A Cross-Modal Deep Feature Fusion Framework Based on Ensemble Learning for Land Use Classification

Land use classification based on multi-modal data fusion has gained significant attention due to its potential to capture the complex characteristics of urban environments. However, effectively extracting and integrating discriminative features derived from heterogeneous geospatial data remain challenging. This study proposes an ensemble learning framework for land use classification by fusing cross-modal deep features from both physical and socioeconomic perspectives. Specifically, the framework utilizes the Masked Autoencoder (MAE) to extract global spatial dependencies from remote sensing imagery and applies long short-term memory (LSTM) networks to model spatial distribution patterns of points of interest (POIs) based on type co-occurrence. Furthermore, we employ inter-modal contrastive learning to enhance the representation of physical and socioeconomic features. To verify the superiority of the ensemble learning framework, we apply it to map the land use distribution of Bejing. By coupling various physical and socioeconomic features, the framework achieves an average accuracy of 84.33 %, surpassing several comparative baseline methods. Furthermore, the framework demonstrates comparable performance when applied to a Shenzhen dataset, confirming its robustness and generalizability. The findings highlight the importance of fully extracting and effectively integrating multi-source deep features in land use classification, providing a robust solution for urban planning and sustainable development

Autoencoder · Convolutional neural network · Deep learning · Discriminative model · Ensemble learning · Feature learning · Geospatial analysis · Human Mobility and Location-Based Analysis · Remote Sensing and Land Use · Remote-Sensing Image Classification

• Coupling mobile phone and social media data

  Wei Tu, Jinzhou Cao et al.•International Journal of…•2017

  Incluir item

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

  Open Access•Liang-Chieh Chen, Yukun Zhu et al.•Computer Vision – ECCV 2018•2018

  Incluir item

• High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform

  Open Access•Xiaoping Liu, Guohua Hu et al.•Remote Sensing of Environment•2018

  Incluir item

• Classifying urban land use by integrating remote sensing and social media data

  Xiaoping Liu, Jialyu He et al.•International Journal of…•2017

  Incluir item

• Extracting urban functional regions from points of interest and human activities on location‐based social networks

  Open Access•Song Gao, Krzysztof Janowicz et al.•Transactions in GIS•2017

  Incluir item

• Places

  Open Access•Bolei Zhou, Agata Lapedriza et al.•IEEE Transactions on Pattern…•2018

  Incluir item

• Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model

  Yao Yao, Xia Li et al.•International Journal of…•2017

  Incluir item

• A Deep-Learning-Based Multimodal Data Fusion Framework for Urban Region Function Recognition

  Open Access•Mingyang Yu, Haiqing Xu et al.•ISPRS International Journal of…•2023

  Incluir item

• Urban Land Use Classification Model Fusing Multimodal Deep Features

  Open Access•Yougui Ren, Zhiwei Xie et al.•ISPRS International Journal of…•2024

  Incluir item

• Research on Land Use and Land Cover Information Extraction Methods for Remote Sensing Images Based on Improved Convolutional Neural Networks

  Open Access•Xue Ding, Zhaoqian Wang et al.•ISPRS International Journal of…•2024

  Incluir item

• Social Sensing

  Yu Liu, Xi Liu et al.•Annals of the Association of…•2015

  Incluir item