Performance of different machine learning algorithms on satellite image classification in rural and urban setup

Abstract In many countries, the increasing population drives the spatiotemporal land use and land cover change (LULCC) at a higher rate, causing heterogeneous landscape. Hence, the LULCC is a dynamic and frequent process causing fragmented land cover, and therefore, extensive research on LULCC pattern is necessary at different spatial and temporal scales. Moreover, it is essential to identify appropriate algorithms to detect LULCC in such fragmented areas. Furthermore, the rate of change is different in rural and urban areas. Hence, the main goal of the study was to describe the performance of different machine learning algorithms on three different spatial and multispectral satellite image classification in rural and urban extents. We carried out atmospheric and geometric correction. To achieve this, we acquired and processed a set of moderate and finer resolution images (Landsat-8, Sentinel-2, and Planet images) having similar phenological stages to finding out the suitable algorithms that provide better performance in LULC classification. Random forest, Support Vector Machine (SVM), and their combined strength (stacked algorithms) were applied on Landsat-8, Sentinel-2, and Planet images separately to assess individual and overall class accuracy of the images. Two unique sets of training data were generated to classify the 6 (3 sensors x 2 locations) imagery. We find that the Sentinel-2 image performs best among the three images. Among the three different algorithms, SVM showed comparatively better results. In both Bhola and Dhaka, the SVM on Sentinel image performed best with an overall accuracy of 0.969, 0.983, and overall kappa of 0.948, and 0.968, respectively. This study illustrates the role of algorithms on LULCC studies for a better understanding of the changes that occurred in the rural and urban areas. These findings assist planners, remote sensing scientists and decision-makers to choose a suitable image classification algorithm in monitoring rapidly changing, fragmented, and diverse landscape in Bangladesh and elsewhere in the world.

[1]  Xia Li,et al.  Modelling sustainable urban development by the integration of constrained cellular automata and GIS , 2000, Int. J. Geogr. Inf. Sci..

[2]  R. Betts,et al.  Land use/land cover changes and climate: modeling analysis and observational evidence , 2011 .

[3]  Li Wen,et al.  Coastal Wetland Mapping Using Ensemble Learning Algorithms: A Comparative Study of Bagging, Boosting and Stacking Techniques , 2020, Remote. Sens..

[4]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[5]  Jin Zhang,et al.  An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping , 2016 .

[6]  Patrick Hostert,et al.  Import Vector Machines for Quantitative Analysis of Hyperspectral Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[7]  Bartosz Mitka,et al.  Analysis of Changes in Forest Structure using Point Clouds from Historical Aerial Photographs , 2019, Remote. Sens..

[8]  H. Briassoulis.  Analysis of Land Use Change: Theoretical and Modeling Approaches , 2000 .

[9]  Xiuzhen Hu,et al.  The Comparison between Random Forest and Support Vector Machine Algorithm for Predicting β-Hairpin Motifs in Proteins , 2013 .

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  M. Batty,et al.  Urban analysis in a GIS environment: population density modelling using ARC/INFO , 1994 .

[12]  Jannatul Ferdush,et al.  Monitoring the spatiotemporal dynamics of waterlogged area in southwestern Bangladesh using time series Landsat imagery , 2018 .

[13]  Andrés Manuel García,et al.  Cellular automata models for the simulation of real-world urban processes: A review and analysis , 2010 .

[14]  Stephen Sitch,et al.  Current challenges of implementing anthropogenic land-use and land-cover change in models contributing to climate change assessments , 2017 .

[15]  A. Dewan,et al.  Land use and land cover change in Greater Dhaka, Bangladesh: Using remote sensing to promote sustainable urbanization , 2009 .

[16]  Peter H. Verburg,et al.  A land-use systems approach to represent land-use dynamics at continental and global scales , 2012, Environ. Model. Softw..

[17]  Jan Bumberger,et al.  Investigating the consequences of climate change under different land‐use regimes: a novel experimental infrastructure , 2019, Ecosphere.

[18]  Steven M. Manson,et al.  Terra Populus: Workflows for Integrating and Harmonizing Geospatial Population and Environmental Data , 2015 .

[19]  H. M. Abdullah,et al.  Exploring standardized precipitation evapotranspiration index for drought assessment in Bangladesh , 2017, Environmental Monitoring and Assessment.

