Showing papers on "Weather station published in 2020"

Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station

Abstract: Non-predictive or inaccurate weather forecasting can severely impact the community of users such as farmers. Numerical weather prediction models run in major weather forecasting centers with several supercomputers to solve simultaneous complex nonlinear mathematical equations. Such models provide the medium-range weather forecasts, i.e., every 6 h up to 18 h with grid length of 10–20 km. However, farmers often depend on more detailed short-to medium-range forecasts with higher-resolution regional forecasting models. Therefore, this research aims to address this by developing and evaluating a lightweight and novel weather forecasting system, which consists of one or more local weather stations and state-of-the-art machine learning techniques for weather forecasting using time-series data from these weather stations. To this end, the system explores the state-of-the-art temporal convolutional network (TCN) and long short-term memory (LSTM) networks. Our experimental results show that the proposed model using TCN produces better forecasting compared to the LSTM and other classic machine learning approaches. The proposed model can be used as an efficient localized weather forecasting tool for the community of users, and it could be run on a stand-alone personal computer.

ClimateEU, scale-free climate normals, historical time series, and future projections for Europe

Abstract: Interpolated climate data have become essential for regional or local climate change impact assessments and the development of climate change adaptation strategies. Here, we contribute an accessible, comprehensive database of interpolated climate data for Europe that includes monthly, annual, decadal, and 30-year normal climate data for the last 119 years (1901 to 2019) as well as multi-model CMIP5 climate change projections for the 21st century. The database also includes variables relevant for ecological research and infrastructure planning, comprising more than 20,000 climate grids that can be queried with a provided ClimateEU software package. In addition, 1 km and 2.5 km resolution gridded data generated by the software are available for download. The quality of ClimateEU estimates was evaluated against weather station data for a representative subset of climate variables. Dynamic environmental lapse rate algorithms employed by the software to generate scale-free climate variables for specific locations lead to improvements of 10 to 50% in accuracy compared to gridded data. We conclude with a discussion of applications and limitations of this database. Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.13190834

The problem of scale in predicting biological responses to climate

Abstract: Many analyses of biological responses to climate rely on gridded climate data derived from weather stations, which differ from the conditions experienced by organisms in at least two respects. First, the microclimate recorded by a weather station is often quite different to that near the ground surface, where many organisms live. Second, the temporal and spatial resolutions of gridded climate datasets derived from weather stations are often too coarse to capture the conditions experienced by organisms. Temporally and spatially coarse data have clear benefits in terms of reduced model size and complexity, but here we argue that coarse-grained data introduce errors that, in biological studies, are too often ignored. However, in contrast to common perception, these errors are not necessarily caused directly by a spatial mismatch between the size of organisms and the scale at which climate data are collected. Rather, errors and biases are primarily due to (a) systematic discrepancies between the climate used in analysis and that experienced by organisms under study; and (b) the non-linearity of most biological responses in combination with differences in climate variance between locations and time periods for which models are fitted and those for which projections are made. We discuss when exactly problems of scale can be expected to arise and highlight the potential to circumvent these by spatially and temporally down-scaling climate. We also suggest ways in which adjustments to deal with issues of scale could be made without the need to run high-resolution models over wide extents.

Investigation of CO2 Variation and Mapping Through Wearable Sensing Techniques for Measuring Pedestrians’ Exposure in Urban Areas

Abstract: Citizens’ wellbeing is mainly threatened by poor air quality and local overheating due to human-activity concentration and land-cover/surface modification in urban areas. Peculiar morphology and metabolism of urban areas lead to the well-known urban-heat-island effect, characterized by higher air temperature in cities than in their surroundings. The environmental mapping of the urban outdoors at the pedestrian height could be a key tool to identify risky areas for humans in terms of both poor-air-quality exposure and thermal comfort. This study proposes urban environment investigation through a wearable miniaturized weather station to get the spatial distribution of key parameters according to the citizens’ perspective. The innovative system monitors and traces the field values of carbon dioxide (CO2) concentration, such as air temperature and wind-speed values, which have been demonstrated to be related to outdoor wellbeing. The presented monitoring campaign focused on a two-way, two-lane road in Rome (Italy) during traffic rush hours on both working days and weekends. Collected data were analyzed with respect to timing and position, and possible correlations among different variables were examined. Results demonstrated the wearable system capability to catch pedestrian-exposure variability in terms of CO2 concentration and local overheating due to urban structure, highlighting potentials in the citizens’ involvement as observation vectors to extensively monitor urban environmental quality.

