Historical Weather Data Research Articles

The Energy Requirement for Supplemental Greenhouse Lighting Can Be Reduced by Considering 'Excess' Light from the Previous Day.

The sunlight greenhouse crops receive varies and is often insufficient for consistent year-round growth in greenhouses. Supplemental lighting is commonly applied in winter, but this practice has a significant energy cost, accounting for 10-30% of operating expenses and impacting greenhouse profitability. Greenhouse lights are traditionally adjusted based on sunlight intensity to meet crops' daily light requirements. However, if plants can withstand lower daily light integrals (DLI) after a sunny day without reducing the growth, there is potential to reduce the energy required for supplemental lighting and increase the profit. To determine whether excess light received one day can be 'carried over' to the next, we grew oakleaf lettuce (Lactuca sativa 'Green Salad Bowl' and 'Red Salad Bowl') under six lighting regimes inside a vertical farm. Plants in all treatments received an average DLI of 15 mol·m-2·d-1, but DLIs alternated from day-to-day (15/15, 17.5/12.5, 20/10, 22.5/7.5, 25/5, and 27.5/2.5 mol·m-2·d-1), resulting in DLI fluctuations from 0 to 25 mol·m-2·d-1. Plants had similar leaf area (~800 cm2/plant) and dry weight (~1.8 g/plant) when grown with DLI fluctuations from 0 to 15 mol·m-2·d-1, while higher DLI fluctuation reduced growth. To confirm this DLI "carrying-over" effect on plants grown under sunlight with supplemental light, we conducted a second study in a greenhouse with 'Green Salad Bowl' lettuce. In this study, plants were grown with five different DLI fluctuations (15/15, 16.75/13.25, 18.5/11.5, 20.25/9.75, and 22/8 mol·m-2·d-1), ranging from 0 to 14 mol·m-2·d-1, while maintaining an average DLI of 15 mol·m-2·d-1 in all the treatments. We observed similar leaf area (~750 cm2/plant) and dry weight (~1.8 g/plant) in lettuce plants grown with DLI fluctuations from 0 to 10.5 mol·m-2·d-1. Higher DLI fluctuations reduced growth. Hence, carrying excess light from a sunny to an overcast day is possible within limits. Our study concluded that the DLI requirement can be reduced by approximately 5.25 mol·m-2·d-1 on the day following a sunny day. By analyzing historical weather data from five US locations, we quantified the potential annual energy savings from incorporating this 'carrying-over DLI' concept. This approach resulted in annual energy savings of approximately 75-190 MWh/ha in greenhouse lettuce production. Such reductions in supplemental lighting energy will enhance the profitability and sustainability of the greenhouse industry.

Life cycle assessment and forecasting for 30kW solar power plant using machine learning algorithms

Highly competitiveness of solar power plants in the energy market requires addressing the active research problem of solar energy forecasting. To make precise forecasts, however, historical meteorological, production, or irradiance data is insufficient. As the conservation of these Renewable Energy Sources (RES) is that much essential, the use of Photovoltaic (PV) panels have subsequently increased. The output of these PV panels completely depends on the climate. As the PV panels convert the solar energy to electrical energy, therefore, it produces the most when there is enough sunlight throughout the summer and the least when there is rain. Accurate forecasting of energy generation from solar power plants is crucial in terms of economics due to this uncertainty in the output in different seasons and the change in meteorological conditions. The objective of this paper is to investigate machine learning algorithms can accurately anticipate solar power for the upcoming hour and hourly days in advance. The Naïve Bayes Algorithm, Multilayer Perceptron Theorem (MLP), and Long Short-Term Memory networks (LSTM) are the machine learning algorithms investigated. Both historical weather data and generation data are used in the study. This study also includes the payback period (PB) and life cycle assessment calculation of the roof top solar power plant located in Bhubaneswar India.

