Recent advances in large language models (LLMs), such as GPT-4, have spurred interest in their potential applications across various fields, including actuarial work. This paper introduces the use of LLMs in actuarial and insurance-related tasks, both as direct contributors to actuarial modelling and as workflow assistants. It provides an overview of LLM concepts and their potential applications in actuarial science and insurance, examining specific areas where LLMs can be beneficial, including a detailed assessment of the claims process. Additionally, a decision framework for determining the suitability of LLMs for specific tasks is presented. Case studies with accompanying code showcase the potential of LLMs to enhance actuarial work. Overall, the results suggest that LLMs can be valuable tools for actuarial tasks involving natural language processing or structuring unstructured data and as workflow and coding assistants. However, their use in actuarial work also presents challenges, particularly regarding professionalism and ethics, for which high-level guidance is provided.

Knowledge of weed seeds present in the soil seedbank is important for understanding population dynamics and forecasting future weed infestations. Quantification of the weed seedbank has historically been laborious, and few studies have attempted to quantify seedbanks on the scale required to make management decisions. An accurate, efficient, and ideally automated method to identify weed seeds in field samples is needed. To achieve sufficient precision, we leveraged YOLOv8, a machine learning object detection to accurately identify and count weed seeds obtained from the soil seedbank and weed seed collection. The YOLOv8 model, trained and evaluated using high-quality images captured with a digital microscope, achieved an overall accuracy and precision exceeding 80% confidence in distinguishing various weed seed species in both images and real-time videos. Despite the challenges associated with species having similar seed morphology, the application of YOLOv8 will facilitate rapid and accurate identification of weed seeds for the assessment of future weed management strategies.

Automatic static cost analysis infers information about the resources used by programs without actually running them with concrete data and presents such information as functions of input data sizes. Most of the analysis tools for logic programs (and many for other languages), as CiaoPP, are based on setting up recurrence relations representing (bounds on) the computational cost of predicates and solving them to find closed-form functions. Such recurrence solving is a bottleneck in current tools: many of the recurrences that arise during the analysis cannot be solved with state-of-the-art solvers, including computer algebra systems (CASs), so that specific methods for different classes of recurrences need to be developed. We address such a challenge by developing a novel, general approach for solving arbitrary, constrained recurrence relations, that uses machine learning (sparse-linear and symbolic) regression techniques to guess a candidate closed-form function, and a combination of an SMT-solver and a CAS to check whether such function is actually a solution of the recurrence. Our prototype implementation and its experimental evaluation within the context of the CiaoPP system show quite promising results. Overall, for the considered benchmark set, our approach outperforms state-of-the-art cost analyzers and recurrence solvers and can find closed-form solutions, in a reasonable time, for recurrences that cannot be solved by them.

Embedding physical knowledge into neural network (NN) training has been a hot topic. However, when facing the complex real world, most of the existing methods still strongly rely on the quantity and quality of observation data. Furthermore, the NNs often struggle to converge when the solution to the real equation is very complex. Inspired by large eddy simulation in computational fluid dynamics, we propose an improved method based on filtering. We analysed the causes of the difficulties in physics-informed machine learning, and proposed a surrogate constraint (filtered partial differential equation, FPDE) of the original physical equations to reduce the influence of noisy and sparse observation data. In the noise and sparsity experiment, the proposed FPDE models (which are optimized by FPDE constraints) have better robustness than the conventional PDE models. Experiments demonstrate that the FPDE model can obtain the same quality solution with 100 % higher noise and 12 % quantity of observation data of the baseline. Besides, two groups of real measurement data are used to show the FPDE improvements in real cases. The final results show that the FPDE still gives more physically reasonable solutions when facing the incomplete equation problem and the extremely sparse and high-noise conditions. The proposed FPDE constraint is helpful for merging real-world experimental data into physics-informed training, and it works effectively in two real-world experiments: simulating cell movement in scratches and blood velocity in vessels.

Understanding consumer choices and their drivers of willingness to pay (WTP) for a bottle of wine has been a research challenge in wine economics, particularly in niche markets such as sparkling wine. This study investigates the determinants of WTP for sparkling wine based on data from Portuguese consumers. The results provided by two alternative methodologies are compared: a traditional econometric model, based on the estimation of an ordered probit model; and a modelling approach based on data-driven and using machine learning algorithms. Both approaches present similar results, highlighting the relevance of some determinants including income, Champagne brand, not being a protected designation of origin and being a red wine consumer as main predictors of WTP for sparkling wine in Portugal.

