(Press-News.org) A research team at the University of Córdoba has developed and evaluated models for the prediction of solar radiation in nine locations in southern Spain and North Carolina (USA).
Measuring solar radiation is costly, as are all the tasks related to the maintenance and calibration of the most commonly used sensors: pyranometers and radiometers. The result is a paucity of reliable data. Hence, a research group from the University of Córdoba has developed and evaluated several Machine Learning models to predict solar radiation in nine locations (southern Spain and North Carolina, USA) spanning a range of different geo-climatic conditions (aridity, distance to the sea, and elevation). The work has been featured in the journal Applied Energy.
One of the main breakthroughs of the models they created is that they only need thermal data to estimate daily solar radiation. "Measuring and having air temperature data today, thanks to low-cost sensorization and IoT (Internet of Things) technologies, is quite affordable," added Javier Estévez Gualda, a researcher and professor at the UCO. Most of the existing meteorological stations around the world have thermal and rainfall sensors, but very few measure solar radiation.
Juan Antonio Bellido, the main author of the work, highlights that one of the problems that currently exist in models based on Artificial Intelligence is the configuration of internal parameters, termed hyperparameters. "We might compare these hyperparameters to the controls on a sound technician's mixing board; their adjustment is essential, as the modification of potentiometers must be constantly prevented from causing sound problems," he explains. To solve this problem, they used an automatic algorithm called Bayesian Optimization (based on Bayes' theory), which is responsible for efficiently and quickly searching for suitable parameters so that the models obtain efficient and accurate results.
All the models used can be classified as supervised models; that is, they require data training. However, they can be classified into several groups: models based on neural networks, whose functioning is similar to that of neurons (Multilayer Perceptron - MLP, Extreme Learning Machine - ELM - and Generalized Regression Neural Networks - GRNN); models based on a tree typology (Random Forest - RF - and Extreme Gradient Boost - XGBoost), and others, such as Support Vector Machine (SVM).
These have been tested in different arid conditions, such as southern Spain, and in North Carolina (USA); that is, in arid, semi-arid, sub-humid, dry and humid areas. 31% of the earth's surface is arid/semi-arid/dry sub-humid, while 67% is humid. In this way, they are applicable to the entire surface of the Earth. When evaluating the efficiency of the models trained in new locations whose data has not been used during the same, significant improvements are yielded in all the locations. For example, those trained with time series from Cabra (Córdoba) and then applied in El Campillo (Huelva) show a considerable improvement.
Professor and researcher Amanda P. García-Marín, who is also part of the team, stated that the results improve on current models, obtaining great precision in estimating daily solar radiation values. "This is crucial in locations with no available or missing/low-quality data sets, and can be used to optimize the determination of potential locations for the construction of solar power plants," concluded researcher Javier Estévez Gualda.
Another of the work's strengths is that the models are available to any researcher,via the free-access GitHub repository, so their use can be extended to any area of the planet, depending on its aridity. In addition, from the agronomic point of view, the precise estimation of solar radiation is vital, since it is a key variable in the development of crops.
This study is part of the Smarity project (AGL2017-87658-R), funded by the Ministry of Science's Social Challenges National R&D Plan, which seeks solutions to climatic aridity in southern Spain and to intelligently predict the spatio-temporal variability of aridity and its effects on agriculture and the environment.
INFORMATION:
Reference
Bellido-Jiménez, J. A., EstévezGualda, J., Penélope García-Marín, A. (2021). Assessing new intra-daily temperature-based machine learning models to outperform solar radiation predictions in different conditions. Applied Energy, Vol. 298. DOI: https://doi.org/10.1016/j.apenergy.2021.117211
Washington, DC, July 8, 2021 - A study in the Journal of the American Academy of Child and Adolescent Psychiatry (JAACAP), published by Elsevier, reports that the type of one-on-one treatment plans delivered to toddlers, aged 12-30 months, diagnosed with autism spectrum disorder (ASD) did not lead to any significantly different outcomes. Neither the type of evidence-based intervention provided, nor the number of hours of therapy were shown to have an impact.
The treatments, or intervention methods, delivered by specialized staff to the very young, during the study were either the Early ...
Of the Swedish men in their late teens who performed well in the physical fitness tests for military conscription, a relatively high proportion were able to avoid hospital care when they became infected with COVID-19 during the pandemic up to 50 years later. This has been shown by University of Gothenburg researchers in a register study, with results now published in the BMJ Open.
