Gamma-ray spectroscopy is essential in nuclear science, enabling the identification of radioactive materials through energy spectrum analysis. However, high count rates lead to pile-up effects, resulting in spectral distortions that hinder accurate isotope identification and activity estimation. This phenomenon highlights the need for automated and precise approaches to pile-up correction. We propose a novel deep learning (DL) framework plugging count rate information of pile-up signals with a 2D attention U-Net for energy spectrum recovery. The input to the model is an Energy–Duration matrix constructed from preprocessed pulse signals. Temporal and spatial features are jointly extracted, with count rate information embedded to enhance robustness under high count rate conditions. Training data were generated using an open-source simulator based on a public gamma spectrum database. The model’s performance was evaluated using Kullback–Leibler (KL) divergence, Mean Squared Error (MSE) Energy Resolution (ER), and Full Width at Half Maximum (FWHM). Results indicate that the proposed framework effectively predicts accurate spectra, minimizing errors even under severe pile-up effects. This work provides a robust framework for addressing pile-up effects in gamma-ray spectroscopy, presenting a practical solution for automated, high-accuracy spectrum estimation. The integration of temporal and spatial learning techniques offers promising prospects for advancing high-activity nuclear analysis applications.

High counting rates pose a challenging problem for nuclear spectrometric systems, where a physical phenomenon known as the pile-up effect distorts direct measurements, resulting in a significant bias in spectrum estimation. In this paper, we propose an innovative neural network that combines the self-attention mechanism and convolutional neural network (CNN) architectures to address the problem of spectrum estimation. The approach was evaluated on spectral data from a small scintillator (NaI) and simulated signals from a dedicated simulator and compared with conventional methods; furthermore, our method was compared to the state-of-the-art (SOTA) time domain method on the Allpix2 simulator and was evaluated on a real-world dataset. The results demonstrate that the proposed method leads to a more accurate inference of the energy spectrum, even at high count rates. Experiments also show that the proposed method is robust with varying sources, different data scenarios, and noise intensities.

Ocean Acoustic Tomography (OAT) is an important marine remote sensing technique used for inverting large-scale ocean environmental parameters, but traditional methods face challenges in computational complexity and environmental interference. This paper proposes a causal analysis-driven AI FOR SCIENCE method for high-precision and rapid inversion of oceanic hydrological parameters in complex underwater environments. Based on the open-source VTUAD (Vessel Type Underwater Acoustic Data) dataset, the method first utilizes a fine-tuned Paraformer (a fast and accurate parallel transformer) model for precise classification of sound source targets. Then, using structural causal models (SCM) and potential outcome frameworks, causal embedding vectors with physical significance are constructed. Finally, a cross-modal Transformer network is employed to fuse acoustic features, sound source priors, and environmental variables, enabling inversion of temperature and salinity in the Georgia Strait of Canada. Experimental results show that the method achieves accuracies of 97.77% and 95.52% for temperature and salinity inversion tasks, respectively, significantly outperforming traditional methods. Additionally, with GPU acceleration, the inference speed is improved by over sixfold, aimed at enabling real-time Ocean Acoustic Tomography (OAT) on edge computing platforms as smart hardware, thereby validating the method’s practicality. By incorporating causal inference and cross-modal data fusion, this study not only enhances inversion accuracy and model interpretability but also provides new insights for real-time applications of OAT.

In recent years, rapid development of information technology has led to an increasing demand for computing and storage, especially in cloud computing field. Optical ports have become one of indispensable hardware in cloud computing services, and their stable operation is crucial. Performing remaining useful life (RUL) prediction on optical ports can effectively prevent accidents from occurring and reduce economic losses. Most existing RUL prediction methods focus on continuous degradation modeling, which often require continuous degradation trending to describe degradation uncertainty so as to achieve RUL distributions and uncertainty characterization. However, in some industrial applications, such as optical ports, their degradation is discrete and their trending is hard to describe by aforementioned function. Therefore, this paper aims to develop an adaptive generalized time interval cumulative methodology for discrete degradation modeling and RUL prediction. Here, the proposed new methodology is integrated with newly defined “virtual jump points” to realize online adaptive model parameters updating. RUL prediction is ultimately achieved by extrapolating the updated model to reach a preset failure threshold. Results show that the proposed new methodology can well model optical port degradation and provide accurate RUL prediction so as to be beneficial to realizing condition based optimal port replacement. Note to Practitioners —Optical ports are one of the important hardware in the field of cloud computing, and their physical characteristics determine their discrete characteristics of degradation. Practitioners need to know how to handle data with discrete degradation features. This paper proposes an adaptive generalized time interval accumulation methodology, which can achieve adaptive selection of discrete degradation data distribution and RUL prediction, offering valuable guidance for equipment operation and maintenance. The paper highlights the superiority of the method by comparing it with existing continuous degradation modeling methods.