Effects Of Weather Research Articles

Mitigating the effects of extreme weather on crop yields: insights from farm management strategies in the Netherlands

Abstract Weather extremes can drive substantial crop losses. Farm level management strategies play a critical role in mitigating the impacts of and consequences for farmer livelihoods and food security. While the impacts of extreme weather on crop yields are well documented in recent studies, these predominantly focused on expansive geographical scales and commonly overlooked the critical role of management practices in modulating the dynamics of weather-crop sensitivities. In our study, a unique data-set is used that explores the timely relationship between extreme weather and crop yields at farm level in the Netherlands. We cover 10 types of crops and elucidate the role of soil types, irrigation and nutrient application in modulating the relationship between extreme weather and crops. We show substantial impacts from drought during the growing- and harvesting period and excessive precipitation during the planting- and growing period. Severe droughts show significant (p≤0.05) reductions in yield for all crops, and lead to yield reductions up to 24 percent relative to average yields during the growing period. Meanwhile, eight crops show significant reductions in yield due to severe water excess during the planting period, with yield reductions up to 18 percent. Soils such as sand or loess amplify the negative impact of drought on crop yield, while softening the impact of excessive precipitation. Irrigation and to a lesser extent nutrient application are shown to moderately decrease the impact of extreme weather on crop yield. Our findings contribute valuable insights to guide local adaptation priorities which are critical given the projected increase in the intensity and frequency of extreme weather under climate change.

The Impact of Crop Year and Crop Density on the Production of Sunflower in Site-Specific Precision Farming in Hungary

Sunflower is considered a plant with extraordinary adaptability. However, the conditions of growing sunflower function as a limiting factor in its production. The hybrids used in production tolerate weather variability to a different level and utilise the nutrient and water resources of the soil, while the yield is also affected by the number of plants per hectare. In this study, the authors attempted to observe the environmental effects influencing sunflower cultivation, the heterogeneous productivity zones of the given production site and the correlation of the number of seeding plants used under various farm practices. The average rainfall of 2021 and the dry weather of 2022 created suitable conditions for examining the yearly weather effect. In the selected experimental areas, three distinguishable zones were defined in terms of productivity. In each productivity zone, three crop density steps were used in four replicates. Based on the performed comparative tests, the rainy year of 2021 resulted higher yield than the drier year of 2022 in the average- and high productivity zones, while in the low-productivity zone, higher yields were harvested under the drier conditions of 2022 than in the rainy year of 2021. In 2021, with the improvement in productivity, the obtained yield was also higher. However, in 2022, this clarity could not be demonstrated. In the zones with low productivity, identical yield results were observed in both weather conditions. Based on the examination of the obtained results, it was shown that the effect of weather conditions and the given number of plants have a smaller influence on the yield results of low-productivity zones, while these factors have a greater influence on the yields of high-productivity zones.

Changes in snow‐dominated streamflow quantity and timing following an extensive wildfire in British Columbia

AbstractThe length and frequency of extreme fire weather has increased across the globe in recent decades, with potential deleterious consequences to streamflow quantity, timing and quality. Changes in the hydrologic regime following wildfire can have substantial downstream consequences, affecting communities and ecosystems through flooding, erosion, loss of habitat and degraded water quality. While there are many studies that address post‐wildfire hydrology across the globe, there are few studies in the snow‐dominated regions. The 2017 Elephant Hill wildfire in south‐central BC burned across or adjacent to four watersheds with long‐term streamflow gauges providing a rare opportunity to evaluate hydrologic change. Several approaches were used to identify patterns of change following the wildfire, all of which suggest increased post‐fire flows. The before‐after‐control‐impact design showed significant increases in annual, spring and summer water yield from the small (49 km2) Arrowstone Creek watershed (30%, 21% and 86%, respectively). Significant increases in spring water yield were observed in the larger (5318 km2) Bonaparte River watershed (48%). Annual and summer water yield increased in the Bonaparte River (31% and 58%, respectively) but these changes were not statistically significant. In both the Bonaparte River and Arrowstone Creek, the onset of spring freshet (26 days earlier in both) was significantly advanced, however, the timing of maximum snowmelt discharge was significantly advanced (27 days earlier) only in Arrowstone Creek. Smaller changes were also observed in the reference watersheds; however, these were not statistically significant. The difference in results between the small and large watershed, as well as the effects of weather and watershed attributes, highlight the need for continued research into the relationships between wildfire and hydrologic regime across diverse landscapes.

