scholarly journals Principal Component Analysis of Urban Expansion Drivers in Greater Lagos, Nigeria

2017 ◽  
Vol 1 (1) ◽  
pp. 156-168
Author(s):  
O. E. Abiodun ◽  
J. B. Olaleye ◽  
J. O. Olusina ◽  
O. g> Omogunloye
Keyword(s):  
Principal Component Analysis ◽  
Environmental Changes ◽  
Urban Expansion ◽  
Principal Component ◽  
Component Analysis ◽  
Land Policy ◽  
Sustainable Urban Development ◽  
Landsat Images ◽  
Water Vegetation

Urban expansion has been identified as a major cause of global climatic and environmental changes. Accurate and up-to-date information about urban expansion in terms of the drivers responsible for this expansion are important for long term planning and sustainable urban development. Lagos is one of the cities that have undergone rapid urban enlargement in the last few decades and, many factors have been adduced to contribute to its sprawling. Therefore, this study aims at using the Principal Component Analysis (PCA) for identifying the principal drivers of urban expansion in greater Lagos. In this study, a set of fourteen (14) drivers of expansion are considered in a multinucleic structure. A sequence of Landsat images of the study area for 1984, 2001, 2006 and 2013 was acquired and processed to six land use classes: dense, moderate urban, water, vegetation, wetland and mangrove. The study area was partitioned into 25 regular cells of 20km by 25km each from where proximate driver values were obtained. The effectiveness of each driver was tested using PCA. The results show that Land Availability accounted for 37.836% of total variance. This result of this study may form the basis for a renewed attention on land policy in the study area as a way to enhance sustainable development.

scholarly journals Bidimensional and Multidimensional Principal Component Analysis in Long Term Atmospheric Monitoring

Atmosphere ◽  
2016 ◽  
Vol 7 (12) ◽  
pp. 155 ◽  
Author(s):  
Barbara Giussani ◽  
Simone Roncoroni ◽  
Sandro Recchia ◽  
Andrea Pozzi
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Atmospheric Monitoring

Long-term runoff forecast using BP neural network based on climatic factors and mutual information method in the Qujiang Catchment of China

2020 ◽  
Author(s):  
Huihui Dai
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Mutual Information ◽  
Bp Neural Network ◽  
Climatic Factors ◽  
Principal Component ◽  
Component Analysis ◽  
Information Method ◽  
Runoff Forecast

<p>The formation of runoff is extremely complicated, and it is not good enough to forecast the future runoff only by using the previous runoff or meteorological data. In order to improve the forecast precision of the medium and long-term runoff forecast model, a set of forecast factor group is selected from meteorological factors, such as rainfall, temperature, air pressure and the circulation factors released by the National Meteorological Center  using the method of mutual information and principal component analysis respectively. Results of the forecast in the Qujiang Catchment suggest the climatic factor-based BP neural network hydrological forecasting model has a better forecasting effect using the mutual information method than using the principal component analysis method.</p>

scholarly journals Forcing variables in simulation of transpiration of water stressed plants determined by principal component analysis

2016 ◽  
Vol 30 (4) ◽  
pp. 431-445
Author(s):  
Angelica Durigon ◽  
Quirijn de Jong van Lier ◽  
Klaas Metselaar
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Specific Humidity ◽  
Leaf Angle ◽  
Prediction Errors ◽  
Angle Distribution ◽  
Time Frequency ◽  
Soil Dryness

AbstractTo date, measuring plant transpiration at canopy scale is laborious and its estimation by numerical modelling can be used to assess high time frequency data. When using the model by Jacobs (1994) to simulate transpiration of water stressed plants it needs to be reparametrized. We compare the importance of model variables affecting simulated transpiration of water stressed plants. A systematic literature review was performed to recover existing parameterizations to be tested in the model. Data from a field experiment with common bean under full and deficit irrigation were used to correlate estimations to forcing variables applying principal component analysis. New parameterizations resulted in a moderate reduction of prediction errors and in an increase in model performance. Agsmodel was sensitive to changes in the mesophyll conductance and leaf angle distribution parameterizations, allowing model improvement. Simulated transpiration could be separated in temporal components. Daily, afternoon depression and long-term components for the fully irrigated treatment were more related to atmospheric forcing variables (specific humidity deficit between stomata and air, relative air humidity and canopy temperature). Daily and afternoon depression components for the deficit-irrigated treatment were related to both atmospheric and soil dryness, and long-term component was related to soil dryness.

