Search

The continuing effects of climate change require farmers and growers to have greater understanding of how these changes affect crop production. However, while climatic data is generally available to help provide much of that understanding, it can often be in a form not easy to digest. The proposed Combined Location Online Weather Data (CLOWD) framework is an easy-to-use online platform for analysing recent and historical weather data of any location within Australia at the click of a map. CLOWD requires no programming skills and operates in any HTML5 web browser on PC and mobile devices. It enables comparison between current and previous growing seasons over a range of environmental parameters, and can create a plain-English PDF report for offline use, using natural language generation (NLG). This paper details the platform, the design decisions taken and outlines how farmers and growers can use CLOWD to better understand current growing conditions. Prototypes of CLOWD are now online for PCs and smartphones. [ABSTRACT FROM AUTHOR]

Evapotranspiration affects uncertain changes in volumetric soil moisture content (θ) of earth surface, which is considerably controlled by temporal variability of weather parameters like rainfall and ambient temperature. Accurate measurement of temporal variation and spatial distribution of θ in a particular land is very challenging. Numerical modelling with any suitable computer code might be useful in such cases. Thus, Hydrus 2D modelling of θ variation in the soil at Odisha University of Agriculture and Technology (OUAT) in Bhubaneswar is undertaken as main objective of present study to investigate soil moisture dynamics in top surface layer. For the study, the θ in OUAT land was measured daily by 5 TM water content sensor for the duration of two years spanning from January 2021 to December 2022. Meteorological data for these 2 years are collected from a nearby weather station at OUAT and used for calculating evapotranspiration (ET) based on five different well known ET models. Soil hydraulic parameters of OUAT land were also evaluated by laboratory investigation. The evapotranspiration so calculated along with precipitation and materials properties were then assigned as the inputs in Hydrus 2D simulations. The simulated results are found to be in good agreement with field observations. It is proven by Pearson's coefficient of determination (R2) and Nash-Sutcliffe efficiency (NSE) which are found to be 0.83 and 0.84 respectively. The soil moisture simulation was the most accurate only when measured soil parameters along with atmospheric boundary involving Penman-Monteith (PM) ET model were considered as model inputs. [ABSTRACT FROM AUTHOR]

Three shrinkage regression and two machine‐learning approaches were evaluated to derive models for the prediction of epidemiological characteristics of white rust of mustard, using data from 112 epidemics in the field. Four epidemiological characteristics were considered: (a) crop age at first appearance of disease, (b) crop age at highest disease severity, (c) highest disease severity in a growing season and (d) area under disease progress curve (AUDPC), along with (e) crop yield to measure the effects of disease on crop performance. We developed models using weather indices to predict these variables using five different approaches: ANN, Elastic Net, LASSO, random forest and ridge regression. One model was developed for each sowing date corresponding to each dependent variable. Two hundred different models were developed. All models performed well at the calibration stage for most of the five variables at all sowing dates. However, at the validation stage, ANN‐derived models outperformed (R2val ~ 1.00, nRMSEV ~0.00 and MBEV ~0.00 in most cases) the three shrinkage regression‐derived models in predicting all five variables. Predictions by random forest‐ and LASSO‐derived models were acceptable for AUDPC and crop yield. Evaluation metrics (including R2val, nRMSEV and MBEV) suggested that ENET‐ and ridge‐derived models do not perform satisfactorily, whereas ANN‐derived models yielded reliable results and thus generate robust predictions. The present work constitutes a systematic effort to compare modelling methods for disease and yield prediction and illustrates the relevance of weather variables in predicting multiple epidemiological variables, and of multiple disease variables as predictors of actual crop yield. [ABSTRACT FROM AUTHOR]

Understanding the impact of climate on peanut growth is crucial, given the importance of temperature in peanut to accumulate Growing Degree Days (GDD). Therefore, our study aimed to compare data sourced from the NASA POWER platform with information from surface weather stations to identify underlying climate variables associated with peanut maturity (PMI). Second, we sought to devise alternative methods for calculating GDD in peanut fields without nearby weather stations. We utilized four peanut production fields in the state of Georgia, USA, using the cultivar Georgia-06G. Weather data from surface stations located near peanut fields were obtained from the University of Georgia’s weather stations. Corresponding data from the NASA POWER platform were downloaded by inputting the geographic coordinates of the weather stations. The climate variables included maximum and minimum temperatures, average temperature, solar radiation, surface pressure, relative humidity, and wind speed. We evaluated the platforms using Pearson correlation (r) analysis (p < 0.05), linear regression analysis, assessing coefficient of determination (R2), root mean square error (RMSE), and Willmott index (d), as well as principal component analysis. Among the climate variables, maximum and minimum temperatures, average temperature, and solar radiation showed the highest R2 values, along with low RMSE values. Conversely, wind speed and relative humidity exhibited lower correlation values with errors higher than those of the other variables. The grid size from the NASA POWER platform contributed to low model adjustments since the grid’s extension is kilometric and can overlap areas. Despite this limitation, NASA POWER proves to be a potential tool for PMI monitoring. It should be especially helpful for growers who do not have surface weather stations near their farms.