Mid-infrared Measurements of Ion-irradiated Carbonaceous Meteorites: How to Better Detect Space Weathering Effects

Remote sensing study of asteroids will soon enter a new era with an increasing amount of data available thanks to the JWST, especially in the mid-infrared (MIR) range that allows identification of mineral species. It will then be possible to establish a taxonomy, as is currently available in the visible–near-infrared range, based on MIR spectral parameters. It had been previously shown that the MIR range is very sensitive to space weathering (SpWe) effects. Thus, it is crucial to determine which spectral changes are involved to disentangle initial composition from surface aging and provide tools to interpret future remote sensing data of asteroids. We present here MIR measurements of a wide variety of ion-irradiated carbonaceous chondrites as a simulation of the solar wind SpWe component. We evaluate several parameters (the Christiansen feature and Reststrahlen band positions, the width of the main Si–O band) and test different measurement conditions (ion energy and geometry of observation). We highlight a dependency of the spectral changes with the initial composition, as hydrated samples are more affected than anhydrous ones. We confirm the role of the geometry in the detection of SpWe effects as already shown in the near-infrared, with a competition effect between the depth probed by photons and the implantation depth of ions (function of the energy used). We will discuss the results in the framework of future observations and Ryugu’s and Bennu’s samples studied in the laboratory.

Perpendicular Electrical Conductivity in the Topside Ionosphere Derived from Swarm Measurements

The study of the physical properties of the topside ionosphere is fundamental to investigating the energy balance of the ionosphere and developing accurate models to predict relevant phenomena, which are often at the root of Space Weather effects in the near-Earth environment. One of the most important physical parameters characterising the ionospheric medium is electrical conductivity, which is crucial for the onset and amplification of ionospheric currents and for calculating the power density dissipated by such currents. We characterise, for the first time, electrical conductivity in the direction perpendicular to the geomagnetic field, namely Pedersen and Hall conductivities, in the topside ionosphere at an altitude of about 450 km. For this purpose, we use eight years of in situ simultaneous measurements of electron density, electron temperature and geomagnetic field strength acquired by the Swarm A satellite. We present global statistical maps of perpendicular electrical conductivity and study their variations depending on magnetic latitude and local time, seasons, and solar activity. Our findings indicate that the most prominent features of perpendicular electrical conductivity are located at low latitudes and are probably driven by the complex dynamics of the Equatorial Ionisation Anomaly. At higher latitudes, perpendicular conductivity is a few orders of magnitude lower than that at low latitudes. Nevertheless, conductivity features are modulated by solar activity and seasonal variations at all latitudes.

Extremes of snow and temperature affect patterns of genetic diversity and differentiation in the alpine butterfly Parnassius smintheus.

Weather is an important short-term, local driver of population size and dispersal, which in turn contribute to patterns of genetic diversity and differentiation within species. Climate change is leading to greater weather variability and more frequent extreme weather events. While the effects of long-term and broad-scale mean climate conditions on genetic variation are well studied, our understanding of the effects of weather variability and extreme conditions on genetic variation is less developed. We assessed the influence of temperature and snow depth on genetic diversity and differentiation of populations of the alpine butterfly, Parnassius smintheus. We examined the relationships between a suite of variables, including those representing extreme conditions, and population-level genetic diversity and differentiation across 1453 single nucleotide polymorphisms, using both linear and gravity models. We additionally examined effects of land cover variables known to influence dispersal and gene flow in this species. We found that extreme low temperature events and the lowest recorded mean snow depth were significant predictors of genetic diversity. Extreme low temperature events, mean snow depth and land cover resistance were significant predictors of genetic differentiation. These results are congruent with known effects of early winter weather on population size and habitat connectivity on dispersal in P. smintheus. Our results demonstrate the potential for changes in the frequency or magnitude of extreme weather events to alter patterns of genetic diversity and differentiation.