Enhancing Subsurface Soil Moisture Forecasting: A Long Short-Term Memory Network Model Using Weather Data

Subsurface soil moisture is a primary determinant for root development and nutrient transportation in the soil and affects the tractability of agricultural vehicles. A statistical forecasting model, Vector AutoRegression (VAR), and a Long Short-Term Memory network (LSTM) were developed to forecast the subsurface soil moisture at a 20 cm depth using 9 years of historical weather data and subsurface soil moisture data from Fort Wayne, Indiana, USA. A time series analysis showed that the weather data and soil moisture have a stationary seasonal tendency and demonstrated that soil moisture can be forecasted from weather data. The VAR model estimates volumetric soil moisture of one-day ahead with an R2, MAE (m3m−3), MSE (m6m−6), and RMSE (m3m−3) of 0.698, 0.0561, 0.0046, and 0.0382 for 2021 corn cropping season, whereas the LSTM model using inputs of previous seven days yielded R2, MAE (m3m−3), MSE (m6m−6), and RMSE (m3m−3) of 0.998, 0.00237, 0.00002, and 0.00382, respectively as tested for cropping season of 2020 and 0.973, 0.00368, 0.00003 and 0.00577 as tested for the cropping season of 2021. The LSTM model presents a viable data-driven alternative to traditional statistical models for forecasting subsurface soil moisture.

Analyses of Climate Variability and Trends in the Oil Palm Belt of Ghana

The current production of oil palm in Africa has been severely limited by long periods of drought and perennial floods due to the increased rates of climate change. The study was aimed at assessing the climatic variability trends in 7 major Oil Palm growing areas (Benso, Mpohor, Bogoso, Twifo Praso, Kade, Juabeng and Brewaniese) located in the oil palm belt in Ghana spanning the semideciduous and the wet evergreen rainforest zones of Ghana using 30 years of historical weather data (1993-2022). The data was analysed to evaluate the extent of seasonal changes in weather over the 30-year period using the Statistical Package for Social Sciences (SPSS 20.0 version), using descriptive statistics and time series analysis. Trend analysis was conducted using the non-parametric Mann-Kendall (MK) and Sen’s slope estimator tests. A seasonal trend in rainfall was observed at all sites with maximum levels observed between May and July as well as a minor rainy season in September to Mid-November. The Mann-Kendall trend analysis showed a generally increasing trend at most stations in rainfall, temperature and solar radiation. A generally increasing trend in annual rainfall was observed from 1993-2022 with significant trends at Mpohor and Juabeng. The trend was higher in the moist evergreen rainforest zone than in the semi-deciduous rainforest zone. An average increase of 6.7 mm/yr in rainfall trend was observed for the period. An increasing trend in monthly maximum, minimum and mean temperatures were also observed. Significant increases in mean temperatures were observed at Bogoso (0.022°C/yr), Benso (0.018°C/yr), Juabeng (0.011°C/yr) and Mpohor (0.017°C/yr). The trend in mean annual solar radiation was generally not significant except in Benso where the mean solar radiation increased at the rate of 0.044 MJ/day. Higher drought levels in the first half year combined with very heavy rains later in the year are features of the ongoing climate change menace.

Predicting the main pollen season of Broussonetia Papyrifera (paper mulberry) tree.

Paper mulberry pollen, declared a pest in several countries including Pakistan, can trigger severe allergies and cause asthma attacks. We aimed to develop an algorithm that could accurately predict high pollen days to underpin an alert system that would allow patients to take timely precautionary measures. We developed and validated two prediction models that take historical pollen and weather data as their input to predict the start date and peak date of the pollen season in Islamabad, the capital city of Pakistan. The first model is based on linear regression and the second one is based on phenological modelling. We tested our models on an original and comprehensive dataset from Islamabad. The mean absolute errors (MAEs) for the start day are 2.3 and 3.7 days for the linear and phenological models, respectively, while for the peak day, the MAEs are 3.3 and 4.0 days, respectively. These encouraging results could be used in a website or app to notify patients and healthcare providers to start preparing for the paper mulberry pollen season. Timely action could reduce the burden of symptoms, mitigate the risk of acute attacks and potentially prevent deaths due to acute pollen-induced allergy.

