Comparison of Machine-Learning Methods for Urban Land-Use Mapping in Hangzhou City, China

Urban land-use information is important for urban land-resource planning and management. However, current methods using traditional surveys cannot meet the demand for the rapid development of urban land management. There is an urgent need to develop new methods to overcome the shortcomings of conventional methods. To address the issue, this study used the random forest (RF), support vector machine (SVM), and artificial neural network (ANN) models to build machine-leaning methods for urban land-use classification. Taking Hangzhou as an example, these machine-leaning methods could all successfully classify the essential urban land use into 6 Level I classes and 13 Level II classes based on the semantic features extracted from Sentinel-2A images, multi-source features of types of points of interest (POIs), land surface temperature, night lights, and building height. The validation accuracy of the RF model for the Level I and Level II land use was 79.88% and 71.89%, respectively, performing better compared to SVM (78.40% and 68.64%) and ANN models (71.30% and 63.02%). However, the variations of the user accuracy among the methods depended on the urban land-use level. For the Level I land-use classification, the user accuracy was high, except for the transportation land by all methods. In general, the RF and SVM models performed better than the ANN model. For the Level II land-use classification, the user accuracy of different models was quite distinct. With the RF model, the user accuracy of educational and medical land was above 80%. Moreover, with the SVM model, the user accuracy of the business office and educational land classification was above 75%. However, the user accuracy of the ANN model on the Level II land-use classification was poor. Our results showed that the RF model performs best, followed by SVM model, and ANN model was relatively poor in the essential urban land-use classification. The results proved that the use of machine-learning methods can quickly extract land-use types with high accuracy, and provided a better method choice for urban land-use information acquisition.

[1]  Luyao Wang,et al.  Improving population mapping using Luojia 1-01 nighttime light image and location-based social media data. , 2020, The Science of the total environment.

[2]  Peng Gong,et al.  Mapping Urban Land Use by Using Landsat Images and Open Social Data , 2016, Remote. Sens..

[3]  J. Zawadzki,et al.  Sentinel-2 Imagery Processing for Tree Logging Observations on the Białowieża Forest World Heritage Site , 2020 .

[4]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[5]  Bing Xu,et al.  Where Does Nighttime Light Come From? Insights from Source Detection and Error Attribution , 2020, Remote. Sens..

[6]  Yaowen Xie,et al.  Detailed Mapping of Urban Land Use Based on Multi-Source Data: A Case Study of Lanzhou , 2020, Remote. Sens..

[7]  David Hernández-López,et al.  Assessing the Accuracy of Multiple Classification Algorithms for Crop Classification Using Landsat-8 and Sentinel-2 Data , 2020, Remote. Sens..

[8]  Jinfei Wang,et al.  Using Linear Regression, Random Forests, and Support Vector Machine with Unmanned Aerial Vehicle Multispectral Images to Predict Canopy Nitrogen Weight in Corn , 2020, Remote. Sens..

[9]  Michael J. Shaw,et al.  Active training of backpropagation neural networks using the learning by experimentation methodology , 1997, Ann. Oper. Res..

[10]  Xiaoping Liu,et al.  Classifying urban land use by integrating remote sensing and social media data , 2017, Int. J. Geogr. Inf. Sci..

[11]  Francesco Pirotti,et al.  Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada , 2020, Remote. Sens..

[12]  Matt Aitkenhead,et al.  Classification of Landsat Thematic Mapper imagery for land cover using neural networks , 2008 .

[13]  Wei Zhang,et al.  Mapping Urban Heat Vulnerability of Extreme Heat in Hangzhou via Comparing Two Approaches , 2020, Complex..

[14]  Antonio J. Plaza,et al.  A New GPU Implementation of Support Vector Machines for Fast Hyperspectral Image Classification , 2020, Remote. Sens..

[15]  José A. Sobrino,et al.  Land surface temperature retrieval from LANDSAT TM 5 , 2004 .

[16]  Yao Yao,et al.  Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models , 2017, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[17]  P. Srivastava,et al.  Quantifying Land Cover Changes in a Mediterranean Environment Using Landsat TM and Support Vector Machines , 2020, Forests.

[18]  M Buscema,et al.  Back propagation neural networks. , 1998, Substance use & misuse.

[19]  Bin Chen,et al.  Regional Mapping of Essential Urban Land Use Categories in China: A Segmentation-Based Approach , 2020, Remote. Sens..

[20]  María-Teresa Sebastiá-Frasquet,et al.  Comparison of Sentinel-2 and High-Resolution Imagery for Mapping Land Abandonment in Fragmented Areas , 2020, Remote. Sens..

[21]  Yuyu Zhou,et al.  Annual maps of global artificial impervious area (GAIA) between 1985 and 2018 , 2020 .

[22]  Bin Chen,et al.  Stable classification with limited sample: transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. , 2019, Science bulletin.

[23]  Yuqi Bai,et al.  Mapping essential urban land use categories in China (EULUC-China): preliminary results for 2018. , 2020, Science bulletin.

[24]  Bing Xu,et al.  Sampling Strategy for Detailed Urban Land Use Classification: A Systematic Analysis in Shenzhen , 2020, Remote. Sens..

[25]  Luhe Wan,et al.  Land Cover/Use Classification Based on Feature Selection , 2015 .

[26]  Wenze Yue,et al.  Spatiotemporal patterns of summer urban heat island in Beijing, China using an improved land surface temperature , 2020, Journal of Cleaner Production.

[27]  P. Shi,et al.  Restoring urbanization process in China in the 1990s by using non-radiance-calibrated DMSP/OLS nighttime light imagery and statistical data , 2006 .

[28]  Jing Sun,et al.  Mapping Essential Urban Land Use Categories in Nanjing by Integrating Multi-Source Big Data , 2020, Remote. Sens..