Abstract Food and beverage (F&B) outlets such as restaurants, delis and fast-food joins are commonly owner-operated small businesses with limited access to modern forecasting technologies. Managers often rely on experience-based forecasting heuristics, which face challenges, as demand is dependent on external factors such as weather conditions, holidays, and regional events. Introducing practical AI-based sales forecasting techniques is a way to improve operational and financial planning and automate repetitive forecasting tasks. This case study proposes an approach to work with F&B owners in creating and introducing machine learning (ML)-based sales forecasting tailored to the unique local aspects of the business. It enhances demand forecasting in the F&B domain by identifying data types and sources that improve predictive models and bolster managerial trust. The case study uses over 5 years of hourly sales data from a fast-food franchise in Germany. It trains a predictive algorithm using historical sales, promotional activities, weather conditions, regional holidays and events, as well as macroeconomic indicators. The AI model surpasses heuristic forecasts, reducing the root mean squared error by 22% to 33% and the mean average error by 19% to 31%. Although the initial implementation demands managerial involvement in selecting predictors and real-world testing, this forecasting method offers practical benefits for F&B businesses, enhancing both their operations and environmental impact.

The proliferation of urban areas and the concurrent increase in vehicular mobility have escalated the urgency for advanced traffic management solutions. This data article introduces two traffic datasets from Madrid, collected between June 2022 and February 2024, to address the challenges of traffic management in urban areas. The first dataset provides detailed traffic flow measurements (vehicles per hour) from urban sensors and road networks, enriched with weather data, calendar data and road infrastructure details from OpenStreetMap. This combination allows for an in-depth analysis of urban mobility. Through preprocessing, data quality is ensured by eliminating inconsistent sensor readings. The second dataset is enhanced for advanced predictive modelling. It includes time-based transformations and a tailored preprocessing pipeline that standardizes numeric data, applies one-hot encoding to categorical features, and uses ordinal encoding for specific features. In constructing the datasets, we initially employed the k-means algorithm to cluster data from multiple sensors, thereby highlighting the most representative ones. This clustering can be adapted or modified according to the user's needs, ensuring flexibility for various analyses and applications.This work underscores the importance of advanced datasets in urban planning and highlights the versatility of these resources for multiple practical applications. We highlight the relevance of the collected data for a variety of essential purposes, including traffic prediction, infrastructure planning, studies on the environmental impact of traffic, event planning, and conducting simulations. These datasets not only provide a solid foundation for academic research but also for designing and implementing more effective and sustainable traffic policies. Furthermore, all related datasets, source code, and documentation have been made publicly available, encouraging further research and practical applications in traffic management and urban planning.

Understanding the impact of climate on peanut growth is crucial, given the importance of temperature in peanut to accumulate Growing Degree Days (GDD). Therefore, our study aimed to compare data sourced from the NASA POWER platform with information from surface weather stations to identify underlying climate variables associated with peanut maturity (PMI). Second, we sought to devise alternative methods for calculating GDD in peanut fields without nearby weather stations. We utilized four peanut production fields in the state of Georgia, USA, using the cultivar Georgia-06G. Weather data from surface stations located near peanut fields were obtained from the University of Georgia's weather stations. Corresponding data from the NASA POWER platform were downloaded by inputting the geographic coordinates of the weather stations. The climate variables included maximum and minimum temperatures, average temperature, solar radiation, surface pressure, relative humidity, and wind speed. We evaluated the platforms using Pearson correlation (r) analysis (p < 0.05), linear regression analysis, assessing coefficient of determination (R2), root mean square error (RMSE), and Willmott index (d), as well as principal component analysis. Among the climate variables, maximum and minimum temperatures, average temperature, and solar radiation showed the highest R2 values, along with low RMSE values. Conversely, wind speed and relative humidity exhibited lower correlation values with errors higher than those of the other variables. The grid size from the NASA POWER platform contributed to low model adjustments since the grid's extension is kilometric and can overlap areas. Despite this limitation, NASA POWER proves to be a potential tool for PMI monitoring. It should be especially helpful for growers who do not have surface weather stations near their farms. [ABSTRACT FROM AUTHOR]

