An Ensemble Learning Approach for Urban Land Use Mapping Based on Remote Sensing Imagery and Social Sensing Data

Abstract

Urban land use mapping is crucial for effective urban management and planning due to the rapid change of urban processes. State-of-the-art approaches rely heavily on the socioeconomic, topographical, infrastructural and land cover information of urban environments via feeding them into ad hoc classifiers for land use classification. Yet, the major challenge lies in the lack of a universal and reliable approach for the extraction and combination of physical and socioeconomic features derived from remote sensing imagery and social sensing data. This article proposes an ensemble-learning-approach-based solution of integrating a rich body of features derived from high resolution satellite images, street-view images, building footprints, points-of-interest (POIs) and social media check-ins for the urban land use mapping task. The proposed approach can statistically differentiate the importance of input feature variables and provides a good explanation for the relationships between land cover, socioeconomic activities and land use categories. We apply the proposed method to infer the land use distribution in fine-grained spatial granularity within the Fifth Ring Road of Beijing and achieve an average classification accuracy of 74.2% over nine typical land use types. The results also indicate that our model outperforms several alternative models that have been widely utilized as baselines for land use classification.

A Comparative Analysis of Spatial Data and Land Use/Land Cover Classification in Urbanized Areas and Areas Subjected to Anthropogenic Pressure for the Example of Poland

“…Source materials were collected in the first stage of the research. The existing land use classification systems were analyzed in the context of formal classification systems that are regulated by legal provisions and are based on cadastral data, CORINE Land Cover data, or Urban Atlas data, as well as informal classification systems that are created based on research results or the existing classification systems and are used for specific analytical needs [42,[44][45][46].…”

“…The following land use classification systems were selected for analysis: Land use classification proposed by Huang et al [44].…”

“…Huang et al [44] developed a land use classification system that is based on the Land Administration Law of the People's Republic of China (GBT 21010-2017). They analyzed 12 land use categories (cultivated land, garden land, water and water conservancy facilities, woodland, grassland, residential land, commercial land, transportation land, industrial land, public management and public service land, special land, and other land) and selected the nine most important categories which were then modified for the needs of the conducted research.…”

Remote Sensing and Social Sensing Data Fusion for Fine-Resolution Population Mapping With a Multimodel Neural Network

“…3) Infrastructure data: POIs (Points of Interest) capture geographic location attributes that indicate population concentration, including information such as the name, category, and location of geographic objects. POIs represents people's understanding of the functions and attributes of a specific place, and it is an important source of social sensing data [55]. Therefore, the social sensing data used in this paper mainly refers to POIs data.…”

Attention-Based Context Aware Network for Semantic Comprehension of Aerial Scenery

“…The classification of each pixel in an image, also known as semantic segmentation in the field of computer vision, can distinguish each tiny target object in an aerial image. Using the approach of semantic segmentation to better grasp the semantic information in images can assist researchers in making breakthroughs in the following areas: keeping track of changes in buildings [ 1 , 2 , 3 ], extracting information about road networks [ 4 , 5 , 6 ], urban planning [ 7 , 8 ], zoning of urban land parcels [ 9 , 10 , 11 ], water coverage surveys [ 12 , 13 ], and so on. With the progressive and dramatic improvement of computing power over the years, deep learning-based methods are playing an essential role in addressing the issues of remote sensing.…”