scholarly journals Using R packages 'tmap', 'raster' and 'ggmap' for cartographic visualization: An example of dem-based terrain modelling of Italy, Apennine Peninsula

2020 ◽  
pp. 99-116
Author(s):  
Polina Lemenkova
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Programming Language ◽  
Slope Aspect ◽  
Regional Mapping ◽  
Geographic Education ◽  
R Programming Language ◽  
Machine Learning Methods ◽  
R Packages ◽  
R Programming

The main purpose of this article is to present the use of R programming language in cartographic visualization demonstrating using machine learning methods in geographic education. Current trends in education technologies are largely influenced by the possibilities of distance-learning, e-learning and selflearning. In view of this, the main tendencies in modern geographic education include active use of open source GIS and publicly available free geospatial datasets that can be used by students for cartographic exercises, data visualization and mapping, both at intermediate and advanced levels. This paper contributes to the development of these methods and is fully based on the datasets and tools available for every student: the R programming language and the free open source datasets. The case study demonstrated in this paper show the examples of both physical geographic mapping (geomorphology) and socio-economic geography (regional mapping) which can be used in the classes and in self-learning. The objective of this research includes geomorphological modelling of the terrain relief in Italy and regional mapping. The data include dem SRTM90 and datasets on regional borders of Italy embedded in R packages 'maps' and 'mapdata'. Modelling references to the characteristics of slope, aspect, hillshade and elevation, their visualization using R packages: 'raster' and 'tmap'. Regional mapping of Italy was made using main package 'ggmap' with the 'ggplot2' as a wrapper. The results present five thematic maps (slope, aspect, hillshade, elevation and regions of Italy) created in R language. Traditionally used in statistical analysis, R is less known as a perfect tool in geographic education. This paper contributes to the development of methods in geographic education by presenting new technologies of the machine learning methods of mapping.

scholarly journals Progress in the R ecosystem for representing and handling spatial data

2020 ◽  
Author(s):  
Roger S. Bivand
Keyword(s):  
New York ◽  
Data Analysis ◽  
Open Source ◽  
Spatial Data ◽  
Spatial Data Analysis ◽  
Data Handling ◽  
Good Match ◽  
R Programming Language ◽  
R Packages ◽  
R Programming

Abstract Twenty years have passed since Bivand and Gebhardt (J Geogr Syst 2(3):307–317, 2000. 10.1007/PL00011460) indicated that there was a good match between the then nascent open-source R programming language and environment and the needs of researchers analysing spatial data. Recalling the development of classes for spatial data presented in book form in Bivand et al. (Applied spatial data analysis with R. Springer, New York, 2008, Applied spatial data analysis with R, 2nd edn. Springer, New York, 2013), it is important to present the progress now occurring in representation of spatial data, and possible consequences for spatial data handling and the statistical analysis of spatial data. Beyond this, it is imperative to discuss the relationships between R-spatial software and the larger open-source geospatial software community on whose work R packages crucially depend.

scholarly journals Face Recognition System with Machine Learning

2021 ◽  
Vol 2089 (1) ◽  
pp. 012047
Author(s):  
Vuppu Padmakar ◽  
B V Ramana Murthy
Keyword(s):  
Machine Learning ◽  
Face Recognition ◽  
Open Source ◽  
Programming Language ◽  
Recognition System ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Face Recognition System ◽  
Machine Learning Models

Abstract This venture plans to give improved security by enabling a client to realize who is actually getting to the framework utilizing facial acknowledgment. The framework enables just approved clients to get entrance. Python is a programming language utilized alongside Machine learning methods and an open source library which is utilized to configuration, construct and train Machine learning models. Interface component is additionally accommodated unapproved clients to enroll to obtain entrance with the earlier authorization from the Admin.

scholarly journals see: An R Package for Visualizing Statistical Models

2021 ◽  
Author(s):  
Daniel Lüdecke ◽  
Indrajeet Patil ◽  
Mattan S. Ben-Shachar ◽  
Brenton M. Wiernik ◽  
Philip Waggoner ◽  
...  
Keyword(s):  
Programming Language ◽  
Statistical Models ◽  
R Package ◽  
Model Parameters ◽  
R Programming Language ◽  
R Packages ◽  
R Programming ◽  
And Performance ◽  
Performance Diagnostics ◽  
Scientific Reporting

The see package is embedded in the easystats ecosystem, a collection of R packages that operate in synergy to provide a consistent and intuitive syntax when working with statistical models in the R programming language (R Core Team, 2021). Most easystats packages return comprehensive numeric summaries of model parameters and performance. The see package complements these numeric summaries with a host of functions and tools to produce a range of publication-ready visualizations for model parameters, predictions, and performance diagnostics. As a core pillar of easystats, the see package helps users to utilize visualization for more informative, communicable, and well-rounded scientific reporting.

scholarly journals Developing codes for validation of PM10, PM2.5, and O3 datasets using R programming language

2019 ◽  
Author(s):  
Ramin Nabizadeh ◽  
Mostafa Hadei
Keyword(s):  
Air Pollution ◽  
Programming Language ◽  
Assessment Method ◽  
Daily Maximum ◽  
Data Handling ◽  
R Programming Language ◽  
Wide Range ◽  
Us Epa ◽  
R Programming ◽  
Pm 10