TOWARDS BUILDING AN INTELLIGENT MOBILE APP FOR RAINFALL PREDICTION USING WEIGHTED AVERAGE ENSEMBLE DEEP SUPERVISED LEARNING

Predicting rainfall accurately and on time is essential for a variety of tasks, including electricity generation, building, flood warnings, aviation operations, and the sustainable use of water resources. Traditionally, rainfall forecasts were based on physical models of the atmosphere, which are imprecise over extended periods of time due to their instability to perturbations and thus, are inaccurate for large periods. Artificial Intelligence (AI) techniques as a means of predicting rainfall have been applied in most developed countries, these have been found to offer many possibilities. AI techniques are more robust to perturbations. Over the past 20 years, rainfall forecasting using AI approaches has demonstrated astounding precision. Rainfall forecasting accuracy could be increased by AI algorithms that use historical weather data elements to reveal hidden trends. This study thereafter proposed the development of an AI mobile app for predicting rainfall that is based on weighted average ensemble deep supervised learning that combines three machine learning algorithms namely; Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). . In order to prevent future outbreaks of rainfall hazards, the proposed AI mobile app for rainfall prediction will aid in raising awareness among the public, government officials, planning agencies, disaster management agencies, and related organizations.

The energy management strategy of a loop microgrid with wind energy prediction and energy storage system day-ahead optimization

Microgrid has been extensively applied in the modern power system as a supplementary mode for the distributed energy resources. The microgrid with wind energy is usually vulnerable to the intermittence and uncertainty of the wind energy. To increase the robustness of the microgrid, the energy storage system (ESS) is necessary to compensate the power imbalance between the power supply and the load. To further maximize the economic efficiency of the system, the system level control for the microgrid is desired to be optimized when it is integrated with the utility grid. Aiming at the aforementioned problem, this paper comprehensively analyzes the power flow of a typical loop microgrid. A transformer-based wind power prediction (WPP) algorithm is proposed and compared with recurrent neural networks algorithm. With the historical weather data, it can accurately predict the 24 h average wind energy. Based on the predicted wind energy and the time-of-use (TOU) electricity price, a day-ahead daily cycling profile of the ESS with particle swarm optimization algorithm is introduced. It comprehensively considers the system capacity constraints and the battery degree of health. The functionality of the proposed energy management strategy is validated from three levels. First, WPP is conducted with the proposed algorithm and the true historical weather data. It has validated the accuracy of the transformer algorithm in prediction of the hourly level wind energy. Second, with the predicted wind energy, a case study is given to validate the day-ahead daily cycling profile. A typical 1 MVA microgrid is utilized as the simulation model to validate performance of the daily cycling optimization algorithm. The case study results show that the ESS daily cycling can effectively reduce the daily energy expense and help to shave the peak power demand in the grid.

Enhancing Solar Radiation Forecasting in Diverse Moroccan Climate Zones: A Comparative Study of Machine Learning Models with Sugeno Integral Aggregation

Hourly solar radiation (SR) forecasting is a vital stage in the efficient deployment of solar energy management systems. Single and hybrid machine learning (ML) models have been predominantly applied for precise hourly SR predictions based on the pattern recognition of historical heterogeneous weather data. However, the integration of ML models has not been fully investigated in terms of overcoming irregularities in weather data that may degrade the forecasting accuracy. This study investigated a strategy that highlights interactions that may exist between aggregated prediction values. In the first investigation stage, a comparative analysis was conducted utilizing three different ML models including support vector machine (SVM) regression, long short-term memory (LSTM), and multilayer artificial neural networks (MLANN) to provide insights into their relative strengths and weaknesses for SR forecasting. The comparison showed the proposed LSTM model had the greatest contribution to the overall prediction of six different SR profiles from numerous sites in Morocco. To validate the stability of the proposed LSTM, Taylor diagrams, violin plots, and Kruskal–Wallis (KW) tests were also utilized to determine the robustness of the model’s performance. Secondly, the analysis found coupling the models outputs with aggregation techniques can significantly improve the forecasting accuracy. Accordingly, a novel aggerated model that integrates the forecasting outputs of LSTM, SVM, MLANN with Sugeno λ-measure and Sugeno integral named (SLSM) was proposed. The proposed SLSM provides spatially and temporary interactions of information that are characterized by uncertainty, emphasizing the importance of the aggregation function in mitigating irregularities associated with SR data and achieving an hourly time scale forecasting accuracy with improvement of 11.7 W/m2.