Principal Component Analysis the Economy of Shanghai in 2010

2011 ◽  
Vol 50-51 ◽  
pp. 404-408
Author(s):  
Xiao Qiang Guo ◽  
Zhen Dong Li ◽  
Dong Dong Hao ◽  
Xin Xie ◽  
Jian Min Wang
Keyword(s):  
Principal Component Analysis ◽  
Economic Development ◽  
Principal Component ◽  
Component Analysis ◽  
Evaluation Index ◽  
Short Term ◽  
Construction Costs ◽  
World Expo ◽  
Shanghai World Expo

This paper from the economic analysis, quantitative evaluation of the 2010 Shanghai World Exop impact. First, from the short-term and long-term benefits of the two considerations, the loss of earnings, base construction costs on the percentage of total funding, permanent building retained, the number of daily tours, the number of participating countries for the evaluation index, subjectively weight to the five indicators，calculate its scores to rank for five World Expos including Shanghai World Expo. Second, using principal component analysis, we get the five indicators of objective weighting and ranking for above five World Expos. The results show that the Shanghai World Expo will boost the economic development and has a huge influence on the economy

Principal Component Analysis to interpret changes in chromatic parameters on paint dosimeters exposed long-term to urban air

2017 ◽  
Vol 167 ◽  
pp. 113-122 ◽  
Author(s):  
Agustín Herrera ◽  
Davide Ballabio ◽  
Natalia Navas ◽  
Roberto Todeschini ◽  
Carolina Cardell
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Urban Air

scholarly journals Comparative Analysis of Change Detection Techniques In Landuse / Landcover Mapping of Oyo Town, Oyo State, Nigeria

2020 ◽  
pp. 44-62
Author(s):  
Olaniyi Saheed S. ◽  
Igbokwe J. I ◽  
Ojiako J. C.
Keyword(s):  
Principal Component Analysis ◽  
Comparative Analysis ◽  
Change Detection ◽  
Accuracy Assessment ◽  
Principal Component ◽  
Component Analysis ◽  
United States Geological Survey ◽  
Landsat Images ◽  
Detection Techniques ◽  
Analysis Of Change

Landcover is the natural surface of the earth undisturbed by human activities. It represents vegetation, natural or man-made features and every other visible evidence of land use. Landuse on the other hand refers to the use of land by humans while Change detection is the process of identifying differences in the state of an object or phenomenon by observing it in different times. This study is aimed at comparative analysis of change detection techniques in landuse/ landcover mapping of Oyo town with the objectives of comparing and evaluating the results of different change detection techniques as well as production of Landuse/ Landcover map of the study area for the period of 1990 and 2016. Landsat images of 1990, 2003 and 2016 covering the study area (Path 191, Row 54 & 55) were collected from the archives of United States Geological Survey (USGS) agency and image processing and analysis were done using ERDAS Imagine 2015 and ArcGIS 10.5. The results of the study were achieved through image pre-processing, image enhancement, image band combination, change detection through pre-classification (image differencing, image ratioing, Principal Component Analysis) and Post-Classification Comparison (PCC) methods, and results analysed. The result of accuracy assessment in this research shows that a PCA produces a better result of 91.67% while PCC delivered accuracy that ranges between 83.33% and 87.5%. However, PCC gives a better result on the change detection in the study area as it affords more analysis on the study area based on the thematic classes generated for each landuse and landcover of the study area. This study hereby recommends Post-Classification Comparison (PCC) and Principal Component Analysis (PCA) for change detection in the study area. Further research on change detection in the study area should be carried out using Object-Based Image Analysis (OBIA) using high resolution images because this research is hinge on pixel based classification of medium resolution images.

Sign in / Sign up

Export Citation Format

Share Document