Iskanje po repozitoriju

A+ | A- | | SLO | ENG

Ključne besede: sea flood prediction, flooding maps, climate change resilience, natural disaster registry, coastal inundation, flood-prone areas
Objavljeno v DiRROS: 08.12.2023; Ogledov: 231; Prenosov: 104
Celotno besedilo (7,60 MB)
Gradivo ima več datotek! Več...

Povzetek: In this study, we estimate the generalization of the performance of previously proposed predictive models for nutrient value prediction across different recipe datasets. For this purpose, we introduce a quantitative indicator that determines the level of generalization of using the developed predictive model for new unseen data not presented in the training process. On a predefined corpus of recipe embeddings from six publicly available recipe datasets (i.e., projecting them in the same meta-feature vector space), we train predictive models on one of the six recipe datasets and test the models on the rest of the datasets. In parallel, we define and calculate generalizability indexes which are numbers that indicate how generalizable a predictive model is i.e., how well will a predictive model learned on one dataset perform on another one not involved in the training. The evaluation results prove the validity of these indexes – their relation with the accuracy of the predictions. Further, we define three sampling techniques for selecting representative data instances that will cover all parts from the feature space uniformly (involving data from all datasets) and further will improve the generalization of a predictive model. We train predictive models with these generalized datasets and test them on instances from the six recipe datasets that are not selected and included in the generalized datasets. The results from the evaluation of these predictive models show improvement compared to the results from the predictive models trained on one recipe dataset and tested on the others separately.
Ključne besede: ML pipeline, predictive modeling, nutrient prediction, recipe datasets
Objavljeno v DiRROS: 25.09.2023; Ogledov: 380; Prenosov: 179
Celotno besedilo (3,27 MB)
Gradivo ima več datotek! Več...

Povzetek: To investigate the effect of leaching on chloride ingress profiles in concrete and mortar, we exposed concrete and mortar specimens for 90 and 180 days to two different exposure solutions: 3% NaCl, and 3% NaCl with KOH added to limit leaching. The solutions were replaced weekly. After exposure, we determined total chloride profiles to investigate the chloride ingress, and portlandite profiles to assess the extent of leaching. The results showed that leaching during exposure greatly affects the chloride ingress profiles in mortar and concrete. We found that leaching leads to considerably higher maximum total chloride content and deeper chloride penetration into the concrete than in the specimens where leaching was limited. We recommend therefore that leaching should be taken into account in standard laboratory testing and that more mechanistic service life models should be used to take into account the impact of leaching.
Ključne besede: chloride ingress, service life prediction, leaching, concrete, portlandite, open access
Objavljeno v DiRROS: 04.05.2023; Ogledov: 277; Prenosov: 173
Celotno besedilo (1,17 MB)
Gradivo ima več datotek! Več...

Povzetek: Water is a basic element of the natural environment and the most important component in human water management. Rainfall is the main source of water. Therefore, determining the amount of precipitation reaching the ground using sensors is crucial information. Precise precipitation data are necessary for better modeling quality, as the observation data from weather stations are used as basics for weather model assessment. The authors compared precipitation from the Hellmann rain gauge (climatic precipitation, 1.0 m above the ground surface) measured throughout the year and the GGI 3000 rain gauge (actual precipitation on the ground level) measured from April to October. Measurement sequences from the years 2011–2020 were considered. The data for analysis were obtained from a weather station located in northern Poland. The authors analyzed the relationships between data from the two sensors. A comparative study showed that the measurements of actual precipitation are higher and there are strong relationships between actual and climatic rainfall (r = 0.99). Using the introduced coefficient it is possible to determine the full–year actual precipitation with high probability, taking into account the precipitation with a correction from the winter half-year and the actual precipitation from the summer half-year, which is of great importance in the calculation of the water balance.
Ključne besede: natural environment, climate change, precipitation, prediction, statistics, analysis, Poland
Objavljeno v DiRROS: 25.01.2023; Ogledov: 376; Prenosov: 230
Celotno besedilo (2,74 MB)
Gradivo ima več datotek! Več...

Povzetek: The European spruce bark beetle (Ips typographus L.) is an eruptive forest pest that has caused a great deal of damage in the last decades because of increasing climatic extremes. In order to effectively manage outbreaks of this pest, it is important to predict where they will occur in the future. In this study we developed a predictive model of the sanitary felling of Norway spruce (Picea abies (L.) H. Karst.) because of bark beetles. We used a time series of sanitary felling because of bark beetles from 1996 to 2020 in Slovenia. For the explanatory variables, we used soil, site, climate, geographic, and tree damage data from the previous year. The model showed that sanitary felling is negatively correlated with slope, soil depth, soil cation exchange capacity, and Standard Precipitation Index (less sanitary felling in wet years). On the other hand, soil base saturation percentage, temperature, sanitary felling because of bark beetles from the previous year, sanitary felling because of other abiotic factors from the previous year, and the amount of spruce were positively correlated with the sanitary felling of Norway spruce due to bark beetles. The model had an R2 of 0.38. A prediction was performed for 2021 combining an occurrence model and a quantitative model. The model can be used to predict the amount of sanitary felling of Norway spruce due to bark beetles and to refine the risk map for the next year, which can be used for forest management planning and economic loss predictions.
Ključne besede: sanitary felling, prediction, Ips typographus, Picea abies, Slovenia, forecasting, insect outbreak forest pest
Objavljeno v DiRROS: 21.02.2022; Ogledov: 628; Prenosov: 516
Celotno besedilo (1,24 MB)
Gradivo ima več datotek! Več...