Weather Variables Research Articles

Burn Period: A use-inspired metric to track wildfire risk across Arizona and New Mexico in the southwest U.S.

Abstract Numerous tools and indices exist for wildland fire managers to anticipate and track changes in wildfire risk driven by variability in weather and climate conditions at hourly to seasonal scales. However, in working closely with southwest U.S. managers, we learned of a simple meteorological metric being informally used, but not widely accessible in existing tools or information products, to gauge short-term changes in wildfire risk. This metric, termed ‘Burn Period’ (BP), is the local count of hours per day with relative humidity values equal to or less than 20%. Our collaboration led to the development of an experimental tool called the ‘Burn Period Tracker’ to ease access and promote use of BP values for planning and response. This study is a climatological analysis of BP values at 124 fire weather stations across Arizona and New Mexico for the period 2000-2022 to aid in interpretation and understanding of this use-inspired metric. BP values reflect the strong seasonality in temperature and moisture deficit-driven wildfire risk across the southwest U.S., with risk climbing through the arid spring season, peaking in June, and then falling rapidly with the onset of the summer monsoon in July. Regression analyses show that short-term variability in BP values are driven by variability in low level atmospheric moisture in all months with strongest relationships during the summer after the onset of the monsoon. This study highlights the utility of BP as a short-term wildfire planning tool as well as an example of collaborative weather and climate services development.

Livelihood diversification and household welfare among farm households in the Philippines

AbstractDiversification of income sources is one of the most common strategies households employ to minimize household income variability and to ensure a minimum level of income that guarantee their food security. This study examines the impact of livelihood diversification on farm profits among smallholder rice farmers in the Central Luzon Region (CLR) of the Philippines using long‐term farm‐level panel data spanning from 1966 to 2016. We employed a random‐effects ordered probit model to investigate the drivers of livelihood diversification and then used the mixed Markov chain model to analyze the transition of households from less to more diversified livelihoods and its impact on farm profits over time. Our findings reveal substantial diversification among households over time. In particular, the elevation of the farm location is a key driver of rice farm households’ probability to diversify. The estimates show that an increase in the latitude of the farm location increases the probability of rice farmers in the CLR to diversify. We find that 64% of the rice farm households constitute farmers for whom diversification can be a strategy for survival. For medium‐ to high‐profit farm categories, diversification tends to protect farmers against farm profit losses arising from adverse climatic and weather variability.

Automatic cleaning suggestion adapting to real-time soiling status of solar farms

Solar farms are subject to various environmental factors that can affect their performance and output. One of the major factors is soiling. Consequently, it is essential to monitor and mitigate the effects of soiling on solar panels to ensure optimal performance and maximum profitability of a solar farm. In this paper, we present a novel cleaning intervention strategy that adapts to the present solar panel performance status to detect cleaning requirements for maximizing profit. This algorithm works with onsite insolation and panel data to give live feedback on cleaning requirements. Moreover, unlike other models in the literature, this method does not require historical or a priori insolation, weather, or soiling data. We have comprehensively tested the algorithm through experiment and simulation under various conditions (i.e., seasonal rain, few annual rainfall or sandstorms, unpredictable dust accumulation). The results show that the adaptive cleaning algorithm, even with no historical insolation or soiling information, outperforms optimal periodic cleaning strategies in terms of net revenue. The adaptive cleaning suggestion system shows significant advantages especially in locations with high variability in weather and soiling conditions. The algorithm is also suitable for practical deployment in solar farms near industrial or construction zones where sudden dust accumulation can occur. Our adaptive model will maximize profit in such unpredictable soiling scenarios, while in comparison, it is not even possible to utilize historical information-based cleaning cycle model in such cases.

