated multi-scale 3D image data for assessment of the effects of DMXAA treatment on the tumor microenvironment including eradiation of cancer cells, immune infiltration, and remodeling of tumor stroma. In summary, this new microscopy method will provide comprehensive spatial information of tumor tissues and benefit a broad cancer research field such as the discovery of new tumor biomarkers and the development of effective cancer therapies. Citation Format: Jingtian Zheng, Steve Seung-Young Lee. Correlated multi-scale 3D optical microscopy of tumor tissues [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 76.

Iterative nanoparticle bioengineering enabled by x-ray fluorescence imaging.

Nanoparticles (NPs) are currently developed for drug delivery and molecular imaging. However, they often get intercepted before reaching their target, leading to low targeting efficacy and signal-to-noise ratio. They tend to accumulate in organs like lungs, liver, kidneys, and spleen. The remedy is to iteratively engineer NP surface properties and administration strategies, presently a time-consuming process that includes organ dissection at different time points. To improve this, we propose a rapid iterative approach using whole-animal x-ray fluorescence (XRF) imaging to systematically evaluate NP distribution in vivo. We applied this method to molybdenum-based NPs and clodronate liposomes for tumor targeting with transient macrophage depletion, leading to reduced accumulations in lungs and liver and eventual tumor detection. XRF computed tomography (XFCT) provided 3D insight into NP distribution within the tumor. We validated the results using a multiscale imaging approach with dye-doped NPs and gene expression analysis for nanotoxicological profiling. XRF imaging holds potential for advancing therapeutics and diagnostics in preclinical pharmacokinetic studies.

Micro LED defect detection with self-attention mechanism-based neural network

We propose a method utilizing a YOLO detector for the precise localization of defective chips and the identification of defect types within multi-scale multi-target images. To address the challenge of optimizing training costs and enhancing model generalization, we introduce an end-to-end deep neural network, CM-YOLOv5, specifically designed for chip detection. We incorporate a novel bottleneck layer, MA-CSP, in conjunction with Multi-Head Self-Attention mechanism (MHSA). Additionally, we propose a class-balanced loss function (CB-BCE Loss) to tackle the issue of uneven distribution of defective samples in the Micro LED dataset. To further enhance convergence speed and detection precision, we introduce the SIoU Loss combined with Meta-AconC. Our experimental results, conducted on the Micro LED dataset, demonstrate notable improvements with CM-YOLOv5 over the basic YOLOv5 algorithm. Specifically, CM-YOLOv5 exhibits a 3.8 % increase in mean average precision and a 3.7 % improvement in precision, surpassing current mainstream object detection algorithms, including YOLOR, YOLOX, and YOLOv6, etc., in terms of general evaluation metrics. Finally, upon deploying our proposed algorithm on the edge device NVIDIA Jetson Xavier NX, CM-YOLOv5 demonstrates commendable speed and detection performance in embedded scenarios.

Deep learning-based spatial downscaling and its application for tropical cyclone detection in the western North Pacific

Resolution of global climate models (GCMs) significantly influences their capacity to simulate extreme weather such as tropical cyclones (TCs). However, improving the GCM resolution is computationally expensive and time-consuming, making it challenging for many research organizations worldwide. Here, we develop a downscaling model, MSG-SE-GAN, based on the Generative Adversarial Networks (GAN) together with Multiscale Gradient (MSG) technique and a Squeeze-and-Excitation (SE) Net, to achieve 10-folded downscaling. GANs consist of a generator and a discriminator network that are trained adversarially, and are often used for generating new data that resembles a given dataset. MSG enables generation and discrimination of multi-scale images within a single model. Inclusion of an attention layer of SE captures better underlying spatial structure while preserving accuracy. The MSG-SE-GAN is stable and fast converging. It outperforms traditional bilinear interpolation and other deep-learning methods such as Super-Resolution Convolutional Neural Networks (SRCNN) and MSG-GAN in downscaling low-resolution meteorological data in assessment metrics and power spectral density. The MSG-SE-GAN has been used to downscale the TC-related variables in the western North Pacific in the low-resolution GCMs of HadGEM3-GC31 and EC-Earth3P, respectively. The downscaled data show highly similar TC activities to the direct outputs of the high-resolution HadGEM3-GC31 and EC-Earth3P, respectively. These results not only suggest the validity of the MSG-SE-GAN but also indicate its possible portability among low-resolution GCMs.