The SME sector in Indonesia comprises 99.99% of businesses, employing 96.9% of the workforce and contributing 60.5% to GDP and non-oil exports. Despite their importance, SMEs face challenges including limited financial access, product hygiene concerns, and fluctuating demand. Accurate demand prediction is crucial for optimizing production, inventory, and resource allocation. SARIMAX and VAR models are commonly used for demand prediction, with SARIMAX proving more effective, especially when integrating weather data. Due to there are quite few literatures about SARIMAX is used at SMEs, in this study we utilized SARIMAX and VAR models with sales and weather data (average temperature and average humidity) from January to June 2023. SARIMAX with optimum parameters optimum parameters (d=1, D=1, p=2, q=3, P=2, Q=2, s=7) outperformed optimized VAR in predicting demand for food and beverage SMEs. SARIMAX obtained AIC 1070.11, MSE 80.393, MAE 7.513, RMSE 8.966 and reduced MSE by 86.35% compared to VAR. This research highlights the significance of accurate demand prediction for SMEs, emphasizing the importance of considering external factors like weather. Understanding and predicting demand patterns are vital for SMEs to make informed decisions and optimize operations efficiently. [ABSTRACT FROM AUTHOR]

Real-world data collections are generally not easily available. Energy measurements from buildings, houses and other devices can be used within different areas of research while being employed to plan or train models, allowing the improvement of power grid energy efficiency or providing more insight on how an energy community can work.This paper provides a dataset concerning a Portuguese community of 172 households that are geographically close to each other, enabling the establishment of relationships among buildings and the analysis of a community's power consumption.In addition to the consumed energy values, the related local weather information is included in the data. The intersection of weather data and energy measurements can be helpful to train AI models, contributing to explain variations in energy consumption and the absolute values of the energy readings.The inclusion of these weather parameters aims to unveil features that can correlate to the energy measurements, enabling them to be used in multiple areas of research. Hence, it will provide added value to the data as it can be reused to explore Machine Learning algorithms or community energy planning by grid operators.

The study examined the performance of four machine learning algorithms (regression trees, boosted trees, random forests, and artificial neural networks) for estimating evapotranspiration (ETo) based on incomplete meteorological data. Meteorological variables (mean and maximum air temperature, average air humidity, average level of solar radiation, vapor pressure deficit, extraterrestrial solar radiation, and day number of the year) were used as input. The simulation used two calculation scenarios: data with and without average solar radiation. The performance of the different machine learning models was evaluated using the mean square error, root mean square error, coefficient of determination, and slope of regression forced through the origin between the measured and simulated ETo. The results demonstrated that the applied models were able to describe nonlinear relationships between weather parameters and evapotranspiration. The accuracy of evapotranspiration estimation depended on the type of input variables and the machine learning model used. The highest level of evapotranspiration prediction was obtained using the artificial neural networks model. Including solar radiation data in the calculations improved the quality of evapotranspiration prediction in all four models. In the absence of data on the actual solar radiation reaching the Earth's surface, it is advisable to supplement the input data with data on extraterrestrial solar radiation and the day number of the year. Such an approach can be helpful in areas and situations with limited access to meteorological data.

Abstract Renewable energy systems depend on the weather, and weather information, thus, plays a crucial role in forecasting time series within such renewable energy systems. However, while weather data are commonly used to improve forecast accuracy, it still has to be determined in which input shape this weather data benefits the forecasting models the most. In the present paper, we investigate how transformations for weather data inputs, i. e., station-based and grid-based weather data, influence the accuracy of energy time series forecasts. The selected weather data transformations are based on statistical features, dimensionality reduction, clustering, autoencoders, and interpolation. We evaluate the performance of these weather data transformations when forecasting three energy time series: electrical demand, solar power, and wind power. Additionally, we compare the best-performing weather data transformations for station-based and grid-based weather data. We show that transforming station-based or grid-based weather data improves the forecast accuracy compared to using the raw weather data between 3.7 and 5.2%, depending on the target energy time series, where statistical and dimensionality reduction data transformations are among the best.

