Search Results (261)

Weed identification and quantification are processes that are usually manual, subjective, and error-prone. Weeds compete with crops for nutrients, minerals, physical space, sunlight, and water. Thus, weed identification is a crucial component of precision agriculture for autonomous removal and site-specific treatments, efficient weed control, and sustainability. Convolutional Neural Networks (CNNs) are very common in weed identification. This work implemented CNN models for semantic segmentation based on the U-Net architecture for automatically segmenting and quantifying weeds in potato crops using RGB images acquired by a drone at 9–10 m height, flying at 1 m/s. Remote sensing images are affected by factors that degrade image quality and the model’s accuracy. Five U-Net variants were evaluated: the original U-Net, Residual U-Net, Double U-Net, Modified U-Net, and AU-Net. The models were trained using the TensorFlow/Keras frameworks on Google Colab Pro+, following the Knowledge Discovery in Databases (KDD) methodology for image analysis. Each model was trained using a diverse custom dataset in uncontrolled environments, considering six classes: background, Broadleaf dock (Rumex obtusifolius), Dandelion (Taraxacum officinale), Kikuyu grass (Cenchrus clandestinum), other weed species, and the crop potato (Solanum tuberosum L.). The models’ segmentation was widely assessed using Mean Dice Coefficient, Mean IoU, and Dice Loss metrics. The results showed that the Residual U-Net model performed the best in multi-class segmentation, achieving a Mean IoU of 0.8021, a performance comparable to or superior to that reported by other authors. Additionally, a Student’s t-test was applied to complement the data analysis, suggesting that the model is reliable for weed quantification. Full article

This study introduces a novel approach for optimizing models that reconstruct high-quality full-dose bone scintigraphy images from their 40% low-dose counterparts using optimized attention-based U-Net architectures. We utilized Genetic and Epigenetic Algorithms (epiGA) hyperparameter optimization of two distinct models: a standard Attention U-Net and an Attention U-Net modified with ResNet blocks. Models were trained using a hybrid Mean Squared Error and Structural Similarity (MSE/SSIM) loss function. Obtained results demonstrated superior performance, achieving an average SSIM of 0.9197 and an average Peak Signal-to-Noise ratio (PSNR) of 34.1516 dB, significantly surpassing the baseline low-dose image quality, by gaining ΔSSIM = 0.0333 and ΔPSNR = 3.0729 dB, due to hyperparameter optimization. Comparative benchmarks against Bayesian optimization revealed that epiGA offers superior search efficiency—exploring twice the architecture space in comparable wall-clock time—while consistently identifying more compact, hardware-efficient solutions. These results highlight the effectiveness of integrating epigenetic mechanisms for robust, scalable hyperparameter tuning in medical image reconstruction. Full article

The latest advances in remote sensing play a central role in providing Earth observation (EO) data for numerous applications in the scope of reaching environmentally sustainable goals. However, over tropical rainforests, optical imaging is often hindered by extensive cloud coverage, which means that analysis-ready images are mostly restricted to the dry season. In this study, we propose combining radar features extracted from short time series of Sentinel-1 Interferometric Wide Swath (IW) data with a deep learning-based classification scheme to continuously monitor the state of forests. The proposed methodology is based on the joint use of SAR backscatter and interferometric coherences at different temporal baselines to perform pixel-wise classification of land cover classes of interest. However, we show that for a sequence of Sentinel-1 time series, different land cover classes exhibit particular seasonal-dependent variations. Another challenge in performing short-term predictions stems from the fact that ground truths are usually available only on a yearly basis. To address these challenges, we propose a seasonal sampling of the training data, masked by potential deforestation, along with a classification based on a modified U-Net model. The classification results show that overall accuracies above 90% can be achieved throughout the whole year with the proposed method, emerging as a potential tool for mapping rainforests with unprecedented temporal resolution. Full article

