Weather Data Research Articles

Changes in cranberry phenology from 1958 to 2022: Implications for spring frost protection in Massachusetts, United States.

Warmer temperatures associated with climate change have affected the phenology of most plants, but limited information exists for the American cranberry (Vaccinium macrocarpon Ait.), an important specialty crop. We examined long-term spatiotemporal trends in spring development of cranberry buds using field observations of cranberry bud stages over a 65-yr period, spanning from 1958-2022. A growing degree day (GDD) model was further used to interpret the observed trends in bud development over the study period. To assess spatial variability in cranberry bud development, the GDDs were computed using gridded weather data for four counties of Massachusetts, representing 85% of the state's cranberry acreage. A Theil-Sen linear regression model was implemented to determine trends in the occurrence of the bud stages. Field observations revealed significant temporal trends (p-value < 0.01) in the annual timing of white bud and cabbage head stages, occurring 18-20 days earlier in the spring than 65 years ago. This earlier bud development can increase the risk of frost damage, especially during late-spring freezes. GDDs accumulated at a faster rate towards the end of the study period due to rising air temperatures. Analysis of 65 years of gridded data revealed a significant trend of earlier development across the four counties. The rate of advancement in cabbage head stage ranged from -0.15 to -0.25 d yr -1 across the study area. These findings highlight the need for updated frost forecasting models that account for the changing growth schedule of cranberry.

Advancements in Wind Power Forecasting: A Comprehensive Review

Accurate wind power forecasting is essential for the seamless integration of wind energy into modern power systems, yet it remains a challenging task due to the inherent variability of wind, complex atmospheric dynamics, and the influence of local terrain. Traditional forecasting models often struggle to capture these complexities, particularly for short-term and intra-hour predictions. This gap necessitates a shift towards machine learning (ML) methodologies, which have emerged as transformative tools in addressing these challenges. By leveraging large datasets and advanced algorithms, ML models can identify intricate patterns and significantly enhance prediction accuracy. Techniques such as deep learning, ensemble methods, and hybrid approaches integrate weather data with historical power output, improving both spatial and temporal resolutions. Despite their promise, challenges such as data quality, model interpretability, and computational demands require further research to fully optimize ML applications in wind power forecasting. The global transition toward smart grids, driven by the increasing penetration of renewable energy sources (RES), underscores the importance of reliable forecasting. Wind energy, as a key RES, plays a pivotal role in reducing greenhouse gas emissions and mitigating global warming. However, the stochastic nature of wind energy complicates power system analysis and management. Accurate forecasting is critical for enhancing power system security, supporting sustainability, and facilitating economic transactions in energy markets. This review examines ML-based methodologies for wind power forecasting, categorizing them into supervised, unsupervised, semi-supervised, and reinforcement learning techniques. It highlights their adaptability, scalability, and real-time capabilities while addressing challenges posed by noisy data, dynamic system behaviors, and complex grid configurations. Hybrid and ensemble models, in particular, demonstrate exceptional potential in overcoming these challenges. Furthermore, this study provides a detailed summary of the latest advancements in wind power forecasting using AI-based approaches. Key aspects such as data preparation, feature selection, and model assessment are explored, offering insights into improving both the precision and efficiency of wind energy prediction algorithms. By identifying research gaps and emerging trends, this review presents strategic directions for the development of innovative ML-driven forecasting methods. Ultimately, the findings underscore the significance of integrating advanced ML techniques to enhance forecasting reliability, support effective grid management, and contribute to a sustainable energy future.

PREDICTING SOLAR POWER GENERATION: A MACHINE LEARNING APPROACH FOR GRID STABILITY AND EFFICIENCY

In countries with high levels of insolation, the demand for renewable energy sources has driven the rapid emergence and growth of solar power plants. Maintaining grid stability and efficient power management in response to weather variations that affect solar radiation intensity and battery consumption limits remains a major challenge. This study aims to develop a machine learning-based prediction model to estimate the electricity generated by solar power plants using weather data. Four algorithms are utilized: Linear Regression, Random Forest Regressor, Decision Tree Regressor, and Gradient Boosting Regressor. The results show that the Random Forest algorithm produces the best model, with MAE and RMSE values of 0.1114281 and 0.3187232, respectively. This research contributes to the literature, particularly on the relatively unexplored topic of using multiple machine learning models to predict energy output from photovoltaic systems. The findings have the potential to inform more efficient energy policies and improve energy integration technologies for grid-connected solar power systems.