Forecast of consumption of natural gas in U.S. based on time series analysis and ARIMA model

Natural gas is a widely used fossil fuel, playing a vital role in both industrial and economic sectors. As a widely used fossil fuel, the prediction of natural gas consumption is crucial for industrial and economics and hence many scholars have been researched on the topic. Due to the weather variation and the sensitivity of industrial demand, a precise consumption forecast is difficult. In the article, ARIMA model, a widely used model in time series analysis and forecasts would be considered in the prediction for consumption for future one year. It turns out that, in the next year, the consumption of natural gas in the coming year is stable and will stay at a still level and the overall trend of the series is increasing, with no significant short-term fluctuations. Therefore, the article suggested that long-term investment in industries related to natural gas is recommended. Besides, short-term investment is not suggested compared to the long-term due to the still level of the consumption within one year.

Antipredator responses of bats during short boreal nights with variable climatic conditions

Abstract The threat of predation can influence the behavior of animals. To minimize the impact of predation, animals rely on antipredatory responses and effectively balance these responses with other activities to maximize survival. Boreal bats are nocturnal animals that must forage within a narrow time frame during short, light summer nights with unpredictable weather. Despite having no specialized predators, boreal bats are still subject to predation. However, whether they express antipredatory responses has not been established. We studied antipredatory responses and responses to climatic conditions in boreal bats in 2 settings: 1) during roost emergence; and 2) during foraging within Tawny Owl territories and at locations with no Tawny Owl sightings. Acoustic data were collected at 23 roosts and 10 foraging grounds. Two controlled predation threats were used—playbacks of Tawny Owl calls and fledgling calls. Fledgling calls were only played during roost emergence. In both experiments, music and no treatment were used as controls. We also incorporated weather variables in the model. According to our results, bats tend to delay their emergence by 16 min when Tawny Owl calls were played outside the roost, but this effect was not noticeable when weather variables were included. There was no difference in exit time when music or fledgling sounds were played. While foraging, bats reduced their activity in Tawny Owl territories when calls of owls or music were played compared to no treatment. These results suggest that bats might display variable antipredatory responses, but weather influences behavior of bats more than predation risk, highlighting the importance of energy-saving strategies at northerly latitudes.

The LTAR Croplands Common Experiment at Upper Mississippi River Basin-Ames.

Agricultural systems evolve from the interactions of climate, crops, soils, management practices (e.g., tillage, cover crops, nutrient management), and economic risks and rewards. Alternatives to the corn (Zea mays L.)-soybean [Glycine max (L.) Merr.] (C-S) cropping systems that dominate in the US Midwest may provide more sustainable use of resources, reduce the documented environmental impacts of current C-S systems, and improve production efficiency and ecosystem services. Innovative management practices are needed to offer producers options to increase farm resilience to variable weather conditions and offset negative environmental impacts. In response to this need, the Upper Mississippi River Basin Long-Term Agroecosystem Research network site at Ames, IA, established a cropland experiment in 2016 to investigate an alternative crop management system that includes reduced tillage, cover crops, and right source, right rate, right time, and right place (4R) nitrogen (N) management. The experimental site is located on the Iowa State University Kelley Research Farm in Boone County, IA. Crop, soil, air, and tile drainage water measurements are made throughout the year using published methods for each agronomic and environmental metric. Our goal is to provide quantitative information to farmers, consultants, agribusiness partners, and state and federal agencies to help guide decisions on the effective use of alternative management practices. Future changes in experimental treatments will adopt a knowledge co-production approach whereby researchers and stakeholders will work collaboratively to identify problems, implement research protocols, and interpret results.

