Although large language models (LLMs) are capable of performing various tasks, they still suffer from producing plausible but incorrect responses. To improve the reliability of LLMs, recent research has focused on uncertainty quantification to predict whether a response is correct or not. However, most uncertainty quantification methods have been evaluated on questions requiring a single clear answer, ignoring the existence of data uncertainty that arises from irreducible randomness. Instead, these methods only consider model uncertainty, which arises from a lack of knowledge. In this paper, we investigate previous uncertainty quantification methods under the presence of data uncertainty. Our contributions are two-fold: 1) proposing a new Multi-Answer Question Answering dataset, MAQA, consisting of world knowledge, mathematical reasoning, and commonsense reasoning tasks to evaluate uncertainty quantification regarding data uncertainty, and 2) assessing 5 uncertainty quantification methods of diverse white- and black-box LLMs. Our findings show that entropy and consistency-based methods estimate the model uncertainty well even under data uncertainty, while other methods for white- and black-box LLMs struggle depending on the tasks. Additionally, methods designed for white-box LLMs suffer from overconfidence in reasoning tasks compared to simple knowledge queries. We believe our observations will pave the way for future work on uncertainty quantification in realistic setting.

In this paper, we compare the performance of three common deep learning architectures, CNN-LSTM, LSTM, and 3D-CNN, in the context of surrogate storm surge modeling. The study site for this paper is the Tampa Bay area in Florida. Using high-resolution atmospheric data from the reanalysis models and historical water level data from NOAA tide stations, we trained and tested these models to evaluate their performance. Our findings indicate that the CNN-LSTM model outperforms the other architectures, achieving a test loss of 0.010 and an R-squared (R2) score of 0.84. The LSTM model, although it achieved the lowest training loss of 0.007 and the highest training R2 of 0.88, exhibited poorer generalization with a test loss of 0.014 and an R2 of 0.77. The 3D-CNN model showed reasonable performance with a test loss of 0.011 and an R2 of 0.82 but displayed instability under extreme conditions. A case study on Hurricane Ian, which caused a significant negative surge of -1.5 meters in Tampa Bay indicates the CNN-LSTM model's robustness and accuracy in extreme scenarios.

Causality inference is prone to spurious causal interactions, due to the substantial confounders in a complex system. While many existing methods based on the statistical methods or dynamical methods attempt to address misidentification challenges, there remains a notable lack of effective methods to infer causality, in particular in the presence of invisible/unobservable confounders. As a result, accurately inferring causation with invisible confounders remains a largely unexplored and outstanding issue in data science and AI fields. In this work, we propose a method to overcome such challenges to infer dynamical causality under invisible confounders (CIC method) and further reconstruct the invisible confounders from time-series data by developing an orthogonal decomposition theorem in a delay embedding space. The core of our CIC method lies in its ability to decompose the observed variables not in their original space but in their delay embedding space into the common and private subspaces respectively, thereby quantifying causality between those variables both theoretically and computationally. This theoretical foundation ensures the causal detection for any high-dimensional system even with only two observed variables under many invisible confounders, which is actually a long-standing problem in the field. In addition to the invisible confounder problem, such a decomposition actually makes the intertwined variables separable in the embedding space, thus also solving the non-separability problem of causal inference. Extensive validation of the CIC method is carried out using various real datasets, and the experimental results demonstrates its effectiveness to reconstruct real biological networks even with unobserved confounders.

The electric vehicle (EV) battery supply chain's vulnerability to disruptions necessitates advanced predictive analytics. We present SHIELD (Schema-based Hierarchical Induction for EV supply chain Disruption), a system integrating Large Language Models (LLMs) with domain expertise for EV battery supply chain risk assessment. SHIELD combines: (1) LLM-driven schema learning to construct a comprehensive knowledge library, (2) a disruption analysis system utilizing fine-tuned language models for event extraction, multi-dimensional similarity matching for schema matching, and Graph Convolutional Networks (GCNs) with logical constraints for prediction, and (3) an interactive interface for visualizing results and incorporating expert feedback to enhance decision-making. Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods (e.g., GPT-4o) in disruption prediction. These results demonstrate SHIELD's effectiveness in combining LLM capabilities with domain expertise for enhanced supply chain risk assessment.

Full-complexity Earth system models (ESMs) are computationally very expensive, limiting their use in exploring the climate outcomes of multiple emission pathways. More efficient emulators that approximate ESMs can directly map emissions onto climate outcomes, and benchmarks are being used to evaluate their accuracy on standardized tasks and datasets. We investigate a popular benchmark in data-driven climate emulation, ClimateBench, on which deep learning-based emulators are currently achieving the best performance. We implement a linear regression-based emulator, akin to pattern scaling, and find that it outperforms the incumbent 100M-parameter deep learning foundation model, ClimaX, on 3 out of 4 regionally-resolved surface-level climate variables. While emulating surface temperature is expected to be predominantly linear, this result is surprising for emulating precipitation. We identify that this outcome is a result of high levels of internal variability in the benchmark targets. To address internal variability, we update the benchmark targets with ensemble averages from the MPI-ESM1.2-LR model that contain 50 instead of 3 climate simulations per emission pathway. Using the new targets, we show that linear pattern scaling continues to be more accurate on temperature, but can be outperformed by a deep learning-based model for emulating precipitation. We publish our code, data, and an interactive tutorial at github.com/blutjens/climate-emulator.