Low cost smart weather station using Arduino and ZigBee

Abstract: This paper presents low cost-effective weather station with monitoring system by using ZigBee communication technique that serves as a communication channel by using hardware and sensors to transmit and receive data in the weather station system. Using ZigBee over the Bluetooth for the short coverage distance about (1-10 m) and over the (WLAN) (wireless local area network) or Wi-Fi, a WLAN has limitation like delay, lacking BW of the handover of a large amount of data, and some areas have no internet coverage. The system includes implementation and design for the weather station using Arduino Uno board and five sensors gives sixth reading data (rain state, wind level, air pressure, dust density, temperature and humidity). The data can be stored in SD card on receiving (clouding and main processing side) from more than one transmitter node (ZigBee Network). It can be retrieved the data in any time and date. Results showed the system has no delay and the data reputedly changing ever second with the new reading.

Evaluation of Daily Precipitation Extremes in Reanalysis and Gridded Observation-Based Data Sets Over Germany

Abstract: Accurate and reliable gridded datasets are important for analyzing extreme weather and climate events. Specifically, these datasets should produce extreme value statistics that are close to reality. Here we use various statistical methods to evaluate the quality of four gridded data products in representing daily precipitation extremes. The data products are the COSMO-REA6 regional reanalysis, the ERA5 global reanalysis, and the E-OBS and HYRAS gridded observation-based datasets. The statistical methods we use offer a thorough insight into the quality of the different datasets by providing temporal and spatial extreme value statistics of daily precipitation. Our results show that all datasets except HYRAS underestimate the magnitude of daily precipitation extremes when compared with weather station data. Moreover, the reanalysis datasets give generally worse extreme value statistics of daily precipitation than the gridded observation-based datasets. In particular, the reanalysis datasets often fail in reproducing the accurate timing of observed daily precipitation extremes.

Analysis of Copernicus' ERA5 Climate Reanalysis Data as a Replacement for Weather Station Temperature Measurements in Machine Learning Models for Olive Phenology Phase Prediction.

Abstract: Knowledge of phenological events and their variability can help to determine final yield, plan management approach, tackle climate change, and model crop development. THe timing of phenological stages and phases is known to be highly correlated with temperature which is therefore an essential component for building phenological models. Satellite data and, particularly, Copernicus' ERA5 climate reanalysis data are easily available. Weather stations, on the other hand, provide scattered temperature data, with fragmentary spatial coverage and accessibility, as such being scarcely efficacious as unique source of information for the implementation of predictive models. However, as ERA5 reanalysis data are not real temperature measurements but reanalysis products, it is necessary to verify whether these data can be used as a replacement for weather station temperature measurements. The aims of this study were: (i) to assess the validity of ERA5 data as a substitute for weather station temperature measurements, (ii) to test different machine learning models for the prediction of phenological phases while using different sets of features, and (iii) to optimize the base temperature of olive tree phenological model. The predictive capability of machine learning models and the performance of different feature subsets were assessed when comparing the recorded temperature data, ERA5 data, and a simple growing degree day phenological model as benchmark. Data on olive tree phenology observation, which were collected in Tuscany for three years, provided the phenological phases to be used as target variables. The results show that ERA5 climate reanalysis data can be used for modelling phenological phases and that these models provide better predictions in comparison with the models trained with weather station temperature measurements.

Smart Weather Forecasting Using Machine Learning: A Case Study in Tennessee.