We report a deep learning-assisted quartz-enhanced photoacoustic spectroscopy (QEPAS) sensor for trace water vapor detection in air. A 1392 nm butterfly-packaged DFB laser is wavelength-modulated at f₀/2, and the QEPAS signal is retrieved by second-harmonic (2f) lock-in demodulation using a commercial quartz tuning fork gas cell. After optimizing the modulation depth to 400 mV, a 1D U-Net denoising network trained with pseudo-clean supervision is applied to the measured 2f traces, yielding an SNR improvement of 2.05× (3.11 dB). Allan deviation analysis indicates a minimum detection limit (MDL) of ~2.21 ppm at an optimum averaging time of ~619 s, corresponding to an ~2.1× improvement compared with the raw output. These results demonstrate that neural-network-based post-processing can improve QEPAS water vapor sensing performance without modifying the optical hardware. Full article

Abdominal Aortic Aneurysm (AAA) remains a significant public health challenge, with an 82.1% increase in related fatalities from 1990 to 2019. In the United States alone, AAA complications resulted in an estimated 13,640 deaths between 2018 and 2021. In clinical practice, computed tomography angiography (CTA) is the primary imaging modality for monitoring and pre-surgical planning of AAA patients. CTA provides high-resolution vascular imaging, enabling detailed assessments of aneurysm morphology and informing critical clinical decisions. However, manual segmentation of CTA images is labor-intensive and time consuming, underscoring the need for automated segmentation algorithms, particularly when feature extraction from clinical images can inform treatment decisions. We propose a framework to automatically segment the outer wall of the abdominal aorta from CTA images and estimate AAA wall stress. Our approach employs a patch-based dilated modified U-Net model to accurately delineate the outer wall boundary of AAAs and Nonlinear Elastic Membrane Analysis (NEMA) to estimate their wall stress. We further integrate Non-Uniform Rational B-Splines (NURBS) to refine the segmentation. During prediction, our deep learning architecture requires $17\pm 0.02$ milliseconds per frame to generate the final segmented output. The latter is used to provide critical insight into the biomechanical state of stress of an AAA. This modeling strategy merges advanced deep learning architecture, the precision of NURBS, and the advantages of NEMA to deliver a robust and efficient method for computational analysis of AAAs. Full article

The sustainable management of water resources and the development of climate-resilient infrastructure depend on the precise identification of water bodies in satellite imagery. This paper presents a novel deep learning architecture that integrates a convolutional block attention module (CBAM) into a modified EfficientNet–UNet backbone. This integration allows the model to prioritize informative features and spatial areas. The model robustness is ensured through a rigorous training regimen featuring five-fold cross-validation, dynamic test-time augmentation, and optimization with the Lovász loss function. The final model achieved the following values on the independent test set: precision = 90.67%, sensitivity = 86.96%, specificity = 96.18%, accuracy = 93.42%, Dice score = 88.78%, and IoU = 79.82%. These results demonstrate improvement over conventional segmentation pipelines, highlighting the effectiveness of attention mechanisms in extracting complex water-body patterns and boundaries. The key contributions of this paper include the following: (i) adaptation of CBAM within a UNet-style architecture tailored for remote sensing water-body extraction; (ii) a rigorous ablation study detailing the incremental impact of decoder complexity, attention integration, and loss function choice; and (iii) validation of a high-fidelity, computationally efficient model ready for deployment in large-scale water-resource and ecosystem-monitoring systems. Our findings show that attention-guided segmentation networks provide a robust pathway toward high-fidelity and sustainable water-body mapping. Full article

