Accurate aircraft trajectory prediction (TP) in air traffic management systems is confounded by a number of epistemic uncertainties, dominated by uncertain meteorological conditions and operator specific procedures. Handling this uncertainty necessitates the use of probabilistic, machine learned models for generating trajectories. However, the trustworthiness of such models is limited if generated trajectories are not physically plausible. For this reason we propose a physics-informed approach in which aircraft thrust and airspeed are learned from data and are used to condition the existing Base of Aircraft Data (BADA) model, which is physics-based and enforces energy-based constraints on generated trajectories. A set of informative features are identified and used to condition a probabilistic model of aircraft thrust and airspeed, with the proposed scheme demonstrating a 20% improvement in skilfulness across a set of six metrics, compared against a baseline probabilistic model that ignores contextual information such as meteorological conditions.
Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Usama Raheel
et al.
Train delays result from complex interactions between operational, technical, and environmental factors. While weather impacts railway reliability, particularly in Nordic regions, existing datasets rarely integrate meteorological information with operational train data. This study presents the first publicly available dataset combining Finnish railway operations with synchronized meteorological observations from 2018-2024. The dataset integrates operational metrics from Finland Digitraffic Railway Traffic Service with weather measurements from 209 environmental monitoring stations, using spatial-temporal alignment via Haversine distance. It encompasses 28 engineered features across operational variables and meteorological measurements, covering approximately 38.5 million observations from Finland's 5,915-kilometer rail network. Preprocessing includes strategic missing data handling through spatial fallback algorithms, cyclical encoding of temporal features, and robust scaling of weather data to address sensor outliers. Analysis reveals distinct seasonal patterns, with winter months exhibiting delay rates exceeding 25\% and geographic clustering of high-delay corridors in central and northern Finland. Furthermore, the work demonstrates applications of the data set in analysing the reliability of railway traffic in Finland. A baseline experiment using XGBoost regression achieved a Mean Absolute Error of 2.73 minutes for predicting station-specific delays, demonstrating the dataset's utility for machine learning applications. The dataset enables diverse applications, including train delay prediction, weather impact assessment, and infrastructure vulnerability mapping, providing researchers with a flexible resource for machine learning applications in railway operations research.
Abstract. This paper presents a pioneering study on the inference of boxplot-valued data using both Bayesian and frequentist approaches within a multivariate framework. This approach leverages complex yet intuitive representations to make large datasets more manageable and enhance their interpretability, which is invaluable in the age of big data. Boxplot-valued data are particularly important due to their ability to capture the inherent variability and distributional characteristics of complex datasets. In our study, we propose novel methodologies for parameter estimation and density estimation for boxplot-valued data and apply these techniques to climatological data. Specifically, we utilize data from the Berkeley Earth Surface Temperature Study, which aggregates 1.6 billion temperature reports from 16 pre-existing archives affiliated with the Lawrence Berkeley National Laboratory. Our methods are validated through extensive simulations comparing the efficiency and accuracy of Bayesian and frequentist estimators. We demonstrate the practical applicability of our approach by analyzing summer average temperatures across various European countries. The proposed techniques provide robust tools for analyzing complex data structures, offering valuable insights into climatic trends and variations. Our study highlights the advantages and limitations of each inferential method, offering guidance for future research and applications in the field of climatology.
Sea surface temperature (SST) is a fundamental physical parameter characterising the thermal state of sea surface. Due to the intricate thermal interactions between land, sea, and atmosphere, the spatial gradients of SST in coastal waters often appear at finer spatial scales than those in open ocean waters. The Thermal Infrared Sensor (TIRS) onboard Landsat-8, with its 100-meter spatial resolution, offers a unique opportunity to uncover fine-scale coastal SST patterns that would otherwise be overlooked by coarser-resolution thermal sensors. In this study, we first analysed the spatiotemporal patterns of SST in South Australia's temperate coastal waters from 2014 to 2023 by developing an operational approach for SST retrieval from the Landsat-8 TIRS sensor. A buoy was deployed off the coast of Port Lincoln, South Australia, to validate the quality of SST retrievals. Then the daily baseline climatology of SST with 100 m resolution was constructed, which allowed for the detection and analysis of anomalous SST events. Our results suggest the following: (1) the satellite-derived SST data aligned well with the in-situ measured SST values; (2) the semi-enclosed, shallow regions of Upper Spencer Gulf and Upper St Vincent Gulf showed higher temperatures during summer and cooler temperatures during winter than waters closer to the open ocean, resulting in a higher seasonal variation in SST; (3) the near-shore shallow areas in Spencer Gulf and St Vincent Gulf, and regions surrounding Kangaroo Island, were identified to have a higher probability of SST anomalies compared to the rest of the study area; and (4) anomalous SST events were more likely to happen during the warm months than the cool months. We hope these findings would be helpful in supporting the fishing and aquaculture industries in the coastal waters of South Australia.