Abstract: Traditionally, weather predictions are performed with the help of large complex models of physics, which utilize different atmospheric conditions over a long period of time. These conditions are often unstable because of perturbations of the weather system, causing the models to provide inaccurate forecasts. The models are generally run on hundreds of nodes in a large High Performance Computing (HPC) environment which consumes a large amount of energy. In this paper, we present a weather prediction technique that utilizes historical data from multiple weather stations to train simple machine learning models, which can provide usable forecasts about certain weather conditions for the near future within a very short period of time. The models can be run on much less resource intensive environments. The evaluation results show that the accuracy of the models is good enough to be used alongside the current state-of-the-art techniques. Furthermore, we show that it is beneficial to leverage the weather station data from multiple neighboring areas over the data of only the area for which weather forecasting is being performed.

Using urban climate modelling and improved land use classifications to support climate change adaptation in urban environments: A case study for the city of Klagenfurt, Austria

Abstract: This study outlines the results of current and future climate scenarios, and potentially realizable climate adaptation measures, for the city of Klagenfurt, Austria. For this purpose, we used the microscale urban climate model (MUKLIMO_3), in conjunction with the cuboid method, to calculate climate indices such as the average number of summer and hot days per year. For the baseline simulation, we used meteorological measurements from 1981 to 2010 from the weather station located at Klagenfurt Airport. Individual building structures and canopy cover from several land monitoring services were used to derive accurate properties for land use classes in the study domain. To characterize the effectiveness of climate adaptation strategies, we compared changes in the climate indices for several (future) climate adaptation scenarios to the reference simulation. Specifically, we considered two major adaptation pathways: (i) an increase in the albedo values of sealed areas (i.e., roofs, walls and streets) and (ii) an increase in green surfaces (i.e., lawns on streets and at roof level) and high vegetated areas (i.e., trees). The results indicate that some climate adaptation measures show higher potential in mitigating hot days than others, varying between reductions of 2.3 to 11.0%. An overall combination of adaptation measures leads to a maximum reduction of up to 44.0%, indicating a clear potential for reduction/mitigation of urban heat loads. Furthermore, the results for the future scenarios reveal the possibility to remain at the current level of urban heat load during the daytime over the next three decades for the overall combination of measures.

Performance Improvement of Artificial Neural Network Model in Short-term Forecasting of Wind Farm Power Output

Abstract: Due to the low dispatchability of wind power, the massive integration of this energy source in power systems requires short-term and very short-term wind power output forecasting models to be as efficient and stable as possible. A study is conducted in the present paper of potential improvements to the performance of artificial neural network (ANN) models in terms of efficiency and stability. Generally, current ANN models have been developed by considering exclusively the meteorological information of the wind farm reference station, in addition to selecting a fixed number of time periods prior to the forecasting. In this respect, new ANN models are proposed in this paper, which are developed by: varying the number of prior 1-h periods (periods prior to the forecasting hour) chosen for the input layer parameters; and/or incorporating in the input layer data from a second weather station in addition to the wind farm reference station. It has been found that the model performance is always improved when data from a second weather station are incorporated. The mean absolute relative error (MARE) of the new models is reduced by up to 7.5%. Furthermore, the longer the forecasting horizon, the greater the degree of improvement.

Low Cost IoT Enabled Weather Station

Abstract: The recent trends in the variations of climatic conditions are drastic throughout the world and furthermore its growing unpredictability is a major concern. The existing solutions are highly global and are inaccessible to the common man. The weather conditions applicable to a city may not be as such for a farmer of small rural region or a worker of a small town. Hence, humidity and temperature measurement plays an important role in different fields like Agriculture, Science, Engineering and Technology. The proposed work provides an optimal solution for monitoring the weather conditions at extremely local level with low cost, compact Internet of Things (IoT) based system. In this paper the design of the system is presented with the use of Node MCU for realizing the low cost solution. This low cost weather station is a product equipped with instruments and sensors for measuring the atmospheric conditions like temperature, humidity, wing speed, wind direction for the purpose of making weather forecasts. With IoT enabling, weather station is able to upload, without any human intervention, the measured atmospheric parameters i.e. temperature, humidity, wind speed, wind direction to the IoT cloud. From the cloud user can access all the atmospheric parameters being measured through weather station from any location across the world from any connected device - laptop or mobile phone. The “Low cost Compact IoT enabled Weather Station” need not to be physically visited to read out the measured atmospheric parameters and thus does not have any display which also makes it power efficient running at only 80mA to 90mA.

