A Comparison of Arima and Random Forest Time Series Models for Urban Drought Prediction

Keywords:
SARIMA, Random Forest, R, Univariate Time Series, Drought Prediction

Abstract:
One of the most devastating natural hazards that can have huge impact on ecosystems, agriculture, water supply and society as a whole is drought. Unlike hydrological and agricultural droughts, urban drought mainly affects populated cities and towns and represents a huge challenge for authorities in terms of managing public health and water supply. Therefore, forecasting urban drought is of great importance. This papers aims to present methodology of data collecting, preprocessing and forecasting meteorological parameters using ARIMA and Random Forest time series models and comparing them based on certain metrics in order to find the best prediction model. Our findings based on RMSE metrics used for evaluation of model accuracy, suggest that ARIMA model outperforms Random Forest model and therefore it is selected as the best model for urban drough prediction.

CITATION:

IEEE format

Copy to clipboard

N. Tihi, S. Popov, “A Comparison of Arima and Random Forest Time Series Models for Urban Drought Prediction,” in Sinteza 2024 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2024, pp. 51-56. doi:10.15308/Sinteza-2024-51-56

APA format

Copy to clipboard

Tihi, N., Popov, S. (2024). A Comparison of Arima and Random Forest Time Series Models for Urban Drought Prediction. Paper presented at Sinteza 2024 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2024-51-56

BibTeX format
Download

RefWorks Tagged format
Download