An approach to interpreting natural indicators of the state of space weather to assess the effects of its impact on high-latitude power systems

The dynamic exploration and development of the Arctic zone of the Russian Federation is inextricably connected with the need to minimize technospheric risks, including those associated with the space weather effects on power equipment systems operated within the boundaries of the auroral oval. At the same time, accompanying monitoring of space weather parameters and geomagnetic field variations in the Arctic is carried out only through a group of satellites and several dozen magnetic stations located mainly in the United States, Canada, northern and central Europe. Obviously, the current situation practically excludes the possibility of promptly diagnostics of the level of geoinduced currents (GIC) for most of the Arctic zone of the Russian Federation, where in fact the only available indicator of the state of space weather is auroras. In the paper the authors propose an approach to interpreting the manifestation of auroras to assess the effects of space weather on objects and systems of high-latitude infrastructure. Thus, using the example of the “Vykhodnoy” substation of the “Severny Transit” main electrical network, it is shown that when recording auroras in the north, zenith and south, the most probable (averaged over 30 min) GIC level is 0.08, 0.23 and 0.68 A accordingly. In this case, the probability that the average half-hour GIC level will exceed 2 A (in the case of auroras in the north, zenith and south) is ∼6, ∼10 and ∼15%, respectively. In conclusion, ways of modernization and the limits of applicability of the proposed approach are considered.

Artificial Intelligence-Empowered Doppler Weather Profile for Low-Earth-Orbit Satellites.

Low-Earth-orbit (LEO) satellites are widely acknowledged as a promising infrastructure solution for global Internet of Things (IoT) services. However, the Doppler effect presents a significant challenge in the context of long-range (LoRa) modulation uplink connectivity. This study comprehensively examines the operational efficiency of LEO satellites concerning the Doppler weather effect, with state-of-the-art artificial intelligence techniques. Two LEO satellite constellations-Globalstar and the International Space Station (ISS)-were detected and tracked using ground radars in Perth and Brisbane, Australia, for 24 h starting 1 January 2024. The study involves modelling the constellation, calculating latency, and frequency offset and designing a hybrid Iterative Input Selection-Long Short-Term Memory Network (IIS-LSTM) integrated model to predict the Doppler weather profile for LEO satellites. The IIS algorithm selects relevant input variables for the model, while the LSTM algorithm learns and predicts patterns. This model is compared with Convolutional Neural Network and Extreme Gradient Boosting (XGBoost) models. The results show that the packet delivery rate is above 91% for the sensitive spread factor 12 with a bandwidth of 11.5 MHz for Globalstar and 145.8 MHz for ISS NAUKA. The carrier frequency for ISS orbiting at 402.3 km is 631 MHz and 500 MHz for Globalstar at 1414 km altitude, aiding in combating packet losses. The ISS-LSTM model achieved an accuracy of 97.51% and a loss of 1.17% with signal-to-noise ratios (SNRs) ranging from 0-30 dB. The XGB model has the fastest testing time, attaining ≈0.0997 s for higher SNRs and an accuracy of 87%. However, in lower SNR, it proves to be computationally expensive. IIS-LSTM attains a better computation time for lower SNRs at ≈0.4651 s, followed by XGB at ≈0.5990 and CNN at ≈0.6120 s. The study calls for further research on LoRa Doppler analysis, considering atmospheric attenuation, and relevant space parameters for future work.