Renewable energy systems depend on the weather, and weather information, thus, plays a crucial role in forecasting time series within such renewable energy systems. However, while weather data are commonly used to improve forecast accuracy, it still has to be determined in which input shape this weather data benefits the forecasting models the most. In the present paper, we investigate how transformations for weather data inputs, i. e., station-based and grid-based weather data, influence the accuracy of energy time series forecasts. The selected weather data transformations are based on statistical features, dimensionality reduction, clustering, autoencoders, and interpolation. We evaluate the performance of these weather data transformations when forecasting three energy time series: electrical demand, solar power, and wind power. Additionally, we compare the best-performing weather data transformations for station-based and grid-based weather data. We show that transforming station-based or grid-based weather data improves the forecast accuracy compared to using the raw weather data between 3.7 and 5.2%, depending on the target energy time series, where statistical and dimensionality reduction data transformations are among the best. [ABSTRACT FROM AUTHOR]

Urban areas can be characterized by higher outdoor air temperatures than rural ones due to the well-known Urban Heat Island (UHI) phenomenon. This significantly affects buildings energy performance, thus influencing energy needs in terms of cooling and heating. Starting from this, the UHI in Rome was here investigated, providing an updated estimation through 2022 climate data. The influence of the UHI on energy efficiency in buildings has been highlighted by applying climatic data logged by different weather stations within a dynamic simulation tool. Thus, actual climate data have been used as thermal boundary conditions to simulate typical building energy needs, for cooling and heating. The findings of this study demonstrate a notable disparity in climatic conditions between the areas outside the city and the urban context. The maximum values of UHI intensities for daytime and night-time were identified as 3.1°C and 3.5°C, respectively. Moreover, the accurate selection of reference data is a crucial factor for obtaining reliable information regarding the energy demands of buildings within the city. The findings emphasized that utilizing data from airport stations instead of weather stations within urban areas can result in disparities up to approximately -17% for heating and more than 50% for cooling requirements. [ABSTRACT FROM AUTHOR]

The development of novel technologies to mitigate the effects of climate change through Smart Grids requires energy related data. Unfortunately, this type of data is not always available in Mexico, especially from non-large urban areas and at the household level. Therefore, we present a dataset that contains electrical demand and consumption time series of 5 households within a small community in Mexico, at various resolutions, as well as weather data. The electrical demand is given in 15 min resolution, while the electrical consumption is presented in both hourly and daily resolutions. The data is contained within 15 separate .csv files; one for each household's resolution. In turn, the weather data is given in two .csv files (for outdoor and indoor variables, respectively) that together contain 24 meteorological variables measured in a 5 min resolution that is not always consistent. The dataset comprises of two separate folders that contain either the electrical demand and consumption files or the weather files. This dataset could aid in the development of novel smart grid methods and algorithms that might be able to push the energy transition in Mexico and other developing countries forward.

ABSTRACT: The health, longevity, and performance of dairy cattle can be adversely affected by heat stress. This study evaluated the in-barn condition [i.e., temperature, relative humidity, and resulting temperature-humidity index (THI)] at 9 dairy barns with various climates and farm design-management combinations. Hourly and daily indoor and outdoor conditions were compared at each farm, including both mechanically and naturally ventilated barns. On-site conditions were compared with on-farm outdoor conditions, meteorological stations up to 125 km away, and NASA Power data. Canadian dairy cattle face periods of extreme cold and periods of high THI, dependent on the regional climate and season. The northernmost location (53°N) experienced about 75% fewer hours of THI >68 compared with the southernmost location (42°N). Milking parlors had higher THI than the rest of the barn during milking times. The THI conditions inside dairy barns were well correlated with THI conditions measured outside the barns. Naturally ventilated barns with metal roofs and without sprinklers fit a linear relationship (hourly and daily means) with a slope

Water management is very important for human life sustainability. Rainfall forecasting is one of the most important factors for the water management of an area. A forecast is simply a calculation of what happens in the future based on past information under the assumption that the pattern followed in the past would continue in the future also. This work aims at obtaining forecasting models for the time series data set using conventional models and computational models. Varanasi City's annual climate data for a total of 113 years is used for the analysis. Initially, the individual model is considered and used for forecasting. Later, hybrid models will be considered and a comparison between individual models and hybrid models would be obtained. The individual statistical models to be considered are moving average, exponential smoothing with one parameter, and autoregressive integrated moving average (ARIMA). The forecast is also done individually using the k-nearest neighbor (kNN) and interpolation technique cubic spline. Finally, the best-chosen statistical models and the interpolation model are coupled with kNN to develop hybrid models and with these hybrid models, the forecast is done for the data. All the models will be compared and the best among them will be chosen. HIGHLIGHT Rainfall forecasting is very important for water management, here we have compared the five latest AI/data science techniques of forecasting.; Study area is Varanasi, the oldest city in India.; 113 years of climate data is used.; Models used are ARIMA, kNN, spline, exponential smoothing.; The hybrid model was prepared for better forecasting.;

