Groundwater scarcity is one of the most concerning issues in arid
and semi-arid regions. In this ... more Groundwater scarcity is one of the most concerning issues in arid and semi-arid regions. In this study, we develop and validate a novel artificial intelligence that is a coupling of five ensemble benchmark algorithms e.g., artificial neural network (ANN), reduced-error pruning trees (REPTree), radial basis function (RBF), M5P and random forest (RF) with particle swarm optimization (PSO) for delineating GWP zones. Further, nine parameters used for the GWP modelling and to test and train the proposed PSObased models. Additionally, this study proposes a receiver operating characteristic (ROC) based sensitivity analysis for GWP modelling. Multicollinearity test, information gain ratio, and correlation attribute evaluation methods used to choose important parameters for the proposed GWP model. The result shows that drainage density, elevation, and land use/land cover have a higher influence on the GWP using correlation attribute evaluation methods. Results showed that the hybrid PSO-RF model performed better than other proposed hybrid models.
built-up area in the periphery (Chadchan and Shankar, Int J Sustainable Built Environ 1:36–49, 20... more built-up area in the periphery (Chadchan and Shankar, Int J Sustainable Built Environ 1:36–49, 2012; Pandey and Seto, J Environ Manag 148:53–66, 2015). With these physical changes, i.e. decrease in green cover and increase in built-up, the land surface temperature (LST) is bound to increase. The green area is a basic need of any city because it is a must for a healthy life and also maintains the aesthetic and ecological beauty in the urban areas (Low et al. 2007). The present study aims to analyse the association between built-up, green cover and land surface temperature for which district-level analysis of the normalised differential built-up index (NDBI), normalised differential vegetation index (NDVI) and land surface temperature (LST) has been done over the urban area of Delhi. In this study, Landsat 7 (ETM+ SLC) for 2003, Landsat 5 (TM) for 2010, and Landsat 8 (OLI/TIRS) for 2017 have been used together with Survey of India (SOI) toposheet of Delhi at 1:25,000. Indices like NDBI, NDVI and LST are calculated for 2003, 2010 and 2017 using the spectral radiance model (SRM), the mono-window algorithm (MWA) and the split window algorithm (SWA). Thereafter, district-wise NDBI, NDVI and LST are extracted by using clip tools in ArcGIS 10.5 software. To analyse the relationship between built-up and green cover with LST, correlation is done in SPSS software and a scatter diagram is made to assess the correlation amongst the variables. The further surface temperature profile is created to know which part of the Delhi has the highest and lowest temperatures on a particular surface. The study shows that NDVI and LST are negatively correlated with each other as vegetation has a cooling effect on the land surface temperature whereas NDBI and LST are positively correlated with each other. The studies show a change in the distribution of vegetation cover and gradually increase in the built-up land which results in the increase in land surface temperature to about 3.31 °C in the last 14 years. The result shows thatMWA give the most accurate result in this study since RMSE ofMWA is the lowest (0.71 °C) amongst the three algorithms used in the study. Temporal analysis of land surface temperature by all the three algorithms shows the increase in land surface temperature of Delhi between 2003 and 2017.
Groundwater scarcity is one of the most concerning issues in arid
and semi-arid regions. In this ... more Groundwater scarcity is one of the most concerning issues in arid and semi-arid regions. In this study, we develop and validate a novel artificial intelligence that is a coupling of five ensemble benchmark algorithms e.g., artificial neural network (ANN), reduced-error pruning trees (REPTree), radial basis function (RBF), M5P and random forest (RF) with particle swarm optimization (PSO) for delineating GWP zones. Further, nine parameters used for the GWP modelling and to test and train the proposed PSObased models. Additionally, this study proposes a receiver operating characteristic (ROC) based sensitivity analysis for GWP modelling. Multicollinearity test, information gain ratio, and correlation attribute evaluation methods used to choose important parameters for the proposed GWP model. The result shows that drainage density, elevation, and land use/land cover have a higher influence on the GWP using correlation attribute evaluation methods. Results showed that the hybrid PSO-RF model performed better than other proposed hybrid models.