As the vulnerabilities of global navigation satellite systems (GNSS) have become more widely recognized, the need for complementary navigation systems has grown. Medium frequency ranging mode (MF R-Mode) has gained attention as an effective backup system during GNSS outages, owing to its strong signal strength and cost-effective scalability. However, to achieve accurate positioning, MF R-Mode requires correction for the additional secondary factor (ASF), a propagation delay affected by terrain. The temporal variation of ASF, known as temporal ASF, is typically corrected using reference stations; however, the effectiveness of this method decreases with distance from the reference station. In this study, we analyzed the correlation between temporal ASF and meteorological factors to evaluate the feasibility of predicting temporal ASF based on meteorological factors. Among these factors, temperature and humidity showed significant correlations with temporal ASF, suggesting their potential utility in ASF correction.
Taewon Kang, Seunghyeon Park, Pyo-Woong Son
et al.
The vulnerabilities of global navigation satellite systems (GNSS) to signal interference have increased the demand for complementary positioning, navigation, and timing (PNT) systems. To address this, South Korea has decided to deploy an enhanced long-range navigation (eLoran) system as a complementary PNT solution. Similar to GNSS, eLoran provides highly accurate timing information, which is essential for applications such as telecommunications, financial systems, and power distribution. However, the primary sources of error for GNSS and eLoran differ. For eLoran, the main source of error is signal propagation delay over land, known as the additional secondary factor (ASF). This delay, influenced by ground conductivity and weather conditions along the signal path, is challenging to predict and mitigate. In this paper, we measure the time difference (TD) between GPS and eLoran using a time interval counter and analyze the correlations between eLoran/GPS TD and eleven meteorological factors. Accurate estimation of eLoran/GPS TD could enable eLoran to achieve timing accuracy comparable to that of GPS. We propose two estimation models for eLoran/GPS TD and compare their performance with existing TD estimation methods. The proposed WLR-AGRNN model captures the linear relationships between meteorological factors and eLoran/GPS TD using weighted linear regression (WLR) and models nonlinear relationships between outputs from expert networks through an anisotropic general regression neural network (AGRNN). The model incorporates terrain elevation to appropriately weight meteorological data, as elevation influences signal propagation delay. Experimental results based on four months of data demonstrate that the WLR-AGRNN model outperforms other models, highlighting its effectiveness in improving eLoran/GPS TD estimation accuracy.
This position paper argues that the next generation of artificial intelligence in meteorological and climate sciences must transition from fragmented hybrid heuristics toward a unified paradigm of physics-guided multimodal transformers. While purely data-driven models have achieved significant gains in predictive accuracy, they often treat atmospheric processes as mere visual patterns, frequently producing results that lack scientific consistency or violate fundamental physical laws. We contend that current ``hybrid'' attempts to bridge this gap remain ad-hoc and struggle to scale across the heterogeneous nature of meteorological data ranging from satellite imagery to sparse sensor measurements. We argue that the transformer architecture, through its inherent capacity for cross-modal alignment, provides the only viable foundation for a systematic integration of domain knowledge via physical constraint embedding and physics-informed loss functions. By advocating for this unified architectural shift, we aim to steer the community away from ``black-box'' curve fitting and toward AI systems that are inherently falsifiable, scientifically grounded, and robust enough to address the existential challenges of extreme weather and climate change.
Abstract The influence of the thermodynamic forcing of the Tibetan Plateau (TP) on the Asian summer monsoon remains controversial because the role of elevated heating across the TP remains unclear at multiple time scales. At the extended-range scale, the boundary forcing is more important than the initial field in the forecast process. In this study, we investigated the role of subdaily thermodynamic forcing across the TP in generating 30-day predictions of precipitation in East Asia by conducting a series of hindcast experiments. The surface potential vorticity forcing was used to identify typical years when the TP forcings were extremely strong or weak. The results indicated that the subdaily thermal forcing of the TP was very important for improving the East Asian precipitation forecast accuracy, especially for predictions longer than 14 days in June 2022, when diffusion heating is very strong and can develop over the TP. In such a case, the corrected TP heating could not only correct for low-level water vapor transport but also modular uplevel circulation, which could propagate downstream, thus favoring the correct prediction of precipitation over East Asia. However, in the other cases, the individual influences of thermal perturbations across the TP are not the only important factors. These findings reveal ways to improve the extended-range forecast skill over East Asia.