RUFCO: a deep-learning framework to post-process subseasonal precipitation accumulation forecasts

Abstract Post-processing is a critical step in attaining calibrated and reliable probabilistic forecast output from numerical weather prediction models. A novel deep-learning framework is proposed to post-process 20 years of 7- and 14-day precipitation accumulation reforecasts from the Global Ensemble Forecast System at subseasonal timescales (week 1, week 2, and combined weeks 3-4 forecasts) over the contiguous United States. The network builds upon previous studies and is a combination of three parallel-trained components suitable for subseasonal prediction. The first is a ResUnet architecture which learns non-linear relationships between binned observed precipitation and input images of weather and geographical variables. The second conditions the network to the month-of-year via a Feature-wise Linear Modulation (FiLM) layer. The third helps the network learn when to revert the forecast to that of climatology. The RUFCO (named for its components ResUnet, FiLM, and Climatological-Offramp) forecasts are compared against raw and climatological forecasts as well as those from a state-of-the-art distributional regression post-processing model, “CSGD,” and a simple bias-corrected model. At week 1, every method exhibited a competitive advantage over climatological forecasts. At week 2, RUFCO generated forecasts with statistically significant improvement over climatology at 82-94% of the domain, beating CSGD’s coverage of 76-90% of the grid points. At week 3, RUFCO’s skillful coverage was 65-85% while CSGD’s dropped to only 12-37%. At the longer lead times, RUFCO achieved the highest domain-averaged skill scores across seasons. However, the network tends to “smooth” forecast skill making it less competitive with CSGD in limited areas with strongly spatially-varying biases.

Dynamical downscaling and data assimilation for a cold-air outbreak in the European Alps during the Year Without a Summer of 1816

Abstract. The “Year Without a Summer” in 1816 was characterized by extraordinarily cold and wet periods in central Europe, and it was associated with severe crop failures, famine, and socio-economic disruptions. From a modern perspective, and beyond its tragic consequences, the summer of 1816 represents a rare opportunity to analyze the adverse weather (and its impacts) after a major volcanic eruption. However, given the distant past, obtaining the high-resolution data needed for such studies is a challenge. In our approach, we use dynamical downscaling, in combination with 3D variational data assimilation of early instrumental observations, for assessing a cold-air outbreak in early June 1816. We find that the cold spell is well represented in the coarse-resolution 20th Century Reanalysis product which is used for initializing the regional Weather Research and Forecasting Model. Our downscaling simulations (including a 19th century land use scheme) reproduce and explain meteorological processes well at regional to local scales, such as a foehn wind situation over the Alps with much lower temperatures on its northern side. Simulated weather variables, such as cloud cover or rainy days, are simulated in good agreement with (eye) observations and (independent) measurements, with small differences between the simulations with and without data assimilation. However, validations with partly independent station data show that simulations with assimilated pressure and temperature measurements are closer to the observations, e.g., regarding temperatures during the coldest night, for which snowfall as low as the Swiss Plateau was reported, followed by a rapid pressure increase thereafter. General improvements from data assimilation are also evident in simple quantitative analyses of temperature and pressure. In turn, data assimilation requires careful selection, preprocessing, and bias-adjustment of the underlying observations. Our findings underline the great value of digitizing efforts of early instrumental data and provide novel opportunities to learn from extreme weather and climate events as far back as 200 years or more.

Revealing the Feedback Loop: Comparing Satellite and Sensor-derived Meteorological Parameters in Groundnut Cultivation

Background: Studying soil moisture’s impact on groundnut, particularly under rainfed conditions, is crucial for improving quality and yield. This research explores soil moisture dynamics using satellite and in-situ sensor data to enhance water management and crop predictions, focusing on the feedback mechanisms between soil moisture and weather variables. Methods: The study was conducted at the Oil Seed Research Station (TNAU) in Tindivanam, Tamil Nadu, using the groundnut variety TMV 14. Soil moisture and weather parameters were monitored at critical crop growth stages, using an in-situ soil moisture sensor (Cr 300) and compared with satellite data from SMAP, ERA5 and Sentinel 1A with environmental factors. Statistical analysis was carried out using SAS JMP Pro and network analysis via Cytoscape 3.8.2 software. Result: Pre-monsoon soil moisture SMAP, SMAP-RZSM and sensor (VWC at 10cm) were found to increase in post-monsoon. Strong positive correlations were attained between SMAP-SM and SMAP-RZSM (r=0.94), indicating a reinforcing loop. Whereas, the negative feedback was observed between SMAP-SM and deeper soil temperatures (-0.91). It underscores the dynamic interplay between soil moisture and atmospheric conditions, essential for developing efficient water management strategies and enhancing crop resilience to climate variability.