built-up area in the periphery (Chadchan and Shankar, Int J Sustainable Built Environ 1:36–49, 20... more built-up area in the periphery (Chadchan and Shankar, Int J Sustainable Built Environ 1:36–49, 2012; Pandey and Seto, J Environ Manag 148:53–66, 2015). With these physical changes, i.e. decrease in green cover and increase in built-up, the land surface temperature (LST) is bound to increase. The green area is a basic need of any city because it is a must for a healthy life and also maintains the aesthetic and ecological beauty in the urban areas (Low et al. 2007). The present study aims to analyse the association between built-up, green cover and land surface temperature for which district-level analysis of the normalised differential built-up index (NDBI), normalised differential vegetation index (NDVI) and land surface temperature (LST) has been done over the urban area of Delhi. In this study, Landsat 7 (ETM+ SLC) for 2003, Landsat 5 (TM) for 2010, and Landsat 8 (OLI/TIRS) for 2017 have been used together with Survey of India (SOI) toposheet of Delhi at 1:25,000. Indices like NDBI, NDVI and LST are calculated for 2003, 2010 and 2017 using the spectral radiance model (SRM), the mono-window algorithm (MWA) and the split window algorithm (SWA). Thereafter, district-wise NDBI, NDVI and LST are extracted by using clip tools in ArcGIS 10.5 software. To analyse the relationship between built-up and green cover with LST, correlation is done in SPSS software and a scatter diagram is made to assess the correlation amongst the variables. The further surface temperature profile is created to know which part of the Delhi has the highest and lowest temperatures on a particular surface. The study shows that NDVI and LST are negatively correlated with each other as vegetation has a cooling effect on the land surface temperature whereas NDBI and LST are positively correlated with each other. The studies show a change in the distribution of vegetation cover and gradually increase in the built-up land which results in the increase in land surface temperature to about 3.31 °C in the last 14 years. The result shows thatMWA give the most accurate result in this study since RMSE ofMWA is the lowest (0.71 °C) amongst the three algorithms used in the study. Temporal analysis of land surface temperature by all the three algorithms shows the increase in land surface temperature of Delhi between 2003 and 2017.
Uploads
Papers
and semi-arid regions. In this study, we develop and validate a
novel artificial intelligence that is a coupling of five ensemble
benchmark algorithms e.g., artificial neural network (ANN),
reduced-error pruning trees (REPTree), radial basis function (RBF),
M5P and random forest (RF) with particle swarm optimization
(PSO) for delineating GWP zones. Further, nine parameters used
for the GWP modelling and to test and train the proposed PSObased
models. Additionally, this study proposes a receiver operating
characteristic (ROC) based sensitivity analysis for GWP modelling.
Multicollinearity test, information gain ratio, and correlation
attribute evaluation methods used to choose important parameters
for the proposed GWP model. The result shows that drainage
density, elevation, and land use/land cover have a higher influence
on the GWP using correlation attribute evaluation methods.
Results showed that the hybrid PSO-RF model performed better
than other proposed hybrid models.