Pronounced cortical porosity and sex-specific patterns of increased bone and osteocyte lacunar mineralization characterize the human distal fibula with aging

The high occurrence of distal fibula fractures among older women suggests a potential link to impaired bone health. Here we used a multiscale imaging approach to investigate the microarchitecture, mineralization, and biomechanics of the human distal fibula in relation to age and sex. Micro-computed tomography was performed to analyze the local volumetric bone mineral density and various microarchitectural parameters of the trabecular and the cortical compartment. Bone mineral density distribution and osteocyte lacunar parameters were quantified using quantitative backscattered electron imaging in periosteal, endocortical, and trabecular regions. Additionally, cortical hardness and Young's modulus were assessed by nanoindentation. While cortical porosity strongly increased with age independent of sex, trabecular microarchitecture remained stable. Notably, nearly half of the specimens showed non-bony hypermineralized tissue located at the periosteum, similar to that previously detected in the femoral neck, with no consistent association with advanced age. Independent of this finding, cortical and trabecular mineralization, i.e., mean calcium content, as well as endocortical tissue hardness increased with age in males but not females. Importantly, we also observed mineralized osteocyte lacunae that increased with age specifically in females. In conclusion, our results indicate that skeletal aging of the distal fibula is signified not only by pronounced cortical porosity but also by an increase in mineralized osteocyte lacunae in females. These findings may provide an explanation for the increased occurrence of ankle fractures in older women.

Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features.

Casting defects in turbine blades can significantly reduce an aero-engine's service life and cause secondary damage to the blades when exposed to harsh environments. Therefore, casting defect detection plays a crucial role in enhancing aircraft performance. Existing defect detection methods face challenges in effectively detecting multi-scale defects and handling imbalanced datasets, leading to unsatisfactory defect detection results. In this work, a novel blade defect detection method is proposed. This method is based on a detection transformer with a multi-scale fusion attention mechanism, considering comprehensive features. Firstly, a novel joint data augmentation (JDA) method is constructed to alleviate the imbalanced dataset issue by effectively increasing the number of sample data. Then, an attention-based channel-adaptive weighting (ACAW) feature enhancement module is established to fully apply complementary information among different feature channels, and further refine feature representations. Consequently, a multi-scale feature fusion (MFF) module is proposed to integrate high-dimensional semantic information and low-level representation features, enhancing multi-scale defect detection precision. Moreover, R-Focal loss is developed in an MFF attention-based DEtection TRansformer (DETR) to further solve the issue of imbalanced datasets and accelerate model convergence using the random hyper-parameters search strategy. An aero-engine turbine blade defect X-ray (ATBDX) image dataset is applied to validate the proposed method. The comparative results demonstrate that this proposed method can effectively integrate multi-scale image features and enhance multi-scale defect detection precision.

MSA-UNet: A Multiscale Lightweight U-Net Lung CT Image Segmentation Algorithm Under Attention Mechanism

Automatic and precise segmentation of lung images can assist doctors in locating and diagnosing lung lesions. However, current traditional lung CT image lesion segmentation algorithms suffer from the problem of low segmentation accuracy, while deep learning-based segmentation algorithms struggle to strike a better balance between lightweight and high accuracy. In response to this issue, a multi-scale and lightweight U-Net lung image segmentation algorithm with an attention mechanism is proposed. This algorithm introduces CA convolution after the convolution in the encoding stage to extract channel relationships and positional information from the feature maps. Furthermore, the RFB module is employed to extract features from different perspectives. Lastly, upward residual connections are introduced between the RFB modules in the encoder and decoder to enhance inter-network information interaction. Experiments conducted on the LUNA (lung nodule analysis) dataset and the COVID-QU-Ex dataset for COVID-19 pneumonia demonstrate that the proposed MSA-UNet algorithm achieves the best results in terms of Precision and Dice metrics. It outperforms mainstream models such as U-Net++ and DeeplabV3+ in terms of segmentation effectiveness and segmentation generality. The model has a floating-point operation count (FLOPs) of 18.15 G, a network parameter counts of 8.83×106, and achieves a Precision of 99.37%. The algorithm achieves a good balance between computational efficiency, model size, and segmentation accuracy.