Tectonic Geomorphology of Ultramafic Complex in Asera, North Konawe Regency

Ultramafic complex in Sulawesi have many potential from mining to environmental aspects. The process of weathering and tectonic is a key factor in understanding how to utilize these potential. Tectonic geomorphology by using morphometric indices and field observation has proven to be a beneficial method in distinguishing the topography and morphogenetic development of a region due to the complex interaction between erosional processes and tectonic movements. IAT measurement of 71 sub-basins shows that tectonic activity in the research area are divided into 4 classes with values ranging from 1,5 – 2,6. Field observation shows that morphologically the research area are faulted hills consist of peridotite, dunite and pyroxenite with various degree of weathering. The effect of weathering also reveal on the shape of sub-basins and drainage density in the research area. Tectonic activity present in the form of intensive joint on some parts, with no clear correlation with IAT Class. keyword: tectonic geomorphology, carbon capture storage, ultramafic, east Sulawesi ophiolite, morphometric indices

Stability Detection of Canopy RGB Images for Different Underlying Surfaces Based on SVM

This study aims to investigate the impact of different environmental conditions on the stability of RGB images in ecological sites and the anti-interference properties of vegetation images on different underlying surfaces. Three vegetation types including sugarcane, forest, and karst (mainly shrub and grass) are used to segment green vegetation using machine learning, and the RGB vegetation indices are calculated using color channel data. Then, The effect of weather, season, and time period on different types of vegetation indices are studied, which provide technical references for quantitative application of RGB image data. The results indicate the following: ① For the vegetation with high canopy density, the SVM machine learning segmentation algorithm used in this study is more applicable, as the RGB image segmentation accuracy of sugarcane and forest is significantly higher than karst. For different weather conditions, the segmentation accuracy of sugarcane and forest RGB images on sunny or cloudy days is higher than that on rainy or foggy days, but the effect on sparse vegetation in karst is not obvious. Additionally, the segmentation accuracy of different vegetation types has a small increase with NLM filter processing. ② Change in weather, season, and time can affect the stability of the image index. For different weather conditions, the vegetation indices of sugarcane and forest images on sunny or cloudy days are the more stable (ExGR, outlier proportion between 3.25% and 5.63%), while on rainy and foggy days they are less stable (ExR, outlier proportion between 17.60% and 21.59%). For different seasons, the stability of the sugarcane and karst image index obtained in spring is better (ExG, outlier proportion between 3.32% and 6.88%), while the stability of the forest image index obtained in summer is better (ExR, outlier proportion = 10.32%). For different times within a day, the sugarcane image index obtained in the morning is more stable (ExGR, outlier proportion = 4.62%), while the stability of the forest image index obtained in the afternoon is better (ExGR, outlier proportion = 9.24%). ③ The stability of the sugarcane image index is more affected by weather and season. For forest, the influence of the weather is more obvious than the season. But, for karst, the effect of season on the vegetation index is greater than that of weather.

Effects of Weather on the Severity of Menstrual Symptoms Among College- and High School-Going Women in the Southern Regions of Saudi Arabia.

The effects of weather on the severity of menstrual symptoms have been a topic of interest and research for many years. While some studies have shown a correlation between weather conditions and increased severity of menstrual symptoms, others have found no significant relationship. The current study aimed to assess the effects of weather on the severity of menstrual symptoms among women going to college and high school in the southern regions of Saudi Arabia. A descriptive cross-sectional study was conducted targeting all women going to college and high school in southern regions of Saudi Arabia. An online questionnaire was used for data collection. The data were entered and analyzed in IBM SPSS Statistics for Windows, version 26 (IBM Corp., Armonk, NY), and stored with no attempts to identify the participants. The study included 484 participants; most of them were 20-30 years old; 64.5% had regular menstrual cycles. It was observed that mood fluctuations, bloating, difficulty concentrating, breast pain, irritability, anxiety, social isolation, feeling tired, headaches, and mood changes are all affected to some degree before and during menstruation. On the other hand, the amount of blood, duration of the course, physical activity during menstruation, nutritional habits, lower back pain, and sleep disorders showed varying percentages of impact. These findings provide valuable insights into the physiological and psychological changes that occur during the menstrual cycle. In conclusion, the relationship between weather and the severity of menstrual symptoms is a complex and multifaceted topic. While some women may perceive a correlation between certain weather conditions and an increase in symptom severity, the scientific evidence in support of this connection is still limited and inconclusive. Further research is needed to better understand the underlying mechanisms and to provide evidence-based recommendations for managing menstrual symptoms in relation to weather conditions.

