# Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data

arXiv: https://arxiv.org/abs/2404.04271 · HTML: https://mlsanity.com/paper/2404.04271/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [ALEX: An Updatable Adaptive Learned Index](https://mlsanity.com/paper/1905.08898/) (2019)
- [STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation](https://mlsanity.com/paper/2010.07024/) (2020)
- [FITing-Tree: A Data-aware Index Structure](https://mlsanity.com/paper/1801.10207/) (2018)
- [Learning Multi-dimensional Indexes](https://mlsanity.com/paper/1912.01668/) (2019)
- [Qd-tree: Learning Data Layouts for Big Data Analytics](https://mlsanity.com/paper/2004.10898/) (2020)
- [The PGM-index: a multicriteria, compressed and learned approach to data indexing](https://mlsanity.com/paper/1910.06169/) (2019)
- [Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence](https://mlsanity.com/paper/1809.10770/) (2018)
- [NLPMM: a Next Location Predictor with Markov Modeling](https://mlsanity.com/paper/2003.07037/) (2020)
- [The Case for Learned Spatial Indexes](https://mlsanity.com/paper/2008.10349/) (2020)
- [Origin-Aware Next Destination Recommendation with Personalized Preference Attention](https://mlsanity.com/paper/2012.01915/) (2020)

## Built on by (most cited first, 3 of 3)

- [Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario](https://mlsanity.com/paper/2410.04740/) (2024)
- [Where to Go Next Day: Multi-scale Spatial-Temporal Decoupled Model for Mid-term Human Mobility Prediction](https://mlsanity.com/paper/2501.06561/) (2025)
- [AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting](https://mlsanity.com/paper/2509.18107/) (2025)

## Abstract (arXiv)

The next point-of-interest (POI) prediction is a significant task in location-based services, yet its complexity arises from the consolidation of spatial and semantic intent. This fusion is subject to the influences of historical preferences, prevailing location, and environmental factors, thereby posing significant challenges. In addition, the uneven POI distribution further complicates the next POI prediction procedure. To address these challenges, we enrich input features and propose an effective deep-learning method within a two-step prediction framework. Our method first incorporates remote sensing data, capturing pivotal environmental context to enhance input features regarding both location and semantics. Subsequently, we employ a region quad-tree structure to integrate urban remote sensing, road network, and POI distribution spaces, aiming to devise a more coherent graph representation method for urban spatial. Leveraging this method, we construct the QR-P graph for the user's historical trajectories to encapsulate historical travel knowledge, thereby augmenting input features with comprehensive spatial and semantic insights. We devise distinct embedding modules to encode these features and employ an attention mechanism to fuse diverse encodings. In the two-step prediction procedure, we initially identify potential spatial zones by predicting user-preferred tiles, followed by pinpointing specific POIs of a designated type within the projected tiles. Empirical findings from four real-world location-based social network datasets underscore the remarkable superiority of our proposed approach over competitive baseline methods.