Enhancing Precipitation Prediction in the Ziz Basin: A Comprehensive Review of Traditional and Machine Learning Approaches

Accurate precipitation forecasting is paramount for various sectors. Traditional methods for rainfall prediction involve understanding physical processes, historical weather data, and statistical models. These methods utilize observations from ground-based weather stations, satellites, and weather radars to assess current conditions and predict future precipitation. However, accurate precipitation prediction remains challenging due to the intricate and non-linear characteristics of rainfall. Over the past few years, machine learning (ML) algorithms have shown promise in improving precipitation prediction accuracy. This research provides an overview of both traditional methods and advanced ML models applicable to rainfall prediction, including regression, classification, and time series models. We conducted a comprehensive review of related works that explore the impact of using ML algorithms for rainfall estimation. Through this analysis, we identified the strengths and limitations of ML models in this context and highlighted advancements in rainfall prediction using these algorithms. We possess a comprehensive dataset, spanning data from 1996 to 2015, comprising historical weather data from the Ziz basin, our designated study area. This dataset contains five key meteorological features: precipitation, humidity, wind, temperature, and evaporation. In terms of perspective, we plan to utilize this dataset and conduct a comprehensive comparative study to evaluate the performance of different ML models. Our objective is to demonstrate the effectiveness and potential of these algorithms in improving weather forecasting capabilities and enhancing the accuracy of rainfall estimation methods in the specific study area.

Multiphase Solar Photovoltaic Prediction Model Based on Season, Hierarchical k‐Means Clustering, GRA‐PCC, SVM, and Neural Network

Solar photovoltaic (PV) has accounted for the highest percentage of power generation capacity among other renewables. However, solar PV power generation is highly variable because of different factors; therefore, accurate forecasting is critical for reliable integration into the power system. This paper proposes a multiphase solar PV prediction model that includes grouping, clustering, linking, classifying, and predicting using historical solar PV power and weather data. Seasonal variation is considered in the grouping phase, followed by hybrid hierarchical k‐means clustering to enhance data division in the clustering phase. A hybrid gray relational analysis‐Pearson correlation coefficient identifies significant weather factors impacting solar PV power in the linking phase. The classification phase employs a support vector machine to establish the relationship between the clusters and the relevant weather factors. Lastly, a neural network (NN) is trained to predict solar PV power. The solar PV power profiles are presented to show the variability in season and time. The simulation results of the proposed model showed relatively accurate forecasting results, including MAE of 0.408 MW, MSE of 460.51 MW, RMSE of 0.679 MW, nRMSE of 4.345%, and MRE of 2.266%. These results represent that the uncertainties of the proposed model are 6 and 12 times lower than those of the conventional methods (i.e., conventional NN and ARMAX). These results assure that the proposed model can provide more accurate solar PV power profiles for reliable power system integration.

Validation of methods for developing typical meteorological years based on future climate models

You Buildings designed for coming decades are more susceptible to global warming, rising average temperatures, and heat waves, which are of a greater risk than in the 1990s. Simulation-based design decisions may be inaccurate if just historical data is used to generate climate files. The building's energy performance, cooling and heating system’s design, and room unit sizing require reliable weather data. So far mainly historic meteorological data has been used for simulations. Annual simulations and cooling/heating system design often use a typical meteorological year (TMY) based on historical data using ISO 15927-4 and ISO 15927-2 thorough instructions for TMY for annual simulations and design day data. The above climate models lack the data needed to construct TMYs for building performance simulation (BPS) tools. Climate model forecast accuracy must also be examined from the BPS perspective. This work aims to illustrate and test methods for producing TMYs using three climate models with different resolution and modality in Tartu, Estonia, from 1985 to 2015. The ISO 15927-4 approach selected months from historical meteorological data appropriate for each climate model. Three BPS TMYs were created, and a reference building's energy needs simulated. Long-term historical data was used to simulate the reference building's energy requirement and develop TMYs. The results showed that all the TMYs developed based on NorESM, MPIESM and ECEarth climate models can represent well the energy needs obtained with the TMY based on historical weather data depending on the TMY generation method while MPIESM shows deficiency in cooling season. TMY based on NorESM have the most consistent energy need simulation results while TMY based on ECEarth also performs well both for predicting cooling and heating needs. The future work includes finding other suitable methods for TMY generation that results in even less errors for all models and further validation with other reference buildings for final climate model selection to develop future climate scenarios.

