# A spatio-temporal LSTM model to forecast across multiple temporal and spatial scales

arXiv: https://arxiv.org/abs/2108.11875 · HTML: https://mlsanity.com/paper/2108.11875/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 71 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow](https://mlsanity.com/paper/1802.10123/) (2018)
- [Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge](https://mlsanity.com/paper/1711.07970/) (2017)
- [Physics informed deep learning for computational elastodynamics without labeled data](https://mlsanity.com/paper/2006.08472/) (2020)
- [Deep Learning for Time-Series Analysis](https://mlsanity.com/paper/1701.01887/) (2017)
- [Image Captioning with Deep Bidirectional LSTMs](https://mlsanity.com/paper/1604.00790/) (2016)
- [70 years of machine learning in geoscience in review](https://mlsanity.com/paper/2006.13311/) (2020)
- [Using Deep Learning to Extend the Range of Air-Pollution Monitoring and Forecasting](https://mlsanity.com/paper/1810.09425/) (2018)
- [Statistical and machine learning ensemble modelling to forecast sea surface temperature](https://mlsanity.com/paper/1909.08573/) (2019)
- [FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods](https://mlsanity.com/paper/1910.12680/) (2019)
- [TSML (Time Series Machine Learnng)](https://mlsanity.com/paper/2005.13191/) (2020)

## Built on by (most cited first, 6 of 6)

- [A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling](https://mlsanity.com/paper/2112.08618/) (2021)
- [RefreshNet: Learning Multiscale Dynamics through Hierarchical Refreshing](https://mlsanity.com/paper/2401.13282/) (2024)
- [KFTD: Koopman-Fourier Time-Differentiable Network for Continuous Ocean Spatiotemporal Forecasting](https://mlsanity.com/paper/2606.17070/) (2026)
- [MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models](https://mlsanity.com/paper/2602.16573/) (2026)
- [Machine Learning Risk Intelligence for Green Hydrogen Investment: Insights for Duqm R3 Auction](https://mlsanity.com/paper/2507.19529/) (2025)
- [Machine Learning in Fish Farming](https://mlsanity.com/paper/2609.13919/) (2026)

## Abstract (arXiv)

This paper presents a novel spatio-temporal LSTM (SPATIAL) architecture for time series forecasting applied to environmental datasets. The framework was evaluated across multiple sensors and for three different oceanic variables: current speed, temperature, and dissolved oxygen. Network implementation proceeded in two directions that are nominally separated but connected as part of a natural environmental system -- across the spatial (between individual sensors) and temporal components of the sensor data. Data from four sensors sampling current speed, and eight measuring both temperature and dissolved oxygen evaluated the framework. Results were compared against RF and XGB baseline models that learned on the temporal signal of each sensor independently by extracting the date-time features together with the past history of data using sliding window matrix. Results demonstrated ability to accurately replicate complex signals and provide comparable performance to state-of-the-art benchmarks. Notably, the novel framework provided a simpler pre-processing and training pipeline that handles missing values via a simple masking layer. Enabling learning across the spatial and temporal directions, this paper addresses two fundamental challenges of ML applications to environmental science: 1) data sparsity and the challenges and costs of collecting measurements of environmental conditions such as ocean dynamics, and 2) environmental datasets are inherently connected in the spatial and temporal directions while classical ML approaches only consider one of these directions. Furthermore, sharing of parameters across all input steps makes SPATIAL a fast, scalable, and easily-parameterized forecasting framework.