Performance Comparison of Bio-Inspired Algorithms for Optimizing an ANN-Based MPPT Forecast for PV Systems.

This study compares bio-inspired optimization algorithms for enhancing an ANN-based Maximum Power Point Tracking (MPPT) forecast system under partial shading conditions in photovoltaic systems. Four algorithms-grey wolf optimizer (GWO), particle swarm optimization (PSO), squirrel search algorithm (SSA), and cuckoo search (CS)-were evaluated, with the dataset augmented by perturbations to simulate shading. The standard ANN performed poorly, with 64 neurons in Layer 1 and 32 in Layer 2 (MSE of 159.9437, MAE of 8.0781). Among the optimized approaches, GWO, with 66 neurons in Layer 1 and 100 in Layer 2, achieved the best prediction accuracy (MSE of 11.9487, MAE of 2.4552) and was computationally efficient (execution time of 1198.99 s). PSO, using 98 neurons in Layer 1 and 100 in Layer 2, minimized MAE (2.1679) but had a slightly longer execution time (1417.80 s). SSA, with the same neuron count as GWO, also performed well (MSE 12.1500, MAE 2.7003) and was the fastest (987.45 s). CS, with 84 neurons in Layer 1 and 74 in Layer 2, was less reliable (MSE 33.7767, MAE 3.8547) and slower (1904.01 s). GWO proved to be the best overall, balancing accuracy and speed. Future real-world applications of this methodology include improving energy efficiency in solar farms under variable weather conditions and optimizing the performance of residential solar panels to reduce energy costs. Further optimization developments could address more complex and larger-scale datasets in real-time, such as integrating renewable energy sources into smart grid systems for better energy distribution.

Smart Grid Forecasting with MIMO Models: A Comparative Study of Machine Learning Techniques for Day-Ahead Residual Load Prediction

With the fast expansion of intermittent renewable energy sources in the upcoming smart grids, simple and accurate day-ahead systems for residual load forecasts are urgently needed. Machine learning strategies can facilitate towards drastic cost minimizations in terms of operating-reserves avoidance to compensate the mismatches between the actual and forecasted values. In this study, a multi-input/multi-output model is developed based on artificial neural networks to map the relationship between different predictor inputs, including time indices, weather variables, human activity parameters, and energy price indicators, and target outputs such as wind and photovoltaic generation. While the information flows in only one direction (from the predictor nodes through the hidden layers to the target node), benchmark training algorithms are employed and assessed under different case studies. The model is evaluated under both parametric and non-parametric formulations, namely neural networks and Gaussian process regression. Essential improvements are achieved by enhancing the number of embedded predictors, while superior performance is observed by using Bayesian regularization mechanisms. In terms of mean-error indices and determination coefficient, this opens the pathway towards minimization via Bayesian inference-based approaches in the presence of increased and highly stochastic renewable inputs.

An Integrated Approach for Development of a Decision Support System for Early Surveillance of Japanese Encephalitis: a Remote Sensing-based study in Conjunction with Epidemiological Scenario in Assam, India

