Accurate mortality forecasting is crucial for actuarial pricing, reserving, and capital planning, yet the traditional Lee-Carter model struggles with non-linear age and cohort patterns, coherent multi-population forecasting, and quantifying prediction uncertainties. Recent advances in deep learning provide a range of tools that can address these limitations, but actuarial surveys have not kept pace. This paper provides the first concise view of deep learning in mortality forecasting. We cover six deep network architectures, namely Recurrent Neural Networks, Convolutional Neural Networks, Transformers, Autoencoders, Locally Connected Networks, and Multi-Task Feed-Forward Networks. We discuss how these architectures tackle cohort effects, population coherence, interpretability, and uncertainty in mortality forecasting. Evidence from the literature shows that carefully calibrated deep learning models can consistently outperform the Lee-Carter baselines; however, no single architecture resolves every challenge, and open issues remain with data scarcity, interpretability, uncertainty quantification, and keeping pace with the advances of deep learning. This review is also intended to provide actuaries with a practical roadmap for adopting deep learning models in mortality forecasting.

The population-based structural health monitoring paradigm has recently emerged as a promising approach to enhance data-driven assessment of engineering structures by facilitating transfer learning between structures with some degree of similarity. In this work, we apply this concept to the automated modal identification of structural systems. We introduce a graph neural network (GNN)-based deep learning scheme to identify modal properties, including natural frequencies, damping ratios, and mode shapes of engineering structures based on the power spectral density of spatially sparse vibration measurements. Systematic numerical experiments are conducted to evaluate the proposed model, employing two distinct truss populations that possess similar topological characteristics but varying geometric (size and shape) and material (stiffness) properties. The results demonstrate that, once trained, the proposed GNN-based model can identify modal properties of unseen structures within the same structural population with good efficiency and acceptable accuracy, even in the presence of measurement noise and sparse measurement locations. The GNN-based model exhibits advantages over the classic frequency domain decomposition method in terms of identification speed, as well as against an alternate multilayer perceptron architecture in terms of identification accuracy, rendering this a promising tool for PBSHM purposes.

Precision weed detection and mapping in vegetable crops are beneficial for improving the effectiveness of weed control. This study proposes a novel method for indirect weed detection and mapping using a detection network based on the You-Only-Look-Once-v8 (YOLOv8) architecture. This approach detects weeds by first identifying vegetables and then segmenting weeds from the background using image processing techniques. Subsequently, weed mapping was established and innovative path planning algorithms were implemented to optimize actuator trajectories along the shortest possible path. Experimental results demonstrated significant improvements in both precision and computational efficiency compared with the original YOLOv8 network. The mean average precision at 0.5 (mAP50) increased by 0.2, while the number of parameters, giga floating-point operations per second (GFLOPS), and model size decreased by 0.57 million, 1.8 GFLOPS, and 1.1 MB, respectively, highlighting enhanced accuracy and reduced computational costs. Among the analyzed path planning algorithms, including Christofides, Dijkstra, and dynamic programming (DP), the Dijkstra algorithm was the most efficient, producing the shortest path for guiding the weeding system. This method enhances the robustness and adaptability of weed detection by eliminating the need to detect diverse weed species. By integrating precision weed mapping and efficient path planning, mechanical actuators can target weed-infested areas with optimal precision. This approach offers a scalable solution that can be adapted to other precision weeding applications.

Good air quality is a critical determinant of public health, influencing life expectancy, respiratory health, work productivity, and the prevention of chronic diseases. This study presents a novel approach to classifying the Air Quality Index (AQI) using deep learning techniques, specifically convolutional neural networks (CNNs). We collected and curated a dataset comprising 11,000 digital images from three distinct regions in Indonesia—Jakarta, Malang, and Semarang—ensuring uniformity through standardized acquisition settings. The images were categorized into four air quality classes: good, moderate, unhealthy for sensitive groups, and unhealthy. We designed and implemented a CNN architecture optimized for AQI classification. The model achieved an impressive accuracy of 99.81% using K-fold cross-validation. In addition, the model’s interpretative capabilities were examined using techniques such as Grad-CAM, providing valuable insights into how the CNN identifies and classifies air quality conditions based on image features. These findings underscore the effectiveness of CNNs for AQI classification and highlight the potential for future work to incorporate a more diverse set of digital images captured from various perspectives to enhance dataset complexity and model robustness. The dataset is publicly accessible at https://doi.org/10.5281/zenodo.15727522.