Introduction: The wide range of studies on air pollution requires accurate and reliable datasets. However, due to many reasons, the measured concentra-tions may be incomplete or biased. The development of an easy-to-use and reproducible exposure assessment method is required for researchers. There-fore, in this article, we describe and present a series of codes written in R Programming Language for data handling, validating and averaging of PM10, PM2.5, and O3 datasets.   Findings: These codes can be used in any types of air pollution studies that seek for PM and ozone concentrations that are indicator of real concentra-tions. We used and combined criteria from several guidelines proposed by US EPA and APHEKOM project to obtain an acceptable methodology. Separate   .csv files for PM 10, PM 2.5 and O3 should be prepared as input file. After the file was imported to the R Programming software, first, negative and zero values of concentrations within all the dataset will be removed. Then, only monitors will be selected that have at least 75% of hourly concentrations. Then, 24-h averages and daily maximum of 8-h moving averages will be calculated for PM and ozone, respectively. For output, the codes create two different sets of data. One contains the hourly concentrations of the interest pollutant (PM10, PM2.5, or O3) in valid stations and their average at city level. Another is the   final 24-h averages of city for PM10 and PM2.5 or the final daily maximum 8-h averages of city for O3. Conclusion: These validated codes use a reliable and valid methodology, and eliminate the possibility of wrong or mistaken data handling and averaging. The use of these codes are free and without any limitation, only after the cita-tion to this article.

scholarly journals Spatial variation of physicochemical parameters in a constructed wetland for wastewater treatment: An example of the use of the R programming language

2021 ◽  
Vol 13 (1) ◽  
pp. 15
Author(s):  
Junior Pastor Pérez-Molina ◽  
Carola Scholz ◽  
Roy Pérez-Salazar ◽  
Carolina Alfaro-Chinchilla ◽  
Ana Abarca Méndez ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Spatial Variation ◽  
Water Flow ◽  
Programming Language ◽  
Constructed Wetland ◽  
Physicochemical Parameters ◽  
Preferential Flow ◽  
Oxygen Demand ◽  
R Programming Language ◽  
R Programming

Introduction: The implementation of wastewater treatment systems such as constructed wetlands has a growing interest in the last decade due to its low cost and high effectiveness in treating industrial and residential wastewater. Objective: To evaluate the spatial variation of physicochemical parameters in a constructed wetland system of sub-superficial flow of Pennisetum alopecuroides (Pennisetum) and a Control (unplanted). The purpose is to provide an analysis of spatial dynamic of physicochemical parameters using R programming language. Methods: Each of the cells (Pennisetum and Control) had 12 piezometers, organized in three columns and four rows with a separation distance of 3,25m and 4,35m, respectively. The turbidity, biochemical oxygen demand (BOD), chemical oxygen demand (COD), total Kjeldahl nitrogen (TKN), ammoniacal nitrogen (N-NH4), organic nitrogen (N-org.) and phosphorous (P-PO4-3) were measured in water under in-flow and out-flow of both conditions Control and Pennisetum (n= 8). Additionally, the oxidation-reduction potential (ORP), dissolved oxygen (DO), conductivity, pH and water temperature, were measured (n= 167) in the piezometers. Results: No statistically significant differences between cells for TKN, N-NH4, conductivity, turbidity, BOD, and COD were found; but both Control and Pennisetum cells showed a significant reduction in these parameters (P<0,05). Overall, TKN and N-NH4 removal were from 65,8 to 84,1% and 67,5 to 90,8%, respectively; and decrease in turbidity, conductivity, BOD, and COD, were between 95,1-95,4%; 15-22,4%; 65,2-77,9% and 57,4-60,3% respectively. Both cells showed ORP increasing gradient along the water-flow direction, contrary to conductivity (p<0,05). However, OD, pH and temperature were inconsistent in the direction of the water flow in both cells. Conclusions: Pennisetum demonstrated pollutant removal efficiency, but presented results similar to the control cells, therefore, remains unclear if it is a superior option or not. Spatial variation analysis did not reflect any obstruction of flow along the CWs; but some preferential flow paths can be distinguished. An open-source repository of R was provided. 

scholarly journals Prediction Success of Machine Learning Methods for Flash Flood Susceptibility Mapping in the Tafresh Watershed, Iran

2019 ◽  
Vol 11 (19) ◽  
pp. 5426 ◽  
Author(s):  
Saeid Janizadeh ◽  
Mohammadtaghi Avand ◽  
Abolfazl Jaafari ◽  
Tran Van Phong ◽  
Mahmoud Bayat ◽  
...  
Keyword(s):  
Machine Learning ◽  
Flash Flood ◽  
Susceptibility Mapping ◽  
Annual Rainfall ◽  
Slope Aspect ◽  
Flood Events ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Flood Susceptibility ◽  
Flood Susceptibility Mapping

Floods are some of the most destructive and catastrophic disasters worldwide. Development of management plans needs a deep understanding of the likelihood and magnitude of future flood events. The purpose of this research was to estimate flash flood susceptibility in the Tafresh watershed, Iran, using five machine learning methods, i.e., alternating decision tree (ADT), functional tree (FT), kernel logistic regression (KLR), multilayer perceptron (MLP), and quadratic discriminant analysis (QDA). A geospatial database including 320 historical flood events was constructed and eight geo-environmental variables—elevation, slope, slope aspect, distance from rivers, average annual rainfall, land use, soil type, and lithology—were used as flood influencing factors. Based on a variety of performance metrics, it is revealed that the ADT method was dominant over the other methods. The FT method was ranked as the second-best method, followed by the KLR, MLP, and QDA. Given a few differences between the goodness-of-fit and prediction success of the methods, we concluded that all these five machine-learning-based models are applicable for flood susceptibility mapping in other areas to protect societies from devastating floods.

Sign in / Sign up

Export Citation Format

Share Document