Mapping urban land surface temperature using remote sensing techniques and artificial neural network modelling (original) (raw)
Related papers
Changes in urban microclimate can have adverse effects on the city dwellers in many ways including thermal discomfort and loss of life due to heat waves, development of air pollutants, etc. Microclimate of urban area primarily depends on the land use and land cover (LULC). Conversion of greenery cover into impervious built up surfaces increase the heat retaining capacity and result in increased land surface temperature (LST) which in turn increase the local air temperature. This paper presents a new approach to the application of artificial neural network (ANN) for prediction of LST image from LULC image. Landsat TM images of the study area for 2001 and 2010 are used to develop LULC and LST images. A feed forward back propagation ANN model with Levenberg-Marquardt training algorithm has been developed to simulate and predict the LST image from LULC image data. Along with LULC, elevation, latitude and longitude data are also given as inputs to optimize the model. The data sets of 2001 are used for training and that of 2010 for testing the model. The model efficiency was found to be of 81.621%. LST image of the year 2015 was predicted from LULC image using the model.
Estimation of land surface temperature (LST) is important for urban climate studies particularly for the study of intensity of urban heat island and its spatial distribution. LST is primarily depends on the land use/land cover (LULC) of the area and changes with extent of urbanization. For LST retrieval, remote sensing satellite images of high resolution with thermal band are required which are scarce. This paper deals with the development of artificial neural network (ANN) model for prediction of LST image from LULC image. The advantage of the model is that model requires only LULC image to get LST image. A feed forward back propagation network is developed with LM training algorithm. For training the model LULC image and LST image of 2001 was used. For testing the model LULC and LST image of 2011 was used. The model was found to give good results. The outputs of the model were converted in to images and presented.
Journal of Taibah University for Science, 2013
The meteorological data such as rainfall and temperatures, covering the period between 1979 and 2008, has been analyzed. The data were simulated using the geographic information systems (GIS) and computer software "MATLAB". The output results were converted into geographical maps. Three parameters were analyzed: annual mean maximum temperature, annual mean minimum temperature, and mean annual rainfall during the period . The analyzed results were also used to forecast for the period (2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018).
The meteorological data such as rainfall and temperatures, covering the period between 1979 and 2008, has been analyzed. Thedata were simulated using the geographic information systems (GIS) and computer software “MATLAB”. The output results wereconverted into geographical maps. Three parameters were analyzed: annual mean maximum temperature, annual mean minimumtemperature, and mean annual rainfall during the period (1979–2008). The analyzed results were also used to forecast for the period(2009–2018).The results show that no change has occurred in the mean annual rainfall in both northern and eastern part, while it has increased inthe central region of Jordan. Although local temperatures fluctuate naturally, but over the past 50 years, the mean local temperaturein Jordan has increased rapidly since 1992 by 1.5–2◦C.It is noticed from the data that the change in both maximum and minimum temperatures has clearly begun after 1991, in whichthis phenomenon may give an indication of changing point in climate of Jordan. As for prediction is concern, the show continuousincrease in both maximum and minimum temperatures in the eastern, northern and southern regions of Jordan.The application of GIS in this study was successfully used to analyze the data and to produce ‘easy to use’ maps to understandthe impact of global warming. This application is the first in terms of its applicability in Jordan. The authors believe that the resultsof this study will be of great help to the decision makers in the field of environment in Jordan.
Modelling and Remote Sensing of Land Surface Temperature in Turkey
Journal of the Indian Society of Remote Sensing, 2011
This study introduces artificial neural networks (ANNs) for the estimation of land surface temperature (LST) using meteorological and geographical data in Turkey (26-45°E and 36-42°N). A generalized regression neural network (GRNN) was used in the network. In order to train the neural network, meteorological and geographical data for the
2020
the soft computing models used for predicting land surface temperature (LST) changes are very useful to evaluate and forecast the rapidly changing climate of the world. In this study, four soft computing techniques, namely, multivariate adaptive regression splines (MARS), wavelet neural network (WNN), adaptive neurofuzzy inference system (ANFIS), and dynamic evolving neurofuzzy inference system (DENFIS), are applied and compared to find the best model that can be used to predict the LST changes of Beijing area. e topographic change is considered in this study to accurately predict LST; furthermore, Landsat 4/5 TM and Landsat 8OLI_TIRS images for four years (1995, 2004, 2010, and 2015) are used to study the LST changes of the research area. e four models are assessed using statistical analysis, coefficient of determination (R 2), root mean square error (RMSE), and mean absolute error (MAE) in the training and testing stages, and MARS is used to estimate the important variables that should be considered in the design models. e results show that the LST for the studied area increases by 0.28°C/year due to the urban changes in the study area. In addition, the topographic changes and previously recorded temperature changes have a significant influence on the LST prediction of the study area. Moreover, the results of the models show that the MARS, ANFIS, and DENFIS models can be used to predict the LST of the study area. e ANFIS model showed the highest performances in the training (R 2 � 0.99, RMSE � 0.78°C, MAE � 0.55°C) and testing (R 2 � 0.99, RMSE � 0.36°C, MAE � 0.16°C) stages; therefore, the ANFIS model can be used to predict the LST changes in the Beijing area. e predicted LST shows that the change in climate and urban area will affect the LST changes of the Beijing area in the future.
Climate change in Jordan prediction using ANN
Jordan Abstract The meteorological data such as rainfall and temperatures, covering the period between 1979 and 2008, has been analyzed. The data were simulated using the geographic information systems (GIS) and computer software “MATLAB”. The output results were converted into geographical maps. Three parameters were analyzed: annual mean maximum temperature, annual mean minimum temperature, and mean annual rainfall during the period (1979–2008). The analysed results were also used to forecast for the period(2009–2018).The results show that no change has occurred in the mean annual rainfall in both northern and eastern part, while it has increased in the central region of Jordan. Although local temperatures fluctuate naturally, but over the past 50 years, the mean local temperature in Jordan has increased rapidly since 1992 by 1.5–2◦C.It is noticed from the data that the change in both maximum and minimum temperatures has clearly begun after 1991, in which this phenomenon may give ...