The rapid growth of civil aviation has posed significant challenges to air traffic management (ATM), highlighting the need for accurate aircraft trajectory prediction (TP). Due to the scarcity of relevant data and the resulting class imbalance in the sample, aircraft TP under severe weather conditions faces significant challenges. This paper proposes an aircraft TP method framework consisting of trajectory data augmentation and TP networks to address this issue. To validate the effectiveness of this framework in solving the TP problem in severe weather, we propose an improved conditional tabular generative adversarial networks (CTGAN)-long short-term memories (LSTMs) hybrid model. We conduct comparative experiments of four LSTM-based models (LSTM, convolutional neural network (CNN)-LSTM, CNN-LSTM-attention, and CNN-BiLSTM) under this framework. The improved CTGAN is also compared with the commonly used data augmentation method, the Synthetic Minority Oversampling Technique (SMOTE). The results show that the TP accuracy can be effectively improved by enhancing the minority-class sample data; compared with SMOTE, the improved CTGAN is more suitable for minority-class sample data augmentation for aircraft TP, and it also shows that for minority-class sample data augmentation, data distribution characteristics are more important than the simple trajectory point accuracy. The hybrid modeling approach with the improved CTGAN as the data augmentation network proposed in this study provides valuable insights into addressing the data imbalance problem in aircraft TP.

Visible satellite imagery (VIS) is essential for monitoring weather patterns and tracking ground surface changes associated with climate change. However, its availability is limited during nighttime. To address this limitation, we present a discrete variational autoencoder (VQVAE) method for translating infrared satellite imagery to VIS. This method departs from previous efforts that utilize a U-Net architecture. By removing the connections between corresponding layers of the encoder and decoder, the model learns a discrete and rich codebook of latent priors for the translation task. We train and test our model on mesoscale data from the Geostationary Operational Environmental Satellite (GOES) West Advanced Baseline Imager (ABI) sensor, spanning 4 years (2019 to 2022) using the Conditional Generative Adversarial Nets (CGAN) framework. This work demonstrates the practical use of a VQVAE for meteorological satellite image translation. Our approach provides a modular framework for data compression and reconstruction, with a latent representation space specifically designed for handling meteorological satellite imagery.

Continuous monitoring of the mass balance of the Greenland ice sheet is crucial to assess its contribution to the rise of sea levels. The GRACE and GRACE-FO missions have provided monthly estimates of the Earth’s gravity field since 2002, which have been widely used to estimate monthly mass changes of ice sheets. However, there is an 11 month gap between the two missions. Here, we propose a data-driven approach that combines atmospheric variables from the ERA5 reanalysis with GRACE-derived mass anomalies from previous months to predict mass changes. Using an auto-regressive structure, the model is naturally predictive for shorter times without GRACE/-FO observations. The results show a high r2-score (> 0.73) between model predictions and GRACE/-FO observations. Validating the model’s ability to reproduce mass anomalies when observations are available builds confidence in estimates used to bridge the GRACE and GRACE/-FO gap. Although GRACE and GRACE-FO are treated equally by the model, we see a decrease in model performance for the period covered by GRACE-FO, indicating that they may not be as well-calibrated as previously assumed. Gap predictions align well with mass change estimates derived from other geodetic methods and remain within the uncertainty envelope of the GRACE-FO observations.

Within the broad context of design research, joint attention within co-creation represents a critical component, linking cognitive actors through dynamic interactions. This study introduces a novel approach employing deep learning algorithms to objectively quantify joint attention, offering a significant advancement over traditional subjective methods. We developed an optimized deep learning algorithm, YOLO-TP, to identify participants’ engagement in design workshops accurately. Our research methodology involved video recording of design workshops and subsequent analysis using the YOLO-TP algorithm to track and measure joint attention instances. Key findings demonstrate that the algorithm effectively quantifies joint attention with high reliability and correlates well with known measures of intersubjectivity and co-creation effectiveness. This approach not only provides a more objective measure of joint attention but also allows for the real-time analysis of collaborative interactions. The implications of this study are profound, suggesting that the integration of automated human activity recognition in co-creation can significantly enhance the understanding and facilitation of collaborative design processes, potentially leading to more effective design outcomes.

The rapid development of AI has resulted in an unprecedented paradigm shift across various industries, with aerospace among the laureates of this transformation. This review paper attempts to explore and provide comprehensive overview of the aerospace research imperatives from the AI perspective, detailing the technical sides of the full lifecycle from vehicle design and operational optimisation to advanced air traffic management systems. By examining real-world engineering implementations, the review demonstrates how AI-driven solutions are directly addressing longstanding challenges in aerospace, such as optimising flight performance, reducing operational costs and improving system reliability. A significant emphasis is placed on the crucial roles of AI in health monitoring and predictive maintenance, areas that are pivotal for ensuring the safety and longevity of aerospace endeavors, and which are now increasingly adopted in industry for remaining useful life (RUL) forecasting and condition-based maintenance strategies. The paper also discusses AI embedded in quality control and inspection processes, where it boosts accuracy, efficiency and fault detection capability. The review provides insight into the state-of-the-art applications of AI in planetary exploration, particularly within the realms of autonomous scientific instrumentation and robotic prospecting, as well as surface operations on extraterrestrial bodies. An important case study is India’s Chandrayaan-3 mission, demonstrating the application of AI in both autonomous navigation and scientific exploration within the challenging environments of space. By furnishing an overview of the field, the paper frames the ever-important, increasing domains of AI as the forefront in the advancement of aerospace engineering and opens avenues for further discussion regarding the limitless possibilities at the juncture of intelligent systems and aerospace innovation.