Powering In-Field Continuous Robotic Systems Using Solar Energy Systems

Highlights Because of variable weather conditions, battery capacity must be at least 2.5 times larger than daily energy demands for continuous off-grid power. At a minimum, the nominal solar panel array size must be large enough to provide the daily energy demand in 3 hours. Because of a trade-off relationship, minimal battery capacity or solar panel size requires more than the minimum for the other component. Limiting operation to March through October reduced required sizes. Adding a backup generator with minimal usage of 50 kg of propane per year also reduced sizes. Abstract. Continuous in-field robotic and automated systems are challenged by the need for a continuous supply of power. This off-grid power supply can be diesel, gasoline, propane, or alternative energy sources like solar or wind. This study investigates the required solar panel arrays and energy storage capacities for an off-grid solar-battery power supply system. This study used 22 years of historical weather data from Lexington, Kentucky, and processed it with the National Renewable Energy Laboratory’s System Advisor Model to model hourly energy output from solar panel arrays of 2 kW, 3 kW, 4 kW, 5 kW, 10 kW, 15 kW, and 20 kW. This was combined with an energy storage model (simulated battery capacities of 5 kWh, 10 kWh, 15 kWh, 20 kWh, 30 kWh, 40 kWh, 50 kWh, and 60 kWh) and an energy use model (simulated daily energy demands of 3.6 kWh, 6 kWh, 12 kWh, 18 kWh, and 24 kWh) to determine which systems could operate over the entire 22 years without reaching critical minimum levels. For a 3.6 kWh daily energy demand, 32 combinations of solar panel arrays and battery capacities remained above critical levels, while this was only 12 combinations for a 6 kWh daily energy demand and no combination could support larger energy demands. An example a feasible system to support a 6 kWh energy demand is one that uses a 15 kW panel array (42 standard panels with an approximate system hardware cost of $22,650) and 30 kWh of energy storage capacity (which with lead acid batteries would cost $11,661 and require a volume of 300 L). There is a tradeoff between solar panel array size and battery capacity so other feasible systems can be realized by increasing one to make up for reductions in the other variable. Additionally, limiting system operation to March through October can reduce the size of the required panel array (to between 33% to 67% of the original size) or energy storage capacity (to between 40% to 67% of the original capacity) for a given daily energy load. The size of the solar battery system could be further decreased by adding an emergency generator that uses no more than 50 kg of propane annually. Battery capacities could be reduced by 17% to 38% compared to the original system, and the solar panel arrays could be reduced by 13% to 15% compared to the original. Specific reduction amounts depended on the specific configuration of the original system and the daily load level that had to be supported. A system that only operated from March through October with a backup generator could also support the 12 and 18 kWh daily energy demands, which could not be supported by the original system. Even with limiting operation to March through October and using an emergency generator, the minimal battery capacity was at least 2.5 times larger than the daily energy demand, and the solar panel array had to be large enough that the nominal output would provide the daily energy demand in 3 hours of full sun. However, because of the trade-off relationship, these minimums cannot be attained together. While continuous in-field robotic deployments show promise for improving agriculture, it will be critical to design with energy efficiency in mind and the off-grid power supply for wide-spread use across agricultural lands. Keywords: Agriculture robot, Autonomous, Batteries, Computer modeling, Energy, Power, Simulation, Sizing, Solar, System.

Effect of a severe cold spell on overwintering survival of an invasive forest insect pest

Cold temperatures can play a significant role in the range and impact of pest insects. Severe cold events can reduce the size of insect outbreaks and perhaps even cause outbreaks to end. Measuring the precise impact of cold events, however, can be difficult because estimates of insect mortality are often made at the end of the winter season. In late January 2023 long-term climate models predicted a significant cold event to occur over eastern North America. We used this event to evaluate the immediate impact on hemlock woolly adelgid (Adelges tsugae Annand) overwintering mortality at four sites on the northern edge of the insects invaded range in eastern North America. We observed complete mortality, partial mortality and no effects on hemlock woolly adelgid mortality that correlated with the location of populations and strength of the cold event. Our data showed support for preconditioning of overwintering adelgids having an impact on their overwintering survival following this severe cold event. Finally, we compared the climatic conditions at our sites to historical weather data and previous observations of mortality in Nova Scotia. The cold event observed in February 2023 resulted in the coldest temperatures observed at these sites, including the period within which hemlock woolly adelgid invaded, suggesting cold conditions, especially under anthropogenic climate forcing, may not be a limiting factor in determining the ultimate northern range of hemlock woolly adelgid in eastern North America.