Evaluation of employing local climate zone classification for mesoscale modelling over Beijing metropolitan area

Abstract: Urban land use and landscape morphology exert notable influences on local climate and its surrounding environment. Better understanding of the complex interplay between urban landscape and overlying atmosphere could contributes to decision-making related to urban planning and risk assessment. This paper classifies local climate zones (LCZs) over Beijing metropolitan area following the World Urban Database and Access Portal Tools (WUDAPT) level 0 method, and evaluates the effect of LCZ classification on mesoscale Weather Research and Forecasting (WRF) modelling over the city. Specifically, according to the method proposed by Stewart and Oke (Bull Am Meteor Soc 93(12):1879–1900, https://doi.org/10.1175/BAMS-D-11-00019.1, 2012), the LCZ classification across Beijing is created based on the Landsat imagery of the Earth’s surface. The derived LCZ system is then imported to the WRF model, and coupled to different urban canopy schemes, i.e. single-layer urban canopy model (SLUCM), multi-layer urban canopy model (BEP—building effect parameterization), and the BEP model with a simple building energy model (BEP + BEM). The performance of employing this refined land use classification scheme versus those using United States Geological Survey land use data is evaluated by comparisons with weather station observations. The results, e.g. the spatial distribution of 2-m temperature and the diurnal variation of the surface heat fluxes, indicate that the LCZ classification scheme yields better comparisons than the default land use method, especially when coupled to the SLUCM as compared to BEP and BEP + BEM. This finding qualifies the coupling scheme of LCZ and SLUCM as a promising albeit simple option for weather modelling in a finer resolution.

Local Climate Zone Classification Scheme Can Also Indicate Local-Scale Urban Ventilation Performance: An Evidence-Based Study

Abstract: Studies on urban ventilation indicate that urban ventilation performance is highly dependent on urban morphology. Some studies have linked local-scale urban ventilation performance with the local climate zone (LCZ) that is proposed for surface temperature studies. However, there is a lack of evidence-based studies showing LCZ ventilation performance and affirming the reliability of using the LCZ classification scheme to demonstrate local-scale urban ventilation performance. Therefore, this study aims to analyse LCZ ventilation performances in order to understand the suitability of using the LCZ classification scheme to indicate local-scale urban ventilation performance. This study was conducted in Shenyang, China, with wind information at 16 weather stations in 2018. The results indicate that the Shenyang weather station had an annual mean wind speed of 2.07 m/s, while the mean wind speed of the overall 16 stations was much lower, only 1.44 m/s in value. The mean wind speed at Shenyang weather station and the 16 stations varied with seasons, day and night and precipitation conditions. The spring diurnal mean wind was strong with the speeds of 3.56 m/s and 2.21 m/s at Shenyang weather station and the 16 stations, respectively. The wind speed (2.21 m/s at Shenyang weather station) under precipitation conditions was higher than that (1.75 m/s at Shenyang weather station) under no precipitation conditions. Downtown ventilation performance was weaker than the approaching wind background, where the relative mean wind speed in the downtown area was only 0.53, much less than 1.0. The downtown ventilation performance also varied with seasons, day and night and precipitation conditions, where spring diurnal downtown ventilation performance was the weakest and the winter nocturnal downtown ventilation performance was the strongest. Moreover, the annual mean wind speed of the 16 zones decreased from the sparse, open low-rise zones to the compact midrise zones, indicating the suitability of using LCZ classification scheme to indicate local-scale urban ventilation performance. The high spatial correlation coefficients under different seasons, day and night and precipitation conditions, ranging between 0.68 and 0.99, further affirmed that LCZ classification scheme is also suitable to indicate local-scale urban ventilation performance, despite without the consideration of street structure like precinct ventilation zone scheme.