The study is based on the Swedish Conscription Register, which contains particulars of over 1.5 million young Swedish men who began their military service in the years 1969-2005. Almost all of these men then underwent both a bicycle test and a strength test. Some 2,500 of the men included in the Conscription Register were later, in spring 2020, hospitalized with COVID-19.
For their study, the scientists ...
A research study from the The Lundbeck Foundation Initiative for Integrative Psychiatric Research iPSYCH shows that people with ADHD, who also have another psychiatric diagnosis, are more likely to stop taking their ADHD medicine.
ADHD is one of the most common psychiatric disorders in childhood and is commonly treated with medication. ADHD medicine can be divided into two groups: medicine that has a stimulating effect - also known as stimulants - and non-stimulants, which are often used if a person does not respond well to the other form of medicine.
The medication can be an effective way of reducing symptoms, by ...
Researchers have used the latest wireless technology to develop a new radio receiver for astronomy. The receiver is capable of capturing radio waves at frequencies over a range several times wider than conventional ones, and can detect radio waves emitted by many types of molecules in space at once. This is expected to enable significant progresses in the study of the evolution of the Universe and the mechanisms of star and planet formation.
Interstellar molecular clouds of gas and dust provide the material for stars and planets. Each type of molecule emits radio waves at characteristic frequencies and astronomers have detected emissions from various molecules ...
(Boston)--As analytical instrumentation (gas- and liquid-chromatographs coupled with mass spectrometers) increase in sensitivity and speed, forensic scientists may find themselves still hindered by the process of preparing samples (blood, urine, etc.) for analysis and seeking more efficient approaches.
In an article in WIRES Forensic Science, researchers from Boston University School of Medicine's (BUSM) Biomedical Forensic Sciences program, provide an overview of sample preparation techniques and information on routine sample types that may be encountered in forensic toxicology cases.
Forensic toxicology encompasses a large variety of scenarios including drug-facilitated crimes, understanding ...
A new UBC Sauder School of Business study shows that depending on how employees understand their boss' motivation, employees can feel anger or guilt, and consequently, react differently to abusive supervision.
Former Apple CEO Steve Jobs was a famously harsh corporate leader, one who pushed his employees to extremes to achieve the company's lofty aims.
But while many aspiring leaders still believe that the "tough love" approach is effective, a new study from UBC Sauder shows that, even when abusive leadership is meant to push employees to new heights, it can land them in deep lows in the long term.
Abusive supervision -- which includes behaviours like yelling at employees, giving them the silent treatment, or putting them down in front of their ...
More than a third of coal miners and former coal miners suffering from black lung disease struggle with depression, and more than one in 10 has recently considered suicide, a new study finds.
The study is believed to be the first to examine mental-health issues in a large population of coal miners in the United States. Based on the troubling results, the researchers are calling for more mental health resources and treatment for current and former miners. They also are urging further study of potential contributors to the problem, including social determinants of health, ...
Evidence from an ancient eggshell has revealed important new information about the extreme climate change faced by human early ancestors.
The research shows parts of the interior of South Africa that today are dry and sparsely populated, were once wetland and grassland 250,000 to 350,000 years ago, at a key time in human evolution.
Philip Kiberd and Dr Alex Pryor, from the University of Exeter, studied isotopes and the amino acid from ostrich eggshell fragments excavated at the early middle Stone Age site of Bundu Farm, in the upper Karoo region ...
Reston, VA--A performance evaluation of the uEXPLORER total-body PET/CT scanner showed that it exhibits ultra-high sensitivity that supports excellent spatial resolution and image quality. Given the long axial field of view (AFOV) of the uEXPLORER, study authors have proposed new, extended measurements for phantoms to characterize total-body PET imaging more appropriately. This research was published in the June issue of The Journal of Nuclear Medicine.
uEXPLORER is the world's first commercially available total-body PET scanner. The scanner has an AFOV of 194 cm, which allows PET data collection from the ...
Scientists at the Department of Energy's Oak Ridge National Laboratory and the University of Tennessee, Knoxville, have found a way to simultaneously increase the strength and ductility of an alloy by introducing tiny precipitates into its matrix and tuning their size and spacing. The precipitates are solids that separate from the metal mixture as the alloy cools. The results, published in the journal Nature, will open new avenues for advancing structural materials.
Ductility is a measure of a material's ability to undergo permanent deformation without breaking. It determines, among other ...