Abstract. Japanese Encephalitis (JE) is one of the serious mosquito borne viral diseases mostly prevalent in India and many of the South Asian countries. A comprehensive study was conducted in Dibrugarh, a JE endemic district of Assam taking into the account of the environmental and social factors that determine the outbreak of the disease. Effect of environmental and climatic factors on mosquito vector densities was investigated using geospatial tools and techniques. Wetlands were found to be the most preferred habitat type for most of the JE-transmitting mosquitoes followed by paddy-growing areas and ponds. The villages abundant with these habitats or located nearby were found to be more vulnerable to JE risk. Based on the spatial distribution of habitat types, villages in the district were divided into three categories of vector abundance and hence the risk of JE. It is found that rainfall (intensity as well as duration) is the most significant determinant in the modulation of mosquito density followed by temperature. It is also observed that the derived models could explain about 61% to 73% variation in mosquito density due to change in weather variables as indicated by R2 values of the Models. Among socio-economic determinants, pig rearing habit of the villagers was found to be most significant. JE risk map was prepared by integrating vector abundance map with the map of host abundance in GIS domain. Attempts were also made to forecast the intensity of JE cases based on a time series analysis of historical morbidity pattern, whereas forecast for onset of the disease was based on the modulation of weather variables in the study area. A web-based decision support system (DSS) developed by integrating the forecasts of JE onset, intensity and JE prone villages has been provided to the concerned health authorities to take timely intervention measures. The JE early warning system developed for Dibrugarh district was extended to two more JE prone districts viz, Sibsagar and Tinsukia as validation sites and observed that the accuracy of forecast was within the range of 69% to 77%. DSS on JE has opened up new opportunities to study similar vector-borne diseases of the JE serogroup viz., West Nile.

Seasonal and monthly stroke incidence in relation to weather variables: a preliminary single-centre epidemiologic study

This single-centre epidemiologic study investigated seasonal/monthly stroke incidence and stroke-related mortality in relation to weather variables, gender, age, as well as stroke subtype and stroke aetiology. The study involved 638 patients hospitalised due to stroke at the Neurology Ward with a stroke unit at the Regional Hospital in Poland, during one complete calendar year. The data collected included the date of admission to the ward, year of birth, sex, type and subtype of stroke relative to the aetiology and location within different arteries as well as mortality. The data related to wind speed, atmospheric pressure, and temperature were acquired from the archive at the weather station in Tarnów, Poland. Majority of the patients in the study group were aged 66–85 years (57.2%), and there were more women than men. Ischaemic stroke was significantly more common than haemorrhagic stroke (87 vs 13%). Large artery atherosclerosis was the predominant cause of stroke, particularly in June and October, and total anterior circulation stroke (TACS) was the most common type, particularly in January and December. The analysis showed that stroke type and aetiology, as well as weather variables such as temperature and pressure, were associated with stroke incidence and mortality rates. The findings suggest that both high and low temperatures may contribute to an increased stroke incidence, as significant differences in the number of stroke cases are observed during periods of extreme temperatures. Therefore, increased vigilance is necessary during periods of both hot and cold weather. Further research is needed to better understand these relationships and develop effective prevention strategies.

Phenological Adaptation of Wheat Varieties to Rising Temperatures: Implications for Yield Components and Grain Quality.

This study examined the effects of late sowing, water restrictions, and interannual weather variations on wheat grain yield and quality through field trials in Spain over two growing seasons. Delayed sowing and water scarcity significantly reduced yields, with grain quality mainly affected under rainfed conditions. Early-maturing varieties performed better in these conditions, benefiting from lower temperatures and extended grain-filling periods, leading to higher solar radiation interception, potentially increased photosynthetic activity, and improved yields. These varieties also saved water through reduced total cumulative evapotranspiration from sowing to maturity (ETo TOT), which was advantageous in water-limited environments. In contrast, late-maturing varieties were exposed to higher maximum temperatures during grain filling and experienced greater ETo TOT, leading to lower yields, reduced hectoliter weight, and a lower P/L ratio (tenacity/extensibility). This study highlighted the importance of optimizing temperature exposure and evapotranspiration for improved grain yield and quality, especially under climate change conditions with higher temperatures and water shortages. Notably, it established, for the first time, the importance of phenology on wheat quality of different varieties, suggesting that targeted selection for specific phenology could mitigate the negative impacts of heat stress not only on grain yield but also on grain quality.