Design and Implement of a Weather Monitoring Station using CoAP on NB-IoT Network

Abstract: The goal of this work is to design and implement a weather station prototype which can monitor and collect weather data. The weather station used Arduino board and other devices which have ability to measure temperature, humidity, wind speed and direction, ozone gas, atmospheric pressure and rainfall data. The system focused on wide range of IoT devices, inexpensive, endurance of battery life, and connection density. Therefore, Narrowband Internet of Things network (NB-IoT) will be used to transfer data to MySQL database server via Constrained Application Protocol (CoAP). Received data can be displayed using Grafana (Open source visualization and analytics software) on a personal computer. Thus, this system will be very beneficial for many who depend on weather data as part of their everyday lives.

A Deep Convolutional Neural Network Model for improving WRF Forecasts.

Abstract: Advancements in numerical weather prediction models have accelerated, fostering a more comprehensive understanding of physical phenomena pertaining to the dynamics of weather and related computing resources. Despite these advancements, these models contain inherent biases due to parameterization and linearization of the differential equations that reduce forecasting accuracy. In this work, we investigate the use of a computationally efficient deep learning method, the Convolutional Neural Network (CNN), as a post-processing technique that improves mesoscale Weather and Research Forecasting (WRF) one day forecast (with a one-hour temporal resolution) outputs. Using the CNN architecture, we bias-correct several meteorological parameters calculated by the WRF model for all of 2018. We train the CNN model with a four-year history (2014-2017) to investigate the patterns in WRF biases and then reduce these biases in forecasts for surface wind speed and direction, precipitation, relative humidity, surface pressure, dewpoint temperature, and surface temperature. The WRF data, with a spatial resolution of 27 km, covers South Korea. We obtain ground observations from the Korean Meteorological Administration station network for 93 weather station locations. The results indicate a noticeable improvement in WRF forecasts in all station locations. The average of annual index of agreement for surface wind, precipitation, surface pressure, temperature, dewpoint temperature and relative humidity of all stations are 0.85 (WRF:0.67), 0.62 (WRF:0.56), 0.91 (WRF:0.69), 0.99 (WRF:0.98), 0.98 (WRF:0.98), and 0.92 (WRF:0.87), respectively. While this study focuses on South Korea, the proposed approach can be applied for any measured weather parameters at any location.

Methods for Estimating Wet Bulb Globe Temperature From Remote and Low-Cost Data: A Comparative Study in Central Alabama.

Abstract: Heat stress is a significant health concern that can lead to illness, injury, and mortality. The wet bulb globe temperature (WBGT) index is one method for monitoring environmental heat risk. Generally, WBGT is estimated using a heat stress monitor that includes sensors capable of measuring ambient, wet bulb, and black globe temperature, and these measurements are combined to calculate WBGT. However, this method can be expensive, time consuming, and requires careful attention to ensure accurate and repeatable data. Therefore, researchers have attempted to use standard meteorological measurements, using single data sources as an input (e.g., weather stations) to calculate WBGT. Building on these efforts, we apply data from a variety of sources to calculate WBGT, understand the accuracy of our estimated equation, and compare the performance of different sources of input data. To do this, WBGT measurements were collected from Kestrel 5400 Heat Stress Trackers installed in three locations in Alabama. Data were also drawn from local weather stations, North American Land Data Assimilation System (NLDAS), and low cost iButton hygrometers. We applied previously published equations for estimating natural wet bulb temperature, globe temperature, and WBGT to these diverse data sources. Correlation results showed that WBGT estimates derived from all proxy data sources-weather station, weather station/iButton, NLDAS, NLDAS/iButton-were statistically indistinguishable from each other, or from the Kestrel measurements, at two of the three sites. However, at the same two sites, the addition of iButtons significantly reduced root mean square error and bias compared to other methods.