Earth’s forests play an important role in the fight against climate change and are in turn negatively affected by it. Effective monitoring of different tree species is essential to understanding and improving the health and biodiversity of forests. In this work, we address the challenge of tree species identification by performing tree crown semantic segmentation using an aerial image dataset spanning over a year. We compare models trained on single images versus those trained on time series to assess the impact of tree phenology on segmentation performance. We also introduce a simple convolutional block for extracting spatio-temporal features from image time series, enabling the use of popular pretrained backbones and methods. We leverage the hierarchical structure of tree species taxonomy by incorporating a custom loss function that refines predictions at three levels: species, genus, and higher-level taxa. Our best model achieves a mean Intersection over Union (mIoU) of 55.97%, outperforming single-image approaches particularly for deciduous trees where phenological changes are most noticeable. Our findings highlight the benefit of exploiting the time series modality via our Processor module. Furthermore, leveraging taxonomic information through our hierarchical loss function often, and in key cases significantly, improves semantic segmentation performance.

In small-plot experiments, weed scientists have traditionally estimated herbicide efficacy through visual assessments or manual counts with wooden frames—methods that are time-consuming, labor-intensive, and error-prone. This study introduces a novel mobile application (app) powered by convolutional neural networks (CNNs) to automate the evaluation of weed coverage in turfgrass. The mobile app automatically segments input images into 10 by 10 grid cells. A comparative analysis of EfficientNet, MobileNetV3, MobileOne, ResNet, ResNeXt, ShuffleNetV1, and ShuffleNetV2 was conducted to identify weed-infested grid cells and calculate weed coverage in bahiagrass (Paspalum notatum Flueggé), dormant bermudagrass [Cynodon dactylon (L.) Pers.], and perennial ryegrass (Lolium perenne L.). Results showed that EfficientNet and MobileOne outperformed other models in detecting weeds growing in bahiagrass, achieving an F1 score of 0.988. For dormant bermudagrass, ResNet performed best, with an F1 score of 0.996. Additionally, app-based coverage estimates (11%) were highly consistent with manual assessments (11%), showing no significant difference (P = 0.3560). Similarly, ResNeXt achieved the highest F1 score of 0.996 for detecting weeds growing in perennial ryegrass, with app-based and manual coverage estimates also closely aligned at 10% (P = 0.1340). High F1 scores across all turfgrass types demonstrate the models’ ability to accurately replicate manual assessments, which is essential for herbicide efficacy trials requiring precise weed coverage data. Moreover, the time for weed assessment was compared, revealing that manual counting with 10 by 10 wooden frames took an average of 39.25, 37.25, and 42.25 s per instance for bahiagrass, dormant bermudagrass, and perennial ryegrass, respectively, whereas the app-based approach reduced the assessment times to 8.23, 7.75, and 14.96 s, respectively. These results highlight the potential of deep learning–based mobile tools for fast, accurate, scalable weed coverage assessments, enabling efficient herbicide trials and offering labor and cost savings for researchers and turfgrass managers.

Recent advancements in data science and artificial intelligence have significantly transformed plant sciences, particularly through the integration of image recognition and deep learning technologies. These innovations have profoundly impacted various aspects of plant research, including species identification, disease detection, cellular signaling analysis, and growth monitoring. This review summarizes the latest computational tools and methodologies used in these areas. We emphasize the importance of data acquisition and preprocessing, discussing techniques such as high-resolution imaging and unmanned aerial vehicle (UAV) photography, along with image enhancement methods like cropping and scaling. Additionally, we review feature extraction techniques like colour histograms and texture analysis, which are essential for plant identification and health assessment. Finally, we discuss emerging trends, challenges, and future directions, offering insights into the applications of these technologies in advancing plant science research and practical implementations.