Brain MRI and CT Image Fusion Using Multiscale Local Extrema and Image Statistics

In medical applications such as radiotherapy and guided-image surgery, data fusion for diagnostic imaging has emerged as a critical issue. Because the objective of medical image fusion is to improve patient diagnosis accuracy, the fused image is created by preserving the source images' prominent details and features. It has been demonstrated that the Multi-Level Local Extrema representation has numerous advantages over traditional image modeling approaches. We propose an innovative MLE-based fusion method for multimodal medical images in this paper. In the MLE schema, the proposed algorithm decomposes source images into coarse and detailed layers, then fuses the source images using weights calculated from these detail images using image statistics. We visually and quantitatively compared the efficacy of the suggested approach to that of existing methods using five different types of medical images from various sources. The experimental results showed that the proposed scheme outperforms other current typical schemes in terms of both qualitative image quality and objective evaluation.

Application of Discrete and Fast Fourier Transforms to Increase the Speed of Multiscale Image Analysis

The paper compares the accuracy of reconstruction using different wavelets, and the authors also use fast and discrete Fourier transforms together to calculate the forward and inverse continuous wavelet transform in the frequency domain. Due to the use of calculations in the frequency domain, it becomes possible to perform decomposition, reconstruction, image filtering, and other transformations with high performance and precision. For multiscale signal analysis, a wavelet with a rectangular amplitude-frequency response has been constructed, which allows for an increase in the accuracy of decomposition and reconstruction compared to the Mallat algorithm presented in Matlab computer mathematics. At the same time, the time of multiscale analysis is reduced several times compared to the Mallat algorithm.

Multiscale permutation entropy gray image coding method and its application in bearing fault diagnosis

Bearing fault diagnosis is of great significance to the normal operation of machinery, and its performance and life span directly affect the operational efficiency and safety of the whole equipment. For existing image coding methods which detecting the bearing fault with a large number of training samples and complex neural networks to achieve the desired detection performance, the Multiscale Permutation Entropy Gray Image Coding (MPEGIC) method is proposed. In order to fully extract the feature information of the time series signal, this paper uses the Multiscale Permutation Entropy (MPE) method to construct a new image coding method by calculating the alignment information of the time series to reflect the complexity and randomness of the time series at different scales, and dividing the obtained feature matrix and mapping it to the gray-scale image domain. And it is experimentally verified by Case Western Reserve University (CWRU) bearing dataset and self-made rotor experimental platform bearing dataset. The results show that the method in this paper effectively reduces the number of training samples and the number of model parameters, and maintains a better detection performance even in a strong noise background.

Multiscale transport and 4D time-lapse imaging in precision-cut liver slices (PCLS).

Monitoring cellular processes across different levels of complexity, from the cellular to the tissue scale, is important for understanding tissue structure and function. However, it is challenging to monitor and estimate these structural and dynamic interactions within three-dimensional (3D) tissue models. The aim of this study was to design a method for imaging, tracking, and quantifying 3D changes in cell morphology (shape and size) within liver tissue, specifically a precision-cut liver slice (PCLS). A PCLS is a 3D model of the liver that allows the study of the structure and function of liver cells in their native microenvironment. Here, we present a method for imaging liver tissue during anisosmotic exposure in a multispectral four-dimensional manner. Three metrics of tissue morphology were measured to quantify the effects of osmotic stress on liver tissue. We estimated the changes in the volume of whole precision cut liver slices, quantified the changes in nuclei position, and calculated the changes in volumetric responses of tissue-embedded cells. During equilibration with cell-membrane-permeating and non-permeating solutes, the whole tissue experiences shrinkage and expansion. As nuclei showed a change in position and directional displacement under osmotic stress, we demonstrate that nuclei could be used as a probe to measure local osmotic and mechanical stress. Moreover, we demonstrate that cells change their volume within tissue slices as a result of osmotic perturbation and that this change in volume is dependent on the position of the cell within the tissue and the duration of the exposure. The results of this study have implications for a better understanding of multiscale transport, mechanobiology, and triggered biological responses within complex biological structures.