Spatiotemporal and weather effects on the reproductive success of piping plovers on Prince Edward Island, Canada.

Piping plovers (Charadrius melodus sp.) rank among North America's most endangered shorebird species, facing compounding environmental challenges that reduce habitat availability and suppress recruitment and survival rates. Despite these challenges, research on the direct effects of climate variability and extremes on their breeding ecology remains limited. Here, we employ a spatiotemporal modelling approach to investigate how location, nest timing and weather conditions influence reproductive success rates in a small breeding population of C. m. melodus in Prince Edward Island (PEI), Canada from 2011 to 2023. Analysis of 40 years of monitoring records from a subset of nesting sites revealed that flooding and predation have been persistent sources of reproductive failures in this population, with unexplained losses increasing in recent years. Contrary to our hypotheses, our modelled results did not support a negative impact of extreme high temperatures and strong precipitation events on reproductive outcomes. Instead, we identified a positive effect of T MAX and no effect of strong precipitation, perhaps due to limited exposure to extreme high temperatures (>32°C) and context-specific risks associated with precipitation-induced flooding. However, trends in regional climate change are likely to increase exposure to-and the influence of-such factors in the near future. Our models also identified spatiotemporal variability in apparent hatch success over the study period, as well as worse hatch outcomes across popular beachgoing regions and for delayed nesting attempts. While our results offer preliminary insights into factors affecting breeding success in this population, further research will be imperative to enhance understanding of constraints on recruitment. To this end, we encourage the collection and analysis of additional time-series data of prey populations, human activities, fine-scale weather data and predator/flood risks associated with each nest on PEI.

Monitoring of space radiation and electromagnetic transients by Moscow State University nano-satellites

Nano-satellites of cubesat format can be used effectively to study different aspects of space weather phenomena, such as high energy charge particle flux variations at near-Earth space as well as for monitoring cosmic gamma-ray bursts (GRBs) and hard X-ray and gamma-ray emission of solar flares. Using a constellation of CubeSats enables cost-effective synchronous measurements of radiation fluxes at different points in space, effectively separating the spatial and temporal effects of observed flux variations.Since July 5, 2019, M. V. Lomonosov Moscow State University (MSU) has realized its own program of cubesat employment. To the present date, 18 satellites in 1.5U, 3U, and 6U formats with the instruments developed at MSU have been launched, and 11 of them continue to operate on the solar-synchronous low-altitude orbits (400–600 km). The number of instruments elaborated especially for cubesats includes the universal Detector of Cosmic Radiation (DeCoR-1, DeCoR-2, and DeCoR-3 modifications), the Advanced Ultraviolet Radiometer (AURA, AURA-2) and the Complex Radiation Detector (CoRaD, i.e., KODIZ in Russian acronym). The DeCoR-1, DeCoR-2 and DeCoR-3 instruments allow for the detection of gamma-quanta and electrons in the energy ranges of 0.02–2.0 MeV and 0.3–10.0 MeV, respectively. The KODIZ instrument is intended especially to detect protons with energies higher than 300 MeV and electrons with energies higher than several MeV. The AURA and AURA-2 instruments are used to monitor atmospheric UV glow in ∼200–400 nm bands. Up until now, the good experience has been accumulated by using these instruments to measure different space weather effects, such as polar cups filling with solar cosmic rays, the dynamics of outer belt boundaries during geomagnetic storms, and electron precipitation in different areas of near-Earth space, including low-latitude regions. As a by-product, a number of GRB candidates were detected. The possibility of further development of multi-satellite group and perspectives to study the mentioned phenomena will be discussed in this paper.