Manag 148:53–66, 2015). With these physical changes, i.e. decrease in green cover and increase in built-up, the land surface
temperature (LST) is bound to increase. The green area is a basic need of any city because it is a must for a healthy life and also
maintains the aesthetic and ecological beauty in the urban areas (Low et al. 2007). The present study aims to analyse the
association between built-up, green cover and land surface temperature for which district-level analysis of the normalised
differential built-up index (NDBI), normalised differential vegetation index (NDVI) and land surface temperature (LST) has
been done over the urban area of Delhi. In this study, Landsat 7 (ETM+ SLC) for 2003, Landsat 5 (TM) for 2010, and Landsat 8
(OLI/TIRS) for 2017 have been used together with Survey of India (SOI) toposheet of Delhi at 1:25,000. Indices like NDBI,
NDVI and LST are calculated for 2003, 2010 and 2017 using the spectral radiance model (SRM), the mono-window algorithm
(MWA) and the split window algorithm (SWA). Thereafter, district-wise NDBI, NDVI and LST are extracted by using clip tools
in ArcGIS 10.5 software. To analyse the relationship between built-up and green cover with LST, correlation is done in SPSS
software and a scatter diagram is made to assess the correlation amongst the variables. The further surface temperature profile is
created to know which part of the Delhi has the highest and lowest temperatures on a particular surface. The study shows that
NDVI and LST are negatively correlated with each other as vegetation has a cooling effect on the land surface temperature
whereas NDBI and LST are positively correlated with each other. The studies show a change in the distribution of vegetation
cover and gradually increase in the built-up land which results in the increase in land surface temperature to about 3.31 °C in the
last 14 years. The result shows thatMWA give the most accurate result in this study since RMSE ofMWA is the lowest (0.71 °C)
amongst the three algorithms used in the study. Temporal analysis of land surface temperature by all the three algorithms shows
the increase in land surface temperature of Delhi between 2003 and 2017.
and semi-arid regions. In this study, we develop and validate a
novel artificial intelligence that is a coupling of five ensemble
benchmark algorithms e.g., artificial neural network (ANN),
reduced-error pruning trees (REPTree), radial basis function (RBF),
M5P and random forest (RF) with particle swarm optimization
(PSO) for delineating GWP zones. Further, nine parameters used
for the GWP modelling and to test and train the proposed PSObased
models. Additionally, this study proposes a receiver operating
characteristic (ROC) based sensitivity analysis for GWP modelling.
Multicollinearity test, information gain ratio, and correlation
attribute evaluation methods used to choose important parameters
for the proposed GWP model. The result shows that drainage
density, elevation, and land use/land cover have a higher influence
on the GWP using correlation attribute evaluation methods.
Results showed that the hybrid PSO-RF model performed better
than other proposed hybrid models.
Manag 148:53–66, 2015). With these physical changes, i.e. decrease in green cover and increase in built-up, the land surface
temperature (LST) is bound to increase. The green area is a basic need of any city because it is a must for a healthy life and also
maintains the aesthetic and ecological beauty in the urban areas (Low et al. 2007). The present study aims to analyse the
association between built-up, green cover and land surface temperature for which district-level analysis of the normalised
differential built-up index (NDBI), normalised differential vegetation index (NDVI) and land surface temperature (LST) has
been done over the urban area of Delhi. In this study, Landsat 7 (ETM+ SLC) for 2003, Landsat 5 (TM) for 2010, and Landsat 8
(OLI/TIRS) for 2017 have been used together with Survey of India (SOI) toposheet of Delhi at 1:25,000. Indices like NDBI,
NDVI and LST are calculated for 2003, 2010 and 2017 using the spectral radiance model (SRM), the mono-window algorithm
(MWA) and the split window algorithm (SWA). Thereafter, district-wise NDBI, NDVI and LST are extracted by using clip tools
in ArcGIS 10.5 software. To analyse the relationship between built-up and green cover with LST, correlation is done in SPSS
software and a scatter diagram is made to assess the correlation amongst the variables. The further surface temperature profile is
created to know which part of the Delhi has the highest and lowest temperatures on a particular surface. The study shows that
NDVI and LST are negatively correlated with each other as vegetation has a cooling effect on the land surface temperature
whereas NDBI and LST are positively correlated with each other. The studies show a change in the distribution of vegetation
cover and gradually increase in the built-up land which results in the increase in land surface temperature to about 3.31 °C in the
last 14 years. The result shows thatMWA give the most accurate result in this study since RMSE ofMWA is the lowest (0.71 °C)
amongst the three algorithms used in the study. Temporal analysis of land surface temperature by all the three algorithms shows
the increase in land surface temperature of Delhi between 2003 and 2017.