Discoloration of the sapwood caused by blue-stain fungi on conifer logs during interim storage causes significant loss to the forest industry. The fungal infection is often associated with bark beetle attacks because the spores are transmitted by the beetles. They can also be disseminated by rain-splash and moist air. While there are methods to protect logs from sap-stain in wood yards, this is often not possible in the forest for practical and regulatory reasons. Timing of harvesting and timely transportation are often the only ways to prevent blue-stain. To estimate the urgency of transportation, knowledge of the growth of blue-stain fungi and its dependence on weather conditions is of great interest. The proportion of discolored sapwood on Norway spruce logs was recorded along a time series, together with weather data in two field experiments conducted in spring and summer at two alpine sites in Austria. A predictive model was developed to estimate the proportion of blue-stained sapwood based on the temperature sum to which the logs were exposed. After harvest in March, there was a time lag of 82 and 97 days at the two respective sites, caused by initially low temperatures, before discoloration started. In contrast, sap-stain occurred 14 days after the harvest in June, when warm conditions prevailed from the start. The nonlinear least square regression model can help to estimate a window of opportunity to transport wood before it loses its value and serves as a sub model for lead time estimation within logistic decision support systems.

At the centre of Reunion Island, a region denoted « Mafate » is non-connected to the main electrical grid. In the context of the “Micro Reseau Mafate” research project, financed by the European Regional Development Fund, the PIMENT Laboratory and the local electrification union SIDELEC aim to develop microgrid stations in this isolated area. More than 300 homes are concerned by this alternative solution that these microgrids represent.Presented data come from an experimental microgrid between 3 homes at the place called « Roche Plate », where electrical production is obtained by photovoltaic panels and storage by batteries. Local data are collected to simulate electrical systems and determine the optimal working point of energy distribution. These data concern the meteorological conditions, the electrical performance of devices and the inhabitants’ usage of appliances. A weather station placed on the solar plant gives the meteorological conditions of this enclave region. Daily loads for the three families are measured and all the data are stored for analysis. A continuous period of one year of measurements is available for the community and is shared throughout this data paper. These datasets will be completed later. Electrical and meteorological data are collected in situ and stored in a central computer server located at the university.

ABSTRACTIn this article, we study snow avalanche activity during the snow seasons of 2017–2020 using four automatic time-lapse cameras strategically positioned along the southwestern slope of Tasiapik Valley, near the village of Umiujaq, in Nunavik (northern Québec, Canada). Over the three snow seasons, cameras helped to detect evidence of 130 avalanche events, scattered over seventy-eight distinct avalanche days. The evolution of weather conditions prior to each avalanche release was detailed according to data from a nearby weather station. Moreover, the time of release, the release type, the surface texture, and whether rocky material was present in the deposits were documented from the photographs. To explore relationships between weather data and avalanche releases, conditional inference tree (CIT) analysis was conducted. Results of the CIT analysis showed that there are different weather patterns associated with avalanche releases depending on the season, and significant thresholds values were defined. In winter, the avalanche probability was greater when three-day snowfall total exceeded 10 cm. In spring, the avalanche probability was greater when cumulative melting degree-days were less than forty-six and when daily minimum air temperature was greater than 2°C. Moreover, cornice failures were found to be a major component of the avalanche dynamic in Tasiapik Valley, mainly because of the slope’s morphology. They have also been the cause of the three largest volume and longest runout avalanches observed by cameras in this study, highlighting potential risks for local communities. The probability of observing cornice failures is enhanced on days when maximum air temperature is greater than −8°C in winter conditions, whereas in spring conditions it is enhanced by daily maximum air temperature greater than 2.5°C. This study represents a necessary first step toward avalanche forecasting based on weather data in Nunavik. Efforts should be continued given the expected higher frequency of natural hazards in northern regions as a consequence of recent climate changes.

This paper investigates the accuracy of corn yield forecasts using machine learning with satellite and weather data. In addition, the study examines the incremental value of these forecasts to augment the World Agricultural Supply and Demand Estimates (WASDE) forecast. To illustrate the potential of machine learning methods for agricultural forecasting, publicly available data are collected from 1984 to 2021 for national corn yield, state corn yield, satellite variables, and weather variables and used with the XGBoost algorithm. The results show that the XGBoost model performed about the same but did not outperform the WASDE corn yield forecasts over a 12‐year out‐of‐sample period. The incremental value analysis results suggest that the XGBoost and WASDE forecasts capture similar information, and no incremental information exits. Although the XGBoost model does not outperform the WASDE August forecast, it is near real‐time and can be produced using publicly available data. The results indicate that the XGBoost machine learning models can produce reasonably accurate crop yield forecasts. [ABSTRACT FROM AUTHOR]