Long-Term Simulated Direct N2O Emissions from German Oilseed Rape Cultivation below the IPCC Emission Factor

The low nitrogen (N)-use efficiency of intensive winter oilseed rape (WOSR) cropping systems may cause negative environmental impacts, especially due to N leaching and gaseous losses. The aim of this study was to use data from field experiments (five sites across Germany representing typical WOSR regions) for parametrization of a nitrous oxide (N2O) emission component for implementation into a process-based dynamic plant-soil-atmosphere model (PSAM). After calibration and evaluation with three years of field data from five different N fertilizer treatments, a long-term simulation with 25-year historical weather data was conducted to derive functional relations and emission factors (EFs). The model performed best at higher aggregation levels (cumulative emissions over the entire cropping period, R2 of 0.48/0.77 for calibration/evaluation), but also reasonably simulated short-term dynamics (e.g., fertilizer applications, extreme weather events). Site-specific and year-specific N2O emissions varied within the range of medians from 0.56–4.93 kg N2O-N ha−1. Mineral fertilizer-induced EFs at economic optimal N inputs ranged from 0.16–0.65%, which was markedly below the aggregated IPCC standard value of 1% for direct N2O emissions. Generally, the simulated emissions were consistently higher with finer soil textures and increasing N inputs. The process-based approach, moreover, allowed the identification of the major source of N2O, which mainly originated from nitrification processes.

Minimum tillage as climate-smart agriculture practice and its impact on food and nutrition security.

Minimum tillage (MT) is a sustainable farming practice that limit soil disturbance only to planting stations while leaving the rest of the soil undisturbed. It is an important component of conservation agriculture, which aims to raise agricultural productivity, improve the livelihoods of farmers and build resilient farming systems. Despite the growing empirical literature on its adoption and benefits, there is a paucity of empirical evidence on the heterogeneous effect of length of MT adoption on household welfare. This study uses plot-level and household data combined with geo-referenced historical weather data to provide microeconomic evidence of the impact of MT on maize yields, food and nutrition security, and farm labor demand in Ghana. We account for potential selection bias and omitted variable problems by using an ordered probit selection model to estimate two transition-specific treatment effects: from conventional tillage systems to short-term MT adoption and from short-term to long-term MT adoption. The empirical results show that longer cropping seasons of MT adoption significantly increases maize yields and dietary diversity by about 4.33% and 14.22%, respectively, and decreases household food insecurity and labor demand by 42.31% and 11.09%, respectively. These findings highlight the necessity of developing and implementing programs that promote and help smallholder farmers to sustain its adoption for longer cropping season.

Modelling the response of tomato on deficit irrigation under greenhouse conditions

To optimize crops irrigation strategy is crucial to improve the production sustainability in a climate change scenario characterized by an ever-increasing water shortage. Crops simulation models, combined with experimental data, can be useful tools. AquaCrop, a crop water productivity model, has been widely used to reach this aim in open field condition but it has been limited adopted under greenhouse conditions. This study aims to calibrate and validate AquaCrop model through a greenhouse tomato cultivation using a split plot experimental design. Crop irrigation management was the main treatment [full irrigation (FI) at 100 % crop evapotranspiration (ETc) vs. deficit irrigation (DI) at 75 % of FI] and fertilization [no fertilization, mineral fertilization, organic fertilization with compost, and organic fertilization with sieved (< 2 mm) compost] the subplots. Fresh yield, above-ground biomass, water productivity, and net irrigation requirements were simulated. The validated model also permitted to evaluate the impacts of changing temperature outside the greenhouse on fruits yield, biomass, and water productivity using 30 years of historical weather data. The results showed that the model accurately estimated crop parameters, although it tended to overestimate soil water content. On average, DI reduced fruit yield by 14.1 % compared to FI. Over the last 30 years, the validated model permitted to calculate an average fruits yield reduction due to DI of 12.6 %. Our findings suggest that models like AquaCrop can assist in optimizing greenhouse agriculture by predicting crop performance under different conditions. Our study also highlights that external temperature and AquaCrop can be used to estimate tomato yields in the greenhouse by providing decision support tools for end-users (farmers, farmer associations, and policymakers) seeking sustainable and efficient greenhouse farming practices in a changing climate.