[20]  Xuefei Hu,et al.  Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method , 2011 .

[21]  Huabing Huang,et al.  The migration of training samples towards dynamic global land cover mapping , 2020 .

[22]  Atul K. Jain,et al.  Spatial modeling of agricultural land use change at global scale , 2013 .

[23]  Bogdan Zagajewski,et al.  Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images , 2017 .

[24]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[25]  A. Yüksel,et al.  Using ASTER Imagery in Land Use/cover Classification of Eastern Mediterranean Landscapes According to CORINE Land Cover Project , 2008, Sensors.

[26]  Xiaocong Xu,et al.  A New Global Land-Use and Land-Cover Change Product at a 1-km Resolution for 2010 to 2100 Based on Human–Environment Interactions , 2017 .

[27]  Yanjiao Ren,et al.  Spatially explicit simulation of land use/land cover changes: Current coverage and future prospects , 2019, Earth-Science Reviews.

[28]  Jan Nyssen,et al.  Land-use/cover changes in relation to stream dynamics in a marginal graben along the northern Ethiopian Rift Valley , 2019 .

[29]  H. M. Abdullah,et al.  Plant Genetic Resources and Traditional Knowledge: Emerging Needs for Conservation , 2015 .

[30]  Haw Yen,et al.  Potential impacts of land use/cover and climate changes on ecologically relevant flows , 2020 .

[31]  Imranul Islam,et al.  Spatiotemporal dynamics of new land development in Bangladesh coast and its potential uses , 2019, Remote Sensing Applications: Society and Environment.

[32]  R. Tateishi,et al.  Evaluating urban expansion and land use change in Shijiazhuang, China, by using GIS and remote sensing , 2006 .

[33]  Jennifer Koch,et al.  An integrated approach to modelling land-use change on continental and global scales , 2011, Environ. Model. Softw..

[34]  K. Seto,et al.  Global urban land-use trends and climate impacts , 2009 .

[35]  Imranul Islam,et al.  Quantifying the spatiotemporal patterns of forest degradation in a fragmented, rapidly urbanizing landscape: A case study of Gazipur, Bangladesh , 2019, Remote Sensing Applications: Society and Environment.

[36]  Nur Shafira Nisa Shaharum,et al.  Oil palm mapping over Peninsular Malaysia using Google Earth Engine and machine learning algorithms , 2020, Remote Sensing Applications: Society and Environment.

[37]  M. Friedl,et al.  A new map of global urban extent from MODIS satellite data , 2009 .

[38]  Lynne Carpenter-Boggs,et al.  Water quality and resident perceptions of declining ecosystem services at Shitalakka wetland in Narayanganj city , 2017 .

[39]  V. Klemas.  Remote Sensing Techniques for Studying Coastal Ecosystems: An Overview , 2010 .

[40]  P. Dirmeyer,et al.  University of Nebraska-Lincoln DigitalCommons @ University of Nebraska-Lincoln Papers in Natural Resources Natural Resources , School of 2014 Land cover changes and their biogeophysical effects on climate , 2016 .

[41]  Delin Liu,et al.  Effects of land use classification on landscape metrics based on remote sensing and GIS , 2013, Environmental Earth Sciences.

[42]  Tsuyoshi Akiyama,et al.  Estimation and validation of biomass of a mountainous agroecosystem by means of sampling, spectral data and QuickBird satellite image , 2011 .

[43]  Aniruddha Ghosh,et al.  A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[44]  Dirk Pflugmacher,et al.  Mapping pan-European land cover using Landsat spectral-temporal metrics and the European LUCAS survey , 2019, Remote Sensing of Environment.

[45]  A. Lechner,et al.  Land cover mapping of the Mekong Delta to support natural resource management with multi-temporal Sentinel-1A synthetic aperture radar imagery , 2020 .

[46]  Li Ma,et al.  A comparison of random forest and support vector machine approaches to predict coal spontaneous combustion in gob , 2019, Fuel.

[47]  L. Kiage,et al.  Linkages between land cover change, lake shrinkage, and sublacustrine influence determined from remote sensing of select Rift Valley Lakes in Kenya. , 2019, The Science of the total environment.

[48]  Keith C. Clarke,et al.  A Self-Modifying Cellular Automaton Model of Historical Urbanization in the San Francisco Bay Area , 1997 .