Fractal theory based identification model for surface crack of building structures

The existing building structures are mainly composed of concrete and masonry structures. This paper proposes a Fractal Theory-based Method (FTM) designed to efficiently detect surface cracks in both concrete and masonry building structures, addressing limitations in existing crack recognition techniques, such as weak adaptability to complex building surfaces and requiring a large amount of computational and human resource. A novel Soft Box-Counting (SBC) algorithm is proposed to calculate texture roughness information from multi-channel and multi-scale crack images, effectively mitigating the influence of non-feature information on crack identification results. The SBC algorithm is integrated into neural networks through the fractal embedding mechanism, enhancing feature analysis through visualization experiments. The resulting FTM model integrates texture roughness information from crack images and employs fractal theory to accurately classify crack regions while minimizing the similarity between crack and non-crack regions. In comparison to existing models, FTM demonstrates superior identification performance at the same computational level on benchmark datasets for surface cracks in both concrete and masonry building structures. The FTM model exhibits enhanced identification universality and higher resource utilization efficiency.

Multiscale Mineralization in the Leopard Gecko Eggshell

AbstractReptilian (non‐avian) eggshell biomineralization is markedly different from avian eggshells. Despite discontinuous/variable mineralization, the reptilian eggshell (like in birds) is responsible for protective and developmental functions of the egg as part of a highly successful reproduction strategy. Using multiscale imaging and characterization methods including X‐ray and electron microscopy/tomography, a 3D overview of eggshell ultrastructure in the gekkotan Eublepharis macularius – the common leopard gecko is provided. Eggshell mineral is shown to be sensitive to aqueous preparations, where cryogenic methods are essential for accurate mineral and organic preservation. Interwoven with the mineral are underlying organic fibers involved in the formation of complex hierarchical order in the eggshell, including nucleation and growth of mineral. The calcitic mineral phase of the eggshell takes on three microstructural motifs at the shell surface: nodular scutes (≈40 µm), intermittent blunt or star‐shaped mineral rosettes (≈1 mm), and smaller mineral corollas (≈10 µm). Individual scutes have two hierarchical mineral structures – mineral nanospheres (≈500 nm) and mineral nanodomains (≈40 nm). Diverse and variable biomineralization features of reptilian eggshells likely reflect the importance of differences in ecology and physiology on egg formation, survival, and eggshell mechanics, and are likely related to hydration sensitivity, structural organic‐inorganic interactions, and mineral polymorphism.

Protein aggregates containing wild-type and mutant NOTCH3 are major drivers of arterial pathology in CADASIL.

Loss of arterial smooth muscle cells (SMCs) and abnormal accumulation of the extracellular domain of the NOTCH3 receptor (Notch3ECD) are the 2 core features of CADASIL, a common cerebral small vessel disease caused by highly stereotyped dominant mutations in NOTCH3. Yet the relationship between NOTCH3 receptor activity, Notch3ECD accumulation, and arterial SMC loss has remained elusive, hampering the development of disease-modifying therapies. Using dedicated histopathological and multiscale imaging modalities, we could detect and quantify previously undetectable CADASIL-driven arterial SMC loss in the CNS of mice expressing the archetypal Arg169Cys mutation. We found that arterial pathology was more severe and Notch3ECD accumulation greater in transgenic mice overexpressing the mutation on a wild-type Notch3 background (TgNotch3R169C) than in knockin Notch3R170C/R170C mice expressing this mutation without a wild-type Notch3 copy. Notably, expression of Notch3-regulated genes was essentially unchanged in TgNotch3R169C arteries. We further showed that wild-type Notch3ECD coaggregated with mutant Notch3ECD and that elimination of 1 copy of wild-type Notch3 in TgNotch3R169C was sufficient to attenuate Notch3ECD accumulation and arterial pathology. These findings suggest that Notch3ECD accumulation, involving mutant and wild-type NOTCH3, is a major driver of arterial SMC loss in CADASIL, paving the way for NOTCH3-lowering therapeutic strategies.