Cointegration Analysis of Crop Yields and Extreme Weather Factors Using Actuaries Climate Index with Application of Bonus–Malus System

This article analyzes the long-term temporal co-movement of the extreme weather variables in the Actuaries Climate Index (ACI) and crop yields, modeling their relationship using an error correction model (ECM). The analysis suggests that significant weather variables can serve as trigger parameters in the pricing framework of weather index crop insurance. To address the challenge of weather index crop insurance while preserving the advantages of a bonus–malus system (BMS), we propose a transition rule that distinguishes between damages caused by severe weather and those resulting from the policyholder’s decisions. Subsequently, we also explore the challenges of implementing such a new hybrid BMS for crop insurance where extreme weather outcomes are integrated into the classical BMS.

Severity of a megafire reduced by interactions of wildland fire suppression operations and previous burns

Abstract Burned area and proportion of high severity fire have been increasing in the western USA, and reducing wildfire severity with fuel treatments or other means is key for maintaining fire-prone dry forests and avoiding fire-catalyzed forest loss. Despite the unprecedented scope of firefighting operations in recent years, their contribution to patterns of wildfire severity is rarely quantified. Here we investigate how wildland fire suppression operations and past fire severity interacted to affect severity patterns of the northern third of the 374 000 ha Dixie Fire, the largest single fire in California history. We developed a map of the intensity and type of suppression operations and a statistical model of the Composite Burn Index (CBI) including weather, fuels, and terrain variables during the fire to quantify the importance of operations and prior fires on wildfire severity. Wildfire severity was estimated without operations and previous fires and then compared with modeled severity under observed conditions. Previous low and moderate-severity fire without operations decreased CBI by 38% and 19% respectively. Heavy operations and offensive firing in the footprint of past fires lowered fire severity even more compared to prior fire alone. Medium operations and defensive firing reduced but did not eliminate the moderating effects of past fires. This analysis demonstrates important interactions between suppression operations and previous burns that drive patterns of fire severity and vegetation dynamics in post-fire landscapes. Given the need to reduce wildfire severity to maintain forest resilience, particularly with a warming climate, increased attention to using operations and severity patterns of previous fires known to reduce wildfire severity in megafires are likely to increase forest resilience and improve ecological outcomes.

Associations between environmental factors and running performance: An observational study of the Berlin Marathon.

Extensive research has delved into the impact of environmental circumstances on the pacing and performance of professional marathon runners. However, the effects of environmental conditions on the pacing strategies employed by marathon participants in general remain relatively unexplored. This study aimed to examine the potential associations between various environmental factors, encompassing temperature, barometric pressure, humidity, precipitation, sunshine, cloud cover, wind speed, and dew point, and the pacing behavior of men and women. The retrospective analysis involved a comprehensive dataset comprising records from a total of 668,509 runners (520,521 men and 147,988 women) who participated in the 'Berlin Marathon' events between the years 1999 and 2019. Through correlations, Ordinary Least Squares (OLS) regression, and machine learning (ML) methods, we investigated the relationships between adjusted average temperature values, barometric pressure, humidity, precipitation, sunshine, cloud cover, wind speed, and dew point, and their impact on race times and paces. This analysis was conducted across distinct performance groups, segmented by 30-minute intervals, for race durations between 2 hours and 30 minutes to 6 hours. The results revealed a noteworthy negative correlation between rising temperatures and declining humidity throughout the day and the running speed of marathon participants in the 'Berlin Marathon.' This effect was more pronounced among men than women. The average pace for the full race showed positive correlations with temperature and minutes of sunshine for both men and women. However, it is important to note that the predictive capacity of our model, utilizing weather variables as predictors, was limited, accounting for only 10% of the variance in race pace. The susceptibility to temperature and humidity fluctuations exhibited a discernible increase as the marathon progressed. While weather conditions exerted discernible influences on running speeds and outcomes, they did not emerge as significant predictors of pacing.