Study on novel control method for small wind – solar hybrid power system using photovoltaic cooperating system in parallel connection mode

Currently, a small-scale wind turbine can be connected to the Power Conditioning System (PCS) of the solar power system by simulating the technical characteristics of the solar panels to enhance the efficiency of the PCS on cloudy or rainy weather days. However, the working efficiency of the entire system has not been optimized because the use of traditional control techniques. P-I control has several problems of high starting overshoot, and slow response to sudden disturbances. Besides, P&O MPPT control has fluctuations in output power and slow response time at peak solar cell power due to weather effects. Therefore, this research proposes a novel control system including Artificial Neural Networks (ANN) MPPT control and digital slide mode control (DMSC) for the power conversion circuit to connect small-scale wind turbine power with the PCS of the solar power system in the parallel mode. The novel control solution in this study can minimize the disadvantages of PI control and P&O MPPT control. The study results showed that DSMC controller has better performance than the PI controller when controlling the PVCS in parallel mode with more 17.5 % power, no static error, 20 % less chattering of the power value of PVCS in the steady state, and 20 % less static error of power. Besides, the ANN MPPT controller also works better when changing solar radiation and has a harvested power of about 0.6 % higher than the power generated by the P&O MPPT controller.

Weather conditions, climate change, and the price of electricity

We estimate the effect of temperature, wind speed, solar radiation, and precipitation on wholesale electricity prices for six European countries, analyzing the full distribution of the weather variables. We provide evidence on nonlinear and extreme weather effects on electricity prices. In all countries, reductions in temperature below a certain threshold increase electricity prices, yet these thresholds tend to be lower for colder countries than for warmer ones. In addition, warmer countries have an upper threshold above which temperatures also increase prices. The precipitation threshold is near the maximum for countries with limited hydroelectric generation and much lower for others with high hydropower capacity, such as Norway. Wind speed has a similar effect on electricity prices across countries, while irradiance has a statistically significant effect in countries with the highest solar capacity and higher average irradiance. Ultimately, the impact of weather conditions on electricity prices is influenced by a country's initial climatic conditions, generation mix, policies, energy efficiency levels, and behavioral factors. Policies aimed at reducing the disproportionately negative impacts of climate change on vulnerable populations should ideally be informed by accurate quantification of the impact of weather on electricity prices.

Effects of haze and weather in 2023 on crop maturation and yield in Ohio

Plain Language SummaryWildfire smoke in 2023 led to hazy conditions throughout the United States in late June and early July. Farmers often asked what effect the haze had on the weather as well as crop growth and development. This report used weather data from Ohio to measure the impacts of smoke and haze on light availability, and to determine how temperatures may have been affected. Light during the season was reduced by up to 9% during the months of May–August, but reductions in temperature were more likely caused by northerly wind patterns rather than the haze. Cooler seasonal temperatures also contributed to delayed maturation and grain drydown in corn. Despite the haze and cooler temperatures, the 2023 state average yield of corn, soybean, and wheat were highest in 10 years. If haze conditions had occurred later in the season, the effect on corn and soybean maturation and yield may have differed.

A Review on the Video-Based River Discharge Measurement Technique.

The hydrological monitoring of flow data is important for flood prevention and modern river management. However, traditional contact methods are increasingly struggling to meet the requirements of simplicity, accuracy, and continuity. The video-based river discharge measurement is a technique to monitor flow velocity without contacting the water body by using the image-recognition algorithms, which has been verified to have the advantages of full coverage and full automation compared with the traditional contact technique. In order to provide a timely summary of the available results and to inform further research and applications, this paper reviews and synthesizes the literature on the general implementation routes of the video-based river discharge measurement technique and the principles and advances of today's popular image-recognition algorithms for velocity detection. Then, it discusses the challenges of image-recognition algorithms in terms of image acquisition conditions, parameter uncertainties, and complex meteorological and water environments. It is concluded that the performance of this technique can be improved by enhancing the robustness and accuracy of video-based discharge measurement algorithms, minimizing weather effects, and improving computational efficiency. Finally, future development directions for further perfecting this technique are outlined.