The health, longevity, and performance of dairy cattle can be adversely affected by heat stress. This study evaluated the in-barn condition [i.e., temperature, relative humidity, and resulting temperature-humidity index (THI)] at 9 dairy barns with various climates and farm design-management combinations. Hourly and daily indoor and outdoor conditions were compared at each farm, including both mechanically and naturally ventilated barns. On-site conditions were compared with on-farm outdoor conditions, meteorological stations up to 125 km away, and NASA Power data. Canadian dairy cattle face periods of extreme cold and periods of high THI, dependent on the regional climate and season. The northernmost location (53°N) experienced about 75% fewer hours of THI >68 compared with the southernmost location (42°N). Milking parlors had higher THI than the rest of the barn during milking times. The THI conditions inside dairy barns were well correlated with THI conditions measured outside the barns. Naturally ventilated barns with metal roofs and without sprinklers fit a linear relationship (hourly and daily means) with a slope <1, indicating that in-barn THI exceeded outdoor THI more at lower THI and reached equality at higher THI. Mechanically ventilated barns fit nonlinear relationships, which showed the in-barn THI exceeded outdoor THI more at lower THI (e.g., 55–65) and approached equality at higher THI. In-barn THI exceedance was greater in the evening and overnight due to factors such as decreased wind speed and latent heat retention. Eight regression equations were developed (4 hourly, 4 daily) to predict in-barn conditions based on outdoor conditions, considering different barn designs and management systems. Correlations between in-barn and outdoor THI were best when using the on-site weather data from the study, but publicly available weather data from stations within 50 km provided reasonable estimates. Climate stations 75 to 125 km away and NASA Power ensemble data gave poorer fit statistics. For studies involving many dairy barns, the use of NASA Power data with equations for estimating average in-barn conditions in a population is likely appropriate especially when public stations have incomplete data. Results from this study show the importance of adapting recommendation on heat stress to the barn design and guide the selection of appropriate weather data depending on the aim of the study. [ABSTRACT FROM AUTHOR]

The increased adoption of infrared thermometers (IRTs) for irrigation management of crops has resulted in increasingly large surface temperature datasets, resulting in a need for data quality assurance and control (QA/QC) procedures similar to those developed for agricultural weather station data. A QC procedure was developed to test for seven common data conditions, including sensor not deployed, missing, too high, too low, upward spike, downward spike, or stuck. The conditions of "too high" or "too low" used a simple energy balance procedure similar to the crop water stress index, where the theoretical lower and upper temperature limits of a surface were calculated, accounting for the vegetation view factor appearing in the IRT field-of-view. After passing the seven tests, data were assigned as Plausible, and further tested as Confirmed or Confirmed+. The Confirmed test compared each IRT to the median of the other IRTs during 2 h before sunrise and applied a threshold of ±0.5 °C. The Confirmed+ test compared each IRT to the median of the other IRTs during ±2 h of solar noon and applied a threshold of ±2.0 °C. The set of tests was applied to an IRT dataset that included six seasons of crops and fallow periods with 15-min time steps. Temperature differences greater than the thresholds (i.e., assigned Plausible but not Confirmed or Confirmed+) could detect anomalies including ice, dirty or obscured lenses, or biased data that other tests did not detect. Of all time intervals when 20 IRTs viewing a crop were deployed, 80% resulted in Plausible, 61% resulted in Confirmed, and 56% resulted in Confirmed+. The procedure can be easily customized and can increase the value of IRT datasets used for irrigation management. [ABSTRACT FROM AUTHOR]

River runoff predictions in ungauged basins are one of the major challenges in hydrology. In the past, the approach using a physical-based conceptual model was the main approach, but recently, a solution using a data-driven model has been evaluated as more appropriate through several studies. In this study, a new data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed. An advantage of recurrent neural networks is that they can learn long-term dependencies between inputs and outputs provided to the network. Decision tree-based algorithms, combined with recurrent neural networks, serve to reflect topographical information treated as constants and can identify the importance of input features. We tested the proposed approach using data from 25 watersheds publicly available on the Korean government's website. The potential of the proposed approach as a regional hydrologic model is evaluated in the view that one regional model predicts river runoff in various watersheds using the leave-one-out cross-validation regionalization setup. [ABSTRACT FROM AUTHOR]

It is necessary to analyze the relationships between the retail sales of various items and weather conditions. However, the relationship between the sales of each item and the weather condition may vary among stores. Additionally, it is necessary to model the statistical relationships between a wide variety of goods and weather conditions by using past sales data. In such a case, it becomes unrealistic to construct a forecast model for every individual item owing to the breadth of items and the number of retail shops. This study proposes a model to analyze the relationships between the sales of various items and weather conditions. This method can be used to decompose the data into three matrices based on the nonnegative tensor factorization (NTF) method. The results of the analysis clarified that the proposed model can identify important items whose demand is strongly influenced by weather conditions, thereby increasing the effectiveness of inventory management. Additionally, the store clusters estimated by the proposed model can facilitate the construction of regression models that demonstrate the relationship between the sales of each item and weather conditions. [ABSTRACT FROM AUTHOR]

