Advances of Four Machine Learning Methods for Spatial Data Handling: a Review

Abstract

Most machine learning tasks can be categorized into classification or regression problems. Regression and classification models are normally used to extract useful geographic information from observed or measured spatial data, such as land cover classification, spatial interpolation, and quantitative parameter retrieval. This paper reviews the progress of four advanced machine learning methods for spatial data handling, namely, support vector machine (SVM)-based kernel learning, semi-supervised and active learning, ensemble learning, and deep learning. These four machine learning modes are representative because they improve learning performances from different views, for example, feature space transform and decision function (SVM), optimized uses of samples (semi-supervised and active learning), and enhanced learning models and capabilities (ensemble learning and deep learning). For spatial data handling via machine learning that can be improved by the four machine learning models, three key elements are learning algorithms, training samples, and input features. To apply machine learning methods to spatial data handling successfully, a four-level strategy is suggested: experimenting and evaluating the applicability, extending the algorithms by embedding spatial properties, optimizing the parameters for better performance, and enhancing the algorithm by multiple means. Firstly, the advances of SVM are reviewed to demonstrate the merits of novel machine learning methods for spatial data, running the line from direct use and comparison with traditional classifiers, and then targeted improvements to address multiple class problems, to optimize parameters of SVM, and to use spatial and spectral features. To overcome the limits of small-size training samples, semi-supervised learning and active learning methods are then utilized to deal with insufficient labeled samples, showing the potential of learning from small-size training samples. Furthermore, considering the poor generalization capacity and instability of machine learning algorithms, ensemble learning is introduced to integrate the advantages of multiple learners and to enhance the generalization capacity. The typical research lines, including the combination of multiple classifiers, advanced ensemble classifiers, and spatial interpolation, are presented. Finally, deep learning, one of the most popular branches of machine learning, is reviewed with specific examples for scene classification and urban structural type recognition from high-resolution remote sensing images. By this review, it can be concluded that machine learning methods are very effective for spatial data handling and have wide application potential in the big data era.

GPU-Accelerated CatBoost-Forest for Hyperspectral Image Classification Via Parallelized mRMR Ensemble Subspace Feature Selection

“…Driven by such challenges, advanced machine learning (ML) algorithms such as support vector machines (SVMs) [4], artificial neural networks (ANNs) [12], extreme learning machines (ELMs) [13], decision forests (DFs) [14][15] and deep neural networks (DNNs) [16][17] have emerged as more accurate and efficient alternatives to conventional modelbased approaches, particularly when faced with highdimensional, complex data spaces, multitemporal and largearea mapping cases [18][19]. However, some ML algorithms (e.g., SVMs, ELMs, ANNs and DNNs) are complicated due to having critical model parameters that need to be tuned first, which is difficult to automate [12][13][14][15][16][17].…”

A Novel Sample Selection Method for Impervious Surface Area Mapping Using JL1-3B Nighttime Light and Sentinel-2 Imagery

“…By selecting the training samples and classifiers, supervised classification can classify the ISA from satellite images. However, the results of supervised classification strongly depend on the quality of training samples in terms of their representativeness and completeness [11], [12]. The generation of training samples is usually through screen digitalization in high-resolution imagery manually, in which the operator should have a comprehensive knowledge of land cover types for the study area [13].…”

Tourism Flow Between Major Cities During China’s National Day Holiday: A Social Network Analysis Using Weibo Check-in Data

“…With the development of Internet, big data including tourism flow has been applied to various fields for the research of the tourism flow [9]. The arrival of big data era has brought opportunities for ''space of flows'' and urban network research.…”