An integrated recurrent neural network and regression model with spatial and climatic couplings for vector-borne disease dynamics

@inproceedings{Li2022AnIR,
  title={An integrated recurrent neural network and regression model with spatial and climatic couplings for vector-borne disease dynamics},
  author={Zhijian Li and Jack Xin and Guofa Zhou},
  booktitle={ICPRAM},
  year={2022}
}
: We developed an integrated recurrent neural network and nonlinear regression spatio-temporal model for vector-borne disease evolution. We take into account climate data and seasonality as external factors that correlate with disease transmitting insects (e.g. flies), also spill-over infections from neighboring regions sur-rounding a region of interest. The climate data is encoded to the model through a quadratic embedding scheme motivated by recommendation systems. The neighboring regions’ in… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 17 REFERENCES
A Recurrent Neural Network and Differential Equation Based Spatiotemporal Infectious Disease Model with Application to COVID-19
TLDR
This work develops an integrated spatiotemporal model based on the epidemic differential equations (SIR) and RNN that out-performs existing temporal models (fully connected NN, SIR, ARIMA) in 1-day, 3- day, and 1-week ahead forecasting especially in the regime of limited training data.
A Spatial-Temporal Graph Based Hybrid Infectious Disease Model with Application to COVID-19
TLDR
The resulting hybrid model (called IeRNN) improves the prediction accuracy on state-level COVID-19 new case data from the US, out-performing standard temporal models (RNN, SEIR, and ARIMA) in 1-day and 7-day ahead forecasting.
Climate Cycles and Forecasts of Cutaneous Leishmaniasis, a Nonstationary Vector-Borne Disease
Background Cutaneous leishmaniasis (CL) is one of the main emergent diseases in the Americas. As in other vector-transmitted diseases, its transmission is sensitive to the physical environment, but
A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
TLDR
This work achieves state-of-the-art forecasting accuracy on the benchmark CDC dataset by using a graph-structured recurrent neural network (GSRNN) and sparsify the network weights via transformed-$\ell_1$ penalty to maintain prediction accuracy at the same level.
Association between climate variability and malaria epidemics in the East African highlands.
TLDR
The results suggest that there was a high spatial variation in the sensitivity of malaria outpatient number to climate fluctuations in the highlands, and that climate variability played an important role in initiating malaria epidemics in the East African highlands.
Accurate estimation of influenza epidemics using Google search data via ARGO
TLDR
An influenza tracking model, ARGO (AutoRegression with GOogle search data), that uses publicly available online search data that outperforms all available Google-search–based real-time tracking models for influenza epidemics at the national level of the United States, including Google Flu Trends.
Spatial Epidemiologic Trends and Hotspots of Leishmaniasis, Sri Lanka, 2001–2018
TLDR
Evidence of temporally progressive and spatially expanding incidence of leishmaniasis in Sri Lanka with distinct geographic patterns and disease hotspots is provided, signaling an urgent need for effective disease control interventions.
Geostatistical Space–Time Models: A Review
TLDR
An annotated survey of models proposed in the literature is attempted, stating contributions and pinpointing shortcomings, and assessment of joint space–time uncertainty via stochastic imaging is suggested.
Long Short-Term Memory
TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Species Distribution Models: Ecological Explanation and Prediction Across Space and Time
Species distribution models (SDMs) are numerical tools that combine observations of species occurrence or abundance with environmental estimates. They are used to gain ecological and evolutionary
...
...