Diurnal Valley Winds in a Deep Alpine Valley: Observations

Abstract: Diurnal valley winds frequently form over complex topography, particularly under fair weather conditions, and have a significant impact on the local weather and climate. Since diurnal valley winds result from complex and multi-scale interactions, their representation in numerical weather prediction models is challenging. Better understanding of these local winds based on observations is crucial to improve the accuracy of the forecasts. This study investigates the diurnal evolution of the three-dimensional mean wind structure in a deep Alpine valley, the Rhone valley at Sion, using data from a radar wind profiler and a surface weather station operated continuously from 1 September 2016 to 17 July 2017. In particular, the wind profiler data was analyzed for a subset of days on which fair weather conditions allowed for the full development of thermally driven winds. A pronounced diurnal cycle of the wind speed, as well as a reversal of the wind direction twice per day is documented for altitudes up to about 2 km above ground level (AGL) in the warm season and less than 1 km AGL in winter. The diurnal pattern undergoes significant changes during the course of the year. Particularly during the warm-weather months of May through to September, a low-level wind maximum occurs, where mean maximum up-valley velocities of 8–10 m s−1 are found between 15–16 UTC at altitudes around 200 m AGL. In addition, during nighttime, a down-valley jet with maximum wind speeds of 4–8 m s−1 around 1 km AGL is found. A case study of a three-day period in September 2016 illustrates the occurrence of an elevated layer of cross-valley flow around 1–1.5 km AGL.

Downscaling fire weather extremes from historical and projected climate models

Abstract: An important aspect of predicting future wildland fire risk is estimating fire weather—weather conducive to the ignition and propagation of fire—under realistic climate change scenarios. Because the majority of area burned occurs on a few days of extreme fire weather, this task should be able to resolve fire weather extremes. In this paper, we present a statistical downscaling procedure based on distribution based scaling (DBS) to bias correct the Fire Weather Index (FWI), part of the Canadian Forest Fire Danger Rating System, as calculated from modeled climate data. Our study area is western Canada (British Columbia and Alberta) and we consider both an historical control period (1990–2000) and three future time periods (2020–2030, 2050–2060, and 2080–2090). The historical data used to calibrate the DBS procedure comprises weather station data and weather from the North American Regional Reanalysis (NARR), whereas the future climate projections are the output of three regional climate models, corresponding to different model parameterizations and downscaled from the NCAR Community Earth System Model under the RCP 8.5 scenario. By fitting a truncated Weibull distribution to observed and modeled FWI values, our method is able to reproduce historical extremes in fire weather indices as determined by the distribution of annual potential spread days, which are defined as days with FWI values greater than 19. Moreover, by calibrating the DBS procedure with gridded reanalysis data as well as station observations, we are able to project future spread day distributions over the entire study area. The results of this study show the DBS procedure leads to a greater number of projected annual spread days at most locations compared with estimates using the uncorrected model output, and that all three RCM models show positive increases in potential annual spread days for the 2050–2060 and 2080–2090 time periods.

Wi-Fi-Based Portable Weather Station for Monitoring Temperature, Relative Humidity, Pressure, Precipitation, Wind Speed, and Direction

Abstract: This manuscript mainly focuses on the development of a model weather station to measure weather data: temperature, relative humidity, atmospheric pressure, wind direction, speed, and rainfall. This type of weather station has been designed to perform unmanned measurement of weather data. The measured data is wirelessly transmitted to the remote station for logging and displays the information to different smart gadgets. This wireless connectivity has been planned using Wi-Fi connections which establishes mesh network for reliable data communication. Furthermore, our consistent outputs do help the dwellers to take necessary precautions.

IoT Based Low-cost Weather Station and Monitoring System for Smart Agriculture

Abstract: It is estimated that the world's population will be about 9.1 billion by 2050. The UN FAO has reported that food production would need to be increased by approximately 70 percent to feed this increased population. Therefore, to ensure high yields and farm profitability, it is very important to improve agricultural productivity. In this sense, the technology of the Internet of Things (IoT) has become the key road towards novel practice in agriculture. In the agriculture sector, climate change is also a major concern. A solution to completely satisfy the requirements of automated and real-time monitoring of environmental parameters such as humidity, temperature and rain is proposed in this paper. The proposed platform, which collects environmental data (temperature, humidity and rain) over a period of one year was tested on a real farm in Tunisia. The results show that the proposed solution can be used as a reference model to meet the requirements for large-scale agricultural farm calculation, transmission and storage.