Weeds are one of the greatest challenges to snap bean production. Anecdotal observation posits certain species frequently escape the weed management system by the time of crop harvest, hereafter called residual weeds. The objectives of this work were to 1) quantify the residual weed community in snap bean (Phaseolus vulgaris L.) grown for processing across the major growing regions in the U.S., and 2) investigate linkages between the density of residual weeds and their contributions to weed canopy cover. In surveys of 358 fields across the Northwest (NW), Midwest (MW), and Northeast (NE), residual weeds were observed in 95% of the fields. While a total of 109 species or species-group were identified, one to three species dominated the residual weed community of individual fields in most cases. It was not uncommon to have >10 weeds m-2 with a weed canopy covering >5% of the field’s surface area. Some of the most abundant and problematic species or species-group escaping control included amaranth species (such as smooth pigweed (Amaranthus hybridus L.), Palmer amaranth (Amaranthus palmeri S. Watson), redroot pigweed (Amaranthus retroflexus L.), and waterhemp [Amaranthus tuberculatus (Moq.) J. D. Sauer]), common lambsquarters (Chenopodium album L.), large crabgrass [Digitaria sanguinalis (L.) Scop.], and ivyleaf morningglory (Ipomoea hederacea Jacq.). Emerging threats include hophornbeam copperleaf (Acalypha ostryifolia Riddell) in the MW and sharppoint fluvellin [Kickxia elatine (L.) Dumort.] in the NW. Beyond crop losses due to weed interference, the weed canopy at harvest poses a risk to contaminating snap bean products with foreign material. Random forest modeling predicts the residual weed canopy is dominated by common lambsquarters, large crabgrass, carpetweed (Mollugo verticillata L.), I. hederacea, amaranth species, and A. ostryifolia. This is the first quantitative report on the weed community escaping control in U.S. snap bean production.

We propose a method for generating rule sets as global and local explanations for tree-ensemble learning methods using answer set programming (ASP). To this end, we adopt a decompositional approach where the split structures of the base decision trees are exploited in the construction of rules, which in turn are assessed using pattern mining methods encoded in ASP to extract explanatory rules. For global explanations, candidate rules are chosen from the entire trained tree-ensemble models, whereas for local explanations, candidate rules are selected by only considering rules that are relevant to the particular predicted instance. We show how user-defined constraints and preferences can be represented declaratively in ASP to allow for transparent and flexible rule set generation, and how rules can be used as explanations to help the user better understand the models. Experimental evaluation with real-world datasets and popular tree-ensemble algorithms demonstrates that our approach is applicable to a wide range of classification tasks.

With the emerging developments in millimeter-wave/5G technologies, the potential for wireless Internet of things devices to achieve widespread sensing, precise localization, and high data-rate communication systems becomes increasingly viable. The surge in interest surrounding virtual reality (VR) and augmented reality (AR) technologies is attributed to the vast array of applications they enable, ranging from surgical training to motion capture and daily interactions in VR spaces. To further elevate the user experience, and real-time and accurate orientation detection of the user, the authors proposes the utilization of a frequency-modulated continuous-wave (FMCW) radar system coupled with an ultra-low-power, sticker-like millimeter-wave identification (mmID). The mmID features four backscattering elements, multiplexed in amplitude, frequency, and spatial domains. This design utilizes the training of a supervised learning classification convolutional neural network, enabling accurate real-time three-axis orientation detection of the user. The proposed orientation detection system exhibits exceptional performance, achieving a noteworthy accuracy of 90.58% over three axes at a distance of 8 m. This high accuracy underscores the precision of the orientation detection system, particularly tailored for medium-range VR/AR applications. The integration of the FMCW-based mmID system with machine learning proves to be a promising advancement, contributing to the seamless and immersive interaction within virtual and augmented environments.

In recent times, the economic and social relevance of constitutions and potential determinants of their validity have been increasingly debated. However, we still know little about the relationships between the text of a constitution and constitutional compliance. Does the wording of a constitution matter in this context? In this paper, drawing on a sample of democratic countries, we apply econometric and machine learning tools to provide some insights on these issues. The results suggest that shorter texts and placing more emphasis on punishments for transgressions seem to be positively correlated with the compliance level. Regarding the precision of constitutional text, in turn, we find mixed evidence. Econometric modelling suggests no statistically significant relationship with constitutional compliance, and machine learning models instead indicate this feature as a potentially important determinant of constitutional compliance.

Interacting particle systems (IPSs) are a very important class of dynamical systems, arising in different domains like biology, physics, sociology and engineering. In many applications, these systems can be very large, making their simulation and control, as well as related numerical tasks, very challenging. Kernel methods, a powerful tool in machine learning, offer promising approaches for analyzing and managing IPS. This paper provides a comprehensive study of applying kernel methods to IPS, including the development of numerical schemes and the exploration of mean-field limits. We present novel applications and numerical experiments demonstrating the effectiveness of kernel methods for surrogate modelling and state-dependent feature learning in IPS. Our findings highlight the potential of these methods for advancing the study and control of large-scale IPS.

