How the Chaos Theory is Defeated in the Yabu Meteorological Station, Cuba

In this work, 8 weather variables were modeled at the Yabu meteorological station, Cuba, a daily database from the Yabu meteorological station, Cuba, of extreme temperatures, extreme humidity and their average value, precipitation, was used. The force of the wind and the cloudiness corresponding to the period from 1977 to 2021, a linear mathematical model is obtained through the methodology of Regressive Objective Regression (ROR) for each variable that explains their behavior, depending on these 15, 13, 10 and 8 years in advance. It is concluded that these models allow the long-term forecast of the weather, opening a new possibility for the forecast, concluding that the chaos in time can be overcome if this way of predicting is used, the calculation of the mean error regarding the forecast of persistence in temperatures, wind force and cloud cover, while the persistence model is better in humidity, this allows to have valuable information in the long term of the weather in a locality, which results in a better decision making in the different aspects of the economy and society that are impacted by the weather forecast. It is the first time that an ROR model has been applied to the weather forecast processes for a specific day 8, 10, 13 and 15 years in advance.

Ecotoxicological effects of silver nanoparticles in marine mussels

In the marine bioindicator species M. galloprovincialis Lam we predicted toxicity and bioaccumulation of 5 nm alkane-coated and 50 nm uncoated silver nanoparticles (AgNPs) along with Ag+, as a function of the actual dose level. We generated a time persistence model of silver concentration in seawater and used the Area Under the Curve (AUC) as independent variable in hazard assessment. This approach allowed us to evaluate unbiased ecotoxicological endpoints for acute (survival) and chronic toxicity (byssal adhesion). Logistic regression analysis rendered LC5096h values of 0.68 ± 0.08; 1.00 ± 0.20; 1.00 ± 0.42 mg h L-1 respectively for Ag+, 5 nm and 50 nm AgNP posing no evidence the silver form is a necessary variable to predict the survival outcome. By contrast, for byssal adhesion regression analysis revealed a much higher toxicological potential of Ag+ vs AgNPs, 0.0021 ± 0.0009; 0.053 ± 0.016; 0.021 (no computable error for 50 nm AgNP) mg h L-1, and undoubtedly confirmed a role of the silver form. Bioaccumulation was higher for Ag+ > 5 nm AgNP > 50 nm AgNP reflecting a parallel with the preferential uptake route / target organ. We, eventually, provided a full range of toxicological endpoints to derive risk quotients.

Short-Term Power Forecasting Framework for Microgrids Using Combined Baseline and Regression Models

Short-term electric power forecasting is a tool of great interest for power systems, where the presence of renewable and distributed generation sources is constantly growing. Specifically, this type of forecasting is essential for energy management systems in buildings, industries and microgrids for optimizing the operation of their distributed energy resources under different criteria based on their expected daily energy balance (the consumption–generation relationship). Under this situation, this paper proposes a complete framework for the short-term multistep forecasting of electric power consumption and generation in smart grids and microgrids. One advantage of the proposed framework is its capability of evaluating numerous combinations of inputs, making it possible to identify the best technique and the best set of inputs in each case. Therefore, even in cases with insufficient input information, the framework can always provide good forecasting results. Particularly, in this paper, the developed framework is used to compare a whole set of rule-based and machine learning techniques (artificial neural networks and random forests) to perform day-ahead forecasting. Moreover, the paper presents and a new approach consisting of the use of baseline models as inputs for machine learning models, and compares it with others. Our results show that this approach can significantly improve upon the compared techniques, achieving an accuracy improvement of up to 62% over that of a persistence model, which is the best of the compared algorithms across all application cases. These results are obtained from the application of the proposed methodology to forecasting five different load and generation power variables for the Savona Campus at the University of Genova in Italy.

Hybrid nowcasting for solar power plants using satellite-data and Numerical Weather Predictions for (Deep) Machine Learning methods

<p>With the expanding penetration of renewable energy in the energy sector, we observe an ever-increasing need for more accurate weather and production forecasts. They are needed by several energy players: plant owners, system operators, service providers (balancing service providers, energy traders). For the energy market needs, in different countries we can already find almost real-time trading markets; in a likely future scenario, the day-ahead market will disappear in favour of 5-15 minutes ahead market. This trend luckily matches the system operators need of predicting in the very short term the energy fed into the grid, to effectively cope with voltage and congestions problems and manage the ancillary services. Overall, the scenario indicates a compelling need for advanced forecasting techniques.</p><p>This article discusses a hybrid solar nowcasting system, predicting energy production from +15 minutes to 3 hours ahead, with a time granularity of 15 minutes. The system combines observed data (especially from satellite) and Numerical Weather Predictions to nowcast data in two steps: the first step is the nowcast of global horizontal irradiance and direct normal irradiance; they are then fed into the following system to predict the energy production. Thus, we disentangle the problem, and we can improve in parallel the two subsystems.</p><p>The weather nowcast model core is a Deep Learning method especially suited for time series problems (Long Short Term Memory Network - LSTM). It has been tested over different sites corresponding to different satellite spatial resolution, weather conditions and climate regions. The results are compared with different benchmarks such as the persistence model, smart persistence model and ground truth (where available), obtaining typical annual MAE results over the 15->3 hours between 10 and 80 W/m2. Other metrics (MBE, RMSE, and the forecast score) are calculated to get a deeper view of the results meaning. We also compared results without the availability of NWP (computationally expensive) or ground sensors (not always available in real-time) to understand the benefits of processing those data.</p><p>The power production system (fed with the output of the previous model) is a combination of different techniques: Decision trees, KNN, and NN. The performance is typical of 3-6% annual NMAE, depending on the site. We compare the results with the persistence benchmark and we calculate other metrics such as MBE, NRMSE and to get a deeper understanding of the results.</p><p>The two-steps model is finally compared with a one-step model only, where just satellite data are fed into a model predicting the power, to compare pros, cons and performance.</p>

Artificial neural network based nowcasting model for beach water quality

Recreational water users may be exposed to elevated pathogen levels that originate from various point and non-point sources. Current daily notifications practice depends on microbial analysis of indicator organisms such as Escherichia coli (E. coli) that require 18-24 hours to provide sufficient response. This research evaluated the use of Artificial Neural Networks (ANNs) for real time prediction of E. coli concentration in water at Toronto beaches (Ontario, Canada). The nowcasting models were developed in combination with readily available real-time environmental and hydro-meteorological data during the bathing season (June-August) of 2008 to 2012. The results of the developed ANN models were compared with historic data and found that the predictions of E. coli concentrations generated by ANN models slightly outperforms than currently used persistence model with better accuracy. The best performing ANN models for each beach are able to predict approximately 74% to 82% of the E. coli concentrations.

Artificial neural network based nowcasting model for beach water quality

Recreational water users may be exposed to elevated pathogen levels that originate from various point and non-point sources. Current daily notifications practice depends on microbial analysis of indicator organisms such as Escherichia coli (E. coli) that require 18-24 hours to provide sufficient response. This research evaluated the use of Artificial Neural Networks (ANNs) for real time prediction of E. coli concentration in water at Toronto beaches (Ontario, Canada). The nowcasting models were developed in combination with readily available real-time environmental and hydro-meteorological data during the bathing season (June-August) of 2008 to 2012. The results of the developed ANN models were compared with historic data and found that the predictions of E. coli concentrations generated by ANN models slightly outperforms than currently used persistence model with better accuracy. The best performing ANN models for each beach are able to predict approximately 74% to 82% of the E. coli concentrations.