Beach litter deposition and turnover, effects of tides and weather, and implications for cleanup strategies: A case study in the Lofoten archipelago, Norway

Plastic pollution is ubiquitous in the marine environment. Beach cleanups are considered a cost-effective mitigative measure with generally few negative environmental impacts. Beached litter is not static, however, and may wash back out to sea or be buried, meaning it is only temporarily available for cleanup. We studied deposition and turnover of litter on three Arctic beaches in Lofoten, Norway, biweekly for 31 months. The mean estimated daily deposition rate was 10 items/100 m, with a median residence time of 99 days. Both processes were impacted by seasons and weather and varied both spatially and temporally. Strong winds during the fall increased litter influx and onshore winds contributed to its loss. Heavier objects and those higher on the beach persisted longer yet were still subject to turnover. Snow temporarily buries litter but protects it in the long run. Given the turnover of litter, frequent (albeit smaller) cleanups can readily remove 3–4 times more litter from circulation in the environment than larger, infrequent cleanups. With limited resources, it is recommended to prioritise late fall cleanups.

How weather and built environment factors influence e-scooter ridership: Understanding non-linear and time varying effects

Our understanding of non-linear and time varying effects on shared e-scooter ridership dynamics is limited. Consequently, both operators and city councils supporting shared e-scooter schemes do not have the requisite information to help optimise infrastructure planning and operation management. Focussing on subtropical Brisbane, Australia, the current study examines time varying and non-linear effects of weather and built environment factors on shared e-scooter ridership. Results from XGBoost models reveal threshold relationships with both the availability of cycling infrastructure and the presence of park and commercial land uses. Additionally, we show how hot weather increases ridership especially around large parks and in commercial areas on both weekdays and weekends. Understanding the intricate (non-linear) interplay (interaction) between weather and built environment factors and their variation over time on shared e-scooter ridership have important implications for policymakers, transportation planners, and environmental advocates in providing the requisite evidence for data driven decision making.

Deep causal inference for understanding the impact of meteorological variations on traffic

Understanding the causal impact of meteorological variations on traffic conditions (e.g., traffic flow and speed) is crucial for effective traffic prediction and management, as well as the mitigation of adverse weather effects on traffic. However, many existing studies focused on establishing associations between meteorological situations and traffic, rather than delving into causal relationships, especially with deep learning techniques. Consequently, the ability to identify specific meteorological conditions that significantly contribute to traffic congestion or delays is still limited. To address this issue, this study proposes the Meteorological-Traffic Causal Inference Variational Auto-Encoder Model (MT-CIVAE) to estimate the causal impact of fine-grained meteorological variations (e.g., rain and temperature) on traffic. Specifically, MT-CIVAE is based on the Variational Auto-Encoder and consists of an encoder to recover the distribution of latent confounders and a decoder to estimate the conditional probabilities of treatments. Transformer encoder layers are incorporated to analyze the spatial and temporal correlations of historical traffic data to further enhance the inference capability. To evaluate the effectiveness of the proposed approach for causal inference, real-world traffic flow and speed datasets collected from California, along with corresponding fine-grained meteorological datasets, are employed. The counterfactual analysis is conducted using artificially generated meteorological conditions as treatments, which allows for the simulation of hypothetical meteorological scenarios and the evaluation of their potential impact on traffic conditions. This study develops deep learning methods for assessing the causal impact of meteorological variations on traffic dynamics, offering explanations and insights that can assist transportation institutions in guiding post-meteorology traffic management strategies.