Abstract Florida’s summertime precipitation patterns are in part influenced by convergence between the synoptic-scale wind and local sea-breeze fronts that form along the east and west coasts of the peninsula. While the National Weather Service previously defined nine sea-breeze regimes resulting from variations in the synoptic-scale vector wind field near Tampa, Florida, these regimes were developed using a shorter 18-yr period and examined primarily for the purposes of short-term weather prediction. This study employs reanalysis data to develop a full 30-yr climatology of the Florida sea-breeze regime distribution and analyze the composite mean atmospheric conditions associated with each regime. Further, given that 1) the synoptic-scale wind primarily varies as a result of movement in the western ridge of the North Atlantic subtropical high (NASH), and 2) previous studies suggest long-term shifts in the mean position of the NASH western ridge, this study also examines variability and trends in the sea-breeze regime distribution and its relationship to rainy-day frequency over a longer 60-yr period. Results indicate that synoptic-scale flow from the west through southwest, which enhances precipitation probabilities along the eastern half of the peninsula, has increased in frequency, while flow from the east through northeast has decreased in frequency. These changes in the sea-breeze regime distribution may be partially responsible for increases in rainy-day frequency during June–August over northeastern Florida, though results suggest that other factors likely contribute to interannual variability in precipitation across the southern peninsula.
Agricultural meteorological recommendations are crucial for enhancing crop productivity and sustainability by providing farmers with actionable insights based on weather forecasts, soil conditions, and crop-specific data. This paper presents a novel approach that leverages large language models (LLMs) and prompt engineering to improve the accuracy and relevance of these recommendations. We designed a multi-round prompt framework to iteratively refine recommendations using updated data and feedback, implemented on ChatGPT, Claude2, and GPT-4. Our method was evaluated against baseline models and a Chain-of-Thought (CoT) approach using manually collected datasets. The results demonstrate significant improvements in accuracy and contextual relevance, with our approach achieving up to 90\% accuracy and high GPT-4 scores. Additional validation through real-world pilot studies further confirmed the practical benefits of our method, highlighting its potential to transform agricultural practices and decision-making.
Grażyna Liczbińska, Szymon Antosik, Marek Brabec
et al.
Abstract This study examines whether exposure to ambient temperature in nineteenth-century urban space affected the ratio of boys to girls at birth. Furthermore, we investigate the details of temperature effects timing upon sex ratio at birth. The research included 66,009 individual births, aggregated in subsequent months of births for the years 1847–1900, i.e. 33,922 boys and 32,087 girls. The statistical modelling of the probability of a girl being born is based on logistic GAM with penalized splines and automatically selected complexity. Our research emphasizes the significant effect of temperature in the year of conception: the higher the temperature was, the smaller probability of a girl being born was observed. There were also several significant temperature lags before conception and during pregnancy. Our findings indicate that in the past, ambient temperature, similar to psychological stress, hunger, malnutrition, and social and economic factors, influenced the viability of a foetus. Research on the effects of climate on the sex ratio in historical populations may allow for a better understanding of the relationship between environmental factors and reproduction, especially concerning historical populations since due to some cultural limitations, they were more prone to stronger environmental stressors than currently.
The intermittent ozone (O<sub>3</sub>) exposure of crops to alternating high and low concentrations is common in fields, but its impact on crop production has not been thoroughly investigated. In this study, two widely planted and O<sub>3</sub>-sensitive crops, winter wheat and soybean, were intermittently exposed to elevated O<sub>3</sub> concentrations in open-top chambers. The results showed that the winter wheat and soybean yields significantly decreased with O<sub>3</sub> exposure (AOT40, cumulative hourly O<sub>3</sub> concentration above 40 ppb) (<i>p</i> < 0.001). The relative yield losses were 0.99% per AOT40 for winter wheat and 1.2% per AOT40 for soybean, respectively. The responses of the crop biomasses to elevated O<sub>3</sub> concentrations were lower than that of crop yield. Although the O<sub>3</sub>-induced crop yield and biomass losses under continuous O<sub>3</sub> exposure were greater than those under intermittent O<sub>3</sub> exposure, the differences were not statistically significant. Therefore, we can conclude that the effects of elevated O<sub>3</sub> concentrations on crops are closely related to the exposure dose but not significantly related to the temporal distribution of elevated O<sub>3</sub> concentrations. This study improves our understanding of how crop production responds to intermittent O<sub>3</sub> exposure.