Short-term associations of diarrhoeal diseases in children with temperature and precipitation in seven low- and middle-income countries from Sub-Saharan Africa and South Asia in the Global Enteric Multicenter Study.

Diarrhoeal diseases cause a heavy burden in developing countries. Although studies have described the seasonality of diarrhoeal diseases, the association of weather variables with diarrhoeal diseases has not been well characterized in resource-limited settings where the burden remains high. We examined short-term associations between ambient temperature, precipitation and hospital visits due to diarrhoea among children in seven low- and middle-income countries. Hospital visits due to diarrhoeal diseases under 5 years old were collected from seven sites in The Gambia, Mali, Mozambique, Kenya, India, Bangladesh, and Pakistan via the Global Enteric Multicenter Study from December 2007 to March 2011. Daily weather data during the same period were downloaded from the ERA5-Land. We fitted time-series regression models to examine the relationships of daily diarrhoea cases with daily ambient temperature and precipitation. Then, we used meta-analytic tools to examine the heterogeneity between the site-specific estimates. The cumulative relative risk (RR) of diarrhoea for temperature exposure (95th percentile vs. 1st percentile) ranged from 0.24 to 8.07, with Mozambique and Bangladesh showing positive associations, while Mali and Pakistan showed negative associations. The RR for precipitation (95th percentile vs. 1st percentile) ranged from 0.77 to 1.55, with Mali and India showing positive associations, while the only negative association was observed in Pakistan. Meta-analysis showed substantial heterogeneity in the association between temperature-diarrhoea and precipitation-diarrhoea across sites, with I2 of 84.2% and 67.5%, respectively. Child diarrhoea and weather factors have diverse and complex associations across South Asia and Sub-Saharan Africa. Diarrhoeal surveillance system settings should be conceptualized based on the observed pattern of climate change in these locations.

Forecasting urban water demand using different hybrid-based metaheuristic algorithms’ inspire for extracting artificial neural network hyperparameters

This research offers a novel methodology for quantifying water needs by assessing weather variables, applying a combination of data preprocessing approaches, and an artificial neural network (ANN) that integrates using a genetic algorithm enabled particle swarm optimisation (PSOGA) algorithm. The PSOGA performance was compared with different hybrid-based metaheuristic algorithms’ behaviour, modified PSO, and PSO as benchmarking techniques. Based on the findings, it is possible to enhance the standard of initial data and select optimal predictions that drive urban water demand through effective data processing. Each model performed adequately in simulating the fundamental dynamics of monthly urban water demand as it relates to meteorological variables, proving that they were all successful. Statistical fitness measures showed that PSOGA-ANN outperformed competing algorithms.

Drone Insights: Unveiling Beach Usage through AI-Powered People Counting

Ocean beaches are a major recreational attraction in many coastal cities, requiring accurate visitor counts for infrastructure planning and value estimation. We developed a novel method to assess beach usage on the Gold Coast, Australia, using 507 drone surveys across 24 beaches. The surveys covered 30 km of coastline, accounting for different seasons, times of day, and environmental conditions. Two AI models were employed: one for counting people on land and in water (91–95% accuracy), and another for identifying usage types (85–92% accuracy). Using drone data, we estimated annual beach usage at 34 million people in 2022/23, with 55% on land and 45% in water—approximately double the most recent estimate from lifeguard counts, which are spatially limited and prone to human error. When applying similar restrictions as lifeguard surveys, drone data estimated 15 million visits, aligning closely with lifeguard counts (within 9%). Temporal (time of day, day of the week, season) and spatial (beach location) factors were the strongest predictors of beach usage, with additional patterns explained by weather variables. Our method, combining drones with AI, enhances the coverage, accuracy, and granularity of beach monitoring, offering a scalable, cost-effective solution for long-term usage assessment.