We present a deep learning architecture that reconstructs a source of data at given spatio-temporal coordinates using other sources. The model can be applied to multiple sources in a broad sense: the number of sources may vary between samples, the sources can differ in dimensionality and sizes, and cover distinct geographical areas at irregular time intervals. The network takes as input a set of sources that each include values (e.g., the pixels for two-dimensional sources), spatio-temporal coordinates, and source characteristics. The model is based on the Vision Transformer, but separately embeds the values and coordinates and uses the embedded coordinates as relative positional embedding in the computation of the attention. To limit the cost of computing the attention between many sources, we employ a multi-source factorized attention mechanism, introducing an anchor-points-based cross-source attention block. We name the architecture MoTiF (multi-source transformer via factorized attention). We present a self-supervised setting to train the network, in which one source chosen randomly is masked and the model is tasked to reconstruct it from the other sources. We test this self-supervised task on tropical cyclone (TC) remote-sensing images, ERA5 states, and best-track data. We show that the model is able to perform TC ERA5 fields and wind intensity forecasting from multiple sources, and that using more sources leads to an improvement in forecasting accuracy.

Monitoring wildlife populations in vast, remote landscapes poses significant challenges for conservation and management, particularly when studying elusive species that range across inaccessible terrain. Traditional survey methods often prove impractical or insufficient in such environments, necessitating innovative technological solutions. This study evaluates the effectiveness of deep learning for automated Bactrian camel detection in drone imagery across the complex desert terrain of the Gobi Desert of Mongolia. Using YOLOv8 and a dataset of 1479 high-resolution drone-captured images of Bactrian camels, we developed and validated an automated detection system. Our model demonstrated strong detection performance with high precision and recall values across different environmental conditions. Scale-aware analysis revealed distinct performance patterns between medium- and small-scale detections, informing optimal drone flight parameters. The system maintained consistent processing efficiency across various batch sizes while preserving detection quality. These findings advance conservation monitoring capabilities for Bactrian camels and other wildlife in remote ecosystems, providing wildlife managers with an efficient tool to track population dynamics and inform conservation strategies in expansive, difficult-to-access habitats.

The logistics, costs, and capacity needed to complete extensive archaeological pedestrian surveys to inventory cultural resources present challenges to public land managers. To address these issues, we developed a workflow combining lidar-derived imagery and deep learning (DL) models tailored for cultural resource management (CRM) programs on public lands. It combines Python scripts that fine-tune models to recognize archaeological features in lidar-derived imagery with denoising QGIS steps that improve the predictions’ performance and applicability. We present this workflow through an applied case study focused on detecting historic agricultural terraces in the Piedmont National Wildlife Refuge, Georgia, USA. For this project, we fine-tuned pretrained U-Net models to teach them to recognize agricultural terraces in imagery, identified the parameter settings that led to the highest recall for detecting terraces, and used those settings to train models on incremental dataset sizes, which allowed us to identify the minimum training size necessary to obtain satisfying models. Results present effective models that can detect most terraces even when trained on small datasets. This study provides a robust methodology that requires basic proficiencies in Python coding but expands DL applications in federal CRM by advancing methods in lidar and machine learning for archaeological inventorying, monitoring, and preservation.

Coherent beam combining (CBC) of laser arrays is increasingly attracting attention for generating free-space structured light, unlocking greater potential in aspects such as power scaling, editing flexibility and high-quality light field creation. However, achieving stable phase locking in a CBC system with massive laser channels still remains a great challenge, especially in the presence of heavy phase noise. Here, we propose an efficient phase-locking method for a laser array with more than 1000 channels by leveraging a deep convolutional neural network for the first time. The key insight is that, by elegantly designing the generation strategy of training samples, the learning burden can be dramatically relieved from the structured data, which enables accurate prediction of the phase distribution. We demonstrate our method in a simulated tiled aperture CBC system with dynamic phase noise and extend it to simultaneously generate orbital angular momentum (OAM) beams with a substantial number of OAM modes.

This study explored mental workload recognition methods for carrier-based aircraft pilots utilising multiple sensor physiological signal fusion and portable devices. A simulation carrier-based aircraft flight experiment was designed, and subjective mental workload scores and electroencephalogram (EEG) and photoplethysmogram (PPG) signals from six pilot cadets were collected using NASA Task Load Index (NASA-TLX) and portable devices. The subjective scores of the pilots in three flight phases were used to label the data into three mental workload levels. Features from the physiological signals were extracted, and the interrelations between mental workload and physiological indicators were evaluated. Machine learning and deep learning algorithms were used to classify the pilots’ mental workload. The performances of the single-modal method and multimodal fusion methods were investigated. The results showed that the multimodal fusion methods outperformed the single-modal methods, achieving higher accuracy, precision, recall and F1 score. Among all the classifiers, the random forest classifier with feature-level fusion obtained the best results, with an accuracy of 97.69%, precision of 98.08%, recall of 96.98% and F1 score of 97.44%. The findings of this study demonstrate the effectiveness and feasibility of the proposed method, offering insights into mental workload management and the enhancement of flight safety for carrier-based aircraft pilots.