Global warming has led to an increasing frequency and intensity of extreme precipitation events worldwide. The extreme precipitation of Henan Province in central China usually occurs in summer, with the climate transition from the northern subtropical to the warm temperate climate. Compared with the study of extreme precipitation events in other regions, the study of Henan Province pays less attention. In order to systematically understand the spatial and temporal characteristics of extreme precipitation in Henan Province, this study applied RClimDex model to obtain nine extreme precipitation indices based on daily precipitation data from 90 meteorological stations from 1981 to 2020. Linear propensity estimation, M-K mutation test, Morlet wavelet analysis, and geostatistical analysis were used to investigate the spatial and temporal variation characteristics of the extreme precipitation indices in the region. The results indicated that continuous dry days (CDD), number of heavy rain days (R20mm), maximum daily precipitation (Rx1day), maximum precipitation for 5 consecutive days (Rx5day), and precipitation intensity (SDII) showed an overall increasing trend, but none passed the significance test (<i>p</i> > 0.01). Extremely strong precipitation (R99p) and Rx5day changed abruptly in 1994, and Rx1day and SDII changed abruptly in 2004. The seven extreme precipitation indices, except CDD and continuous wet days (CWD), had a 30-year cyclical pattern. The multi-year average of extreme precipitation indices showed that the CDD gradually decreased from north to south, CWD and R20mm gradually increased from north to south. Rx1day and Rx5day gradually increased from northwest to southeast, and SDII increased from west to east. The results can contribute valuable insights to extreme precipitation trends and future climate predictions in Henan Province and provide scientific support for coping with extreme precipitation changes and disaster prevention.
Julie Peeling, Jasmeet Judge, Vasubandhu Misra
et al.
The rather unique sub-tropical, flat, peninsular region of Florida is subject to a unique climate with extreme weather events across the year that impacts agriculture, public health, and management of natural resources. Meteorological data at high temporal resolutions especially in the tropical latitudes are essential to understand diurnal and semi-diurnal variations of climate, which are considered to be the fundamental modes of climate variations of our Earth system. However, many meteorological datasets contain gaps that limit their use for validation of models and further detailed observational analysis. The objective of this paper is to apply a set of data gap filling strategies to develop a gap-free dataset with 15-minute observations for the sub-tropical region of Florida. Using data from the Florida Automated Weather Network (FAWN), methods of linear interpolation, trend continuation, reference to external sources, and nearest station substitution were applied to fill in the data gaps depending on the extent of the gap. The outcome of this study provides continuous, publicly accessible surface meteorological observations for 30 FAWN stations at 15-minute intervals for the years 2005-2020.
Weather forecasting is one of the cornerstones of meteorological work. In this paper, we present a new benchmark dataset named Weather2K, which aims to make up for the deficiencies of existing weather forecasting datasets in terms of real-time, reliability, and diversity, as well as the key bottleneck of data quality. To be specific, our Weather2K is featured from the following aspects: 1) Reliable and real-time data. The data is hourly collected from 2,130 ground weather stations covering an area of 6 million square kilometers. 2) Multivariate meteorological variables. 20 meteorological factors and 3 constants for position information are provided with a length of 40,896 time steps. 3) Applicable to diverse tasks. We conduct a set of baseline tests on time series forecasting and spatio-temporal forecasting. To the best of our knowledge, our Weather2K is the first attempt to tackle weather forecasting task by taking full advantage of the strengths of observation data from ground weather stations. Based on Weather2K, we further propose Meteorological Factors based Multi-Graph Convolution Network (MFMGCN), which can effectively construct the intrinsic correlation among geographic locations based on meteorological factors. Sufficient experiments show that MFMGCN improves both the forecasting performance and temporal robustness. We hope our Weather2K can significantly motivate researchers to develop efficient and accurate algorithms to advance the task of weather forecasting. The dataset can be available at https://github.com/bycnfz/weather2k/.