Precipitation is one of the most relevant weather and climate processes. Its formation rate is sensitive to perturbations such as by the interactions between aerosols, clouds, and precipitation. These interactions constitute one of the biggest uncertainties in determining the radiative forcing of climate change. High-resolution simulations such as the ICOsahedral non-hydrostatic large-eddy model (ICON-LEM) offer valuable insights into these interactions. However, due to exceptionally high computation costs, it can only be employed for a limited period and area. We address this challenge by developing new models powered by emerging machine learning approaches capable of forecasting autoconversion rates—the rate at which small droplets collide and coalesce becoming larger droplets—from satellite observations providing long-term global spatial coverage for more than two decades. In particular, our approach involves two phases: (1) we develop machine learning models which are capable of predicting autoconversion rates by leveraging high-resolution climate model data, (2) we repurpose our best machine learning model to predict autoconversion rates directly from satellite observations. We compare the performance of our machine learning models against simulation data under several different conditions, showing from both visual and statistical inspections that our approaches are able to identify key features of the reference simulation data to a high degree. Additionally, the autoconversion rates obtained from the simulation output and satellite data (predicted) demonstrate statistical concordance. By efficiently predicting this, we advance our comprehension of one of the key processes in precipitation formation, crucial for understanding cloud responses to anthropogenic aerosols and, ultimately, climate change.

Classical approaches for flood prediction apply numerical methods for the solution of partial differential equations that capture the physics of inundation processes (e.g., the 2D Shallow Water equations). However, traditional inundation models are still unable to satisfy the requirements of many relevant applications, including early-warning systems, high-resolution (or large spatial domain) simulations, and robust inference over distributions of inputs (e.g., rainfall events). Machine learning (ML) approaches are a promising alternative to physics-based models due to their ability to efficiently capture correlations between relevant inputs and outputs in a data-driven fashion. In particular, once trained, ML models can be tested/deployed much more efficiently than classical approaches. Yet, few ML-based solutions for spatio-temporal flood prediction have been developed, and their reliability/accuracy is poorly understood. In this paper, we propose FloodGNN-GRU, a spatio-temporal flood prediction model that combines a graph neural network (GNN) and a gated recurrent unit (GRU) architecture. Compared to existing approaches, FloodGNN-GRU (i) employs a graph-based model (GNN); (ii) operates on both spatial and temporal dimensions; and (iii) processes the water flow velocities as vector features, instead of scalar features. We evaluate FloodGNN-GRU using a LISFLOOD-FP simulation of Hurricane Harvey (2017) in Houston, Texas. Our results, based on several metrics, show that FloodGNN-GRU outperforms several data-driven alternatives in terms of accuracy. Moreover, our approach can be trained 100x faster and tested 1000x faster than the time required to run a comparable simulation. These findings illustrate the potential of ML-based methods to efficiently emulate physics-based inundation models, especially for short-term predictions.

Damage initiation hotspots around features, such as bolts and ply drops, must be investigated during the preliminary design phase of large composite structures, such as composite airframes. A global-local modelling approach is commonly employed to perform this investigation, whereby a global low-fidelity model is used to drive high-fidelity local models around the features of interest. However, this methodology is slow, repetitive and expert-dependent. In this investigation, we address these issues by applying machine learning techniques to this global-local modelling framework and demonstrate the time-saving benefit when predicting damage initiation of bolted composite joints. Feature engineering of model inputs and outputs, and appropriate customisation of machine learning methods enables damage initiation prediction. Special consideration is given to the boundary conditions that must be varied to simulate the response of the bolted composite joints. Results show over three orders of magnitude time-saving benefit and satisfactory accuracy of the proposed methodology. This indicates its potential to be developed further into a rapid design and optimisation tool.

Cost efficiency is a critical factor in the competitive aviation sector. These efficiency factors force airline operators to develop new approaches in their organizations. Predictive maintenance helps to build scheduling maintenance programs for airline operators or MROs. Scheduled maintenance programs benefit cost efficiency in the aviation sector. Predictive maintenance methods predict the failure time of any equipment. Predictions can be made by analyzing the sensor values from equipment.

In this paper, we predicted the remaining useful life (RUL) of turbofan engines using machine learning models and a similarity-based approach. Sensor datasets from the Prognostics Data Repository of NASA, called CMAPPS, were utilized. Using the FD0002 sub-dataset, a health index (HI) was created, and models were trained. Once the models were trained, train and test HIs were estimated. The predicted test HI was matched with the predicted train HI based on a similarity-based approach, and then a RUL prediction was made. The results obtained were compared with the actual results to calculate the accuracy, and the algorithm that resulted in the maximum accuracy was identified.

We selected six machine learning algorithms and also created an ensemble model by averaging the predictions of six machine learning algorithms for comparing prediction accuracy. The different algorithms were compared to obtain the prediction model with the closest prediction of remaining useful lifecycle in terms of the number of life cycles. This experiment showed us the effect of the similarity-based approach on the basic version of machine learning models for RUL prediction.