Updated Typical Weather Years for the Energy Simulation of Buildings in Mediterranean Climate. A Case Study for Sicily

Abstract: Building energy simulations are normally run through Typical Weather Years (TWYs) that reflect the average trend of local long-term weather data. This paper presents a research aimed at generating updated typical weather files for the city of Catania (Italy), based on 18 years of records (2002–2019) from a local weather station. The paper reports on the statistical analysis of the main recorded variables, and discusses the difference with the data included in a weather file currently available for the same location based on measurements taken before the 1970s but still used in dynamic energy simulation tools. The discussion also includes a further weather file, made available by the Italian Thermotechnical Committee (CTI) in 2015 and built upon the data registered by the same weather station but covering a much shorter period. Three new TWYs are then developed starting from the recent data, according to well-established procedures reported by ASHRAE and ISO standards. The paper discusses the influence of the updated TWYs on the results of building energy simulations for a typical residential building, showing that the cooling and heating demand can differ by 50% or even 65% from the simulations based on the outdated weather file.

Educational Mechatronics and Internet of Things: A Case Study on Dynamic Systems Using MEIoT Weather Station.

Abstract: This paper presents the design and development of an IoT device, called MEIoT weather station, which combines the Educational Mechatronics and IoT to develop the required knowledge and skills for Industry 4.0. MEIoT weather station connects to the internet, measures eight weather variables, and upload the sensed data to the cloud. The MEIoT weather station is the first device working with the IoT architecture of the National Digital Observatory of Intelligent Environments. In addition, an IoT open platform, GUI-MEIoT, serves as a graphic user interface. GUI-MEIoT is used to visualize the real-time data of the weather variables, it also shows the historical data collected, and allows to export them to a csv file. Finally, an OBNiSE architecture application to Engineering Education is presented with a dynamic system case of study that includes the instructional design carried out within the Educational Mechatronics Conceptual Framework (EMCF) to show the relevance of this proposal. This work main contribution to the state of art is the design and integration of the OBNiSE architecture within the EMCF offering the possibility to add more IoT devices for several smart domains such as smart campus, smart cities, smart people and smart industries.

Groundwater level prediction using genetic programming: the importance of precipitation data and weather station location on model accuracy

Abstract: Groundwater (GW) level prediction is important for effective GW resource management. It is hypothesized that using precipitation data in GW level modelling will increase the overall accuracy of the results and that the distance of the observation well to the weather station (where precipitation data are obtained) will affect the model outcome. Here, genetic programming (GP) was used to predict GW level fluctuation in multiple observation wells under three scenarios to test these hypotheses. In Scenario 1, GW level and precipitation data were used as input data. Scenarios 2 only had GW level data as inputs to the model, and in Scenarios 3, only precipitation data were used as inputs. Long-term GW level time series data covering a period of 8 years were used to train and test the GP model. Further, to examine the effect of data from previous time periods on the accuracy of GW level prediction, 12 models with input data up to 12 months prior to the current period were investigated. Model performance was evaluated using two criteria, coefficient of determination (R2) and root mean square error (RMSE). Results show that when predicting GW levels through GP, using GW level and precipitation data together (Scenario 1) produces results with higher accuracy compared to only using GW level (Scenario 2) or precipitation data (Scenario 3). Additionally, it was found that model accuracy was highest for the well located closest to the weather station (where precipitation data were collected), demonstrating the importance of weather station location in GW level prediction. It was also found that using data from up to six previous time periods (months) can be the most efficient combination of input data for accurate predictions. The findings from this study are useful for increasing the prediction accuracy of GW level variations in unconfined aquifers for sustainable GW resource management.