Transparency in AI for emergency management: building trust and accountability

Abstract Artificial intelligence (AI) stands at the forefront of transforming emergency management, offering unprecedented capabilities in disaster preparedness and response. Recent implementations demonstrate this shift from reactive to proactive approaches, particularly through flood prediction algorithms and maritime search-and-rescue optimization systems that integrate real-time vessel locations and weather data. However, the current landscape reveals a critical challenge: the opacity of AI systems creates a significant trust deficit among emergency responders and communities. Research findings paint a concerning picture of this transparency gap. A comprehensive survey of emergency management AI systems reveals striking statistics: 68% lack adequate documentation of their data sources, while 42% fail to provide clear justifications for their recommendations. This “black box” phenomenon carries serious implications, particularly when flood prediction models disproportionately affect vulnerable populations or when opaque decision-making processes lead to suboptimal resource allocation during critical rescue operations. Analysis of real-world applications in flood preparedness and search-and-rescue operations exposes systematic communication deficiencies within these essential emergency response frameworks. The research examines how varying levels of AI transparency directly influence emergency responders' decision-making during crises, exploring the delicate balance between operational openness and security considerations. These findings highlight an urgent need for robust oversight mechanisms and context-specific transparency protocols to ensure ethical AI deployment in emergency management. The evidence points toward a clear solution: developing human-centric approaches that enhance rather than replace human capabilities in emergency response. This strategy requires establishing tailored transparency guidelines and monitoring systems that address current challenges while facilitating effective AI integration. By prioritizing both technological advancement and human oversight, emergency management systems can better serve their critical public safety mission.

Short-Term Traffic Flow Prediction Considering Weather Factors Based on Optimized Deep Learning Neural Networks: Bo-GRA-CNN-BiLSTM

Accurately predicting road traffic flows is a primary challenge in the development of smart cities, providing a scientific basis and reference for urban planning, construction, and traffic management. Road traffic flow is influenced by various complex features, including temporal and weather conditions, which introduce challenges to traffic flow prediction. To enhance the accuracy of traffic flow prediction and improve the adaptability across different weather conditions, this study introduced a traffic flow prediction model with explicit consideration of weather factors including temperature, rainfall, air quality index, and wind speed. The proposed model utilized grey relational analysis (GRA) to transform weather data into weighted traffic flow data, expanded input variables into a new data matrix, and employed one-dimensional convolutional neural networks (CNNs) to extract valuable feature information from these input variables, as well as bidirectional long short-term memory (BiLSTM) to capture temporal dependencies within the time-series data. Bayesian optimization was employed to fine-tune the hyperparameters of the model, offering advantages such as fewer iterations, high efficiency, and fast speed. The performance of the proposed prediction model was validated using the traffic flow data collected at an intersection in China and on the M25 motorway in the United Kingdom. The results demonstrated the effectiveness of the proposed model, achieving improvements of at least 9.0% in MAE, 2.8% in RMSE, 2.3% in MAPE, and 0.06% in R2 compared to five baseline models.

Assessing fire hazard using remote sensing and fire behaviour models in the telagh region of Sidi Bel Abbes, Algeria

ABSTRACT Understanding the occurrence and causes of wildfires in relation to fuels, weather, and geography allows fire management to assess fire risk accurately and direct mitigation efforts to reduce specific dangers. This study used the FlamMap tool to simulate wildfire dynamics under various environmental conditions. Spatial data on land cover were used to categorise fuel types, with FlamMap integrating these models for accurate fire behaviour predictions. Critical input factors included fuel loads, topography, wind, and weather data, gathered through field surveys and GIS software. The study area was categorised into 15 fuel models, revealing dense shrubland and thuja wooded shrub as high-risk areas because of their significant fuel loads. The Fire Danger Index was developed to assess and categorise fire risk levels across the landscape. Results indicated significant variations in fire behaviour. Dense shrublands and mixed pine-thuja forests posed substantial fire hazards. Grasslands and agricultural lands exhibited lower risks.