Energy assessments and studies for the coming years in buildings show that the effects of climate change, particularly the problem of global warming, play an important role in increasing the accuracy of these calculations. A similar educational building in two different cities, Tehran and Tabriz, was considered in this study. The goal was to investigate and assess the impact of new and old data on predicting energy consumption in the coming years. The Typical Meteorological Year data was prepared using a Typical Meteorological Year data Creator software. To simulate energy consumption, the Energy Plus software was also used. Taking into account the hot and cold seasons in the forecasted years (2020–2050–2080), this issue has been proven so that for the city of Tehran in the year 2080 compared to 2020, there will be a 24% reduction in energy consumption in the heating part and a 5% increase in the cooling part. In addition, for the city of Tabriz in 2080, we will see a 19% reduction in heating energy consumption and a 7% increase in cooling energy consumption. It should be noted that, using more recent data produces estimates that are more precise than those produced using older data. Furthermore, as temperatures rise in the coming years as a result of global warming, heating will decrease and cooling will increase in Tabriz and Tehran.

Although corn production is affected by several harmful insects, its most important pest in the southeastern region of Europe is the European corn borer (ECB), Ostrinia nubilalis Hübner, 1796 (Lepidoptera: Pyralidae). Chemical control of O. nubilalis remains the main strategy in conventional corn production. The key to successfully achieving a high efficiency of insecticides is determining the appropriate moment of application, including the exact time in the insect's life cycle when it is most vulnerable. In this study, monitoring data on the flight dynamics of ECB adults from a seven-year period (2014–2020) were exploited for the development of a predictive model of adult numbers within the growing season. ECB monitoring was performed by using light traps at 15 different locations in the Vojvodina region (Serbia) during the specified time period. First, the calendar for Vojvodina was created based on the analytics of the collected monitoring data. Additionally, the calendar was converted to the probability of ECB occurrence during the growing season, specifying the time interval between the appearance of each generation of the pest. Second, using machine learning techniques, a phenological model was designed that included daily values of relevant meteorological features, such as cumulative degree-days, relative humidity, and precipitation. The calendar had a lower prediction error when compared to the phenological model, and it was tested as a supporting management tool for the ECB in 2021, with a root-mean-square error of the number of adults of 46.67. Such an approach could significantly reduce both the consumption of insecticides and the number of chemical treatments, respectively. Above all, this approach has broad potential in IPM and organic farming, and it is fully compatible with biological control methods. [ABSTRACT FROM AUTHOR]

This paper addresses the modification of the F-test for count data following the Poisson distribution. The F-test when the count data are expressed in intervals is considered in this paper. The proposed F-test is evaluated using real data from climatology. The comparative study showed the efficiency of the F-test for count data under neutrosophic statistics over the F-test for count data under classical statistics.

This study aims to see how well three different types of Artificial Neural Networks (ANNs) can predict the concentrations of four air pollutants (CO, NO2, PM10, and SO2) before, during, and after the COVID-19 pandemic. MATLAB software was used to construct and test the suggested networks. The World Air Quality Project website included the metrological data and data on air pollutant concentrations. The data were utilized to approximate and estimate the actual performance of proposed models during the development phase. The ANN findings were validated using the results generated during the training phase. Statistics on the three metrology variables were used to compare the performance of the three models (R, RMSE, and MBE). The Elman model was the best and most accurate coefficient of correlation (R) and provided the more precise correlation between meteorological factors and air pollution concentrations in Amman, Jordan. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) techniques can be used to convert Big Data into valuable information for agri-environmental applications, such as predictive pest modeling. Lobesia botrana (Denis & Schiffermüller) 1775 (Lepidoptera: Tortricidae) is one of the main pests of grapevine, causing high productivity losses in some vineyards worldwide. This work focuses on the optimization of the Touzeau model, a classical correlation model between temperature and L. botrana development using data-driven models. Data collected from field observations were combined with 30 GB of registered weather data updated every 30 min to train the ML models and make predictions on this pest's flights, as well as to assess the accuracy of both Touzeau and ML models. The results obtained highlight a much higher F1 score of the ML models in comparison with the Touzeau model. The best-performing model was an artificial neural network of four layers, which considered several variables together and not only the temperature, taking advantage of the ability of ML models to find relationships in nonlinear systems. Despite the room for improvement of artificial intelligence-based models, the process and results presented herein highlight the benefits of ML applied to agricultural pest management strategies. [ABSTRACT FROM AUTHOR]