Road traffic congestion prediction is a crucial component of intelligent transportation systems, since it enables proactive traffic management, enhances suburban experience, reduces environmental impact, and improves overall safety and efficiency. Although there are several public datasets, especially for metropolitan areas, these datasets may not be applicable to practical scenarios due to insufficiency in the scale of data (i.e. number of sensors and road links) and several external factors like different characteristics of the target area such as urban, highways and the data collection location. To address this, this paper introduces a novel IBB Traffic graph dataset as an alternative benchmark dataset to mitigate these limitations and enrich the literature with new geographical characteristics. IBB Traffic graph dataset covers the sensor data collected at 2451 distinct locations. Moreover, we propose a novel Road Traffic Prediction Model that strengthens temporal links through feature engineering, node embedding with GLEE to represent inter-related relationships within the traffic network, and traffic prediction with ExtraTrees. The results indicate that the proposed model consistently outperforms the baseline models, demonstrating an average accuracy improvement of 4%.

During the last week of July, Russia mounted its largest assaults in eight months in eastern Ukraine's Donetsk region, seizing a string of settlements in an apparent bid to cut off key supply routes and force a mass Ukrainian retreat. At the same time, Ukraine scored a high number of hits on Russian energy infrastructure and occupied Crimea, suggesting that its strategy of degrading Russian air defences is working. Russian assaults focused on central and southern Donetsk – from areas west of Bakhmut, which fell in May last year, to areas west of Avdiivka, which was lost in February, down to areas west of the city of Donetsk, which pro-Moscow separatists have controlled since 2014 – a line about 130km (80 miles) long. Russian forces have pressed their advantage in these areas to prevent Ukraine from digging entrenched defences, and they have inched forward for months, swallowing settlements at a staggering cost to their own troops. British military intelligence estimated that Russian casualties in May and June reached record daily highs of about 1,200 – about 70,000 soldiers for just those two months.

Elasmobranchs (sharks and rays) can be important components of marine ecosystems but are experiencing global population declines. Effective monitoring of these populations is essential to their protection. Baited Remote Underwater Video Stations (BRUVS) have been a key tool for monitoring, but require time-consuming manual analysis. To address these challenges, we developed SharkTrack, an AI-enhanced BRUVS analysis software. SharkTrack uses Convolutional Neural Networks and Multi-Object Tracking to detect and track elasmobranchs and provides an annotation pipeline to manually classify elasmobranch species and compute MaxN, the standard metric of relative abundance. We tested SharkTrack on BRUVS footage from locations unseen by the model during training. SharkTrack computed MaxN with 89% accuracy over 207 hours of footage. The semi-automatic SharkTrack pipeline required two minutes of manual classification per hour of video, a 97% reduction of manual BRUVS analysis time compared to traditional methods, estimated conservatively at one hour per hour of video. Furthermore, we demonstrate SharkTrack application across diverse marine ecosystems and elasmobranch species, an advancement compared to previous models, which were limited to specific species or locations. SharkTrack applications extend beyond BRUVS analysis, facilitating rapid annotation of unlabeled videos, aiding the development of further models to classify elasmobranch species. We provide public access to the software and an unprecedentedly diverse dataset, facilitating future research in an important area of marine conservation.

Significant wave height (SWH) is a vital metric in marine science, and accurate SWH estimation is crucial for various applications, e.g., marine energy development, fishery, early warning systems for potential risks, etc. Traditional SWH estimation methods that are based on numerical models and physical theories are hindered by computational inefficiencies. Recently, machine learning has emerged as an appealing alternative to improve accuracy and reduce computational time. However, due to limited observational technology and high costs, the scarcity of real-world data restricts the potential of machine learning models. To overcome these limitations, we propose an ocean SWH estimation framework, namely Orca. Specifically, Orca enhances the limited spatio-temporal reasoning abilities of classic LLMs with a novel spatiotemporal aware encoding module. By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data. Experimental results on the Gulf of Mexico demonstrate that Orca achieves state-of-the-art performance in SWH estimation.

We present a knowledge-guided machine learning (KGML) framework for modeling multi-scale processes, and study its performance in the context of streamflow forecasting in hydrology. Specifically, we propose a novel hierarchical recurrent neural architecture that factorizes the system dynamics at multiple temporal scales and captures their interactions. This framework consists of an inverse and a forward model. The inverse model is used to empirically resolve the system's temporal modes from data (physical model simulations, observed data, or a combination of them from the past), and these states are then used in the forward model to predict streamflow. In a hydrological system, these modes can represent different processes, evolving at different temporal scales (e.g., slow: groundwater recharge and baseflow vs. fast: surface runoff due to extreme rainfall). A key advantage of our framework is that once trained, it can incorporate new observations into the model's context (internal state) without expensive optimization approaches (e.g., EnKF) that are traditionally used in physical sciences for data assimilation. Experiments with several river catchments from the NWS NCRFC region show the efficacy of this ML-based data assimilation framework compared to standard baselines, especially for basins that have a long history of observations. Even for basins that have a shorter observation history, we present two orthogonal strategies of training our FHNN framework: (a) using simulation data from imperfect simulations and (b) using observation data from multiple basins to build a global model. We show that both of these strategies (that can be used individually or together) are highly effective in mitigating the lack of training data. The improvement in forecast accuracy is particularly noteworthy for basins where local models perform poorly because of data sparsity.