Dilution Rate of Solid NaCl Anti-Icers Under Freezing Rain Conditions

ABSTRACT In order to address environmental concerns and control cost, road salt should only be applied at the rate required to prevent or break the bond between snow and pavement. The effectiveness duration of solid salt anti-icers depends upon the pavement temperature, surface storage capacity, rainfall rate, and salt application rate. In order to better understand the likely dilution rate of solid salt under freezing rain conditions, Automated Surface Observing System (ASOS) weather data from 2018 to 2023 were analyzed for the U.S. cities of Minneapolis, Chicago, Cleveland, Indianapolis, Pittsburgh, and Louisville. Freezing rain events were defined as periods spanning 3 hours before the first indication of freezing rain or drizzle to 3 hours after the last indication. The median rainfall rates during these periods in five of the six cities was 0.001 in./hr (0.0025 cm/hr), and the average rainfall rates ranged from 0.014 to 0.029 in./hr (0.036–0.074 cm/hr). Making the simplifying assumptions of ignoring salt loss due to traffic action and that salt will quickly and uniformly dissolve in surface moisture, a first approximation change in the percentage of sodium chloride, freezing point depression, and anti-icing effectiveness duration is calculated for typical freezing rain rates, surface storage capacities, and temperatures. At rainfall rates greater than 0.02 in./hr (0.051 cm/hr), solid salt may be diluted too quickly for practical anti-icing, but at many common rainfall rates, applying pre-wet or treated rock salt to dry pavement may be considered for anti-icing.

Advancing pearl millet yield forecasting: Comparative analysis of individual and ensemble machine learning approaches over Rajasthan, India.

Pearl millet (Pennisetum glaucum L.) is a resilient crop known for its ability to thrive in arid and semi-arid regions, making it a crucial staple in regions prone to drought. Rajasthan, a state in India, emerged as the top producer of pearl millet. This study enhances yield forecasting for pearl millet using machine learning models across nine districts viz. Jaipur, Ajmer, Jodhpur, Bikaner, Bharatpur, Alwar, Sikar, Jhunjhunu and Nagaur in Rajasthan, India. Data from 1997-2019 (23 years), including yield data from the Directorate of Economics and Statistics and weather data from the NASA POWER web portal, were analysed. The study employed individual machine learning methods (GLM, ELNET, XGB, SVR and RF) and their ensemble combinations (GLM, ELNET, Cubist and RF). Discerning the overall best performing model across all locations remained challenging. For instance, while ensemble models exhibited subpar performance in Barmer and Nagaur, their performance ranged from satisfactory to commendable in other locations. To identify the best model, all models were ranked based on their R2 and nRMSE (%) values. Combined average ranks during training and testing revealed the model performance ranking as I-XGB (3.83) > I-GLM (4.28) > E-ELNET (4.32) > I-RF (4.67) > E-GLM (4.88) > I-SVR (4.90) > I-ELNET (4.94) > E-RF (6.03) > E-Cubist (7.15), where I denotes individual model, while E denotes ensemble model. Intriguingly, while individual GLM and XGB models demonstrated superior performance during calibration, they exhibited poorer performance during validation, potentially indicating issues of data overfitting. Hence, the ensemble ELNET approach is recommended for accurate prediction of pearl millet yield, followed by the individual RF model. These performances underscore the importance of tailored model selection based on specific geographic and environmental conditions.

Dataset for multi-model comparison and ensemble simulations of canola growth and yield across global sites

This paper describes the dataset that was used to test the reliability of eight crop models in simulating growth and yield of canola in response to sowing dates, nitrogen inputs and climate variability across five countries. The dataset includes four spring cultivars and three winter cultivars across six sites, which represents a diverse range of canola production areas around the world. Model calibration and validation were conducted in the framework of the Agricultural Model Intercomparison and Improvement Project for canola (AgMIP-Canola). Field experimental datasets include site characterization, soil profile characterization, initial soil conditions (soil water and mineral nitrogen contents), in-season and end-season crop measurements (phenology, LAI, biomass, and nitrogen content in leaves, stems and pods, some with seed oil content), and daily weather data. Simulation datasets include the simulation results generated by ten individual model frameworks (eight crop models, APSIM and DSSAT respectively by two groups) for the experimental periods, and scenario simulations using 30 years historical weather data (1981 – 2010) together with a full multi-factorial combinations of temperature (-3, 0, +3, +6, +9 oC), rainfall (-25%, -10%, 0, +10%, +25%), CO2 concentrations (360, 450, 540, 630, 720 ppm) and nitrogen input rates (0, +25%, +50%, +100%, +150%).