The classification of weather data involves categorizing meteorological phenomena into classes, thereby facilitating nuanced analyses and precise predictions for various sectors such as agriculture, aviation, and disaster management. This involves utilizing machine learning models to analyze large, multidimensional weather datasets for patterns and trends. These datasets may include variables such as temperature, humidity, wind speed, and pressure, contributing to meteorological conditions. Furthermore, it's imperative that classification algorithms proficiently navigate challenges such as data imbalances, where certain weather events (e.g., storms or extreme temperatures) might be underrepresented. This empirical study explores data augmentation methods to address imbalanced classes in tabular weather data in centralized and federated settings. Employing data augmentation techniques such as the Synthetic Minority Over-sampling Technique or Generative Adversarial Networks can improve the model's accuracy in classifying rare but critical weather events. Moreover, with advancements in federated learning, machine learning models can be trained across decentralized databases, ensuring privacy and data integrity while mitigating the need for centralized data storage and processing. Thus, the classification of weather data stands as a critical bridge, linking raw meteorological data to actionable insights, enhancing our capacity to anticipate and prepare for diverse weather conditions.
By using various skill scores and spatial characteristics of spatial verification methods and traditional techniques of the model evaluation tool, the gridded precipitation observation, known as Climate Prediction Center Morphing Technique, gauge observation and three datasets that were derived from local, Shanghai, and Grapes models, respectively, were conducted to assess the 3 lead day rainfall forecast with 0.5 day intervals during the summer of 2020 over Central East China. Results have shown that the local model generally outperforms the other two for the most skill scores but usually with relatively larger uncertainties than the Shanghai model, and it has the least displacement errors for moderate rainfall among the three datasets. However, the rainfall of the Grapes model has been heavily underestimated and is accompanied with a large displacement error. Both the local and Shanghai model can effectively forecast the large-scale convection and rainstorms but over forecast the local convection, while the local model likely over forecasts the local rainstorms. In addition, the Shanghai model slightly favors over forecasting on a broad scale range and a broad threshold range, and the local model slightly misses the rainfall exceeding 100 mm. Generally, for a broadly comparative evaluation on rainfall, the popular dichotomous methods should be recommended when considering reasonable classification of thresholds if the accuracy is highly demanding. In addition, most spatial methods are suggested to conduct with proper pre-handling of non-rainfall event cases. Especially, the verification metrics including spatial characteristic difference information should be recommended to emphasize rewarding the severe events forecast under a global warming background.
Owen King, Sajid Ghuffar, Atanu Bhattacharya
et al.
Despite their extreme elevation, glaciers on the Tibetan Plateau are losing mass in response to atmospheric warming, the pattern of which purportedly reflects regional contrasts in climate. Here we examine the evolution of glaciers along ~500 km of the Tanggula Shan, Central-Eastern Tibetan Plateau. Using remotely sensed datasets, we quantified changes in glacier mass, area and surface velocity, and compared these results to time series of meteorological observations, in order to disentangle drivers of glacier mass loss since the 1960s. Glacier mass loss has increased (from −0.21 ± 0.12 m w.e. a−1 in 1960s–2000s, to −0.52 ± 0.18 m w.e. a−1 in 2000s–2015/18) in association with pervasive positive temperature anomalies (up to 1.85°C), which are pronounced at the end of the now lengthened ablation season. However, glacier mass budget perturbations do not mirror the magnitude of temperature anomalies in sub-regions, thus additional factors have heightened glacier recession. We show how proglacial lake expansion and glacier surging have compounded glacier recession over decadal/multi-decadal time periods, and exert similar influence on glacier mass budgets as temperature changes. Our results demonstrate the importance of ice loss mechanisms not often incorporated into broad-scale glacier projections, which need to be better considered to refine future glacier runoff estimates.
Thomas J. Galarneau Jr., Xubin Zeng, Ross D. Dixon
et al.
Abstract Mesoscale convective systems (MCSs) in the tropics play an integral role in the water cycle, are associated with local hazardous weather conditions, and have significant remote impacts on the midlatitude jet stream. Although it is known that MCSs occur in relatively moist environments, it is unclear how far in advance favorable ingredients (lift, instability, and moisture) in the mesoscale environment precede MCS formation. In this study, an automated MCS tracking algorithm and global reanalyses are used to examine the pre‐MCS environment for 3295 MCSs that occurred in the tropics in a 3‐month period. Results showed that increased water vapor and mesoscale ascent implied by low‐level convergence and upper‐level divergence preceded MCS formation by up to 24 h. Regional variations in pre‐MCS environment conditions were apparent and are discussed. Future work will study to what extent these moisture and wind anomalies can be used to predict MCS formation.