Cell nucleus segmentation in microscopy images is an initial step in the quantitative analysis of imaging data, which is crucial for diverse biological and biomedical applications. While traditional machine learning methodologies have demonstrated limitations, recent advances in U-Net models have yielded promising improvements. However, it is noteworthy that these models perform well on balanced datasets, where the ratio of background to foreground pixels is equal. Within the realm of microscopy image segmentation, state-of-the-art models often encounter challenges in accurately predicting small foreground entities such as nuclei. Moreover, the majority of these models exhibit large parameter sizes, predisposing them to overfitting issues. To overcome these challenges, this study introduces a novel architecture, called mA-UNet, designed to excel in predicting small foreground elements. Additionally, a data preprocessing strategy inspired by road segmentation approaches is employed to address dataset imbalance issues. The experimental results show that the MIoU score attained by the mA-UNet model stands at $95.50\%$, surpassing the nearest competitor, UNet++, on the 2018 Data Science Bowl dataset. Ultimately, our proposed methodology surpasses all other state-of-the-art models in terms of both quantitative and qualitative evaluations. The mA-UNet model is also implemented in VHDL on the Zynq UltraScale+ FPGA, demonstrating its ability to perform complex computations with minimal hardware resources, as well as its efficiency and scalability on advanced FPGA platforms. Full article

Natural disasters occur worldwide and cause significant financial and human losses. Wildfires are among the most important natural disasters, occurring more frequently in recent years due to global warming. Fast and accurate post-disaster damage detection could play an essential role in swift rescue planning and operations. Remote sensing (RS) data is an important source for tracking damage detection. Deep learning (DL) methods, as efficient tools, can extract valuable information from RS data to generate an accurate damage map for future operations. The present study proposes an encoder–decoder architecture composed of pre-trained Yolov11 blocks as the encoder path and Modified UNet (MUNet) blocks as the decoder path. The proposed network includes three main steps: (1) pre-processing, (2) network training, (3) prediction multilabel damage map and accuracy evaluation. To evaluate the network’s performance, the US and Canada datasets were considered. The datasets are satellite images of the 2023 wildfires in the US and Canada. The proposed method reaches the Overall Accuracy (OA) of 97.36, 97.47, and Kappa Coefficient (KC) of 0.96, 0.87 for the US and Canada 2023 wildfire datasets, respectively. Regarding the high OA and KC, an accurate final burnt map can be generated to assist in rescue and recovery efforts after the wildfire. The proposed YOLOv11–MUNet framework introduces an efficient and accurate post-event-only approach for wildfire damage detection. By overcoming the dependency on pre-event imagery and reducing model complexity, this method enhances the applicability of DL in rapid post-disaster assessment and management. Full article

The deployment of wireless seismic nodal systems necessitates the efficient identification of optimal locations for sensor installation, considering factors such as ground stability and the absence of interference. Semantic segmentation of satellite imagery has advanced significantly, and its application to this specific task remains unexplored. This work presents a baseline empirical evaluation of the U-Net architecture for the semantic segmentation of surfaces applicable for seismic sensor installation. We utilize a novel dataset of Sentinel-2 multispectral images, specifically labeled for this purpose. The study investigates the impact of pretrained encoders (EfficientNetB2, Cross-Stage Partial Darknet53—CSPDarknet53, and Multi-Axis Vision Transformer—MAxViT), different combinations of Sentinel-2 spectral bands (Red, Green, Blue (RGB), RGB+Near Infrared (NIR), 10-bands with 10 and 20 m/pix spatial resolution, full 13-band), and a technique for improving small object segmentation by modifying the input convolutional layer stride. Experimental results demonstrate that the CSPDarknet53 encoder generally outperforms the others (IoU = 0.534, Precision = 0.716, Recall = 0.635). The combination of RGB and Near-Infrared bands (10 m/pixel resolution) yielded the most robust performance across most configurations. Reducing the input stride from 2 to 1 proved beneficial for segmenting small linear objects like roads. The findings establish a baseline for this novel task and provide practical insights for optimizing deep learning models in the context of automated seismic nodal network installation planning. Full article