Enhancing green bean crop maturity and yield prediction by harnessing the power of statistical analysis, crop records and weather data.

Climate change impacts require us to reexamine crop growth and yield under increasing temperatures and continuing yearly climate variability. Agronomic and agro-meteorological variables were concorded for a large number of plantings of green bean (Phaseolus vulgaris L.) in three growing seasons over several years from semi-tropical Queensland. Using the Queensland government's SILO meteorological database matched to sowing dates and crop phenology, we derived planting specific agro-meteorological variables. Linear and nonlinear statistical models were used to predict duration of vegetative and pod filling periods and fresh yield using agro-meteorological variables including thermal time, radiation and days of high temperature stress. High temperatures over 27.5∘C and 30∘C in the pod fill period were associated with a lower fresh bean yield. Differences between specific bean growing sites were examined using our bespoke open source software to derive agro-meteorological variables. Agronomically informed statistical models using production data were useful in predicting time of harvest. These methods can be applied to other commercial crops when crop phenology dates are collected.

Optimizing Solar-Integrated Microgrid Design for Sustainable Rural Electrification: Insights from the LEOPARD Project

This paper presents findings from the LEOPARD project, part of the LEAP-RE program, a joint European Union (EU) and African Union initiative to advance renewable energy solutions. The study employs a simulation-based approach to optimize solar-integrated microgrid configurations for rural electrification. The project deployed a solar-integrated pilot microgrid at the Songhai agroecological center in Benin to address key challenges, including load profile estimation, energy balancing, and diesel dependency reduction. A hybrid methodology integrating predictive modeling, real-time solar and weather data analysis, and performance simulations was employed, leading to a 65% reduction in diesel reliance and an LCOE of EUR 0.47/kWh. Quality control measures, including compliance with IEC 61215 and IEC 62485-2 standards, ensured system reliability under extreme conditions. Over 150 days, the system consistently supplied energy, preventing 10.16 tons of CO2 emissions. Beyond the Benin pilot, the project conducted feasibility assessments in Senegal to evaluate microgrid replicability across different socio-economic and environmental conditions. These analyses highlight the scalability potential and the economic viability of expanding solar microgrids in rural areas. Additionally, this research explores innovative business models and real-time diagnostics to enhance microgrid sustainability. By providing a replicable framework, it promotes long-term energy access and regional adaptability. With a focus on community involvement and capacity building, this study supports efforts to reduce energy poverty, strengthen European–African collaboration, and advance the global clean energy agenda.

COFACTOR Drammen dataset - 4 years of hourly energy use data from 45 public buildings in Drammen, Norway.

To limit energy consumption and peak loads with increased electrification of our society, more information is needed about the energy use in buildings. This article presents a data set that contains 4 years (Jan. 2018- Dec. 2021/Mar. 2022) of hourly measurements of energy and weather data from 45 public buildings located in Drammen, Norway. The buildings are schools (16), kindergartens (20), nursing homes (7) and offices (2). For each building, the data set contains contextual data about the buildings including their floor area, construction year, energy label, information about their heating system and ventilation system in addition to time series data of energy use and weather data. For some of the buildings, the energy measurements only contain measurements of hourly imported electricity, while the time series data for other buildings have submeters for different energy services and technologies. Researchers, energy analysts, building owners and policy makers can benefit from the dataset for e.g. hourly load disaggregation, forecasting of energy loads and flexibility, grid planning and modelling activities.

Leveraging Explainable Artificial Intelligence in Solar Photovoltaic Mappings: Model Explanations and Feature Selection

This work explores the effectiveness of explainable artificial intelligence in mapping solar photovoltaic power outputs based on weather data, focusing on short-term mappings. We analyzed the impact values provided by the Shapley additive explanation method when applied to two algorithms designed for tabular data—XGBoost and TabNet—and conducted a comprehensive evaluation of the overall model and across seasons. Our findings revealed that the impact of selected features remained relatively consistent throughout the year, underscoring their uniformity across seasons. Additionally, we propose a feature selection methodology utilizing the explanation values to produce more efficient models, by reducing data requirements while maintaining performance within a threshold of the original model. The effectiveness of the proposed methodology was demonstrated through its application to a residential dataset in Madeira, Portugal, augmented with weather data sourced from SolCast.