Range prediction of electric vehicles requires knowledge of many parameters, including information about the vehicle environment. As an alternative to onboard measurement, external data sources (secondary data) can be used. The presented methods are suitable for estimating climatic data for vehicle application including urban areas and areas of complex topography. Compared to an inverse distance weighting approach for ambient temperature values, Kriging yields better overall accuracy especially for areas of complex topography, improving accuracy in urban regions, however, remains a challenge. An approach to improve accuracy in urban areas by considering local climate zones in the selection of secondary data sources produces mixed results. [ABSTRACT FROM AUTHOR]

In this article, we study snow avalanche activity during the snow seasons of 2017–2020 using four automatic time-lapse cameras strategically positioned along the southwestern slope of Tasiapik Valley, near the village of Umiujaq, in Nunavik (northern Québec, Canada). Over the three snow seasons, cameras helped to detect evidence of 130 avalanche events, scattered over seventy-eight distinct avalanche days. The evolution of weather conditions prior to each avalanche release was detailed according to data from a nearby weather station. Moreover, the time of release, the release type, the surface texture, and whether rocky material was present in the deposits were documented from the photographs. To explore relationships between weather data and avalanche releases, conditional inference tree (CIT) analysis was conducted. Results of the CIT analysis showed that there are different weather patterns associated with avalanche releases depending on the season, and significant thresholds values were defined. In winter, the avalanche probability was greater when three-day snowfall total exceeded 10 cm. In spring, the avalanche probability was greater when cumulative melting degree-days were less than forty-six and when daily minimum air temperature was greater than 2°C. Moreover, cornice failures were found to be a major component of the avalanche dynamic in Tasiapik Valley, mainly because of the slope's morphology. They have also been the cause of the three largest volume and longest runout avalanches observed by cameras in this study, highlighting potential risks for local communities. The probability of observing cornice failures is enhanced on days when maximum air temperature is greater than −8°C in winter conditions, whereas in spring conditions it is enhanced by daily maximum air temperature greater than 2.5°C. This study represents a necessary first step toward avalanche forecasting based on weather data in Nunavik. Efforts should be continued given the expected higher frequency of natural hazards in northern regions as a consequence of recent climate changes. [ABSTRACT FROM AUTHOR]

The electricity consumption of a residence depends on many factors such as the habits and economical status of the occupants, the properties of the household and many more. To shed more light on the subject a data set for households was created. The data were collected in Greece through an anonymous survey that comprises 26 questions, resulting in 188 data points from 104 households from different time periods. Each data point contains attributes that are divided into four categories. In the first category, the information is about the household data such as the type and properties of the residence. Next, occupants’ socio-economic features are gathered. In this category information for the number and type of the occupants, the employment status and the total income of the residents is included. The third category of attributes is about the energy-related occupants’ behavior. Finally, the location of the household was provided from the users to estimate the weather conditions for the provided time. Data augmentation was performed to discover non-trivial relationships between the data points. Thus, a secondary set of features was computed based on the raw attributes and is also included. The provided data set can be used to extract insights that could be valuable during the imminent energy crisis.

Tourism demand forecasting comprises an important task within the overall tourism demand management process since it enables informed decision making that may increase revenue for hotels. In recent years, the extensive availability of big data in tourism allowed for the development of novel approaches based on the use of deep learning techniques. However, most of the proposed approaches focus on short-term tourism demand forecasting, which is just one part of the tourism demand forecasting problem. Another important part is that most of the proposed models do not integrate exogenous data that could potentially achieve better results in terms of forecasting accuracy. Driven from the aforementioned problems, this paper introduces a deep learning-based approach for long-term tourism demand forecasting. In particular, the proposed forecasting models are based on the long short-term memory network (LSTM), which is capable of incorporating data from exogenous variables. Two different models were implemented, one using only historical hotel booking data and another one, which combines the previous data in conjunction with weather data. The aim of the proposed models is to facilitate the management of a hotel unit, by leveraging their ability to both integrate exogenous data and generate long-term predictions. The proposed models were evaluated on real data from three hotels in Greece. The evaluation results demonstrate the superior forecasting performance of the proposed models after comparison with well-known state-of-the-art approaches for all three hotels. By performing additional benchmarks of forecasting models with and without weather-related parameters, we conclude that the exogenous variables have a noticeable influence on the forecasting accuracy of deep learning models. [ABSTRACT FROM AUTHOR]

Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China's major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average R2 of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions. [ABSTRACT FROM AUTHOR]