This paper presents ACTD-Net (Attention-Convolutional Transformer Denoising Network), a novel hybrid deep learning approach for speckle noise reduction from differential synthetic aperture radar (SAR) interferometric phase maps. Differential interferometric SAR (DInSAR) is a powerful technique for detecting and quantifying surface deformations, but the obtained phase maps are corrupted by speckle noise, topographic contributions, and atmospheric artifacts. Effective speckle denoising is crucial for accurate extraction of the desired deformation information. ACTD-Net combines the strengths of convolutional neural networks (CNNs) and vision transformers (ViTs) in a two-stage architecture. First, a modified U-Net model with residual connections performs initial despeckling of the input DInSAR phase map. Then, the denoised phase map is fed into a Swin Transformer adapted with a masked self-attention mechanism, which further refines the denoising while preserving fine details and discontinuities related to surface deformations. Experimental results on simulated and real DInSAR data, including from the September 2023 Morocco earthquake region, demonstrate the effectiveness of ACTD-Net, outperforming traditional techniques and current deep learning methods in terms of quantitative metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and edge preservation index (EPI). The comprehensive evaluation shows that ACTD-Net achieves up to 33.55 dB PSNR, 0.96 SSIM, and 0.94 EPI on simulated data, and 33.62 ± 2.75 dB PSNR on 388 real Morocco earthquake patches, with significant improvements in preserving phase discontinuities and reducing unwrapping errors by approximately 62% on real earthquake data. Full article

The mechanical and durability performance of cementitious materials is fundamentally governed by the symmetry, anisotropy, and hierarchical organization of their microstructures. Conventional experimental characterization—based on imaging, spectroscopy, and physical testing—often struggles to capture these multiscale spatial patterns and their nonlinear correlations with macroscopic performance. Recent advances in machine learning (ML) provide unprecedented opportunities to interpret structural symmetry and anisotropy through data-driven analytics, computer vision, and physics-informed models. Furthermore, we summarize cases where symmetry-informed descriptors improve performance prediction accuracy in fiber- and nano-modified composites, demonstrating that ML-based symmetry analysis can substantially complement the limitations of conventional experimental-based characterization. We confirm that image-based models such as CNN and U-Net quantify the directionality and connectivity of pores and cracks, and that physically informative neural networks (PINNs) and heterogeneous data-based models enhance physical consistency and computational efficiency compared to conventional FEM and CFD. Finally, we present the conceptual and methodological foundation for developing AI-based microstructural symmetry analysis, aiming to go beyond simple prediction and establish a conceptual foundation for AI-driven cement design based on microstructure–performance causality. Full article

Objectives: This study utilized artificial intelligence (AI)–based radiomics analysis of computed tomography (CT) images using a modified U–Net for lung nodule segmentation and convolutional neural network based on VGG–16 to predict lymphovascular invasion (LVI) in stage 0–I lung adenocarcinoma. Additionally, the study investigated whether combining radiomics data with serum microRNA (miR)–30d level as a potential biomarker could enhance predictive performance. Methods: A total of 1265 patients who underwent complete resection between 2008 and 2018 were included. AI–based CT analysis was performed, and logistic regression was applied to predict LVI using 35 imaging features. A risk score (RS) generated from 840 patients in the derivation cohort was used to identify a high–risk group, with validation performed using 425 patients. Additionally, 47 cases with extracellular vesicle (EV)–derived miR–30d level data were analyzed to evaluate the value of the integrated approach. Results: Among all the patients, 467 patients (36.9%) were LVI–positive, and LVI was independently associated with poorer overall survival. The receiver operating characteristic curve for LVI based on the RS yielded an area under the curve of 0.899. For LVI prediction, the sensitivity, specificity, and accuracy were 84.8%, 83.7%, and 83.9%, respectively, in the derivation group, and 82.3%, 79.4%, and 80.5%, respectively, in the validation group. The integrated approach with miR–30d enhanced the predictability of LVI, achieving a sensitivity of 93.3%, specificity of 70.5%, and accuracy of 85.1%. Conclusions: AI–based radiomics demonstrated high effectiveness for predicting LVI, with RSs showing broad clinical applications. The addition of EV–derived miR–30d modestly improved predictability. Full article