Weather Routing Benefit for Different Wind Propulsion Systems

_ Impact of weather routing on a post-panamax bulk carrier equipped with different wind propulsion systems was studied. The studied wind propulsion systems were rotor sails, wing sails, and suction wings and the studied route was a typical bulk carrier route between China and Brazil. A 4 degrees of freedom (4-DoF) performance prediction program was used to generate a performance model of the ship with different wind propulsion devices and the performance models were used in the voyage optimization. The voyage optimization simulations were carried out using historical weather data during the years 2015 to 2019 with one departure per week on both ways. It was found that there is a significant reduction in fuel consumption when weather routing is used on wind propulsion ships, but the magnitudes of the weather routing benefit vary from system to system depending on its versatility. Higher benefits from weather routing were found first for rotor sails, then for suction wings, and finally for wing sails.

A novel wind power prediction model using graph attention networks and bi-directional deep learning long and short term memory

&lt;span lang="EN-US"&gt;Today, integrating wind energy forecasting is an important area of research due to the erratic nature of wind. To achieve this goal, we propose a new model of wind speed prediction based on graph attention networks (GAT), we added a new attention mechanism and a learnable adjacency matrix to the GAT structure to obtain attention scores for each weather variable. The results of the GAT-based model are merged with the bi-directional deep learning long and short-term memory (BiLSTM) layer to take advantage of the geographic and temporal properties of historical weather data. The experiments and analyzes are carried out using precise meteorological data collected from wind farms in the Moroccan city of Tetouan. We show that the proposed model can learn complex input-output correlations of meteorological data more efficiently than previous wind speed prediction algorithms. Due to the resulting attention weights, the model also provides more information about the main weather factors for the evaluated forecast work.&lt;/span&gt;

Pre-Processing and Normalization of the Historical Weather Data Collected from Secondary Data Source for Rainfall Prediction

In the twenty first century, data analysis has become the talk of the town. Almost every company or organization depends on data analysis for taking future decision. The most important step in data analysis after data collection is the preprocessing of the collected data. The main aim of data analysis is to find meaningful pattern by processing large amount of data. In data preprocessing, the inconsistency of collected data has been removed. After storing data for a relatively longer period, it becomes noisy and inconsistent. While measuring various parameter due to error in the instrument or human error, the value become incorrect or invalid. It is necessary to remove the invalid data otherwise it will deflect the results and produce error in the prediction. In this work preprocessing of the weather data has been analyzed for rainfall prediction using data mining.

How to minimise the cost of green hydrogen with hybrid supply: A regional case study in China

Hydrogen produced from renewables-fuelled electrolysis has the potential to provide deep decarbonisation for sectors that are the most difficult to decarbonise, but the intermittency of renewable sources may result in low electrolyser utilisation and, consequently, high costs. This study determines the greenhouse gas (GHG) emissions and levelised cost of hydrogen (LCOH) associated with blending wind electricity with the grid to increase electrolyser utilisation. A novel cost model was developed to determine the production performance, costs and embodied CO2 emissions of an electrolyser with hybrid fuel supply (wind and grid) considering dynamic load constraints of alkaline (ALK) and Proton exchange membrane (PEM) electrolysers and using high-resolution historical weather data to determine wind production profiles in two case study regions: northern (Bayannur) and southern (Pingtan) China. The results show that using 52% of grid electricity in an ALK electrolyser in Bayannur reduces LCOH by 11%, increasing hydrogen production by 74% but with 17.4 kg CO2/ kg H2 generated in CO2 emissions. When a carbon price is accounted for, the optimal electrolyser utilisation is reduced to 40%, with the LCE 44% reduced. Emissions of 9.8 kg CO2/kg H2 are lower than for stream methane reforming with carbon capture. In Southern China (Pingtan), LCOH is higher than Bayanur because of the high electricity cost. The economic benefits of increasing grid power depend primarily on the total CAPEX cost, grid power cost, and carbon tax. By altering the carbon tax, the optimal blend of wind/ grid differs. The grid contribution to the optimal blend diminishes as a carbon tax approaches 35 USD/ t CO2.