Mini weather balloons and AI give fresh weather data to African farmers

Mini weather balloons and AI give fresh weather data to African farmers

Predicting atmospheric turbulence for secure quantum communications in free space

Atmospheric turbulence is the main barrier to large-scale free-space quantum communication networks. Aberrations distort optical information carriers, thus limiting or preventing the possibility of establishing a secure link between two parties. For this reason, forecasting the turbulence strength within an optical channel is highly desirable, as it allows for knowing the optimal timing to establish a secure link in advance. Here, we train a recurrent neural network, TAROQQO, to predict the turbulence strength within a free-space channel. The training is based on weather and turbulence data collected over 9 months for a 5.4 km intra-city free-space link across the City of Ottawa. The implications of accurate predictions from our network are demonstrated in a simulated high-dimensional quantum key distribution protocol based on orbital angular momentum states of light across different turbulence regimes. TAROQQO will be crucial in validating a free-space channel to optimally route the key exchange for secure communications in real experimental scenarios.

Multi-Building Energy Forecasting Through Weather-Integrated Temporal Graph Neural Networks

While existing building energy prediction methods have advanced significantly, they face fundamental challenges in simultaneously modeling complex spatial–temporal relationships between buildings and integrating dynamic weather patterns, particularly in dense urban environments where building interactions significantly impact energy consumption patterns. This study presents an advanced deep learning system combining temporal graph neural networks with weather data parameters to enhance prediction accuracy across diverse building types through innovative spatial–temporal modeling. This approach integrates LSTM layers with graph convolutional networks, trained using energy consumption data from 150 commercial buildings over three years. The system incorporates spatial relationships through a weighted adjacency matrix considering building proximity and operational similarities, while weather parameters are integrated via a specialized neural network component. Performance evaluation examined normal operations, data gaps, and seasonal variations. The results demonstrated a 3.2% mean absolute percentage error (MAPE) for 15 min predictions and a 4.2% MAPE for 24 h forecasts. The system showed robust data recovery, maintaining 95.8% effectiveness even with 30% missing values. Seasonal analysis revealed consistent performance across weather conditions (MAPE: 3.1–3.4%). The approach achieved 33.3% better prediction accuracy compared to conventional methods, with 75% efficiency across four GPUs. These findings demonstrate the effectiveness of combining spatial relationships and weather parameters for building energy prediction, providing valuable insights for energy management systems and urban planning. The system’s performance and scalability make it particularly suitable for practical applications in smart building management and urban sustainability.

Adaptive Machine Learning for Automatic Load Optimization in Connected Smart Green Townhouses

This paper presents an adaptive Machine Learning (ML)-based framework for automatic load optimization in Connected Smart Green Townhouses (CSGTs) The system dynamically optimizes load consumption and transitions between grid-connected and island modes. Automatic mode transitions reduce the need for manual changes, ensuring reliable operation. Actual occupancy, load demand, weather, and energy price data are used to manage loads which improves efficiency, cost savings, and sustainability. An adaptive framework is employed that combines data processing and ML. A hybrid Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN) model is used to analyze time series and spatial data. Multi-Objective Particle Swarm Optimization (MOPSO) is employed to balance costs, carbon emissions, and efficiency. The results obtained show a 3–5% improvement in efficiency for grid-connected mode and 10–12% for island mode, as well as a 4–6% reduction in carbon emissions.

Predicting energy consumption of an educational building using group method of data handling based on weather data

Predicting energy consumption of an educational building using group method of data handling based on weather data

Prediction of winter wheat nitrogen status using UAV imagery, weather data, and machine learning

Prediction of winter wheat nitrogen status using UAV imagery, weather data, and machine learning

Leveraging deep-learning and unconventional data for real-time surveillance, forecasting, and early warning of respiratory pathogens outbreak.

Leveraging deep-learning and unconventional data for real-time surveillance, forecasting, and early warning of respiratory pathogens outbreak.