The precise identification of photovoltaic power stations is essential for advancing the assessment of energy infrastructure and for the efficient management of land resources. To address the need for spatially explicit data on photovoltaic (PV) development in arid and semi-arid regions amid green energy transitions, particularly in the context of identification challenges induced by the widespread distribution of bare ground, this study optimized a remote sensing-based identification method integrating Principal Component Analysis (PCA), automated sampling via Google Earth Engine (GEE), and deep learning models, and applied it to Qinghai Province, one of China’s largest PV regions. The results showed that HRNetv2 (validation Dice = 0.9463) outperformed UNet (0.9328), Attention UNet (0.9399), and HRNet + OCR (0.9184) in small-sample (1871 training samples) PV segmentation; the PV installed area during 2020–2024 accounted for 63.5% of the total pre-2024 area (~607 km²), exceeding the cumulative area before 2019, with projects predominantly distributed in areas with elevation less than 2500 m and slope less than 2°; bare land dominated PV land use (88.7%), followed by grassland (6.9%) and shrubland (3.9%), and PV construction contributed to desert greening by modifying microclimates. The study concludes that its optimized method effectively supports PV spatial identification, and the revealed PV distribution and land use patterns provide scientific guidance for synergistic PV development and ecological conservation in arid regions, while acknowledging limitations in generalizability to other regions due to Qinghai-specific data, suggesting future algorithm refinement and expanded research scales. Full article

Reliable land surface temperature (LST) data are required for monitoring climate variability, hydrological processes, and land–atmosphere interactions. Yet existing satellite-derived LST products, such as those from thermal infrared (TIR) sensors, are limited by gaps due to clouds, while passive microwave (PMW) observations, though less affected by atmospheric interference, suffer from coarse resolution and larger uncertainty. This study presents the first validated clear-sky merged LST product for the USA and combines downscaled PMW data from AMSR-E and AMSR2 with MODIS TIR observations, using a modified U-Net deep learning network. The merged dataset covers 2004–2021 at 5 km resolution, providing a compromise between spatial detail and robustness. The model performs well, with low mean squared errors and $R^2$ values of 0.80 (day) and 0.75 (night). The merged time series captures seasonal trends and shows a marked reduction in cloud-contamination artefacts compared to MODIS and AMSR signals. Spatially, the product is consistent across sensor transitions and reduces artefacts from TIR cloud contamination. Validation against ground stations shows results between those of TIR and PMW, with better accuracy at night and moderate positive biases influenced by land cover and terrain. Although the merged product does not match the fine resolution of TIR data by choice, it enhances spatial coverage over AMSR alone and temporal completeness over MODIS alone, where single-sensor products are limited. Residual temporal and seasonal biases are moderate, with systematic warm and cold deviations linked to land cover, propagation of emissivity errors, and sampling differences. Strong positive biases remain over terrain with complex surface properties as the downscaled AMSR is closer to MODIS temperatures. Results demonstrate the combined benefits of PMW’s broader coverage and cloud tolerance with TIR’s spatial detail. Overall, results demonstrate the potential of sensor fusion for producing spatially consistent LST records suitable for long-term environmental and climate monitoring. Full article

Pneumonia, a prevalent respiratory infection, remains a leading cause of morbidity and mortality worldwide, particularly among vulnerable populations. Chest X-rays serve as a primary tool for pneumonia detection; however, variations in imaging conditions and subtle visual indicators complicate consistent interpretation. Automated tools can enhance traditional methods by improving diagnostic reliability and supporting clinical decision-making. In this study, we propose a novel multi-scale transformer approach for pneumonia detection that integrates lung segmentation and classification into a unified framework. Our method introduces a lightweight transformer-enhanced TransUNet for precise lung segmentation, achieving a Dice score of 95.68% on the “Chest X-ray Masks and Labels” dataset with fewer parameters than traditional transformers. For classification, we employ pre-trained ResNet models (ResNet-50 and ResNet-101) to extract multi-scale feature maps, which are then processed through a convolutional Residual Attention Module and a modified transformer module to enhance pneumonia detection. This integration of multi-scale feature extraction and lightweight attention mechanisms ensures robust performance, making our method suitable for resource-constrained clinical environments. Our approach achieves 93.75% accuracy on the “Kermany” dataset and 96.04% accuracy on the “Cohen” dataset, outperforming existing methods while maintaining computational efficiency. Full article