A multiscale carotid plaque detection method based on two-stage analysis

To develop a method for accurate identification of multiscale carotid plaques in ultrasound images. We proposed a two-stage carotid plaque detection method based on deep convolutional neural network (SM-YOLO).A series of algorithms such as median filtering, histogram equalization, and Gamma transformation were used to preprocess the dataset to improve image quality. In the first stage of the model construction, a candidate plaque set was built based on the YOLOX_l target detection network, using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes. In the second stage, the Histogram of Oriented Gradient (HOG) features and Local Binary Pattern (LBP) features were extracted and fused, and a Support Vector Machine (SVM) classifier was used to screen the candidate plaque set to obtain the final detection results. This model was compared quantitatively and visually with several target detection models (YOLOX_l, SSD, EfficientDet, YOLOV5_l, Faster R-CNN). SM-YOLO achieved a recall of 89.44%, an accuracy of 90.96%, a F1-Score of 90.19%, and an AP of 92.70% on the test set, outperforming other models in all performance indicators and visual effects. The constructed model had a much shorter detection time than the Faster R-CNN model (only one third of that of the latter), thus meeting the requirements of real-time detection. The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

Automatic mapping of 500 m daily open water body fraction in the American continent using GOES-16 ABI imagery

Timely and large-area monitoring of terrestrial water bodies using remote sensing data is essential to protect water resource security for humans and ecosystems. Although efforts have been made to monitor inter-monthly water bodies at the regional, continental and global scales, surface open water bodies may experience rapid changes within a short duration. At the same time, the data gaps caused by the long revisit frequencies of satellite sensor imaging systems and the extremely cloudy and rainy weather in certain areas mean that a suitable operational method for recording such rapid changes over large areas does not yet exist. The recently launched operational geostationary satellite sensor GOES-16 ABI can provide multi-scale optical images every 10 min in the Americas, and it has great potential to provide a new solution for timely open surface water monitoring. In this research, a framework based on a multi-scale non-linear mixture model (NLMM) was proposed for the automatic estimation of 500 m daily open water body fraction maps across the full extent of the American continent from GOES-16 ABI imagery. Specifically, an exterior spectral library was created firstly from many pairs of training GOES-16 ABI images and 500 m water body fraction maps derived from Landsat images, and an inherited interior pure spectral library was then derived from a pair of the testing GOES-16 ABI image and the corresponding pure water and non-water (i.e., vegetation and soil/rock substrate) fractions extracted from the monthly water recurrence dataset. Furthermore, a synthetic interior mixed spectral library was built finally based on the linear and non-linear mixtures of randomly selected pure endmembers of water and non-water (i.e., vegetation and soil/rock substrate) in the testing image. All the exterior and interior pure and synthetic mixed spectral libraries were employed jointly in the NLMM machine learning method for estimating daily water body fractions with GOES-16 ABI images. Experiments show that the integration of all three different spectral libraries produced 500 m open water body fraction maps with the greatest accuracies. Compared to traditional linear spectral unmixing and a water index thresholding method, the proposed method produced more accurate results both quantitatively and visually. Moreover, the proposed method can produce time-series daily 500 m open water body fraction maps with minimal cloud coverage for the full extent of the Americas by combining dense GOES-16 ABI images at half-hour intervals, opening up great possibilities for near real-time rapid open water body changes monitoring, such as flooding and drought, over large areas, even with a high frequency of cloud cover.